From 07efe987ea01cd786fd414ced96c52cdf844a673 Mon Sep 17 00:00:00 2001 From: Daniel Osorio Date: Wed, 1 Mar 2017 15:49:00 -0500 Subject: [PATCH 01/50] Minor changes to some functions aacomp, aindex, boman functions: the argument name was added autoCorrelation function: an argument description was fixed DESCRIPTION: the package description was fixed --- DESCRIPTION | 2 +- R/aacomp.R | 2 +- R/aindex.R | 4 +++- R/boman.R | 6 ++++-- man/aacomp.Rd | 2 +- man/aindex.Rd | 2 +- man/autoCorrelation.Rd | 2 +- man/boman.Rd | 2 +- 8 files changed, 13 insertions(+), 9 deletions(-) diff --git a/DESCRIPTION b/DESCRIPTION index c979b31..a68b535 100644 --- a/DESCRIPTION +++ b/DESCRIPTION @@ -1,7 +1,7 @@ Package: Peptides Version: 1.2.1 Date: 2017-02-20 -Title: Calculate Indices and Theoretical Properties of Protein Sequences +Title: Calculate Indices and Theoretical Physicochemical Properties of Protein Sequences Author: Daniel Osorio, Paola Rondon-Villarreal and Rodrigo Torres. Maintainer: Daniel Osorio URL: https://github.com/dosorio/Peptides/ diff --git a/R/aacomp.R b/R/aacomp.R index 520c227..82ad43c 100755 --- a/R/aacomp.R +++ b/R/aacomp.R @@ -35,7 +35,7 @@ #' # Acidic (B+D+E+Z) 0 00.000 #' #' ## AA composition of PDB: 1D9J Cecropin Peptide -#' aacomp("KWKLFKKIGIGKFLHSAKKFX") +#' aacomp(seq= "KWKLFKKIGIGKFLHSAKKFX") #' #' ## Output #' # Number Mole % diff --git a/R/aindex.R b/R/aindex.R index ac6378a..fe6364a 100755 --- a/R/aindex.R +++ b/R/aindex.R @@ -1,7 +1,9 @@ #' @export aindex #' @title Compute the aliphatic index of a protein sequence #' @description This function calculates the Ikai (1980) aliphatic index of a protein. The \code{aindex} is defined as the relative volume occupied by aliphatic side chains (Alanine, Valine, Isoleucine, and Leucine). It may be regarded as a positive factor for the increase of thermostability of globular proteins. +#' #' @param seq An amino-acids sequence +#' #' @return The computed aliphatic index for a given amino-acids sequence #' @references Ikai (1980). Thermostability and aliphatic index of globular proteins. Journal of Biochemistry, 88(6), 1895-1898. #' @details Aliphatic amino acids (A, I, L and V) are responsible for the thermal stability of proteins. The aliphatic index was proposed by Ikai (1980) and evaluates the thermostability of proteins based on the percentage of each of the aliphatic amino acids that build up proteins. @@ -10,7 +12,7 @@ #' # SEQUENCE: SDKEVDEVDAALSDLEITLE #' # Aliphatic index: 117.00 #' -#' aindex("SDKEVDEVDAALSDLEITLE") +#' aindex(seq = "SDKEVDEVDAALSDLEITLE") #' # [1] 117 aindex <- function(seq) { diff --git a/R/boman.R b/R/boman.R index 85d24cc..a55b4bb 100755 --- a/R/boman.R +++ b/R/boman.R @@ -3,7 +3,9 @@ #' @description This function computes the potential protein interaction index proposed by Boman (2003) based in the amino acid sequence of a protein. #' The index is equal to the sum of the solubility values for all residues in a sequence, it might give an overall estimate of the potential of a peptide to bind to membranes or other proteins as receptors, to normalize it is divided by the number of residues. #' A protein have high binding potential if the index value is higher than 2.48. +#' #' @param seq An amino-acid sequence +#' #' @return The computed potential protein-protein interaction for a given amino-acids sequence #' @references Boman, H. G. (2003). Antibacterial peptides: basic facts and emerging concepts. Journal of Internal Medicine, 254(3), 197-215. #' @details The potential protein interaction index was proposed by Boman (2003) as an easy way to differentiate the action mechanism of hormones (protein-protein) and antimicrobial peptides (protein-membrane) through this index. This function predicts the potential peptide interaction with another protein. @@ -13,7 +15,7 @@ #' # SEQUENCE: FLPVLAGLTPSIVPKLVCLLTKKC #' # BOMAN INDEX -1.24 #' -#' boman("FLPVLAGLTPSIVPKLVCLLTKKC") +#' boman(seq = "FLPVLAGLTPSIVPKLVCLLTKKC") #' # [1] -1.235833 #' boman <- function(seq) { @@ -47,7 +49,7 @@ boman <- function(seq) { unlist(strsplit(seq, "")) }) bindex <- lapply(seq, function(seq) { - return(-1 * sum(boman[seq], na.rm = TRUE) / length(seq)) + return(-1 * mean(boman[seq],na.rm = TRUE)) }) return(unlist(bindex)) } diff --git a/man/aacomp.Rd b/man/aacomp.Rd index cc4ddf2..8d2e2ed 100644 --- a/man/aacomp.Rd +++ b/man/aacomp.Rd @@ -51,7 +51,7 @@ Further information: http://emboss.sourceforge.net/apps/cvs/emboss/apps/pepstats # Acidic (B+D+E+Z) 0 00.000 ## AA composition of PDB: 1D9J Cecropin Peptide -aacomp("KWKLFKKIGIGKFLHSAKKFX") +aacomp(seq= "KWKLFKKIGIGKFLHSAKKFX") ## Output # Number Mole \% diff --git a/man/aindex.Rd b/man/aindex.Rd index 9f73426..5221110 100644 --- a/man/aindex.Rd +++ b/man/aindex.Rd @@ -24,7 +24,7 @@ Aliphatic amino acids (A, I, L and V) are responsible for the thermal stability # SEQUENCE: SDKEVDEVDAALSDLEITLE # Aliphatic index: 117.00 -aindex("SDKEVDEVDAALSDLEITLE") +aindex(seq = "SDKEVDEVDAALSDLEITLE") # [1] 117 } \references{ diff --git a/man/autoCorrelation.Rd b/man/autoCorrelation.Rd index 57816a3..6f8f6b5 100644 --- a/man/autoCorrelation.Rd +++ b/man/autoCorrelation.Rd @@ -9,7 +9,7 @@ autoCorrelation(sequence, lag, property, center = TRUE) \arguments{ \item{sequence}{An amino-acids sequence} -\item{lag}{A value for a lag, the max value is equal to the length of the shortest peptide minus one.} +\item{lag}{A value for a lag, the max value is equal to the length of shortest peptide minus one.} \item{property}{A property to use as value to be correlated.} diff --git a/man/boman.Rd b/man/boman.Rd index 2a4b715..2b5c94f 100644 --- a/man/boman.Rd +++ b/man/boman.Rd @@ -26,7 +26,7 @@ The potential protein interaction index was proposed by Boman (2003) as an easy # SEQUENCE: FLPVLAGLTPSIVPKLVCLLTKKC # BOMAN INDEX -1.24 -boman("FLPVLAGLTPSIVPKLVCLLTKKC") +boman(seq = "FLPVLAGLTPSIVPKLVCLLTKKC") # [1] -1.235833 } From f7a2931c7e07febc85a5b6d9e6a60515685ae3a7 Mon Sep 17 00:00:00 2001 From: Daniel Osorio Date: Wed, 1 Mar 2017 16:31:09 -0500 Subject: [PATCH 02/50] Minor changes to some functions --- R/boman.R | 4 +-- R/charge.R | 26 +++++++------- R/crucianiProperties.R | 8 ++--- R/hydrophobicity.R | 76 +++++++++++++++++++-------------------- R/instaindex.R | 2 +- R/lengthpep.R | 2 +- R/membpos.R | 4 +-- R/mw.R | 5 ++- R/pI.R | 18 +++++----- R/plot.xvg.R | 6 ++-- R/read.xvg.R | 11 ++++-- man/boman.Rd | 2 +- man/charge.Rd | 26 +++++++------- man/crucianiProperties.Rd | 2 +- man/hydrophobicity.Rd | 76 +++++++++++++++++++-------------------- man/instaindex.Rd | 2 +- man/lengthpep.Rd | 2 +- man/membpos.Rd | 4 +-- man/mw.Rd | 5 ++- man/pI.Rd | 18 +++++----- man/plot.xvg.Rd | 4 +-- man/read.xvg.Rd | 4 +-- 22 files changed, 160 insertions(+), 147 deletions(-) diff --git a/R/boman.R b/R/boman.R index a55b4bb..6dec63b 100755 --- a/R/boman.R +++ b/R/boman.R @@ -15,7 +15,7 @@ #' # SEQUENCE: FLPVLAGLTPSIVPKLVCLLTKKC #' # BOMAN INDEX -1.24 #' -#' boman(seq = "FLPVLAGLTPSIVPKLVCLLTKKC") +#' boman(seq= "FLPVLAGLTPSIVPKLVCLLTKKC") #' # [1] -1.235833 #' boman <- function(seq) { @@ -49,7 +49,7 @@ boman <- function(seq) { unlist(strsplit(seq, "")) }) bindex <- lapply(seq, function(seq) { - return(-1 * mean(boman[seq],na.rm = TRUE)) + return(-1 * sum(boman[seq], na.rm = TRUE) / length(seq)) }) return(unlist(bindex)) } diff --git a/R/charge.R b/R/charge.R index 5b4032f..ff24ae6 100755 --- a/R/charge.R +++ b/R/charge.R @@ -31,23 +31,23 @@ #' # SEQUENCE: FLPVLAGLTPSIVPKLVCLLTKKC #' # Charge = 3.0 #' -#' charge(seq="FLPVLAGLTPSIVPKLVCLLTKKC",pH=7, pKscale="Bjellqvist") +#' charge(seq= "FLPVLAGLTPSIVPKLVCLLTKKC",pH= 7, pKscale= "Bjellqvist") #' # [1] 2.737303 -#' charge(seq="FLPVLAGLTPSIVPKLVCLLTKKC",pH=7, pKscale="EMBOSS") +#' charge(seq= "FLPVLAGLTPSIVPKLVCLLTKKC",pH= 7, pKscale= "EMBOSS") #' # [1] 2.914112 -#' charge(seq="FLPVLAGLTPSIVPKLVCLLTKKC",pH=7, pKscale="Murray") +#' charge(seq= "FLPVLAGLTPSIVPKLVCLLTKKC",pH= 7, pKscale= "Murray") #' # [1] 2.907541 -#' charge(seq="FLPVLAGLTPSIVPKLVCLLTKKC",pH=7, pKscale="Sillero") +#' charge(seq= "FLPVLAGLTPSIVPKLVCLLTKKC",pH= 7, pKscale= "Sillero") #' # [1] 2.919812 -#' charge(seq="FLPVLAGLTPSIVPKLVCLLTKKC",pH=7, pKscale="Solomon") +#' charge(seq= "FLPVLAGLTPSIVPKLVCLLTKKC",pH= 7, pKscale= "Solomon") #' # [1] 2.844406 -#' charge(seq="FLPVLAGLTPSIVPKLVCLLTKKC",pH=7, pKscale="Stryer") +#' charge(seq= "FLPVLAGLTPSIVPKLVCLLTKKC",pH= 7, pKscale= "Stryer") #' # [1] 2.876504 -#' charge(seq="FLPVLAGLTPSIVPKLVCLLTKKC",pH=7, pKscale="Lehninger") +#' charge(seq= "FLPVLAGLTPSIVPKLVCLLTKKC",pH= 7, pKscale= "Lehninger") #' # [1] 2.87315 -#' charge(seq="FLPVLAGLTPSIVPKLVCLLTKKC",pH=7, pKscale="Dawson") +#' charge(seq= "FLPVLAGLTPSIVPKLVCLLTKKC",pH= 7, pKscale= "Dawson") #' # [1] 2.844406 -#' charge(seq="FLPVLAGLTPSIVPKLVCLLTKKC",pH=7, pKscale="Rodwell") +#' charge(seq= "FLPVLAGLTPSIVPKLVCLLTKKC",pH= 7, pKscale= "Rodwell") #' # [1] 2.819755 #' #' # COMPARED TO YADAMP @@ -57,15 +57,15 @@ #' # CHARGE pH7: 2.91 #' # CHARGE pH9: 1.09 -#' charge(seq="FLPVLAGLTPSIVPKLVCLLTKKC",pH=5, pKscale="EMBOSS") +#' charge(seq= "FLPVLAGLTPSIVPKLVCLLTKKC",pH= 5, pKscale= "EMBOSS") #' # [1] 3.037398 -#' charge(seq="FLPVLAGLTPSIVPKLVCLLTKKC",pH=7, pKscale="EMBOSS") +#' charge(seq= "FLPVLAGLTPSIVPKLVCLLTKKC",pH= 7, pKscale= "EMBOSS") #' # [1] 2.914112 -#' charge(seq="FLPVLAGLTPSIVPKLVCLLTKKC",pH=9, pKscale="EMBOSS") +#' charge(seq= "FLPVLAGLTPSIVPKLVCLLTKKC",pH= 9, pKscale= "EMBOSS") #' # [1] 0.7184524 #' #' # JUST ONE COMMAND -#' charge(seq="FLPVLAGLTPSIVPKLVCLLTKKC",pH=seq(from = 5,to = 9,by = 2), pKscale="EMBOSS") +#' charge(seq= "FLPVLAGLTPSIVPKLVCLLTKKC",pH= seq(from = 5,to = 9,by = 2), pKscale= "EMBOSS") #' # [1] 3.0373984 2.9141123 0.7184524 charge <- function(seq, pH = 7, pKscale = "Lehninger") { diff --git a/R/crucianiProperties.R b/R/crucianiProperties.R index dcf40cb..afde8a2 100644 --- a/R/crucianiProperties.R +++ b/R/crucianiProperties.R @@ -4,7 +4,7 @@ #' @param seq An amino-acids sequence #' @return The computed average of Cruciani properties of all the amino acids in the corresponding peptide sequence. Each PP represent an amino-acid property as follows: \itemize{\item{PP1:} Polarity, \item{PP2:} Hydrophobicity, \item{PP3:} H-bonding} #' @references Cruciani, G., Baroni, M., Carosati, E., Clementi, M., Valigi, R., and Clementi, S. (2004) Peptide studies by means of principal properties of amino acids derived from MIF descriptors. J. Chemom. 18, 146-155. -#' @examples crucianiProperties("QWGRRCCGWGPGRRYCVRWC") +#' @examples crucianiProperties(seq = "QWGRRCCGWGPGRRYCVRWC") #' # PP1 PP2 PP3 #' # -0.1130 -0.0220 0.2735 crucianiProperties <- function(seq) { @@ -17,8 +17,8 @@ crucianiProperties <- function(seq) { seq <- strsplit(toupper(seq), split = "") # Calculate averages lapply(seq, function(seq) { - c(PP1 = mean(CP[["PP1"]][seq]), - PP2 = mean(CP[["PP2"]][seq]), - PP3 = mean(CP[["PP3"]][seq])) + c(PP1 = mean(CP[["PP1"]][seq],na.rm = TRUE), + PP2 = mean(CP[["PP2"]][seq],na.rm = TRUE), + PP3 = mean(CP[["PP3"]][seq],na.rm = TRUE)) }) } \ No newline at end of file diff --git a/R/hydrophobicity.R b/R/hydrophobicity.R index 66e9c73..089d511 100755 --- a/R/hydrophobicity.R +++ b/R/hydrophobicity.R @@ -96,81 +96,81 @@ #' # SEQUENCE: QWGRRCCGWGPGRRYCVRWC #' # GRAVY: -0.950 #' -#' hydrophobicity("QWGRRCCGWGPGRRYCVRWC","Aboderin") +#' hydrophobicity(seq = "QWGRRCCGWGPGRRYCVRWC",scale = "Aboderin") #' #[1] 3.84 -#' hydrophobicity("QWGRRCCGWGPGRRYCVRWC","AbrahamLeo") +#' hydrophobicity(seq = "QWGRRCCGWGPGRRYCVRWC",scale = "AbrahamLeo") #' #[1] 0.092 -#' hydrophobicity("QWGRRCCGWGPGRRYCVRWC","Argos") +#' hydrophobicity(seq = "QWGRRCCGWGPGRRYCVRWC",scale = "Argos") #' #[1] 1.033 -#' hydrophobicity("QWGRRCCGWGPGRRYCVRWC","BlackMould") +#' hydrophobicity(seq = "QWGRRCCGWGPGRRYCVRWC",scale = "BlackMould") #' #[1] 0.50125 -#' hydrophobicity("QWGRRCCGWGPGRRYCVRWC","BullBreese") +#' hydrophobicity(seq = "QWGRRCCGWGPGRRYCVRWC",scale = "BullBreese") #' #[1] 0.1575 -#' hydrophobicity("QWGRRCCGWGPGRRYCVRWC","Casari") +#' hydrophobicity(seq = "QWGRRCCGWGPGRRYCVRWC",scale = "Casari") #' #[1] 0.38 -#' hydrophobicity("QWGRRCCGWGPGRRYCVRWC","Chothia") +#' hydrophobicity(seq = "QWGRRCCGWGPGRRYCVRWC",scale = "Chothia") #' #[1] 0.262 -#' hydrophobicity("QWGRRCCGWGPGRRYCVRWC","Cid") +#' hydrophobicity(seq = "QWGRRCCGWGPGRRYCVRWC",scale = "Cid") #' #[1] 0.198 -#' hydrophobicity("QWGRRCCGWGPGRRYCVRWC","Cowan3.4") +#' hydrophobicity(seq = "QWGRRCCGWGPGRRYCVRWC",scale = "Cowan3.4") #' #[1] 0.0845 -#' hydrophobicity("QWGRRCCGWGPGRRYCVRWC","Cowan7.5") +#' hydrophobicity(seq = "QWGRRCCGWGPGRRYCVRWC",scale = "Cowan7.5") #' #[1] 0.0605 -#' hydrophobicity("QWGRRCCGWGPGRRYCVRWC","Eisenberg") +#' hydrophobicity(seq = "QWGRRCCGWGPGRRYCVRWC",scale = "Eisenberg") #' #[1] -0.3265 -#' hydrophobicity("QWGRRCCGWGPGRRYCVRWC","Engelman") +#' hydrophobicity(seq = "QWGRRCCGWGPGRRYCVRWC",scale = "Engelman") #' #[1] 2.31 -#' hydrophobicity("QWGRRCCGWGPGRRYCVRWC","Fasman") +#' hydrophobicity(seq = "QWGRRCCGWGPGRRYCVRWC",scale = "Fasman") #' #[1] -1.2905 -#' hydrophobicity("QWGRRCCGWGPGRRYCVRWC","Fauchere") +#' hydrophobicity(seq = "QWGRRCCGWGPGRRYCVRWC",scale = "Fauchere") #' #[1] 0.527 -#' hydrophobicity("QWGRRCCGWGPGRRYCVRWC","Goldsack") +#' hydrophobicity(seq = "QWGRRCCGWGPGRRYCVRWC",scale = "Goldsack") #' #[1] 1.2245 -#' hydrophobicity("QWGRRCCGWGPGRRYCVRWC","Guy") +#' hydrophobicity(seq = "QWGRRCCGWGPGRRYCVRWC",scale = "Guy") #' #[1] 0.193 -#' hydrophobicity("QWGRRCCGWGPGRRYCVRWC","HoppWoods") +#' hydrophobicity(seq = "QWGRRCCGWGPGRRYCVRWC",scale = "HoppWoods") #' #[1] -0.14 -#' hydrophobicity("QWGRRCCGWGPGRRYCVRWC","Janin") +#' hydrophobicity(seq = "QWGRRCCGWGPGRRYCVRWC",scale = "Janin") #' #[1] -0.105 -#' hydrophobicity("QWGRRCCGWGPGRRYCVRWC","Jones") +#' hydrophobicity(seq = "QWGRRCCGWGPGRRYCVRWC",scale = "Jones") #' #[1] 1.4675 -#' hydrophobicity("QWGRRCCGWGPGRRYCVRWC","Juretic") +#' hydrophobicity(seq = "QWGRRCCGWGPGRRYCVRWC",scale = "Juretic") #' #[1] -1.106 -#' hydrophobicity("QWGRRCCGWGPGRRYCVRWC","Kidera") +#' hydrophobicity(seq = "QWGRRCCGWGPGRRYCVRWC",scale = "Kidera") #' #[1] -0.0405 -#' hydrophobicity("QWGRRCCGWGPGRRYCVRWC","Kuhn") +#' hydrophobicity(seq = "QWGRRCCGWGPGRRYCVRWC",scale = "Kuhn") #' #[1] 0.9155 -#' hydrophobicity("QWGRRCCGWGPGRRYCVRWC","KyteDoolittle") +#' hydrophobicity(seq = "QWGRRCCGWGPGRRYCVRWC",scale = "KyteDoolittle") #' #[1] -0.95 -#' hydrophobicity("QWGRRCCGWGPGRRYCVRWC","Levitt") +#' hydrophobicity(seq = "QWGRRCCGWGPGRRYCVRWC",scale = "Levitt") #' #[1] -0.21 -#' hydrophobicity("QWGRRCCGWGPGRRYCVRWC","Manavalan") +#' hydrophobicity(seq = "QWGRRCCGWGPGRRYCVRWC",scale = "Manavalan") #' #[1] 13.0445 -#' hydrophobicity("QWGRRCCGWGPGRRYCVRWC","Miyazawa") +#' hydrophobicity(seq = "QWGRRCCGWGPGRRYCVRWC",scale = "Miyazawa") #' #[1] 5.739 -#' hydrophobicity("QWGRRCCGWGPGRRYCVRWC","Parker") +#' hydrophobicity(seq = "QWGRRCCGWGPGRRYCVRWC",scale = "Parker") #' #[1] 1.095 -#' hydrophobicity("QWGRRCCGWGPGRRYCVRWC","Ponnuswamy") +#' hydrophobicity(seq = "QWGRRCCGWGPGRRYCVRWC",scale = "Ponnuswamy") #' #[1] 0.851 -#' hydrophobicity("QWGRRCCGWGPGRRYCVRWC","Prabhakaran") +#' hydrophobicity(seq = "QWGRRCCGWGPGRRYCVRWC",scale = "Prabhakaran") #' #[1] 9.67 -#' hydrophobicity("QWGRRCCGWGPGRRYCVRWC","Rao") +#' hydrophobicity(seq = "QWGRRCCGWGPGRRYCVRWC",scale = "Rao") #' #[1] 0.813 -#' hydrophobicity("QWGRRCCGWGPGRRYCVRWC","Rose") +#' hydrophobicity(seq = "QWGRRCCGWGPGRRYCVRWC",scale = "Rose") #' #[1] 0.7575 -#' hydrophobicity("QWGRRCCGWGPGRRYCVRWC","Roseman") +#' hydrophobicity(seq = "QWGRRCCGWGPGRRYCVRWC",scale = "Roseman") #' #[1] -0.495 -#' hydrophobicity("QWGRRCCGWGPGRRYCVRWC","Sweet") +#' hydrophobicity(seq = "QWGRRCCGWGPGRRYCVRWC",scale = "Sweet") #' #[1] -0.1135 -#' hydrophobicity("QWGRRCCGWGPGRRYCVRWC","Tanford") +#' hydrophobicity(seq = "QWGRRCCGWGPGRRYCVRWC",scale = "Tanford") #' #[1] -0.2905 -#' hydrophobicity("QWGRRCCGWGPGRRYCVRWC","Welling") +#' hydrophobicity(seq = "QWGRRCCGWGPGRRYCVRWC",scale = "Welling") #' #[1] -0.666 -#' hydrophobicity("QWGRRCCGWGPGRRYCVRWC","Wilson") +#' hydrophobicity(seq = "QWGRRCCGWGPGRRYCVRWC",scale = "Wilson") #' #[1] 3.16 -#' hydrophobicity("QWGRRCCGWGPGRRYCVRWC","Wolfenden") +#' hydrophobicity(seq = "QWGRRCCGWGPGRRYCVRWC",scale = "Wolfenden") #' #[1] -6.307 -#' hydrophobicity("QWGRRCCGWGPGRRYCVRWC","Zimmerman") +#' hydrophobicity(seq = "QWGRRCCGWGPGRRYCVRWC",scale = "Zimmerman") #' #[1] 0.943 hydrophobicity <- function(seq, scale = "KyteDoolittle") { seq <- gsub("[[:space:]]+", "", seq) diff --git a/R/instaindex.R b/R/instaindex.R index e23d4aa..7561bd4 100755 --- a/R/instaindex.R +++ b/R/instaindex.R @@ -10,7 +10,7 @@ #' # SEQUENCE: QWGRRCCGWGPGRRYCVRWC #' # The instability index (II) is computed to be 83.68 #' -#' instaindex("QWGRRCCGWGPGRRYCVRWC") +#' instaindex(seq = "QWGRRCCGWGPGRRYCVRWC") #' # [1] 83.68 #' instaindex <- function(seq) { diff --git a/R/lengthpep.R b/R/lengthpep.R index 327d1dc..003060c 100755 --- a/R/lengthpep.R +++ b/R/lengthpep.R @@ -8,7 +8,7 @@ #' # SEQUENCE: QWGRRCCGWGPGRRYCVRWC #' # Number of amino acids: 20 #' -#' lengthpep("QWGRRCCGWGPGRRYCVRWC") +#' lengthpep(seq = "QWGRRCCGWGPGRRYCVRWC") #' # [1] 20 lengthpep <- function(seq) { seq <- gsub("[[:space:]]+", "", seq) diff --git a/R/membpos.R b/R/membpos.R index bf2127e..f441295 100755 --- a/R/membpos.R +++ b/R/membpos.R @@ -8,7 +8,7 @@ #' #' D. Eisenberg, R. M. Weiss, and T. C. Terwilliger. The helical hydrophobic moment: A measure of the amphiphilicity of a helix. Nature, 299(5881):371-374, 1982. [p7, 8] #' @details Eisenberg et al. (1982) found a correlation between hydrophobicity and hydrophobic moment that defines the protein section as globular, transmembrane or superficial. The function calculates the hydrophobicity (H) and hydrophobic moment (uH) based on the standardized scale of Eisenberg (1984) using windows of 11 amino acids for calculate the theoretical fragment type. -#' @examples membpos("ARQQNLFINFCLILIFLLLI",100) +#' @examples membpos(seq = "ARQQNLFINFCLILIFLLLI",angle = 100) #' # Pep H uH MembPos #' # 1 ARQQNLFINFCL 0.083 0.353 Globular #' # 2 RQQNLFINFCLI 0.147 0.317 Globular @@ -20,7 +20,7 @@ #' # 8 INFCLILIFLLL 0.944 0.108 Transmembrane #' # 9 NFCLILIFLLLI 0.944 0.132 Transmembrane #' -#' membpos("ARQQNLFINFCLILIFLLLI",160) +#' membpos(seq = "ARQQNLFINFCLILIFLLLI",angle = 160) #' # Pep H uH MembPos #' # 1 ARQQNLFINFCL 0.083 0.467 Globular #' # 2 RQQNLFINFCLI 0.147 0.467 Globular diff --git a/R/mw.R b/R/mw.R index 032fbc2..f64fe17 100755 --- a/R/mw.R +++ b/R/mw.R @@ -11,8 +11,11 @@ #' # SEQUENCE: QWGRRCCGWGPGRRYCVRWC #' # Theoretical pI/Mw: 9.88 / 2485.91 #' -#' mw("QWGRRCCGWGPGRRYCVRWC") +#' mw(seq = "QWGRRCCGWGPGRRYCVRWC",monoisotopic = FALSE) #' # [1] 2485.911 +#' +#' mw(seq = "QWGRRCCGWGPGRRYCVRWC",monoisotopic = TRUE) +#' # [1] 2484.12 mw <- function(seq, monoisotopic = FALSE) { seq <- gsub("[[:space:]]", "", seq) # Create the weight scale diff --git a/R/pI.R b/R/pI.R index 0754950..476cc6c 100755 --- a/R/pI.R +++ b/R/pI.R @@ -9,7 +9,7 @@ #' # SEQUENCE: QWGRRCCGWGPGRRYCVRWC #' # Theoretical pI: 9.88 #' -#' pI("QWGRRCCGWGPGRRYCVRWC","Bjellqvist") +#' pI(seq= "QWGRRCCGWGPGRRYCVRWC",pKscale= "Bjellqvist") #' # [1] 9.881 #' #' # COMPARED TO EMBOSS PEPSTATS @@ -17,24 +17,24 @@ #' # SEQUENCE: QWGRRCCGWGPGRRYCVRWC #' # Isoelectric Point = 9.7158 #' -#' pI("QWGRRCCGWGPGRRYCVRWC","EMBOSS") +#' pI(seq= "QWGRRCCGWGPGRRYCVRWC",pKscale= "EMBOSS") #' # [1] 9.716 #' #' # OTHER SCALES #' -#' pI("QWGRRCCGWGPGRRYCVRWC","Murray") +#' pI(seq= "QWGRRCCGWGPGRRYCVRWC",pKscale= "Murray") #' # [1] 9.818 -#' pI("QWGRRCCGWGPGRRYCVRWC","Sillero") +#' pI(seq= "QWGRRCCGWGPGRRYCVRWC",pKscale= "Sillero") #' # [1] 9.891 -#' pI("QWGRRCCGWGPGRRYCVRWC","Solomon") +#' pI(seq= "QWGRRCCGWGPGRRYCVRWC",pKscale= "Solomon") #' # [1] 9.582 -#' pI("QWGRRCCGWGPGRRYCVRWC","Stryer") +#' pI(seq= "QWGRRCCGWGPGRRYCVRWC",pKscale= "Stryer") #' # [1] 9.623 -#' pI("QWGRRCCGWGPGRRYCVRWC","Lehninger") +#' pI(seq= "QWGRRCCGWGPGRRYCVRWC",pKscale= "Lehninger") #' # [1] 9.931 -#' pI("QWGRRCCGWGPGRRYCVRWC","Dawson") +#' pI(seq= "QWGRRCCGWGPGRRYCVRWC",pKscale= "Dawson") #' # [1] 9.568 -#' pI("QWGRRCCGWGPGRRYCVRWC","Rodwell") +#' pI(seq= "QWGRRCCGWGPGRRYCVRWC",pKscale= "Rodwell") #' # [1] 9.718 pI <- function (seq, pKscale = "EMBOSS") { seq <- gsub("[[:space:]]+", "", seq) diff --git a/R/plot.xvg.R b/R/plot.xvg.R index a0c1d2a..35bee41 100755 --- a/R/plot.xvg.R +++ b/R/plot.xvg.R @@ -1,16 +1,18 @@ #' @export plot.xvg #' @rawNamespace S3method(plot,xvg) #' @title Plot time series from GROMACS XVG files +#' #' @param x A .XVG output file of the GROMACS molecular dynamics package #' @param ... Arguments to be passed to methods, such as graphical parameters. +#' #' @description Read and plot output data from a XVG format file. #' @references Pronk, S., Pall, S., Schulz, R., Larsson, P., Bjelkmar, P., Apostolov, R., ... & Lindahl, E. (2013). GROMACS 4.5: a high-throughput and highly parallel open source molecular simulation toolkit. Bioinformatics, 29 (7), 845-854. #' @details GROMACS (GROningen MAchine for Chemical Simulations) is a molecular dynamics package designed for simulations of proteins, lipids and nucleic acids. It is free, open source software released under the GNU General Public License. #' The file format used by GROMACS is XVG. This format can be displayed in graphical form through the GRACE program on UNIX/LINUX systems and the GNUPlot program on Windows. XVG files are plain text files containing tabular data separated by tabulators and two types of comments which contain data labels. Although manual editing is possible, this is not a viable option when working with multiple files of this type. #' For ease of reading, information management and data plotting, the functions \code{read.xvg} and \code{plot.xvg} were incorporated. #' @author Daniel Osorio -#' @examples file <- system.file("xvg-files/epot.xvg",package="Peptides") -#' plot.xvg(file) +#' @examples XVGfile <- system.file("xvg-files/epot.xvg",package="Peptides") +#' plot.xvg(XVGfile) plot.xvg <- function(x, ...) { # Read flat file diff --git a/R/read.xvg.R b/R/read.xvg.R index 3d4bce0..cc10487 100755 --- a/R/read.xvg.R +++ b/R/read.xvg.R @@ -8,8 +8,8 @@ #' The file format used by GROMACS is XVG. This format can be displayed in graphical form through the GRACE program on UNIX/LINUX systems and the GNUPlot program on Windows. XVG files are plain text files containing tabular data separated by tabulators and two types of comments which contain data labels. Although manual editing is possible, this is not a viable option when working with multiple files of this type. #' For ease of reading, information management and data plotting, the functions \code{read.xvg} and \code{plot.xvg} were incorporated. #' @examples # READING FILE -#' file <- system.file("xvg-files/epot.xvg",package="Peptides") -#' read.xvg(file) +#' XVGfile <- system.file("xvg-files/epot.xvg",package="Peptides") +#' read.xvg(XVGfile) #' #' # Time (ps) Potential #' # 1 1 6672471040 @@ -28,6 +28,11 @@ read.xvg <- function(file) { replacement = "", x = content[grep(pattern = "^@ s[[:digit:]]+", x = content)]) headers <- gsub("\\\"", "", headers) + xlabel <- + gsub("@[[:space:]]+xaxis[[:space:]]+label[[:space:]]+", + "", + content[grep("^@ xaxis", content)]) + xlabel <- gsub("\"", "", xlabel) # Extracting the data content <- sub("#", replacement = "@", content) content <- content[!grepl("@", content)] @@ -40,7 +45,7 @@ read.xvg <- function(file) { byrow = TRUE ) # Asign colnames - colnames(content) <- c("Time", headers) + colnames(content) <- c(xlabel, headers) # Return a matrix return(content) } diff --git a/man/boman.Rd b/man/boman.Rd index 2b5c94f..35cd8fe 100644 --- a/man/boman.Rd +++ b/man/boman.Rd @@ -26,7 +26,7 @@ The potential protein interaction index was proposed by Boman (2003) as an easy # SEQUENCE: FLPVLAGLTPSIVPKLVCLLTKKC # BOMAN INDEX -1.24 -boman(seq = "FLPVLAGLTPSIVPKLVCLLTKKC") +boman(seq= "FLPVLAGLTPSIVPKLVCLLTKKC") # [1] -1.235833 } diff --git a/man/charge.Rd b/man/charge.Rd index cceb82a..ff5e53f 100644 --- a/man/charge.Rd +++ b/man/charge.Rd @@ -22,23 +22,23 @@ This function computes the net charge of a protein sequence based on the Henders # SEQUENCE: FLPVLAGLTPSIVPKLVCLLTKKC # Charge = 3.0 -charge(seq="FLPVLAGLTPSIVPKLVCLLTKKC",pH=7, pKscale="Bjellqvist") +charge(seq= "FLPVLAGLTPSIVPKLVCLLTKKC",pH= 7, pKscale= "Bjellqvist") # [1] 2.737303 -charge(seq="FLPVLAGLTPSIVPKLVCLLTKKC",pH=7, pKscale="EMBOSS") +charge(seq= "FLPVLAGLTPSIVPKLVCLLTKKC",pH= 7, pKscale= "EMBOSS") # [1] 2.914112 -charge(seq="FLPVLAGLTPSIVPKLVCLLTKKC",pH=7, pKscale="Murray") +charge(seq= "FLPVLAGLTPSIVPKLVCLLTKKC",pH= 7, pKscale= "Murray") # [1] 2.907541 -charge(seq="FLPVLAGLTPSIVPKLVCLLTKKC",pH=7, pKscale="Sillero") +charge(seq= "FLPVLAGLTPSIVPKLVCLLTKKC",pH= 7, pKscale= "Sillero") # [1] 2.919812 -charge(seq="FLPVLAGLTPSIVPKLVCLLTKKC",pH=7, pKscale="Solomon") +charge(seq= "FLPVLAGLTPSIVPKLVCLLTKKC",pH= 7, pKscale= "Solomon") # [1] 2.844406 -charge(seq="FLPVLAGLTPSIVPKLVCLLTKKC",pH=7, pKscale="Stryer") +charge(seq= "FLPVLAGLTPSIVPKLVCLLTKKC",pH= 7, pKscale= "Stryer") # [1] 2.876504 -charge(seq="FLPVLAGLTPSIVPKLVCLLTKKC",pH=7, pKscale="Lehninger") +charge(seq= "FLPVLAGLTPSIVPKLVCLLTKKC",pH= 7, pKscale= "Lehninger") # [1] 2.87315 -charge(seq="FLPVLAGLTPSIVPKLVCLLTKKC",pH=7, pKscale="Dawson") +charge(seq= "FLPVLAGLTPSIVPKLVCLLTKKC",pH= 7, pKscale= "Dawson") # [1] 2.844406 -charge(seq="FLPVLAGLTPSIVPKLVCLLTKKC",pH=7, pKscale="Rodwell") +charge(seq= "FLPVLAGLTPSIVPKLVCLLTKKC",pH= 7, pKscale= "Rodwell") # [1] 2.819755 # COMPARED TO YADAMP @@ -47,15 +47,15 @@ charge(seq="FLPVLAGLTPSIVPKLVCLLTKKC",pH=7, pKscale="Rodwell") # CHARGE pH5: 3.00 # CHARGE pH7: 2.91 # CHARGE pH9: 1.09 -charge(seq="FLPVLAGLTPSIVPKLVCLLTKKC",pH=5, pKscale="EMBOSS") +charge(seq= "FLPVLAGLTPSIVPKLVCLLTKKC",pH= 5, pKscale= "EMBOSS") # [1] 3.037398 -charge(seq="FLPVLAGLTPSIVPKLVCLLTKKC",pH=7, pKscale="EMBOSS") +charge(seq= "FLPVLAGLTPSIVPKLVCLLTKKC",pH= 7, pKscale= "EMBOSS") # [1] 2.914112 -charge(seq="FLPVLAGLTPSIVPKLVCLLTKKC",pH=9, pKscale="EMBOSS") +charge(seq= "FLPVLAGLTPSIVPKLVCLLTKKC",pH= 9, pKscale= "EMBOSS") # [1] 0.7184524 # JUST ONE COMMAND -charge(seq="FLPVLAGLTPSIVPKLVCLLTKKC",pH=seq(from = 5,to = 9,by = 2), pKscale="EMBOSS") +charge(seq= "FLPVLAGLTPSIVPKLVCLLTKKC",pH= seq(from = 5,to = 9,by = 2), pKscale= "EMBOSS") # [1] 3.0373984 2.9141123 0.7184524 } \references{ diff --git a/man/crucianiProperties.Rd b/man/crucianiProperties.Rd index d30c54b..663209f 100644 --- a/man/crucianiProperties.Rd +++ b/man/crucianiProperties.Rd @@ -16,7 +16,7 @@ The computed average of Cruciani properties of all the amino acids in the corres This function calculates the Cruciani properties of an amino-acids sequence using the scaled principal component scores that summarize a broad set of descriptors calculated based on the interaction of each amino acid residue with several chemical groups (or "probes"), such as charged ions, methyl, hydroxyl groups, and so forth. } \examples{ -crucianiProperties("QWGRRCCGWGPGRRYCVRWC") +crucianiProperties(seq = "QWGRRCCGWGPGRRYCVRWC") # PP1 PP2 PP3 # -0.1130 -0.0220 0.2735 } diff --git a/man/hydrophobicity.Rd b/man/hydrophobicity.Rd index fb946f5..df09f32 100644 --- a/man/hydrophobicity.Rd +++ b/man/hydrophobicity.Rd @@ -26,81 +26,81 @@ The hydrophobicity is an important stabilization force in protein folding; this # SEQUENCE: QWGRRCCGWGPGRRYCVRWC # GRAVY: -0.950 -hydrophobicity("QWGRRCCGWGPGRRYCVRWC","Aboderin") +hydrophobicity(seq = "QWGRRCCGWGPGRRYCVRWC",scale = "Aboderin") #[1] 3.84 -hydrophobicity("QWGRRCCGWGPGRRYCVRWC","AbrahamLeo") +hydrophobicity(seq = "QWGRRCCGWGPGRRYCVRWC",scale = "AbrahamLeo") #[1] 0.092 -hydrophobicity("QWGRRCCGWGPGRRYCVRWC","Argos") +hydrophobicity(seq = "QWGRRCCGWGPGRRYCVRWC",scale = "Argos") #[1] 1.033 -hydrophobicity("QWGRRCCGWGPGRRYCVRWC","BlackMould") +hydrophobicity(seq = "QWGRRCCGWGPGRRYCVRWC",scale = "BlackMould") #[1] 0.50125 -hydrophobicity("QWGRRCCGWGPGRRYCVRWC","BullBreese") +hydrophobicity(seq = "QWGRRCCGWGPGRRYCVRWC",scale = "BullBreese") #[1] 0.1575 -hydrophobicity("QWGRRCCGWGPGRRYCVRWC","Casari") +hydrophobicity(seq = "QWGRRCCGWGPGRRYCVRWC",scale = "Casari") #[1] 0.38 -hydrophobicity("QWGRRCCGWGPGRRYCVRWC","Chothia") +hydrophobicity(seq = "QWGRRCCGWGPGRRYCVRWC",scale = "Chothia") #[1] 0.262 -hydrophobicity("QWGRRCCGWGPGRRYCVRWC","Cid") +hydrophobicity(seq = "QWGRRCCGWGPGRRYCVRWC",scale = "Cid") #[1] 0.198 -hydrophobicity("QWGRRCCGWGPGRRYCVRWC","Cowan3.4") +hydrophobicity(seq = "QWGRRCCGWGPGRRYCVRWC",scale = "Cowan3.4") #[1] 0.0845 -hydrophobicity("QWGRRCCGWGPGRRYCVRWC","Cowan7.5") +hydrophobicity(seq = "QWGRRCCGWGPGRRYCVRWC",scale = "Cowan7.5") #[1] 0.0605 -hydrophobicity("QWGRRCCGWGPGRRYCVRWC","Eisenberg") +hydrophobicity(seq = "QWGRRCCGWGPGRRYCVRWC",scale = "Eisenberg") #[1] -0.3265 -hydrophobicity("QWGRRCCGWGPGRRYCVRWC","Engelman") +hydrophobicity(seq = "QWGRRCCGWGPGRRYCVRWC",scale = "Engelman") #[1] 2.31 -hydrophobicity("QWGRRCCGWGPGRRYCVRWC","Fasman") +hydrophobicity(seq = "QWGRRCCGWGPGRRYCVRWC",scale = "Fasman") #[1] -1.2905 -hydrophobicity("QWGRRCCGWGPGRRYCVRWC","Fauchere") +hydrophobicity(seq = "QWGRRCCGWGPGRRYCVRWC",scale = "Fauchere") #[1] 0.527 -hydrophobicity("QWGRRCCGWGPGRRYCVRWC","Goldsack") +hydrophobicity(seq = "QWGRRCCGWGPGRRYCVRWC",scale = "Goldsack") #[1] 1.2245 -hydrophobicity("QWGRRCCGWGPGRRYCVRWC","Guy") +hydrophobicity(seq = "QWGRRCCGWGPGRRYCVRWC",scale = "Guy") #[1] 0.193 -hydrophobicity("QWGRRCCGWGPGRRYCVRWC","HoppWoods") +hydrophobicity(seq = "QWGRRCCGWGPGRRYCVRWC",scale = "HoppWoods") #[1] -0.14 -hydrophobicity("QWGRRCCGWGPGRRYCVRWC","Janin") +hydrophobicity(seq = "QWGRRCCGWGPGRRYCVRWC",scale = "Janin") #[1] -0.105 -hydrophobicity("QWGRRCCGWGPGRRYCVRWC","Jones") +hydrophobicity(seq = "QWGRRCCGWGPGRRYCVRWC",scale = "Jones") #[1] 1.4675 -hydrophobicity("QWGRRCCGWGPGRRYCVRWC","Juretic") +hydrophobicity(seq = "QWGRRCCGWGPGRRYCVRWC",scale = "Juretic") #[1] -1.106 -hydrophobicity("QWGRRCCGWGPGRRYCVRWC","Kidera") +hydrophobicity(seq = "QWGRRCCGWGPGRRYCVRWC",scale = "Kidera") #[1] -0.0405 -hydrophobicity("QWGRRCCGWGPGRRYCVRWC","Kuhn") +hydrophobicity(seq = "QWGRRCCGWGPGRRYCVRWC",scale = "Kuhn") #[1] 0.9155 -hydrophobicity("QWGRRCCGWGPGRRYCVRWC","KyteDoolittle") +hydrophobicity(seq = "QWGRRCCGWGPGRRYCVRWC",scale = "KyteDoolittle") #[1] -0.95 -hydrophobicity("QWGRRCCGWGPGRRYCVRWC","Levitt") +hydrophobicity(seq = "QWGRRCCGWGPGRRYCVRWC",scale = "Levitt") #[1] -0.21 -hydrophobicity("QWGRRCCGWGPGRRYCVRWC","Manavalan") +hydrophobicity(seq = "QWGRRCCGWGPGRRYCVRWC",scale = "Manavalan") #[1] 13.0445 -hydrophobicity("QWGRRCCGWGPGRRYCVRWC","Miyazawa") +hydrophobicity(seq = "QWGRRCCGWGPGRRYCVRWC",scale = "Miyazawa") #[1] 5.739 -hydrophobicity("QWGRRCCGWGPGRRYCVRWC","Parker") +hydrophobicity(seq = "QWGRRCCGWGPGRRYCVRWC",scale = "Parker") #[1] 1.095 -hydrophobicity("QWGRRCCGWGPGRRYCVRWC","Ponnuswamy") +hydrophobicity(seq = "QWGRRCCGWGPGRRYCVRWC",scale = "Ponnuswamy") #[1] 0.851 -hydrophobicity("QWGRRCCGWGPGRRYCVRWC","Prabhakaran") +hydrophobicity(seq = "QWGRRCCGWGPGRRYCVRWC",scale = "Prabhakaran") #[1] 9.67 -hydrophobicity("QWGRRCCGWGPGRRYCVRWC","Rao") +hydrophobicity(seq = "QWGRRCCGWGPGRRYCVRWC",scale = "Rao") #[1] 0.813 -hydrophobicity("QWGRRCCGWGPGRRYCVRWC","Rose") +hydrophobicity(seq = "QWGRRCCGWGPGRRYCVRWC",scale = "Rose") #[1] 0.7575 -hydrophobicity("QWGRRCCGWGPGRRYCVRWC","Roseman") +hydrophobicity(seq = "QWGRRCCGWGPGRRYCVRWC",scale = "Roseman") #[1] -0.495 -hydrophobicity("QWGRRCCGWGPGRRYCVRWC","Sweet") +hydrophobicity(seq = "QWGRRCCGWGPGRRYCVRWC",scale = "Sweet") #[1] -0.1135 -hydrophobicity("QWGRRCCGWGPGRRYCVRWC","Tanford") +hydrophobicity(seq = "QWGRRCCGWGPGRRYCVRWC",scale = "Tanford") #[1] -0.2905 -hydrophobicity("QWGRRCCGWGPGRRYCVRWC","Welling") +hydrophobicity(seq = "QWGRRCCGWGPGRRYCVRWC",scale = "Welling") #[1] -0.666 -hydrophobicity("QWGRRCCGWGPGRRYCVRWC","Wilson") +hydrophobicity(seq = "QWGRRCCGWGPGRRYCVRWC",scale = "Wilson") #[1] 3.16 -hydrophobicity("QWGRRCCGWGPGRRYCVRWC","Wolfenden") +hydrophobicity(seq = "QWGRRCCGWGPGRRYCVRWC",scale = "Wolfenden") #[1] -6.307 -hydrophobicity("QWGRRCCGWGPGRRYCVRWC","Zimmerman") +hydrophobicity(seq = "QWGRRCCGWGPGRRYCVRWC",scale = "Zimmerman") #[1] 0.943 } \references{ diff --git a/man/instaindex.Rd b/man/instaindex.Rd index f3f8c2e..dbf8a39 100644 --- a/man/instaindex.Rd +++ b/man/instaindex.Rd @@ -21,7 +21,7 @@ This function calculates the instability index proposed by Guruprasad (1990). Th # SEQUENCE: QWGRRCCGWGPGRRYCVRWC # The instability index (II) is computed to be 83.68 -instaindex("QWGRRCCGWGPGRRYCVRWC") +instaindex(seq = "QWGRRCCGWGPGRRYCVRWC") # [1] 83.68 } diff --git a/man/lengthpep.Rd b/man/lengthpep.Rd index 1c68875..e19b9ac 100644 --- a/man/lengthpep.Rd +++ b/man/lengthpep.Rd @@ -21,6 +21,6 @@ All proteins are formed by linear chains of small residues known as amino acids # SEQUENCE: QWGRRCCGWGPGRRYCVRWC # Number of amino acids: 20 -lengthpep("QWGRRCCGWGPGRRYCVRWC") +lengthpep(seq = "QWGRRCCGWGPGRRYCVRWC") # [1] 20 } diff --git a/man/membpos.Rd b/man/membpos.Rd index cd71147..b4a48ad 100644 --- a/man/membpos.Rd +++ b/man/membpos.Rd @@ -21,7 +21,7 @@ This function calculates the theoretical class of a protein sequence based on th Eisenberg et al. (1982) found a correlation between hydrophobicity and hydrophobic moment that defines the protein section as globular, transmembrane or superficial. The function calculates the hydrophobicity (H) and hydrophobic moment (uH) based on the standardized scale of Eisenberg (1984) using windows of 11 amino acids for calculate the theoretical fragment type. } \examples{ -membpos("ARQQNLFINFCLILIFLLLI",100) +membpos(seq = "ARQQNLFINFCLILIFLLLI",angle = 100) # Pep H uH MembPos # 1 ARQQNLFINFCL 0.083 0.353 Globular # 2 RQQNLFINFCLI 0.147 0.317 Globular @@ -33,7 +33,7 @@ membpos("ARQQNLFINFCLILIFLLLI",100) # 8 INFCLILIFLLL 0.944 0.108 Transmembrane # 9 NFCLILIFLLLI 0.944 0.132 Transmembrane -membpos("ARQQNLFINFCLILIFLLLI",160) +membpos(seq = "ARQQNLFINFCLILIFLLLI",angle = 160) # Pep H uH MembPos # 1 ARQQNLFINFCL 0.083 0.467 Globular # 2 RQQNLFINFCLI 0.147 0.467 Globular diff --git a/man/mw.Rd b/man/mw.Rd index 19ec152..1be752d 100644 --- a/man/mw.Rd +++ b/man/mw.Rd @@ -26,8 +26,11 @@ The molecular weight is the sum of the masses of each atom constituting a molecu # SEQUENCE: QWGRRCCGWGPGRRYCVRWC # Theoretical pI/Mw: 9.88 / 2485.91 -mw("QWGRRCCGWGPGRRYCVRWC") +mw(seq = "QWGRRCCGWGPGRRYCVRWC",monoisotopic = FALSE) # [1] 2485.911 + +mw(seq = "QWGRRCCGWGPGRRYCVRWC",monoisotopic = TRUE) +# [1] 2484.12 } \references{ Gasteiger, E., Hoogland, C., Gattiker, A., Wilkins, M. R., Appel, R. D., & Bairoch, A. (2005). Protein identification and analysis tools on the ExPASy server. In The proteomics protocols handbook (pp. 571-607). Humana Press. Chicago diff --git a/man/pI.Rd b/man/pI.Rd index 520b70b..fa9eff7 100644 --- a/man/pI.Rd +++ b/man/pI.Rd @@ -23,7 +23,7 @@ The isoelectric point (pI) is the pH at which the net charge of the protein is e # SEQUENCE: QWGRRCCGWGPGRRYCVRWC # Theoretical pI: 9.88 -pI("QWGRRCCGWGPGRRYCVRWC","Bjellqvist") +pI(seq= "QWGRRCCGWGPGRRYCVRWC",pKscale= "Bjellqvist") # [1] 9.881 # COMPARED TO EMBOSS PEPSTATS @@ -31,23 +31,23 @@ pI("QWGRRCCGWGPGRRYCVRWC","Bjellqvist") # SEQUENCE: QWGRRCCGWGPGRRYCVRWC # Isoelectric Point = 9.7158 -pI("QWGRRCCGWGPGRRYCVRWC","EMBOSS") +pI(seq= "QWGRRCCGWGPGRRYCVRWC",pKscale= "EMBOSS") # [1] 9.716 # OTHER SCALES -pI("QWGRRCCGWGPGRRYCVRWC","Murray") +pI(seq= "QWGRRCCGWGPGRRYCVRWC",pKscale= "Murray") # [1] 9.818 -pI("QWGRRCCGWGPGRRYCVRWC","Sillero") +pI(seq= "QWGRRCCGWGPGRRYCVRWC",pKscale= "Sillero") # [1] 9.891 -pI("QWGRRCCGWGPGRRYCVRWC","Solomon") +pI(seq= "QWGRRCCGWGPGRRYCVRWC",pKscale= "Solomon") # [1] 9.582 -pI("QWGRRCCGWGPGRRYCVRWC","Stryer") +pI(seq= "QWGRRCCGWGPGRRYCVRWC",pKscale= "Stryer") # [1] 9.623 -pI("QWGRRCCGWGPGRRYCVRWC","Lehninger") +pI(seq= "QWGRRCCGWGPGRRYCVRWC",pKscale= "Lehninger") # [1] 9.931 -pI("QWGRRCCGWGPGRRYCVRWC","Dawson") +pI(seq= "QWGRRCCGWGPGRRYCVRWC",pKscale= "Dawson") # [1] 9.568 -pI("QWGRRCCGWGPGRRYCVRWC","Rodwell") +pI(seq= "QWGRRCCGWGPGRRYCVRWC",pKscale= "Rodwell") # [1] 9.718 } diff --git a/man/plot.xvg.Rd b/man/plot.xvg.Rd index 6b53e86..66dc599 100644 --- a/man/plot.xvg.Rd +++ b/man/plot.xvg.Rd @@ -20,8 +20,8 @@ The file format used by GROMACS is XVG. This format can be displayed in graphica For ease of reading, information management and data plotting, the functions \code{read.xvg} and \code{plot.xvg} were incorporated. } \examples{ -file <- system.file("xvg-files/epot.xvg",package="Peptides") -plot.xvg(file) +XVGfile <- system.file("xvg-files/epot.xvg",package="Peptides") +plot.xvg(XVGfile) } \references{ Pronk, S., Pall, S., Schulz, R., Larsson, P., Bjelkmar, P., Apostolov, R., ... & Lindahl, E. (2013). GROMACS 4.5: a high-throughput and highly parallel open source molecular simulation toolkit. Bioinformatics, 29 (7), 845-854. diff --git a/man/read.xvg.Rd b/man/read.xvg.Rd index 16e09d7..b0119f8 100644 --- a/man/read.xvg.Rd +++ b/man/read.xvg.Rd @@ -19,8 +19,8 @@ For ease of reading, information management and data plotting, the functions \co } \examples{ # READING FILE -file <- system.file("xvg-files/epot.xvg",package="Peptides") -read.xvg(file) +XVGfile <- system.file("xvg-files/epot.xvg",package="Peptides") +read.xvg(XVGfile) # Time (ps) Potential # 1 1 6672471040 From 8edad6e667b3dfc28e61629b55c8038e0897b0e7 Mon Sep 17 00:00:00 2001 From: Daniel Osorio Date: Thu, 2 Mar 2017 17:10:09 -0500 Subject: [PATCH 03/50] Zscales added --- data/Z.RData | Bin 0 -> 580 bytes 1 file changed, 0 insertions(+), 0 deletions(-) create mode 100644 data/Z.RData diff --git a/data/Z.RData b/data/Z.RData new file mode 100644 index 0000000000000000000000000000000000000000..fbc60e70cce9b938f7b09cb7cc132eb3c7c75f90 GIT binary patch literal 580 zcmV-K0=xYmiwFP!000001KpIrPgFq=$Cvlsne!yv5wFJfECnquvqtdF_#@tF6bX%m zb{dSG*3>jM+Coh$g~_ZKV}k}`aT*gN64U@jFdpZD-ud=@XI=t-!fo;9yKi>qz5UG0 z)TPA zI~g|L$d#vN8??SsnJ+$Ap}!^>HjBA6vM!8wm6|VHe#i$p<_2MHkc6$fLrZ?Vb_ML? zUB7&B#)eo&-x1dh#vjX-@3~0!Mfk4+2guyLdFR&sSQPxv>#0twsH?c7VpPQ$6=N!D zDk>_fD$c36pyIrWiz?2lxUAxeimNKFtGJ=!TKwoJd>06e2oR|4k6hcNAAricfIy$c zzw8-J&ACE3p+()1WbmFxTbbwIfK8izR(!}yNGf%cT;}L)l7lL5OS1X^-R7s07dC`- z8TbJ|==KV4S_LoHFFd!vlR8q=19;CZ@Zx8}uOa+|Kkp@Jo8%T8E|k1|O43lIE$=Pu z&_D2{UuYKImUUmGsXl@?|3TbdoVO=p6n5Dra9@04aDs=-X#6cFL8fRTdZEP8JwHe(BHf)_5L2* z>FNGDPcQ#>lE0r)_p6v&BYm`n{PBm!emvo}%v)05kHEcmc<(z$Mx4RKiBt`zY9v)B SQ*{baOy@rf957|G2LJ$x{wF;E literal 0 HcmV?d00001 From c1b7cba5189204c7f89b80e775d85f8e2627e244 Mon Sep 17 00:00:00 2001 From: jspaezp Date: Thu, 2 Mar 2017 17:44:36 -0500 Subject: [PATCH 04/50] generalized plot.xvg and read.xvg --- R/plot.xvg.R | 67 ++++++++++++++++++++-------------------------------- R/read.xvg.R | 57 +++++++++++++++++++++++++------------------- 2 files changed, 59 insertions(+), 65 deletions(-) diff --git a/R/plot.xvg.R b/R/plot.xvg.R index 35bee41..760e8a9 100755 --- a/R/plot.xvg.R +++ b/R/plot.xvg.R @@ -1,8 +1,7 @@ -#' @export plot.xvg -#' @rawNamespace S3method(plot,xvg) +#' @export plot_xvg #' @title Plot time series from GROMACS XVG files #' -#' @param x A .XVG output file of the GROMACS molecular dynamics package +#' @param XVGfile A .XVG output file of the GROMACS molecular dynamics package #' @param ... Arguments to be passed to methods, such as graphical parameters. #' #' @description Read and plot output data from a XVG format file. @@ -14,50 +13,36 @@ #' @examples XVGfile <- system.file("xvg-files/epot.xvg",package="Peptides") #' plot.xvg(XVGfile) -plot.xvg <- function(x, ...) { +plot_xvg <- function(XVGfile, ...) { # Read flat file - content <- readLines(x) - # Read colnames - headers <- - gsub("^@ s[[:digit:]]+ legend ", "", content[grep(pattern = "^@ s[[:digit:]]+", content)]) - headers <- gsub("\\\"", "", headers) - # Read axis and title - title <- - gsub("[[:punct:]]", "", gsub("@ title ", "", content[grep("^@ title", content)])) - xlabel <- - gsub("@[[:space:]]+xaxis[[:space:]]+label[[:space:]]+", - "", - content[grep("^@ xaxis", content)]) - xlabel <- gsub("\"", "", xlabel) - ylabel <- - gsub("@[[:space:]]+yaxis[[:space:]]+label[[:space:]]+", - "", - content[grep("^@ yaxis", content)]) - ylabel <- gsub("\"", "", ylabel) - # Extracting the data - content <- sub("#", replacement = "@", content) - content <- content[!grepl("@", content)] - content <- gsub("^[[:space:]]+", "", content) - content <- strsplit(content, "[[:space:]]+") - content <- - matrix( - data = as.numeric(unlist(content)), - ncol = length(headers) + 1, - byrow = TRUE - ) - # Asign colnames - colnames(content) <- c("Time", headers) - # Plot - graphics::par(mfcol = c(1, (dim(content)[2] - 1)), oma = c(0, 0, 2.5, 0)) - for (i in seq_len((dim(content)[2] - 1))) { + content <- read.xvg(XVGfile) + xlabel <- colnames(content)[[1]] + + try({ + # overwrites the x axis name if it exists + xlabel <- attr(content, 'xvg_labels')[1] + }) + + # Get graphical parameters to revert to them later + original_par <- par(no.readonly = TRUE) + + # Plot plot maximum 4 facets per row + graphics::par(mfcol = c((ncol(content) - 1) %/% 4 + 1, + min((ncol(content) - 1), 4)), + oma = c(0, 0, 2.5, 0)) + for (i in seq_len(ncol(content) - 1)) { + graphics::plot( x = content[, 1], y = content[, i + 1], type = "l", - ylab = headers[i], + ylab = colnames(content)[[i + 1]], xlab = xlabel, ... ) } - title(title, outer = TRUE) -} \ No newline at end of file + title(attr(content, 'title'), outer = TRUE) + + # Revert to the previous graphical parameters + par(original_par) +} diff --git a/R/read.xvg.R b/R/read.xvg.R index cc10487..a998bb4 100755 --- a/R/read.xvg.R +++ b/R/read.xvg.R @@ -1,6 +1,8 @@ -#' @export read.xvg +#' @export read_xvg #' @title Read output data from a XVG format file. +#' #' @param file A .XVG output file of the GROMACS molecular dynamics package +#' #' @description XVG is the default format file of the GROMACS molecular dynamics package, contains data formatted to be imported into the Grace 2-D plotting program. #' @references Pronk, S., Pall, S., Schulz, R., Larsson, P., Bjelkmar, P., Apostolov, R., ... & Lindahl, E. (2013). GROMACS 4.5: a high-throughput and highly parallel open source molecular simulation toolkit. Bioinformatics, 29 (7), 845-854. #' @author Daniel Osorio @@ -19,33 +21,40 @@ #' # 5 5 6015310336 #' # 6 6 5854271488 -read.xvg <- function(file) { +read_xvg <- function(file) { + ## Helper functions + # Remove quotes, starting and ending whitespaces + unquote <- function(x, ...) { gsub("\\\"|^\\s|\\s$", "", x, ...) } + + # Subsets a list for elments that match a regex and then removes that regex + perlgsub <- function(pattern, replacement, x, ...) { + gsub(pattern = pattern, + replacement = replacement, + x = grep(pattern = pattern, x, value = TRUE, perl = TRUE, ... ), + perl = TRUE, ...) + } + # Read flat file content <- readLines(file) - # Read colnames - headers <- - gsub(pattern = "^@ s[[:digit:]]+ legend ", - replacement = "", - x = content[grep(pattern = "^@ s[[:digit:]]+", x = content)]) - headers <- gsub("\\\"", "", headers) - xlabel <- - gsub("@[[:space:]]+xaxis[[:space:]]+label[[:space:]]+", - "", - content[grep("^@ xaxis", content)]) - xlabel <- gsub("\"", "", xlabel) + + # Read colnames and title + variables <- unquote(perlgsub("^@ s[0-9]+ legend ", "", content)) + xvg_labels <- perlgsub("^@ \\s+[a-z]axis\\s+label ", "", content) + xvg_labels <- unquote(unlist(strsplit(xvg_labels, ','))) + title <- unquote(perlgsub("^@ \\s+title ", "", content)) + # Extracting the data - content <- sub("#", replacement = "@", content) - content <- content[!grepl("@", content)] - content <- gsub("^[[:space:]]+", "", content) - content <- strsplit(content, "[[:space:]]+") - content <- - matrix( - data = as.numeric(unlist(content)), - ncol = length(headers) + 1, - byrow = TRUE - ) + content <- perlgsub('^\\s+', "", content) + content <- plyr::ldply(content, (function(x) {unlist(strsplit(x, "\\s+"))})) + # Asign colnames - colnames(content) <- c(xlabel, headers) + x_axis_label <- perlgsub('(?!=\\w+)\\W+\\(\\w*\\)$', "", xvg_labels) + colnames(content) <- c(x_axis_label, variables) + + # Add units and title as attribute + attr(content, 'xvg_labels') <- xvg_labels + attr(content, 'title') <- title + # Return a matrix return(content) } From afb59b074529ef70539e40e0a33e325862d576b9 Mon Sep 17 00:00:00 2001 From: jspaezp Date: Thu, 2 Mar 2017 17:48:16 -0500 Subject: [PATCH 05/50] added radial distribution function file --- .Rbuildignore | 2 + .gitignore | 4 + DESCRIPTION | 2 + NAMESPACE | 1 + Peptides.Rproj | 17 ++ inst/xvg-files/RDF.xvg | 490 +++++++++++++++++++++++++++++++++++++++++ 6 files changed, 516 insertions(+) create mode 100644 .Rbuildignore create mode 100644 .gitignore create mode 100644 Peptides.Rproj create mode 100644 inst/xvg-files/RDF.xvg diff --git a/.Rbuildignore b/.Rbuildignore new file mode 100644 index 0000000..91114bf --- /dev/null +++ b/.Rbuildignore @@ -0,0 +1,2 @@ +^.*\.Rproj$ +^\.Rproj\.user$ diff --git a/.gitignore b/.gitignore new file mode 100644 index 0000000..5b6a065 --- /dev/null +++ b/.gitignore @@ -0,0 +1,4 @@ +.Rproj.user +.Rhistory +.RData +.Ruserdata diff --git a/DESCRIPTION b/DESCRIPTION index a68b535..c354f18 100644 --- a/DESCRIPTION +++ b/DESCRIPTION @@ -5,6 +5,8 @@ Title: Calculate Indices and Theoretical Physicochemical Properties of Protein S Author: Daniel Osorio, Paola Rondon-Villarreal and Rodrigo Torres. Maintainer: Daniel Osorio URL: https://github.com/dosorio/Peptides/ +Depends: + plyr Suggests: RUnit Description: Calculate physicochemical properties and indices from amino-acid diff --git a/NAMESPACE b/NAMESPACE index bf08c34..2bd7067 100755 --- a/NAMESPACE +++ b/NAMESPACE @@ -21,3 +21,4 @@ export(plot.xvg) export(read.xvg) importFrom(stats,embed) importFrom(utils,data) +importFrom(plyr,ldply) diff --git a/Peptides.Rproj b/Peptides.Rproj new file mode 100644 index 0000000..21a4da0 --- /dev/null +++ b/Peptides.Rproj @@ -0,0 +1,17 @@ +Version: 1.0 + +RestoreWorkspace: Default +SaveWorkspace: Default +AlwaysSaveHistory: Default + +EnableCodeIndexing: Yes +UseSpacesForTab: Yes +NumSpacesForTab: 2 +Encoding: UTF-8 + +RnwWeave: Sweave +LaTeX: pdfLaTeX + +BuildType: Package +PackageUseDevtools: Yes +PackageInstallArgs: --no-multiarch --with-keep.source diff --git a/inst/xvg-files/RDF.xvg b/inst/xvg-files/RDF.xvg new file mode 100644 index 0000000..06db9e4 --- /dev/null +++ b/inst/xvg-files/RDF.xvg @@ -0,0 +1,490 @@ +# This file was created Wed Feb 15 20:41:38 2017 +# Created by: +# :-) GROMACS - gmx rdf, VERSION 5.1.4 (-: +# +# Executable: /usr/local/gromacs/bin/gmx +# Data prefix: /usr/local/gromacs +# Command line: +# gmx rdf -n index.ndx -o RDF_OO -f production_run02.xtc -s production_run02.tpr +# gmx rdf is part of G R O M A C S: +# +# Great Red Owns Many ACres of Sand +# +@ title "Radial distribution" +@ xaxis label "r (nm)" +@ yaxis label "g(r)" +@TYPE xy +@ subtitle "reference OW" +@ view 0.15, 0.15, 0.75, 0.85 +@ legend on +@ legend box on +@ legend loctype view +@ legend 0.78, 0.8 +@ legend length 2 +@ s0 legend "OW" + 0.000 0.000 + 0.002 0.000 + 0.004 0.000 + 0.006 0.000 + 0.008 0.000 + 0.010 0.000 + 0.012 0.000 + 0.014 0.000 + 0.016 0.000 + 0.018 0.000 + 0.020 0.000 + 0.022 0.000 + 0.024 0.000 + 0.026 0.000 + 0.028 0.000 + 0.030 0.000 + 0.032 0.000 + 0.034 0.000 + 0.036 0.000 + 0.038 0.000 + 0.040 0.000 + 0.042 0.000 + 0.044 0.000 + 0.046 0.000 + 0.048 0.000 + 0.050 0.000 + 0.052 0.000 + 0.054 0.000 + 0.056 0.000 + 0.058 0.000 + 0.060 0.000 + 0.062 0.000 + 0.064 0.000 + 0.066 0.000 + 0.068 0.000 + 0.070 0.000 + 0.072 0.000 + 0.074 0.000 + 0.076 0.000 + 0.078 0.000 + 0.080 0.000 + 0.082 0.000 + 0.084 0.000 + 0.086 0.000 + 0.088 0.000 + 0.090 0.000 + 0.092 0.000 + 0.094 0.000 + 0.096 0.000 + 0.098 0.000 + 0.100 0.000 + 0.102 0.000 + 0.104 0.000 + 0.106 0.000 + 0.108 0.000 + 0.110 0.000 + 0.112 0.000 + 0.114 0.000 + 0.116 0.000 + 0.118 0.000 + 0.120 0.000 + 0.122 0.000 + 0.124 0.000 + 0.126 0.000 + 0.128 0.000 + 0.130 0.000 + 0.132 0.000 + 0.134 0.000 + 0.136 0.000 + 0.138 0.000 + 0.140 0.000 + 0.142 0.000 + 0.144 0.000 + 0.146 0.000 + 0.148 0.000 + 0.150 0.000 + 0.152 0.000 + 0.154 0.000 + 0.156 0.000 + 0.158 0.000 + 0.160 0.000 + 0.162 0.000 + 0.164 0.000 + 0.166 0.000 + 0.168 0.000 + 0.170 0.000 + 0.172 0.000 + 0.174 0.000 + 0.176 0.000 + 0.178 0.000 + 0.180 0.000 + 0.182 0.000 + 0.184 0.000 + 0.186 0.000 + 0.188 0.000 + 0.190 0.000 + 0.192 0.000 + 0.194 0.000 + 0.196 0.000 + 0.198 0.000 + 0.200 0.000 + 0.202 0.000 + 0.204 0.000 + 0.206 0.000 + 0.208 0.000 + 0.210 0.000 + 0.212 0.000 + 0.214 0.000 + 0.216 0.000 + 0.218 0.000 + 0.220 0.000 + 0.222 0.000 + 0.224 0.000 + 0.226 0.000 + 0.228 0.000 + 0.230 0.000 + 0.232 0.000 + 0.234 0.000 + 0.236 0.000 + 0.238 0.000 + 0.240 0.000 + 0.242 0.001 + 0.244 0.004 + 0.246 0.013 + 0.248 0.035 + 0.250 0.082 + 0.252 0.176 + 0.254 0.335 + 0.256 0.545 + 0.258 0.836 + 0.260 1.189 + 0.262 1.569 + 0.264 1.960 + 0.266 2.325 + 0.268 2.630 + 0.270 2.861 + 0.272 3.025 + 0.274 3.059 + 0.276 3.071 + 0.278 3.010 + 0.280 2.855 + 0.282 2.730 + 0.284 2.555 + 0.286 2.370 + 0.288 2.202 + 0.290 2.019 + 0.292 1.854 + 0.294 1.695 + 0.296 1.564 + 0.298 1.443 + 0.300 1.322 + 0.302 1.238 + 0.304 1.151 + 0.306 1.083 + 0.308 1.026 + 0.310 0.983 + 0.312 0.942 + 0.314 0.905 + 0.316 0.885 + 0.318 0.857 + 0.320 0.840 + 0.322 0.831 + 0.324 0.821 + 0.326 0.812 + 0.328 0.810 + 0.330 0.802 + 0.332 0.797 + 0.334 0.811 + 0.336 0.804 + 0.338 0.806 + 0.340 0.808 + 0.342 0.816 + 0.344 0.821 + 0.346 0.816 + 0.348 0.825 + 0.350 0.832 + 0.352 0.834 + 0.354 0.842 + 0.356 0.843 + 0.358 0.843 + 0.360 0.854 + 0.362 0.861 + 0.364 0.874 + 0.366 0.877 + 0.368 0.889 + 0.370 0.886 + 0.372 0.899 + 0.374 0.899 + 0.376 0.905 + 0.378 0.919 + 0.380 0.926 + 0.382 0.930 + 0.384 0.941 + 0.386 0.943 + 0.388 0.951 + 0.390 0.958 + 0.392 0.969 + 0.394 0.978 + 0.396 0.989 + 0.398 1.000 + 0.400 0.998 + 0.402 1.005 + 0.404 1.010 + 0.406 1.022 + 0.408 1.024 + 0.410 1.031 + 0.412 1.041 + 0.414 1.039 + 0.416 1.050 + 0.418 1.065 + 0.420 1.065 + 0.422 1.068 + 0.424 1.072 + 0.426 1.079 + 0.428 1.085 + 0.430 1.092 + 0.432 1.092 + 0.434 1.094 + 0.436 1.101 + 0.438 1.096 + 0.440 1.108 + 0.442 1.116 + 0.444 1.110 + 0.446 1.112 + 0.448 1.109 + 0.450 1.111 + 0.452 1.108 + 0.454 1.114 + 0.456 1.114 + 0.458 1.106 + 0.460 1.116 + 0.462 1.103 + 0.464 1.103 + 0.466 1.098 + 0.468 1.099 + 0.470 1.097 + 0.472 1.089 + 0.474 1.089 + 0.476 1.086 + 0.478 1.085 + 0.480 1.077 + 0.482 1.068 + 0.484 1.066 + 0.486 1.058 + 0.488 1.053 + 0.490 1.055 + 0.492 1.048 + 0.494 1.036 + 0.496 1.032 + 0.498 1.034 + 0.500 1.027 + 0.502 1.017 + 0.504 1.018 + 0.506 1.011 + 0.508 1.002 + 0.510 0.999 + 0.512 0.998 + 0.514 0.991 + 0.516 0.985 + 0.518 0.983 + 0.520 0.982 + 0.522 0.970 + 0.524 0.967 + 0.526 0.964 + 0.528 0.958 + 0.530 0.954 + 0.532 0.948 + 0.534 0.944 + 0.536 0.943 + 0.538 0.937 + 0.540 0.930 + 0.542 0.926 + 0.544 0.925 + 0.546 0.918 + 0.548 0.914 + 0.550 0.908 + 0.552 0.910 + 0.554 0.910 + 0.556 0.906 + 0.558 0.906 + 0.560 0.905 + 0.562 0.902 + 0.564 0.900 + 0.566 0.899 + 0.568 0.902 + 0.570 0.901 + 0.572 0.903 + 0.574 0.908 + 0.576 0.910 + 0.578 0.912 + 0.580 0.914 + 0.582 0.912 + 0.584 0.918 + 0.586 0.921 + 0.588 0.922 + 0.590 0.925 + 0.592 0.928 + 0.594 0.931 + 0.596 0.937 + 0.598 0.939 + 0.600 0.942 + 0.602 0.951 + 0.604 0.952 + 0.606 0.957 + 0.608 0.961 + 0.610 0.966 + 0.612 0.971 + 0.614 0.973 + 0.616 0.976 + 0.618 0.980 + 0.620 0.984 + 0.622 0.988 + 0.624 0.995 + 0.626 0.993 + 0.628 0.998 + 0.630 0.999 + 0.632 1.003 + 0.634 1.007 + 0.636 1.014 + 0.638 1.012 + 0.640 1.017 + 0.642 1.017 + 0.644 1.023 + 0.646 1.022 + 0.648 1.029 + 0.650 1.031 + 0.652 1.030 + 0.654 1.030 + 0.656 1.038 + 0.658 1.034 + 0.660 1.041 + 0.662 1.040 + 0.664 1.034 + 0.666 1.044 + 0.668 1.039 + 0.670 1.042 + 0.672 1.043 + 0.674 1.047 + 0.676 1.047 + 0.678 1.044 + 0.680 1.045 + 0.682 1.047 + 0.684 1.045 + 0.686 1.044 + 0.688 1.042 + 0.690 1.045 + 0.692 1.042 + 0.694 1.043 + 0.696 1.044 + 0.698 1.040 + 0.700 1.037 + 0.702 1.040 + 0.704 1.038 + 0.706 1.038 + 0.708 1.037 + 0.710 1.035 + 0.712 1.029 + 0.714 1.033 + 0.716 1.032 + 0.718 1.030 + 0.720 1.026 + 0.722 1.026 + 0.724 1.023 + 0.726 1.017 + 0.728 1.019 + 0.730 1.018 + 0.732 1.016 + 0.734 1.014 + 0.736 1.012 + 0.738 1.011 + 0.740 1.009 + 0.742 1.007 + 0.744 1.009 + 0.746 1.006 + 0.748 0.999 + 0.750 1.002 + 0.752 1.001 + 0.754 0.998 + 0.756 0.995 + 0.758 1.001 + 0.760 0.995 + 0.762 0.995 + 0.764 0.996 + 0.766 0.995 + 0.768 0.992 + 0.770 0.993 + 0.772 0.990 + 0.774 0.991 + 0.776 0.988 + 0.778 0.984 + 0.780 0.985 + 0.782 0.989 + 0.784 0.987 + 0.786 0.988 + 0.788 0.988 + 0.790 0.985 + 0.792 0.980 + 0.794 0.987 + 0.796 0.984 + 0.798 0.982 + 0.800 0.986 + 0.802 0.984 + 0.804 0.987 + 0.806 0.988 + 0.808 0.988 + 0.810 0.987 + 0.812 0.988 + 0.814 0.985 + 0.816 0.987 + 0.818 0.985 + 0.820 0.987 + 0.822 0.989 + 0.824 0.991 + 0.826 0.987 + 0.828 0.990 + 0.830 0.992 + 0.832 0.992 + 0.834 0.993 + 0.836 0.991 + 0.838 0.992 + 0.840 0.992 + 0.842 0.992 + 0.844 0.994 + 0.846 0.994 + 0.848 0.995 + 0.850 0.992 + 0.852 0.994 + 0.854 0.996 + 0.856 0.998 + 0.858 0.999 + 0.860 1.000 + 0.862 1.000 + 0.864 0.996 + 0.866 0.994 + 0.868 0.996 + 0.870 1.001 + 0.872 1.000 + 0.874 0.999 + 0.876 1.000 + 0.878 1.001 + 0.880 1.002 + 0.882 1.001 + 0.884 1.000 + 0.886 1.003 + 0.888 1.000 + 0.890 1.001 + 0.892 1.002 + 0.894 1.002 + 0.896 1.000 + 0.898 1.001 + 0.900 1.001 + 0.902 0.999 + 0.904 1.001 + 0.906 1.002 + 0.908 1.005 + 0.910 1.003 + 0.912 0.998 + 0.914 1.002 + 0.916 1.000 + 0.918 1.000 + 0.920 1.001 + 0.922 1.004 + 0.924 1.000 + 0.926 0.998 + 0.928 0.999 + 0.930 0.998 From f75eb5b731bdc68c46e385ccf673d4c396e9ba42 Mon Sep 17 00:00:00 2001 From: jspaezp Date: Thu, 2 Mar 2017 17:51:49 -0500 Subject: [PATCH 06/50] removal of Rproj file --- .gitignore | 1 + Peptides.Rproj | 17 ----------------- 2 files changed, 1 insertion(+), 17 deletions(-) delete mode 100644 Peptides.Rproj diff --git a/.gitignore b/.gitignore index 5b6a065..1ca3e0d 100644 --- a/.gitignore +++ b/.gitignore @@ -1,4 +1,5 @@ .Rproj.user +**.Rproj .Rhistory .RData .Ruserdata diff --git a/Peptides.Rproj b/Peptides.Rproj deleted file mode 100644 index 21a4da0..0000000 --- a/Peptides.Rproj +++ /dev/null @@ -1,17 +0,0 @@ -Version: 1.0 - -RestoreWorkspace: Default -SaveWorkspace: Default -AlwaysSaveHistory: Default - -EnableCodeIndexing: Yes -UseSpacesForTab: Yes -NumSpacesForTab: 2 -Encoding: UTF-8 - -RnwWeave: Sweave -LaTeX: pdfLaTeX - -BuildType: Package -PackageUseDevtools: Yes -PackageInstallArgs: --no-multiarch --with-keep.source From 7265ba7da006f21e4c4f1364573e5f86176237be Mon Sep 17 00:00:00 2001 From: jspaezp Date: Thu, 2 Mar 2017 19:05:48 -0500 Subject: [PATCH 07/50] removed plyr as a dependency --- DESCRIPTION | 2 -- NAMESPACE | 2 -- R/read.xvg.R | 11 ++++++++--- 3 files changed, 8 insertions(+), 7 deletions(-) diff --git a/DESCRIPTION b/DESCRIPTION index c354f18..a68b535 100644 --- a/DESCRIPTION +++ b/DESCRIPTION @@ -5,8 +5,6 @@ Title: Calculate Indices and Theoretical Physicochemical Properties of Protein S Author: Daniel Osorio, Paola Rondon-Villarreal and Rodrigo Torres. Maintainer: Daniel Osorio URL: https://github.com/dosorio/Peptides/ -Depends: - plyr Suggests: RUnit Description: Calculate physicochemical properties and indices from amino-acid diff --git a/NAMESPACE b/NAMESPACE index 2bd7067..9715bd2 100755 --- a/NAMESPACE +++ b/NAMESPACE @@ -1,6 +1,5 @@ # Generated by roxygen2: do not edit by hand -S3method(plot,xvg) export(aacomp) export(aindex) export(autoCorrelation) @@ -21,4 +20,3 @@ export(plot.xvg) export(read.xvg) importFrom(stats,embed) importFrom(utils,data) -importFrom(plyr,ldply) diff --git a/R/read.xvg.R b/R/read.xvg.R index a998bb4..51d73fe 100755 --- a/R/read.xvg.R +++ b/R/read.xvg.R @@ -1,4 +1,4 @@ -#' @export read_xvg +#' @export read.xvg #' @title Read output data from a XVG format file. #' #' @param file A .XVG output file of the GROMACS molecular dynamics package @@ -21,7 +21,7 @@ #' # 5 5 6015310336 #' # 6 6 5854271488 -read_xvg <- function(file) { +read.xvg <- function(file) { ## Helper functions # Remove quotes, starting and ending whitespaces unquote <- function(x, ...) { gsub("\\\"|^\\s|\\s$", "", x, ...) } @@ -45,7 +45,12 @@ read_xvg <- function(file) { # Extracting the data content <- perlgsub('^\\s+', "", content) - content <- plyr::ldply(content, (function(x) {unlist(strsplit(x, "\\s+"))})) + content <- as.data.frame( + t(sapply( + content, + (function(x) {unlist(strsplit(x, "\\s+"))}), + USE.NAMES = FALSE) + )) # Asign colnames x_axis_label <- perlgsub('(?!=\\w+)\\W+\\(\\w*\\)$', "", xvg_labels) From 1f67598ee28e0a1f390e44c39b0f3d646a7ce046 Mon Sep 17 00:00:00 2001 From: "J. Sebastian Paez" Date: Thu, 2 Mar 2017 20:05:26 -0500 Subject: [PATCH 08/50] reverting accidental change reverting accidental change from plot.xvg to plot_xvg () --- R/plot.xvg.R | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/R/plot.xvg.R b/R/plot.xvg.R index 760e8a9..1fc2869 100755 --- a/R/plot.xvg.R +++ b/R/plot.xvg.R @@ -1,4 +1,4 @@ -#' @export plot_xvg +#' @export plot.xvg #' @title Plot time series from GROMACS XVG files #' #' @param XVGfile A .XVG output file of the GROMACS molecular dynamics package @@ -13,7 +13,7 @@ #' @examples XVGfile <- system.file("xvg-files/epot.xvg",package="Peptides") #' plot.xvg(XVGfile) -plot_xvg <- function(XVGfile, ...) { +plot.xvg <- function(XVGfile, ...) { # Read flat file content <- read.xvg(XVGfile) xlabel <- colnames(content)[[1]] From 1b4409735455da9f5736e9d1d31630d44a474303 Mon Sep 17 00:00:00 2001 From: Daniel Osorio Date: Thu, 2 Mar 2017 21:18:50 -0500 Subject: [PATCH 09/50] Update Peptides --- .Rbuildignore | 2 -- .gitignore | 5 ----- NAMESPACE | 7 +++++-- R/crucianiProperties.R | 12 +++++------ R/data-Z.R | 13 ++++++++++++ R/kideraFactors.R | 2 +- R/{plot.xvg.R => plotXVG.R} | 13 +++++++----- R/{read.xvg.R => readXVG.R} | 10 +++++---- R/zScales.R | 36 +++++++++++++++++++++++++++++++++ README.md | 10 +++++---- data/datalist | 3 ++- man/Z.Rd | 21 +++++++++++++++++++ man/crucianiProperties.Rd | 4 ++-- man/{plot.xvg.Rd => plotXVG.Rd} | 16 ++++++++------- man/{read.xvg.Rd => readXVG.Rd} | 14 +++++++------ man/zScales.Rd | 32 +++++++++++++++++++++++++++++ 16 files changed, 155 insertions(+), 45 deletions(-) delete mode 100644 .Rbuildignore delete mode 100644 .gitignore create mode 100644 R/data-Z.R rename R/{plot.xvg.R => plotXVG.R} (89%) rename R/{read.xvg.R => readXVG.R} (94%) create mode 100644 R/zScales.R create mode 100644 man/Z.Rd rename man/{plot.xvg.Rd => plotXVG.Rd} (82%) rename man/{read.xvg.Rd => readXVG.Rd} (89%) create mode 100644 man/zScales.Rd diff --git a/.Rbuildignore b/.Rbuildignore deleted file mode 100644 index 91114bf..0000000 --- a/.Rbuildignore +++ /dev/null @@ -1,2 +0,0 @@ -^.*\.Rproj$ -^\.Rproj\.user$ diff --git a/.gitignore b/.gitignore deleted file mode 100644 index 1ca3e0d..0000000 --- a/.gitignore +++ /dev/null @@ -1,5 +0,0 @@ -.Rproj.user -**.Rproj -.Rhistory -.RData -.Ruserdata diff --git a/NAMESPACE b/NAMESPACE index 9715bd2..bd35ad9 100755 --- a/NAMESPACE +++ b/NAMESPACE @@ -16,7 +16,10 @@ export(lengthpep) export(membpos) export(mw) export(pI) -export(plot.xvg) -export(read.xvg) +export(plotXVG) +export(readXVG) +export(zScales) +importFrom(graphics,par) +importFrom(graphics,title) importFrom(stats,embed) importFrom(utils,data) diff --git a/R/crucianiProperties.R b/R/crucianiProperties.R index afde8a2..abce72d 100644 --- a/R/crucianiProperties.R +++ b/R/crucianiProperties.R @@ -5,8 +5,8 @@ #' @return The computed average of Cruciani properties of all the amino acids in the corresponding peptide sequence. Each PP represent an amino-acid property as follows: \itemize{\item{PP1:} Polarity, \item{PP2:} Hydrophobicity, \item{PP3:} H-bonding} #' @references Cruciani, G., Baroni, M., Carosati, E., Clementi, M., Valigi, R., and Clementi, S. (2004) Peptide studies by means of principal properties of amino acids derived from MIF descriptors. J. Chemom. 18, 146-155. #' @examples crucianiProperties(seq = "QWGRRCCGWGPGRRYCVRWC") -#' # PP1 PP2 PP3 -#' # -0.1130 -0.0220 0.2735 +#' # PP1 PP2 PP3 +#' # -0.1130 -0.0220 0.2735 crucianiProperties <- function(seq) { # Remove spaces and line breaks seq <- gsub("[[:space:]]+", "", seq) @@ -17,8 +17,8 @@ crucianiProperties <- function(seq) { seq <- strsplit(toupper(seq), split = "") # Calculate averages lapply(seq, function(seq) { - c(PP1 = mean(CP[["PP1"]][seq],na.rm = TRUE), - PP2 = mean(CP[["PP2"]][seq],na.rm = TRUE), - PP3 = mean(CP[["PP3"]][seq],na.rm = TRUE)) + sapply(names(CP), function(property) { + (sum(CP[[property]][seq])/length(seq)) + }) }) -} \ No newline at end of file +} diff --git a/R/data-Z.R b/R/data-Z.R new file mode 100644 index 0000000..17dd191 --- /dev/null +++ b/R/data-Z.R @@ -0,0 +1,13 @@ +#' @name Z +#' @docType data +#' @title The 5 Z-scales from Sandberg et al. (1998) +#' @description The five Sandberg et al. (1998) Z-scales describe each amino acid with numerical values, descriptors, which represent the physicochemical properties of the amino acids including NMR data and thin-layer chromatography (TLC) data. +#' @usage data(Z) +#' @format A list with the five Sandberg et al. (1998) Z-scales. Each Z-scale represent an amino-acid property as follows: #' \itemize{ +#' \item{Z1:} Lipophilicity +#' \item{Z2:} Steric properties (Steric bulk/Polarizability) +#' \item{Z3:} Electronic properties (Polarity / Charge) +#' \item{Z4 and Z5:} They relate electronegativity, heat of formation, electrophilicity and hardness. +#' } +#' @references Sandberg M, Eriksson L, Jonsson J, Sjostrom M, Wold S: New chemical descriptors relevant for the design of biologically active peptides. A multivariate characterization of 87 amino acids. J Med Chem 1998, 41:2481-2491. +NULL \ No newline at end of file diff --git a/R/kideraFactors.R b/R/kideraFactors.R index 9a2142b..dfe42eb 100644 --- a/R/kideraFactors.R +++ b/R/kideraFactors.R @@ -40,7 +40,7 @@ kideraFactors <- function (seq) { }) kFactors <- lapply(seq, function(seq) { sapply(names(K), function(factor) { - sum(K[[factor]][seq], na.rm = TRUE) / length(seq) + (sum(K[[factor]][seq], na.rm = TRUE) / length(seq)) }) }) return(kFactors) diff --git a/R/plot.xvg.R b/R/plotXVG.R similarity index 89% rename from R/plot.xvg.R rename to R/plotXVG.R index 1fc2869..8753854 100755 --- a/R/plot.xvg.R +++ b/R/plotXVG.R @@ -1,4 +1,5 @@ -#' @export plot.xvg +#' @export plotXVG +#' @importFrom graphics par title #' @title Plot time series from GROMACS XVG files #' #' @param XVGfile A .XVG output file of the GROMACS molecular dynamics package @@ -9,13 +10,15 @@ #' @details GROMACS (GROningen MAchine for Chemical Simulations) is a molecular dynamics package designed for simulations of proteins, lipids and nucleic acids. It is free, open source software released under the GNU General Public License. #' The file format used by GROMACS is XVG. This format can be displayed in graphical form through the GRACE program on UNIX/LINUX systems and the GNUPlot program on Windows. XVG files are plain text files containing tabular data separated by tabulators and two types of comments which contain data labels. Although manual editing is possible, this is not a viable option when working with multiple files of this type. #' For ease of reading, information management and data plotting, the functions \code{read.xvg} and \code{plot.xvg} were incorporated. -#' @author Daniel Osorio +#' @author Latest: J. Sebastian Paez +#' +#' Original: Daniel Osorio #' @examples XVGfile <- system.file("xvg-files/epot.xvg",package="Peptides") -#' plot.xvg(XVGfile) +#' plotXVG(XVGfile) -plot.xvg <- function(XVGfile, ...) { +plotXVG <- function(XVGfile, ...) { # Read flat file - content <- read.xvg(XVGfile) + content <- readXVG(XVGfile) xlabel <- colnames(content)[[1]] try({ diff --git a/R/read.xvg.R b/R/readXVG.R similarity index 94% rename from R/read.xvg.R rename to R/readXVG.R index 51d73fe..fb7a7fe 100755 --- a/R/read.xvg.R +++ b/R/readXVG.R @@ -1,17 +1,19 @@ -#' @export read.xvg +#' @export readXVG #' @title Read output data from a XVG format file. #' #' @param file A .XVG output file of the GROMACS molecular dynamics package #' #' @description XVG is the default format file of the GROMACS molecular dynamics package, contains data formatted to be imported into the Grace 2-D plotting program. #' @references Pronk, S., Pall, S., Schulz, R., Larsson, P., Bjelkmar, P., Apostolov, R., ... & Lindahl, E. (2013). GROMACS 4.5: a high-throughput and highly parallel open source molecular simulation toolkit. Bioinformatics, 29 (7), 845-854. -#' @author Daniel Osorio +#' @author Latest: J. Sebastian Paez +#' +#' Original: Daniel Osorio #' @details GROMACS (GROningen MAchine for Chemical Simulations) is a molecular dynamics package designed for simulations of proteins, lipids and nucleic acids. It is free, open source software released under the GNU General Public License. #' The file format used by GROMACS is XVG. This format can be displayed in graphical form through the GRACE program on UNIX/LINUX systems and the GNUPlot program on Windows. XVG files are plain text files containing tabular data separated by tabulators and two types of comments which contain data labels. Although manual editing is possible, this is not a viable option when working with multiple files of this type. #' For ease of reading, information management and data plotting, the functions \code{read.xvg} and \code{plot.xvg} were incorporated. #' @examples # READING FILE #' XVGfile <- system.file("xvg-files/epot.xvg",package="Peptides") -#' read.xvg(XVGfile) +#' readXVG(XVGfile) #' #' # Time (ps) Potential #' # 1 1 6672471040 @@ -21,7 +23,7 @@ #' # 5 5 6015310336 #' # 6 6 5854271488 -read.xvg <- function(file) { +readXVG <- function(file) { ## Helper functions # Remove quotes, starting and ending whitespaces unquote <- function(x, ...) { gsub("\\\"|^\\s|\\s$", "", x, ...) } diff --git a/R/zScales.R b/R/zScales.R new file mode 100644 index 0000000..0b2c277 --- /dev/null +++ b/R/zScales.R @@ -0,0 +1,36 @@ +#' @export zScales +#' @title Compute the Z-scales of a protein sequence +#' @description Z-scales are based on physicochemical properties of the AAs including NMR data and thin-layer chromatography (TLC) data. +#' @references Sandberg M, Eriksson L, Jonsson J, Sjostrom M, Wold S: New chemical descriptors relevant for the design of biologically active peptides. A multivariate characterization of 87 amino acids. J Med Chem 1998, 41:2481-2491. +#' @param seq An amino-acids sequence +#' +#' @return The computed average of Z-scales of all the amino acids in the corresponding peptide sequence. Each Z scale represent an amino-acid property as follows: +#' \itemize{ +#' \item{Z1:} Lipophilicity +#' \item{Z2:} Steric properties (Steric bulk/Polarizability) +#' \item{Z3:} Electronic properties (Polarity / Charge) +#' \item{Z4 and Z5:} They relate electronegativity, heat of formation, electrophilicity and hardness. +#' } +#' @examples +#' zScales(seq = "QWGRRCCGWGPGRRYCVRWC") +#' # [[1]] +#' # Z1 Z2 Z3 Z4 Z5 +#' # 0.6200 0.0865 0.0665 0.7280 -0.8740 +zScales <- function(seq) { + # Remove spaces and line breaks + seq <- gsub("[[:space:]]+", "", seq) + + # Split the sequence by amino-acids + seq <- strsplit(seq, "") + + # Load the Z-scales + utils::data(Z, envir = environment()) + Z <- Z + + # Computes the Z-scales for given sequences + lapply(seq, function(seq) { + sapply(names(Z), function(scale) { + (sum(Z[[scale]][seq], na.rm = TRUE) / length(seq)) + }) + }) +} \ No newline at end of file diff --git a/README.md b/README.md index 34bf55a..d4c2e17 100755 --- a/README.md +++ b/README.md @@ -38,18 +38,20 @@ Available functions |membpos | Compute theoretically the class of a protein sequence | |mw | Compute the molecular weight of a protein sequence | |pI | Compute the isoelectic point (pI) of a protein sequence | -|plot.xvg | Plot time series from GROMACS XVG files | -|read.xvg | Read XVG files from GROMACS molecular dynamics package | +|plotXVG | Plot time series from GROMACS XVG files | +|readXVG | Read XVG files from GROMACS molecular dynamics package | +|zScales| Compute the Z-scales of a protein sequence | Available datasets ------------------- | Code | Description | |:----------- |:------------| -|CP | The 3 properties from Cruciani *et. al* (2004) | +|CP | The 3 properties from Cruciani *et al.* (2004) | |H | 38 Hydrophobicity values for amino acids form various sources | -|K | The 10 factors from Kidera *et. al* (1985)| +|K | The 10 factors from Kidera *et al.* (1985)| |pepdata | A data frame with 21 physicochemical properties and indices from 100 amino-acid sequences (50 antimicrobial and 50 non antimicrobial) | |pK | 9 pKa scales for the side chain of charged amino acids from various sources | +|Z|The 5 Z-scales from Sandberg *et al.* (1998)| Citation -------- diff --git a/data/datalist b/data/datalist index 557fb7c..a6dbae2 100755 --- a/data/datalist +++ b/data/datalist @@ -2,4 +2,5 @@ pepdata H pK K -CP \ No newline at end of file +CP +Z \ No newline at end of file diff --git a/man/Z.Rd b/man/Z.Rd new file mode 100644 index 0000000..6b1631e --- /dev/null +++ b/man/Z.Rd @@ -0,0 +1,21 @@ +% Generated by roxygen2: do not edit by hand +% Please edit documentation in R/data-Z.R +\docType{data} +\name{Z} +\alias{Z} +\title{The 5 Z-scales from Sandberg et al. (1998)} +\format{A list with the five Sandberg et al. (1998) Z-scales. Each Z-scale represent an amino-acid property as follows: #' \itemize{ +\item{Z1:} Lipophilicity +\item{Z2:} Steric properties (Steric bulk/Polarizability) +\item{Z3:} Electronic properties (Polarity / Charge) +\item{Z4 and Z5:} They relate electronegativity, heat of formation, electrophilicity and hardness. +}} +\usage{ +data(Z) +} +\description{ +The five Sandberg et al. (1998) Z-scales describe each amino acid with numerical values, descriptors, which represent the physicochemical properties of the amino acids including NMR data and thin-layer chromatography (TLC) data. +} +\references{ +Sandberg M, Eriksson L, Jonsson J, Sjostrom M, Wold S: New chemical descriptors relevant for the design of biologically active peptides. A multivariate characterization of 87 amino acids. J Med Chem 1998, 41:2481-2491. +} diff --git a/man/crucianiProperties.Rd b/man/crucianiProperties.Rd index 663209f..00606af 100644 --- a/man/crucianiProperties.Rd +++ b/man/crucianiProperties.Rd @@ -17,8 +17,8 @@ This function calculates the Cruciani properties of an amino-acids sequence usin } \examples{ crucianiProperties(seq = "QWGRRCCGWGPGRRYCVRWC") -# PP1 PP2 PP3 -# -0.1130 -0.0220 0.2735 +# PP1 PP2 PP3 +# -0.1130 -0.0220 0.2735 } \references{ Cruciani, G., Baroni, M., Carosati, E., Clementi, M., Valigi, R., and Clementi, S. (2004) Peptide studies by means of principal properties of amino acids derived from MIF descriptors. J. Chemom. 18, 146-155. diff --git a/man/plot.xvg.Rd b/man/plotXVG.Rd similarity index 82% rename from man/plot.xvg.Rd rename to man/plotXVG.Rd index 66dc599..12d39e8 100644 --- a/man/plot.xvg.Rd +++ b/man/plotXVG.Rd @@ -1,13 +1,13 @@ % Generated by roxygen2: do not edit by hand -% Please edit documentation in R/plot.xvg.R -\name{plot.xvg} -\alias{plot.xvg} +% Please edit documentation in R/plotXVG.R +\name{plotXVG} +\alias{plotXVG} \title{Plot time series from GROMACS XVG files} \usage{ -\method{plot}{xvg}(x, ...) +plotXVG(XVGfile, ...) } \arguments{ -\item{x}{A .XVG output file of the GROMACS molecular dynamics package} +\item{XVGfile}{A .XVG output file of the GROMACS molecular dynamics package} \item{...}{Arguments to be passed to methods, such as graphical parameters.} } @@ -21,11 +21,13 @@ For ease of reading, information management and data plotting, the functions \co } \examples{ XVGfile <- system.file("xvg-files/epot.xvg",package="Peptides") -plot.xvg(XVGfile) +plotXVG(XVGfile) } \references{ Pronk, S., Pall, S., Schulz, R., Larsson, P., Bjelkmar, P., Apostolov, R., ... & Lindahl, E. (2013). GROMACS 4.5: a high-throughput and highly parallel open source molecular simulation toolkit. Bioinformatics, 29 (7), 845-854. } \author{ -Daniel Osorio +Latest: J. Sebastian Paez + +Original: Daniel Osorio } diff --git a/man/read.xvg.Rd b/man/readXVG.Rd similarity index 89% rename from man/read.xvg.Rd rename to man/readXVG.Rd index b0119f8..5ab5baa 100644 --- a/man/read.xvg.Rd +++ b/man/readXVG.Rd @@ -1,10 +1,10 @@ % Generated by roxygen2: do not edit by hand -% Please edit documentation in R/read.xvg.R -\name{read.xvg} -\alias{read.xvg} +% Please edit documentation in R/readXVG.R +\name{readXVG} +\alias{readXVG} \title{Read output data from a XVG format file.} \usage{ -read.xvg(file) +readXVG(file) } \arguments{ \item{file}{A .XVG output file of the GROMACS molecular dynamics package} @@ -20,7 +20,7 @@ For ease of reading, information management and data plotting, the functions \co \examples{ # READING FILE XVGfile <- system.file("xvg-files/epot.xvg",package="Peptides") -read.xvg(XVGfile) +readXVG(XVGfile) # Time (ps) Potential # 1 1 6672471040 @@ -34,5 +34,7 @@ read.xvg(XVGfile) Pronk, S., Pall, S., Schulz, R., Larsson, P., Bjelkmar, P., Apostolov, R., ... & Lindahl, E. (2013). GROMACS 4.5: a high-throughput and highly parallel open source molecular simulation toolkit. Bioinformatics, 29 (7), 845-854. } \author{ -Daniel Osorio +Latest: J. Sebastian Paez + +Original: Daniel Osorio } diff --git a/man/zScales.Rd b/man/zScales.Rd new file mode 100644 index 0000000..ddbc50e --- /dev/null +++ b/man/zScales.Rd @@ -0,0 +1,32 @@ +% Generated by roxygen2: do not edit by hand +% Please edit documentation in R/zScales.R +\name{zScales} +\alias{zScales} +\title{Compute the Z-scales of a protein sequence} +\usage{ +zScales(seq) +} +\arguments{ +\item{seq}{An amino-acids sequence} +} +\value{ +The computed average of Z-scales of all the amino acids in the corresponding peptide sequence. Each Z scale represent an amino-acid property as follows: +\itemize{ +\item{Z1:} Lipophilicity +\item{Z2:} Steric properties (Steric bulk/Polarizability) +\item{Z3:} Electronic properties (Polarity / Charge) +\item{Z4 and Z5:} They relate electronegativity, heat of formation, electrophilicity and hardness. +} +} +\description{ +Z-scales are based on physicochemical properties of the AAs including NMR data and thin-layer chromatography (TLC) data. +} +\examples{ +zScales(seq = "QWGRRCCGWGPGRRYCVRWC") +# [[1]] +# Z1 Z2 Z3 Z4 Z5 +# 0.6200 0.0865 0.0665 0.7280 -0.8740 +} +\references{ +Sandberg M, Eriksson L, Jonsson J, Sjostrom M, Wold S: New chemical descriptors relevant for the design of biologically active peptides. A multivariate characterization of 87 amino acids. J Med Chem 1998, 41:2481-2491. +} From 55482a536d30cb0c54cb769807ea365f6534855e Mon Sep 17 00:00:00 2001 From: Daniel Osorio Date: Thu, 2 Mar 2017 21:55:24 -0500 Subject: [PATCH 10/50] Peptides 1.19.1 --- R/aindex.R | 2 +- R/autocorrelation.R | 4 ++-- R/autocovariance.R | 2 +- R/boman.R | 2 +- R/charge.R | 2 +- R/crosscovariance.R | 2 +- R/crucianiProperties.R | 2 +- R/hmoment.R | 2 +- R/hydrophobicity.R | 2 +- R/instaindex.R | 2 +- R/kideraFactors.R | 2 +- R/lengthpep.R | 2 +- R/membpos.R | 2 +- R/mw.R | 2 +- R/pI.R | 2 +- R/zScales.R | 2 +- data/AA.RData | Bin 0 -> 6876 bytes data/CP.RData | Bin 407 -> 0 bytes data/H.RData | Bin 5354 -> 0 bytes data/K.RData | Bin 3593 -> 0 bytes data/Z.RData | Bin 580 -> 0 bytes data/datalist | 8 ++------ data/pK.RData | Bin 3053 -> 0 bytes 23 files changed, 19 insertions(+), 23 deletions(-) create mode 100644 data/AA.RData delete mode 100644 data/CP.RData delete mode 100644 data/H.RData delete mode 100644 data/K.RData delete mode 100644 data/Z.RData delete mode 100644 data/pK.RData diff --git a/R/aindex.R b/R/aindex.R index fe6364a..cec30fd 100755 --- a/R/aindex.R +++ b/R/aindex.R @@ -16,7 +16,7 @@ #' # [1] 117 aindex <- function(seq) { - seq <- gsub("[[:space:]]+", "", seq) + seq <- gsub("[[:space:]]+","",as.vector(seq)) # Divide the amino acid sequence and extracts the relative frequency of Alanine, Valine, Leucine and Isoleucine seq <- lapply(seq, function(seq) { diff --git a/R/autocorrelation.R b/R/autocorrelation.R index af2f1db..1ba69af 100644 --- a/R/autocorrelation.R +++ b/R/autocorrelation.R @@ -33,9 +33,9 @@ autoCorrelation <- function(sequence, lag, property, center = TRUE) { if (center == TRUE) { - property <- scale(property)[, ] + property <- scale(property)[,] } - sequence <- gsub("[[:space:]]+", "", sequence) + sequence <- gsub("[[:space:]]+", "", as.vector(sequence)) if (lag < (min(nchar(sequence)) - 1)) { sequence <- strsplit(sequence, "") unlist(lapply(sequence, function(sequence) { diff --git a/R/autocovariance.R b/R/autocovariance.R index 12e358d..d1d6a69 100644 --- a/R/autocovariance.R +++ b/R/autocovariance.R @@ -34,7 +34,7 @@ autoCovariance <- function(sequence, lag, property, center = TRUE) { if (center == TRUE) { property <- scale(property)[,] } - sequence <- gsub("[[:space:]]+", "", sequence) + sequence <- gsub("[[:space:]]+", "", as.vector(sequence)) if (lag < (min(nchar(sequence)) - 1)) { sequence <- strsplit(sequence, "") unlist(lapply(sequence, function(sequence) { diff --git a/R/boman.R b/R/boman.R index 6dec63b..a28cd20 100755 --- a/R/boman.R +++ b/R/boman.R @@ -19,7 +19,7 @@ #' # [1] -1.235833 #' boman <- function(seq) { - seq <- gsub("[[:space:]]", "", seq) + seq <- gsub("[[:space:]]+", "", as.vector(seq)) # Create the Boman scale vector boman <- c( diff --git a/R/charge.R b/R/charge.R index ff24ae6..52924c1 100755 --- a/R/charge.R +++ b/R/charge.R @@ -70,7 +70,7 @@ charge <- function(seq, pH = 7, pKscale = "Lehninger") { # Divide the amino acid sequence and makes an absolute frequencies table - seq <- gsub("[[:space:]]", "", seq) + seq <- gsub("[[:space:]]+", "", as.vector(seq)) aa <- lapply(seq, function(seq) { table(factor(unlist(strsplit( diff --git a/R/crosscovariance.R b/R/crosscovariance.R index 5c0f421..33cdc9c 100644 --- a/R/crosscovariance.R +++ b/R/crosscovariance.R @@ -43,7 +43,7 @@ crossCovariance <- property1 <- scale(property1)[,] property2 <- scale(property2)[,] } - sequence <- gsub("[[:space:]]+", "", sequence) + sequence <- gsub("[[:space:]]+", "", as.vector(sequence)) if (lag < (min(nchar(sequence)) - 1)) { sequence <- strsplit(sequence, "") unlist(lapply(sequence, function(sequence) { diff --git a/R/crucianiProperties.R b/R/crucianiProperties.R index abce72d..d6de42a 100644 --- a/R/crucianiProperties.R +++ b/R/crucianiProperties.R @@ -9,7 +9,7 @@ #' # -0.1130 -0.0220 0.2735 crucianiProperties <- function(seq) { # Remove spaces and line breaks - seq <- gsub("[[:space:]]+", "", seq) + seq <- gsub("[[:space:]]+", "", as.vector(seq)) # Load Cruciani Properties utils::data(CP, envir = environment()) CP <- CP diff --git a/R/hmoment.R b/R/hmoment.R index 4222d23..a398211 100755 --- a/R/hmoment.R +++ b/R/hmoment.R @@ -26,7 +26,7 @@ hmoment <- function(seq, angle = 100, window = 11) { # Loading hydrophobicity scale - seq <- gsub("[[:space:]]", "", seq) + seq <- gsub("[[:space:]]+", "", as.vector(seq)) data(H, envir = environment()) H <- H h <- H[["Eisenberg"]] diff --git a/R/hydrophobicity.R b/R/hydrophobicity.R index 089d511..6c68a50 100755 --- a/R/hydrophobicity.R +++ b/R/hydrophobicity.R @@ -173,7 +173,7 @@ #' hydrophobicity(seq = "QWGRRCCGWGPGRRYCVRWC",scale = "Zimmerman") #' #[1] 0.943 hydrophobicity <- function(seq, scale = "KyteDoolittle") { - seq <- gsub("[[:space:]]+", "", seq) + seq <- gsub("[[:space:]]+", "", as.vector(seq)) # Loading hydrophobicity scales utils::data(H, envir = environment()) H <- H diff --git a/R/instaindex.R b/R/instaindex.R index 7561bd4..1bc48aa 100755 --- a/R/instaindex.R +++ b/R/instaindex.R @@ -419,7 +419,7 @@ instaindex <- function(seq) { "NA" = 1 ) # Divide the amino acid sequence in dipeptides - seq <- gsub("[[:space:]]+", "", seq) + seq <- gsub("[[:space:]]+", "", as.vector(seq)) aa <- lapply(seq, function(seq) { unlist(strsplit(seq, "")) }) diff --git a/R/kideraFactors.R b/R/kideraFactors.R index dfe42eb..6da79ab 100644 --- a/R/kideraFactors.R +++ b/R/kideraFactors.R @@ -30,7 +30,7 @@ kideraFactors <- function (seq) { # Remove the break lines from the sequence - seq <- gsub("[[:space:]]+", "", seq) + seq <- gsub("[[:space:]]+", "", as.vector(seq)) # Load the KFactors data data(K, envir = environment()) K <- K diff --git a/R/lengthpep.R b/R/lengthpep.R index 003060c..86581c9 100755 --- a/R/lengthpep.R +++ b/R/lengthpep.R @@ -11,7 +11,7 @@ #' lengthpep(seq = "QWGRRCCGWGPGRRYCVRWC") #' # [1] 20 lengthpep <- function(seq) { - seq <- gsub("[[:space:]]+", "", seq) + seq <- gsub("[[:space:]]+", "", as.vector(seq)) # Count the amino acids nchar(seq) } diff --git a/R/membpos.R b/R/membpos.R index f441295..222e346 100755 --- a/R/membpos.R +++ b/R/membpos.R @@ -33,7 +33,7 @@ #' # 9 NFCLILIFLLLI 0.944 0.229 Surface membpos <- function(seq, angle = 100) { # Setting input length - seq <- gsub("[[:space:]]+", "", seq) + seq <- gsub("[[:space:]]+", "", as.vector(seq)) window <- min(nchar(seq), 11) lapply(seq, function(seq){ pep <- diff --git a/R/mw.R b/R/mw.R index f64fe17..93ce23a 100755 --- a/R/mw.R +++ b/R/mw.R @@ -17,7 +17,7 @@ #' mw(seq = "QWGRRCCGWGPGRRYCVRWC",monoisotopic = TRUE) #' # [1] 2484.12 mw <- function(seq, monoisotopic = FALSE) { - seq <- gsub("[[:space:]]", "", seq) + seq <- gsub("[[:space:]]", "", as.vector(seq)) # Create the weight scale if (monoisotopic == TRUE) { weight <- diff --git a/R/pI.R b/R/pI.R index 476cc6c..ba9f950 100755 --- a/R/pI.R +++ b/R/pI.R @@ -37,7 +37,7 @@ #' pI(seq= "QWGRRCCGWGPGRRYCVRWC",pKscale= "Rodwell") #' # [1] 9.718 pI <- function (seq, pKscale = "EMBOSS") { - seq <- gsub("[[:space:]]+", "", seq) + seq <- gsub("[[:space:]]+", "", as.vector(seq)) # Define pH values pHs <- seq(0 , 14 , 0.0001) # Evaluate the net charge for defined pHs diff --git a/R/zScales.R b/R/zScales.R index 0b2c277..1a287d8 100644 --- a/R/zScales.R +++ b/R/zScales.R @@ -18,7 +18,7 @@ #' # 0.6200 0.0865 0.0665 0.7280 -0.8740 zScales <- function(seq) { # Remove spaces and line breaks - seq <- gsub("[[:space:]]+", "", seq) + seq <- gsub("[[:space:]]+","",as.vector(seq)) # Split the sequence by amino-acids seq <- strsplit(seq, "") diff --git a/data/AA.RData b/data/AA.RData new file mode 100644 index 0000000000000000000000000000000000000000..7c2bd0ec314cb0a9ee39e55f7ad5f91522c74066 GIT binary patch literal 6876 zcmV<28YAT&iwFP!000001MOUASQXd0rZ;ISVna|wL`5vvf@KB)v7iDfn8c_X*uvKB z-mn2h?7c;aUC<~IjV89lXzb3|(O}1hsG!nBkgf>G0p|V2139_(p6BK{$+Pd}2W!om znKiTD^{sEcUs>bpKE9{Xcq0uB4J{3AZ7mHg?V75NR?R<64IK@`+ICmhntx4eYPu-x zYf96a(t@>^QuoJd2!G5==ej>8Q)t(q_A=p^sZ6TuD(+Nqqlynz zJgDMHm7!D_MinorjG)R$stlouH&w<^Wh_(t%u%akP4cD$Q=U3*(}I+s%W6r+Kxj?fSDq3(7Irb6gP0AH(GZSa1%v<_fV z$PWp)GEeJZ2xAHb{6(RE20VVQy~^he-Op+YwNi;wFkMYnTV+Pi${zOlDFA zCBwX_>vlf#2IKOYl$*NY4f)Q5T)lyOQoEp5jF`75)1Vh}Am6x;dnd>z_W^Q^`N3sC zKfM?3<1S+&$KcXFan8TvTorFGk zjFPUW`?09fG08VaB|VSsZ+N}9c&i!Sk07sD_n33g-xr}z>GzYqz6v=fxhHug{ZIN~ z2l{#307tq%33}rO)`>fHVm(xRt{~<^)ei5C0?u3t&13L~0-ggC#P}5ndP?o^CY;|3cyR^5pY$~GwtVox zhs4u_KVA#C65b%|yaw9APnZhu%Uoey;9lW5G+yt3H$AshkbAYm`vLUmdjUW0E%>u0 z=5;pKxjaGcIPf{bn|lTQQ3ZVfyt((l5%YqnfF7aodnM=-j`RrRpLv9FQ(HbL$Q`c( zJ&+AKe*+weKjeZxWC`QJJcGQ8>m~S20q)26F_2@X7#64g%J*8n}-~eG0(Qed?-M>0rU!tbzTqGwG;Z|8wvgKCcu^W5Y|_b2Z9F?FX45B z{?rcd>tz2y&q7Z#rGoz8TYyJ^KeJl(oh)22^iNY^e(+6%`&lzVet8o?PWdLl8@yW7 z=a^5t5#~_={0qkP1ogt3fuDqarzm&C8=!|d@HblL2n~iOeggedf%~xzFc=S}64zxx zkL-q?f&O5%&>xL=v9PYH9o{5wRAv$n!!h&*^Fok+jX(Hf^`VcnvCfkICZ{3%Bdn+= za2|Y}^b)IAf85j#Z?Y3V3iFxPL7L}W8IJRzUti<8`>@l~1e`eVWsdkC>`ks*;B~wP zct;lTKFB-lDB_=_-?$RtSl#d@yhy%iJ)>h<7aO+IpNKc{z{>jaO7=gmQ~y5Z9`w%R z2J5O;eSWHLc#FTA7#Hwr7QCEzwm6Sy-jM&6)>m^i z<=+}ZO5pnpASL^f+>mVdjunzF6bn_SP>k7Q>!Al%* zy(7le{;ZJyU>_;)m5vg@f71p1b;k3%O;byL!Zrh5=D^1Uc_hX-wn1qMK4${n*BCsG zl84&u6Zl+Pj33$e?F5Cv+M3lZoMJ!b!aB+}#<4a0D9r`?m9D z^=c{L?8XZ6+7{<~K(1ZwVb7qw6V|!TknfI=ee~Bs zJ^2a66~sIQ`2CnOkT>}0#P-|3tq}Gj@$h%V&ygo|yn%efo}oMkF@FegGm&?b|FKj} z?RknvQk)U?9>q18Jm5sfR3dI5+Dnv&M*4~Tt#nN1={aNvk)1==AwErUe6_`|_m;z~k4tY(AxQKFvugzOCt z@f$9W{6>&lU}!_VPQfuDeb|3%EdfRHf zHAO#V=sykP30yhEFNr5o{Fy_kZg`9F7RnDK9!_>nOPs$(_6O+=w3C0SG5BID@}t-H zpR?8|HPJufH$0A6;)7OrZgVxYcdC&m;w;Q(zP%u)dn-o#CNGAy-j-eUH$w_(lcT_ zjqFeZ_&s#ML&{07lRp;nt&8^a(AUJrkq5)-gU?s0n?9-cJM3}Nz%@V_Bvr{2I5u(( zP)R~0)4ilhwCK93f|cQPdazs)IBlddQXV9>M9SrZRZ?lV6fJsgl5mMih9iBq5M@M& zOoBsgHyPb&;HI1@Q8+vGs(0MisW*-dJ!IihMSxTlOc!`4f~E555_(s?A(HS(j=cu8l}9MfY*N)(bA68WcB9x0n8iI&Wy z{`9;hs%cUcA?vMFC?dmWN~Y6$H}Y0V0zxFyBr35BZC?oul#Z`b90UE@`X_93$IO&U z={5AnN)%I+DjEiTf2mw9QxM2{{xW&El5RBgSIVbI6+u$5;S1UH=~7i~*TN*O-3h5J zE>@Jh1*Zb@x_**6kyIuhWJ^q5#iS(?jPqhrD;6UT{fT6bNEao;6Pcq;Y4_?IA%Dtb z7U!@ytN%K3K*lQtOXY+B+F^y8r9L^46+K_rbxEN$XA+2FVVSr*5Elr;JilkcDW ziN^Hb2yc=nG3ZL0JLvZ(BFT%4VA^a0BaOjk1JQW634Cch;OyjxTvO5q##OwZ#+At6 z`9INF^tZsf-tW*RW#{eP<5RWgr>gTmDI+6sa$pCDxbuiC27oJCas(zt*0FPgcG!p+ z3)rzkJBY=MD=}jklcAv{h)G8lCRw2B!z_R|c^cp`CE*n_hiNAz2|Z1g>iQXzlu4q2 zKXDPEon&t@9+aU84=P30DI!74kt|TP!<#(F@Dy_-&y-05OIgf7Er;A<2cGCD0@EdB zB%UW_{*WRwu>2|0rx@cvp4l9V2&rf0$p2?X{fF_U9b>?U=D+As#k^+3ox#xeL|#bV ziTn`x#Eu4*^b4&IAfaN0Hu~X;g!MwyM`=`3GrTFXLSJ$K*`UZ6s}1>wXPd}2kw^wR zNQgA@8k7Nrc|tqhX}*vr4`h)6?nHJtMAqnfwZj|ajUjoaox8w^@S+`$4DFb~&PJ|^ z$T;{68DFHQiGNV!fXM$xtf!>!iQJR1B!0m|&G062O*=$sXA<#0`f>y5l}EJ04ER$9 zCGF&(ovoCiK=XhymMPP$s6k0aDt0E5v8rx(i}RUw{L^|zMl0>8fxh4#0G|(#XPg%! zx1=vfUMVt9JKMpl#hve1AH{KikxQA}>V`Mr!iei8wjK&g{N9vUKXQc20}rxQBD zi9l`=UUQW)QV}Fm1Um_@qw&eUHiWzxvbGv^f2=uWG$NwZ92r{3kYgQC(y=k@G(?;l z;A!}~F?avnm=FEk!1^{EE1kfxq9;{HQCt5sRSem-FjdUx)lpK?V26gUj`N1N51YLI zidV-+-NaX?edm;)*a5HDsllsLysw>b{Fk7PlvObW7OyCxjucl1q_o<#$JSt^n6#H* zOYC3p>d4N;E~DSQddCJOy*fn!5&iosU)>aLs{iiQJ3yf5>w;}H@b{m8by35hq&*ic zA>(#<#fBQ@Z!k^&ry8c=H2oXAI%$~3coiy1!~Bt6|0`epUp~rc@KmW>9yUW3PO&dN zcgf68(JeiXk%LE%p@rYjOB$l6S@Oj0^+wjLgA!VT^?j8=Gi$n|!!a_sT&hxvhf29} z`lp`9M5tzou+mpU1zHTVi#0}Kv;pRu8Da}$?o|R-19C4@q5%>Q%#d);C{V%;-xwPv@nK6|=T9_4{uVI=BvflrVu0|w8FEJuO(wT>8qULP=FMRy z6giV-_kYiJ! zokPO3=stp*negXe)^YEUaHEZJBQqQyE@F^aMs5$TkYZ+-M{qCE2c^^vZ;Jhi8!LbV zj}O_3Zc}`Kj5mOphOi2)P~rz|$(;|}MY*O#8JLq?8QgRTm$8lD#)F%RV)W{UHzh8M zAMS*kS=6iaVOqE?xZ99-iUl99FXy7ZC-)nLw~*M%YG58wZUnhq@!=5;3Dw+23Y)15 z-t~TmE>3EF(L=2D6l>06t(REq{a^HAI`m&z*-Zjfk%2OaLgrm_PFiDFi)lb6)9Uhm zhDZV9s=2R*7iey%srU5_ z-qk$jalZ97#~%l`S8>d+MxK3A&jgrMEX>jjcrvH|lag-n=aTxCeO(y6s_o96k|~2z zqW5T~ln3mue)WZ>qP+F|FMmq)xsbN__UseP&~0n^S7|HO?)|O1%edsHgRfYKM+E}g{sQn25ZeEShy1p1W|La?hv;-vxb6 z^>5RD-0G^SS2Az8?%2P2vYE5_ss$%JMqEz#5T0Jtzstepiw-V}dYIe4{~o;wPHT?0 z)fj438FixBw(}Z>xv#PgIIp;PFvz{EwbiYizUyYRYTtgVfy={l32WzUX*Ku#fKyf5 zlb3kG@r)e%`Hf`Zs&8nT*}w*@n5_>t<^^E7Q-bRN(Qfq_Yh@9v;}Pl8Z(pVT z01ul<7iL=&t&F_S$mUkW9vy7B#4pg*Ev_Z^)F|8Y;fneDBj3j7Y88xFsFUqu_4(m* zY27^rEZv(H>h$dXfpKG&vnTF6`sT~+H$HZmlj!ooAkyXiXq9r~iX^MNjW=iH*t*F! zPf~t+IC=Btw);{J_(V)~>E?QQzG>XOh^x*ihmZPq$b28%#jStB>VOqnt#?*A+GpP` zK3TagL)rH3iROpm%$}b8GVQr+n0w)bQTAK4dge?Y`s-sKw?2#F)1A&9@S7LBtk9!z zb1kdEk;RM89&kJOW0wni0^!ZyeGS0?)UKF{61%_Do( zQQvOQV~_fr8d^N($ob{7b1HW3i`bhuv6120uOD4Le0NnurBC?K_^6;gX9KPL8eg5F z8El-CZt!&{pQVX=BEQL7n78(F^uW?P@sr;y$(&&rI3(l!sH_b;Qu@W+88slxS6ly) z!?UMxQ`bj+$iMX=_tr|ySvx0Y#jiTD^}0zx_aJH3kkP$c2Zv1!oHyvJJu!D}Ztpie zR<)v4?zH<$Q={g&nY64Pzu$4i`~B9lVy)kfU(Y_Ym}D=hitqnrJg0eY!mI1AoZY;o z2XZvzvkX6M4!wEM-O4ob(lkqM(U}*=0~6$-_mUD<+Le5>CwzUJcjDC^>pS;dll;)Q zS8i3id-fTN6V@j!Y2)+ybMvlmdz2@fDw`0u)UMRiz1*0;G}&z0g^|sA>nu1L+uGUJ zyxjVS^yxVL9N&Il1TRmm!^|zIT3F=Rw}`NqygRkge8Vdd}R(zq98T85Ng$oAmwR-1b9{CwZ4J6<`Qo2GiT**iIJ$Cj2p_E(L~Hn~*WB<=EVo_FK?#RG?Q6B~8B zXdTclwa5G!6HnVe=yD{r&qD6(v+Gs2c7EI4Z`xJMP zbzC!Vapu784{zqPQJ%;@{Wwr7@M9X`*pQsoq>z#&rwlf zdlqkO{E_=l$l7`dXDe>h8N(%gSrfksZI?mbhy|=ZuKwax19-fzIrUN;=pI#%bmDeo;yoVI9dN>+_HZ{`RqI8;mfXi zRXUs;zR2(VF=vJKOY3=epJXQ3^qcFxY+H-{<(&>)I=`uS@My{M(fg<8UD}_0_*(Qn zNkaaHre$`A66NI;aK5EAYNoz@|N zl~SW)ra`-YR92bk?N}IfHh;$bXckiBS#CRBpN`25nLGEGt4p$0!d}Jm!dQLXb!qV`8+SQ%ZUH$r5iL$#%>?qPwS6E6Tr^YT#nL zW9QsN(dMo1>q0j41Aa)t6n|IC_W<+Y-^=#E-y*63o(CSz+p=29=QXVJjOQ2e9u*N3 z8Nm7jFBsX`+}_$3FfK2T!N3ebnqZkAP7ouQB}fq@2$BTz1d9X<1WN>S1P;Lp!79Nz z!3M#a=(;`eTk6ee-qd131I6-{mIqKrQDv8NlTbks$(&2vcZMRKporyxd0mfyV)smG z>N;dLujxYYB0ci*T72VoSoEgP#XpNmSbm5))BA6=AAosyLVsSfN@!li_>DTof=ASs z{J6mL8U?ih&hfLOuf6@`>mB-WrPmFQ-v8cVV$yV+={|=07}1+p_YYo8F*(Bo006tw B!G8b% diff --git a/data/H.RData b/data/H.RData deleted file mode 100644 index d35e5c2b548c09c0fbac26710bcdfeb8f22400b4..0000000000000000000000000000000000000000 GIT binary patch literal 0 HcmV?d00001 literal 5354 zcmV?eBWl zcYU8{Egz?V@$v!k91cgEBOxZv5tr!AN{aXX5#va5 zclo!?Lr2`Z;Wlmk5Z+jEeZuR9j>*jnk0w9LEH6r!)V6u$lV?1N|3Q4W*aQ0fnr^q` znKK-MWYS9fAJ}M3y`EvWLN?JQ&}wG>%>({~tn-|q*DFfT*1tbKe8j{WP2u>!-G7|S z_gp_Tga}&v>nz`SYb6qbT-5G!PH5;~l9I@rd);qrgs0|v*=mp5mKweF2qI>O0iy5H`vHZl98ec7wgmV4StYWKOE z1sDHxo3Q82o4*s+nK*iJ+xY&CAx;}Z4yP8q{2pidx;{nbanQ#Jq0_0?ZbUQx+L^?4 z%K8$m!&X0^MSF`aUE8W$b+kUDaNF#FgZ#TQH)@Yhx^gaEqF_HcL~Z^HJLUg8`fzmO z8*jR3<*SEAKchoei3fHs-x+@`|?bF=)Kt9M+@8pipayIo1q$#Gsr zu1~G-$mchzQ_aGHhOOfF$i$j;CeE`=@jPjn{FSP@nm=9VT5)l4)ZdL786K+FQg4w7 zuk`dnLvMU-7Tf>JDkHa1kAe?*nCeo>-;aklyZpMgYnxqy&$ZOWk5dX%*AERi!Jj;; z%XRGUU)&E`zdIB0^LZO@{W4RN1wW?w=~=%JAGI$z>+GJZPn@1l_M4<_>6Fmn)Tk)4 zL~4q9$r7!Tf(r$~%QA8{Wh5T7SlA<`EjDHAuIP2^Rg`F_ZSl+Oiie0NAGO`LfwtRQ zdFr=I!|h7`us5jvYtLJUap|iL&0FZIX>aYhI&kz7q7c)?E`V4RZGoQ zpK+JgomgmjTw(k#n>VEFwYgMi^zhgrl@a+GORKVOMV%Qg^>Rt(U%~T6FM6@_VconR z`_xxj$uWn7Wy=5ua@kmbo`?+*zUbCI8zW?dMMmB@q~2ca^5A4%&LNv!3TJjD2e&)Z-esfhlDjOn zwT|3mbli51ti>2Vg|z+72gB6$)O?-KB`uijs9}Cc%)H@7sBK}*km5Ec`N+HD^R3(F zKir}6&?NXo>=chjBdf}f=Efa+azN^I=B#yTH%;H?-64B~Nt0sg)+By+TC_Sip!{8! z?e+GoXpV57U8>GBjRWCE`7LUu<*GMrRvy-DDQ-I4evEh-VD9QTT0!B&*E~z}A=VG?8jujyHc%r zD`)cg+kcMA^9s#vxMq5N?3%KzCu{|eZ@5Y1%uBAx+GaIk^vc~`6&mrzat=CKOF3rG zyYuwz)_6NlDmAhz({Z)DU8nH6W8M5t>+t8-WA|`QCZ6=Yb;hE)?PXm@9xYv5HZ#J) zQ#z|@uWbB|?ABGm8cTE)o(`K|o~o%9vcWm!v=v9!<9E%%l|B>ZjxTR=h)(_P=oFjr z>CNz=F$rHH-i*Dw`%>QJ^ees+PqsOPWGZFc>v70C-BnXuX>vQ{(5@}jyGBPAElI5C z5`437IFezU)XF{6H1FcW)GwI_Y|XYPdN;~?L|zZ_+hwPa-|@|swFRW-7Jtv zUXva{mqfPMZ8>VVEqd$?qs71a$*$*}PTSPTL`0F%`fJ(d?yKG^be@Z`+bnI>uuS%2 z-8?HDrwOK01HO3V*bdE6uHzRT%lketPNUw^F5ll?H@NwI<;tr+^@|tHdS-M>YtreC z3eB{jS)qBKTz?%eJ8m6$_K4Hf%-Kz@YBwg{s#Q-=;piQ#^>A3@+mqj@)~OwpA)J4! zDAl?nc-M)i`BkeM%`cp6KOZ$E$WA@*fbeVfx3RC@E;f$N4UJkT&e7Dg(k`zz=G{q+ zso7+>Bu}xV(ZV)%?#dM_muMNrw~c>sC%>XeGsG=f($7qD)fmf)EoKs?);0@_t$QAn z`2Gz0txj-3OFqeXQm*RRdu4VmQbcygv9xOe+o+t>DaQ6THIiFP%l2JOlHWM;@K0s^ zr!x+2H2yHz^=+DM>Gz;A^5x=c&(dw7MI$eE9xV!dx+cxOtRduVcgYdgHRH0EP7mDm zX>04d&n>HmsBsTUR~4shySy_yq~(E0rN+J~Z%xLHa0%}Cd$QjtwZHs)WZ%a*2iGh&77M;xNOw(l z{_rWK%75rY-SpY|sW!t_h>zMd$ID>*C*KuSC-=Pn;-DN~H1==T=()k_w;y@iJh3~! zUuDU{OAn8P{H{4Nu6Wa(T1w}9=M0zbJK0t)hNZ=0`OQ@wa;8MQx@fJzEZjExJ>Y&(pg*d=~qonkFO@k&A7imMo!trYjWy4t%6MD z=vTAXZI!te-BqdPEZ$T8+bYKyH{$IRbIi0nsy1=o@(lu?z8bzeefQyS7f(FU$=ka! z*Rr+p!RtwZOAW-5=B&P`XyCqKVTWf_P<6tcD_S?6`*(2dr)8*{d{?s0cvbD7?&|7) zPqOCd6ibCgOLnG&?kA4y-dfv6t=^d$Fy*=Kvc)rv*D8IHysyH&`|*HkwRh2n()gFP z3(iFxnWNhjU*VRcvy`ABUT-+sz4x$Xh_r`gVb<`XxQbKB=_$pL;fwf9%F}-7P~Nes zcH@I3nffKN;)~W?)-K#LXOPwtbL|y(>b)7$-c+eK)gUz%_5Vl?^CLb@=>HL4n0gM@ zw=iX*tElhym{fssdwSn*KWPN1F|==jc7`zi2xeST9oosla|Nb7X$0*Iplpb59`FHD zd~OskrZ=O~_s`>3O~Z^2X1p-tgc(Q7%)*Q_W?cS32Qo7-%y?pEI%d2vGaEC$ znDNKVT+H;&2&V_ZC(6v5^S90)NlVP{&rr>JH)hrRu1~#qEpH!v{5A1$YySi4OJB9# z4XPx+ui_p;L!~5CxLnjoBqc6t^yM(6B^Z#2dH`Fpzq=37bi8li6V%^*-4ZIOw|#Gs zw_7rughLqDpOu}`W4>>AbwRSEpm#`L4^!~DHv?4EcIeANj3TYzV((E>ya z??0LKOu=SJl`~&S;bz$b^}xdvY>L!P;Db^~u|4*OO%=;%-xQ|!KI}iZJ-c~}7~XHd zUSZ!O?f`$^13ty?N4_ouJ4d@mdqw_7emD%{ln%lX`xgOkJcfPZS-)AkvhQWg+*Rc8 z-o@Zdy~TA5`k{_V2`r<1H!ymF`U*G}L%Xg%_{>`fd=9#Uw@S69>Mwh%Fr~&;@#moos0qmXKFG1hb zL4TM(0_>P*1iWE?pn%6I)ZwUi(BA7slfO|%kmiu8gA)$UHVt-+&OB)V>!A+nWr0_~ zS*N9;ogp(GJ%kyLRs>v855fM*>Ojyzs7q)`W;~I@`yu*&z_Y;9L^H!5v=-heYtPfg^=}#&%_Dd@=c1o)O-k_^lK8N*0%fmXVgZP31zCpC`CLm6N-^tn? z>IUFp3iKQ9bBG2(qdo!t>4g5U4-haPL>IKH0vwsgPr!4~>&Q!_^uT!&IlR$N>|xe3?t{3_ zsTL@I2Y&q<+LeHxUe4e|fnKIi|AD_rwKKYo=78>~Lfr@U4t^BsPvkeMi7AU3-iR04 z7w%_R#(i;cJ^om{Q3rMnv{&^1X~}{8h!?;+rGxfW@qzkO)bM7%8|@MCL;oCfAsg?2 zl1M3IjKiHqA2KA$09tY!(@d1&;y9WI}z!&^&0^)k8OIW+Cgm?$y4E;$t;Ab)5 ziw^KFJ3y~UGkiiygWkb-45XwIQ%_1k|8AyUj>8k#&2 z=bk~kL2)fs7sCEHIIhjcztOL6hyAw##sgjvHM~)W5bc0F_tOo(-|D^{9>AL?`53=V*|4;QGIkNv?VJT_G>{p~I=na!>MsHX; z^z#O32Iuf*h5fuknll$ENOOp*Sot&kECFv*&?Oeo-U8;;^fq(H!QNx?{b1*KA=LmQ&3h-giH^1UJ0L%x(4M{oBAwMDB zh`0H{vm33(>h>pGib)%thE`O9ZAMs4dD4WumB_fHxkk+eR{uMCW5BAWUH&lT8v2oU!p^1$98 zPRG_418();KcWtAMSTwUgmMPiH~2Gn&w;%^1m|X~?#B3Ivxxfhcpi!8jNtF#xhC-q zaKbXCaBjf*OLz|r`3d8#SjOl09`u9I&%t(ZK8@%2B8NAehttZy-w+3R=pwVEmlagH#O0 zhw~d6$|UMRU3jmii26G};hx9@W}@;r<&5 z_X+6{z!$BsKUNPsC!#f=ojSw!v?iol!294gi5%XjcQHlYM&4~5cs~<)hCNS1KU5at z9+IF#+L6~W9t-v@1@(7gYH)&t6u$4rE>oO5^#j~~JlF2)AV{KdS;C@%i5($l#y|CD5>bK@3< z@r3wq$hrt3Lt}dXTYR%iTs)5KDu|Bu7YIV}v!vX(d=>&JHvylAPh{NUguK}Bh4@PM z@Lsg=V>n-DJJ-K}DGH&EQ|FUOzJU4;69LJOP z<_aTtLPXYEz~{%sEayhy|2@Q8$PEeOMsS7f5E4FIoG3{j0XqjWeffW|k(#}n$HRX^ z#+S=qBoN{>$oTUjBg6R!vb2AAWQ+hi%J~Z-7xDO^Jhoz9cvKWm*f(^)QE__y2fBLf Iw;n?P0K2XGg#Z8m diff --git a/data/K.RData b/data/K.RData deleted file mode 100644 index cc0e6dccdbdf7658af06d03d908a179fad830349..0000000000000000000000000000000000000000 GIT binary patch literal 0 HcmV?d00001 literal 3593 zcmV+k4)*aMiwFP!000001KpPSBUE1>$H!X98ef$Pp%fZJiZoo5UG}o&o59!;V}`Pm zLZNSC%Tm6{_7D*&+vEzNs797S+fbIG8vBxXFz0%n=llEz?hkX`bM9x(o%{N{&*yy1 zPg*N-S#zOKC{`338!L*HZAG%Pu6(ed*il zfzf1LAzQi%dUt-qCoyu=q~Cb$0=NF>UjsB%y{7`cv&v%4%O8KpeczGOj0&>hzP0na zTWJ0@lF=FIz-#SaDyFWmDblt@6)NVaMTNSW_1t{AF94?`dW$vPZct;ehgU1CTE~;K zqxKv*XF1|eR)A$T3w-3=TBjNHRc#MTr3w3z%T%Ww3%lW=M0+ZyR`;c}DGRO> zvtjMC-$TbSS1Ua^?|1s1{ey=rS3<0EeDbA6oX+XPEjg*%p~(V;ViL0M80TH_tqKVt zw92-92qeg(g4MS>!}hug$&7rPB0<^Kh#T}$dl@f`6(kd_KIdcNZ(b;6_n_@?Rgk#( z<~E_8Cm);P@rH_*lGZ#~#0ekkMoo#=(TT(;dlyGH%R)wA;P{^Y=f^*mi*dZH&HILa zh_N#wc34d3kE={3iBDz_YkS@weL=o#8KgcRW1vL$Dtd9gpd`de6K~yZvOBD{oOo5R zjxtc)LV7GC?#;IpHYThn_M~of|HCU=H+$YYN?|2qs-Jm9?1FX*>yip( z_uotJo=HAizp3q28J+eyLp{Hal)zy6!Ch_uy$`Ydwj7)qHKaZWBq3 z7`dzbOE@_tE}k2I`9$VvZu8?ujK8##=B1srcZN9gQhl{M-`Ylz)pI}jx4~O#ZtDE@ zK1Ai|dNV0DYb6j-lcLdBd`?t2^XJzy+aq`J2aCygV#r3h6)JoxW0Tq@-+dRC_dA(K z2RwS^ut_P}0Q=MHsVh$J5(kIjXZp2*RJE$P#%Bfl4GID^`6kLcGCBJrCQNc4rFEMr zy&-SWUk3!uq$*BaH$L?bE(gTWA zHn%jD*3J0X;uKDY7dSa_*(r8Nc3y4T$7t@cZp{$Ol^3#K9;|Lyj!+e=ZecVY%A%md zxP)+j71iHwpK*8-_dM9SPl~#8_>qM9YrXtf@}9V~TpYzzt3}b;r9&fC`Oin57u)p) z?oCwlCc*rCAM3`frRFTpW=C&(nAD$H-sIZ$N9Z{RVaKt0PKNP;J0tEz^H!4Bgx`|H z#_uMW*V8De7>2rvN#wS^#6u}$tfSIm>giKS8OCf{wk9#Cj8Q$T%~XVG8HCE>S!&Re zjjQIK|0ME0$B1BV>(&-7_AA=bxDy&V7^t}L_~0f}TT+hPv4t(Zg0kp@lSTs$5~_r_ z>zH_l+#}WlB@<)$G9S9z1cQ4Q)t?%c<@h%+9wc9Gyy2&2y_d%)koJ50;jnxGWuIBC zrDkke{TD|z@!N+dDf8{7rctH42JY%WZrO!aMwo1`MW=$OiRaNFDE&QH-%_*U&BmC) z>VpQk)DZ6Bv8_Y0NixfBZ(FpJ94aWMjM920#k>5zMRckOjEo(#8{@Bhjm`FHBBtIL zC3G0wkP7$cQ)%V9oL;~82DNL7gR-@SHwjIch#0NCQTJ1UhP{1ofGlJ#E%Eko)8^|+ z+1wuCq&r_@g13by#fDorZWZ!JcO3|Fp{p*wnxtBqq9*m?>zZf;DB`lnW5?5D>IXzq$GNqolqm->EQ&c$YTeDi38j5IJX##izpYli zwVNEPb99Wcc*fFG`e=fw+pu_|Zc1BBLO%WJuxLG|%=bX{QcaOec_2l|dGCa9pfJW@ zXG)H~zE9zKX$-kd1y|T7G~RZ1`0j*cN*`6C5fMr85XV2ev?idMU#2>G;{lTvZpdmPRA0u^mOVoD-rDRp@|mY*Ka zX}vJUWX>D%Qp_*uQ>A~hIY!>m8i_t?+IGZEVeyXZ&Iw5enefo7N2YXjIj<3$O;kBG z%S|7I`g#gwxFCwq@qeoR09buNz4V`+IDj5Q0_vfF&lxQwf>* zBT`(VV=8~UD2o)h#!+=eXjpA4pF;fO`wxy>^A_=`lJEI6NYNyxc}#lAKM>-->7SJz z-&Jw`Nx^07#Wzv3)IE(ajVRNmqJNxI=%ZD-OWEEEs$tLONnXPL6qAi$E8om`E{RDS zJE9l6f6gZu*CT(wKJU#Zt-;^!R(33*xAzHnisim|IwPzaZ8ND(hz^hB?I&;@k82#? zGuqJbGRlxLvcFEOomkl3pnN~Q(N{2ysF>5JySG(Opy!3atvgkXQ_8XE$gmdOH_5Dd zEvRQ2-y(LV`*`y!!#G-zfr!i|k(=$U9K9bxUwWB7 z?_G>0|GKcytG)f=RR+Bbl~tyV8h{O}bZlSvUu&n>=;k3O^Uzc`pc+;n5gK-hK za;fdTS;T(+k+J>y&jX~Qy^eLI@F#~Q49o3Uy7>9%{O!{X`oZrx9%L$K1uP1ZQ{`yK zo{Kk(+K@ZnFGXJ9I%t`=ynKGYet?O^#{km#I1|fJ`#X$xuI^XJ;!k6?9h=UQp7w7jsHfP-}S9vQ+j$N{D;k^K&Os+a=OjJOp=@!^-KM4qs#k z-ld9Ono*E`R_@ZJqf;hz^`2|Yk-H)jV*Z$1|B!L^GtUj?K8x<>&AsT=pfz;(Iwo4w z$3~(xqSY5J#C{IG;z3IBxvTz%+d;1uV(rliwxXYTroV&3&gu?%#9}nEtCVaN#4a55<;4uw2 zBj%oG@_^n04oDv6fr($O;q-yqfoT^3caWF$`+ZE4!!+h|;0Y#Q2;>Kv1bG++|Kn@g z>Xoj6V&-+j@oooPe*Y&hQEfnNb1WdFn8fj_~%MtH+hp!in-u880JL4D{4^K(r88c2OX z4vR6s7Zi6GtOHLl50CYFL`T#H<2?fSePHs1Xw3QvH8A;WumS%M06zlX!4$xc0mi?X zd8tEz!*U+%lQ~fDk^KVd6Z|f6&Cn3w4h?`qco5_d#BVs>FMuBrKUV;M15OAp=o{dY z1M0{$*#Ex)|8JnV`2qF=Qm2t-WDw*NG$rs7I8Tv!{}GHG%t8;3GuPj6ydN?7!9Bp| zlfd6dGdP5dfMXAnzXmJd58@y?@bL&3!MYH#4?sPtV+H=7_{RwL4a5MyE8dv>$@+c< z{lxmY2)IELfH$ZYa5vzy0Q?N@LxW5|BK^#|UqPP<{Q~_XXtI&M2st0u^H2cx3#e}! zjW@ytT0b{|zd>L8A76t01N4jQ^?m{5V-ffgtOI=p=P&4g;P>F1MEV&dzeqoi#M8k( z`@+oI#^L=x@4*Fb^10zX-Tl#ycrRx(frxiOrb+J3c(jun&fN=5au39VX#u>y?@A=z z8BOvf{&zgDTYxjso8ac{=-hN)r?q05F=HFqy PH)`qMs*~V;ff)b*eMB`& diff --git a/data/Z.RData b/data/Z.RData deleted file mode 100644 index fbc60e70cce9b938f7b09cb7cc132eb3c7c75f90..0000000000000000000000000000000000000000 GIT binary patch literal 0 HcmV?d00001 literal 580 zcmV-K0=xYmiwFP!000001KpIrPgFq=$Cvlsne!yv5wFJfECnquvqtdF_#@tF6bX%m zb{dSG*3>jM+Coh$g~_ZKV}k}`aT*gN64U@jFdpZD-ud=@XI=t-!fo;9yKi>qz5UG0 z)TPA zI~g|L$d#vN8??SsnJ+$Ap}!^>HjBA6vM!8wm6|VHe#i$p<_2MHkc6$fLrZ?Vb_ML? zUB7&B#)eo&-x1dh#vjX-@3~0!Mfk4+2guyLdFR&sSQPxv>#0twsH?c7VpPQ$6=N!D zDk>_fD$c36pyIrWiz?2lxUAxeimNKFtGJ=!TKwoJd>06e2oR|4k6hcNAAricfIy$c zzw8-J&ACE3p+()1WbmFxTbbwIfK8izR(!}yNGf%cT;}L)l7lL5OS1X^-R7s07dC`- z8TbJ|==KV4S_LoHFFd!vlR8q=19;CZ@Zx8}uOa+|Kkp@Jo8%T8E|k1|O43lIE$=Pu z&_D2{UuYKImUUmGsXl@?|3TbdoVO=p6n5Dra9@04aDs=-X#6cFL8fRTdZEP8JwHe(BHf)_5L2* z>FNGDPcQ#>lE0r)_p6v&BYm`n{PBm!emvo}%v)05kHEcmc<(z$Mx4RKiBt`zY9v)B SQ*{baOy@rf957|G2LJ$x{wF;E diff --git a/data/datalist b/data/datalist index a6dbae2..5445c9b 100755 --- a/data/datalist +++ b/data/datalist @@ -1,6 +1,2 @@ -pepdata -H -pK -K -CP -Z \ No newline at end of file +AA +pepdata \ No newline at end of file diff --git a/data/pK.RData b/data/pK.RData deleted file mode 100644 index b2c828981026d36318182062c614256e622a06e6..0000000000000000000000000000000000000000 GIT binary patch literal 0 HcmV?d00001 literal 3053 zcmVWl7dtYNmT{_ukjNfBm}OKc4UBd!F;0^ZuUa zobU6X3~dgu+pq%w01$wQ2?PK!ZAoU()&&S)2C!|n`#Avzve-|&qjYv;zvF| z@&IlAmFSXmBnCPUeQAXl=yXK+U(h+}uS)Vq{5#MkY~{Yx5p3aL#;Vg1f375-hV~kN8eDa^bI2cpxa-M{oNU5 zKxb4KUOEcHGb+q~D)PS*{ohW-u74im;o%#I^$(!8uo$8*_>o`?V zXfJ1PPZfU*#(66SZ*gz+176+Inkd&?0mA!Pu`H!~`qF;SVI~|1jlO4&;I+sJpkr@{ zPVb^Bsk%jT>C#+ql0?n{w2OXEa2~K{#j$X6^bF8zML7KI{XS&fQ1t7I6)@wh)SA(u zgw*_3YTBo${rZg}AD(>1^c=NV3=q9)cg)ebOq4(A@XjugdDx>i1vqJRHepke5HNF} zZ;$*jT4aHDo_PQ&LZebgRQgo%#`(tacD-AL$qw95o}`EhBhv=*s{io3j$(0qRB;@> zo2H|a$6~9J@>l|3EV7QT*ppQYV55yr6hRZ}i=7RZghkqOP*(zlq@^=hwY#gysUbIn zLYH+bH?pZQ2xRQ={k59C(fzf#LLN%%xJ5f&^+8pI;mi5W;FDJoqOi_`ZNd-{uG3XX zK8KtVPaCq_==tL#s&A*XuX+@Z46_uD1R`9p^)-LH!fN|8Z2?hFYV8%j3t8t6PE_W& z%yC04>`uduKNbpV>Qv6L=C|=!nGJ0Y#=9P!A?_V1dHsG!m_vxw!V(sr%Bkg>8Ma`* z5`1UiNN%}0l3mP&mC{~z!ZN;a)2uuP_<~jDsaYNf(7`!jefuZN<4=+{UblPA>L|q3agBKS?s0wP zvLB#$SG$H!`|aG^jmlf!zV4omhp?I+>--p+(Eh%)wY;IY^vIGFpqGT|>XdO{{xm+t zvj{Y_i8uzUlrvP#$w8PIk!&!1N=yS_CZR)c5k6ODBOFqzU|mMnNZh{eBHw%>t`mk0 zUCVr=&lY3lq-Q`BeBRGKiRexUFT{N!(LkR~Bbg_WBBx8Mht!O8WAlf6R0cYWPFcpo zE8e`jd^WrFn_>t>dxRCIy?nyY`&vSa$jr62z$qyMY`VSo%~EQ5xsQ9SB|0huN{HP3RcD6=u_lId zw&pS!paWB$#(%y?8fZk3hE=MHtioL5=8Sj+KqC6Mh3KjxgW`LNb@{}aw0+!17DBps zBED$!Mn9z~0Bg<5O?Ertu2J{lMB$5vt^j|k~}h&l83uI6FHOG5PbN{8 zqfi42Owkm;BZzG^-KVYCP=pKj!kzzl)U%PtPGk?Cw=I-J$l~QZ|1_cnrD=bff@TV} zoAV%TL-MW6STs4UB}Nqa@idR}r~NDB$|YN3EaVHqaD}txg#)*H-SIu@%n^?=g`p^( z6|uX+o>K%<-Kj_dg)@Uc&LZv)E9(KH5cJC6)kO!Eh0)>~Kk$>hrn7GH?z4Odq_8zQ z?Ye{+zbyak0?8Vt91gQ5FlRTERrgeHD6908W-&CT6LKDD+YK?BH{ICpGZdeqX3b zbRxd_sX+F_LVbCl29HnVyi~7_b{Gi8FQm~`^6lGruaT=Lt(yb9t6ms&uALAAViJ&+Mvxchc57_S(U?;{_41Lu=JY;n^3K?5 z9;CGb;>_6E3w5yO-RkU;_x7v#UT;*>NZ8F!E&|Fz2Cs0U-G^4WPr1d#m8-188^<5}~BuZrNt@wUvs!x5C8<7S0Qp-H%uXlvQs zA2>DAMtYzTy9Nd*0a9jcz~G1H4&(2AKBm-IN*nSUO}C)V+`1u%lxgDRzOKC~-jZuA zFwKRnRxsZ5t*S)WGa^QwWD8|^ta)vT^-x4sY1reac1?|S@o zYw%gD78(nRSlN`Y=<&m9-R*azym}-gr8B3SmzS)gauZnIytCQKtLJa2p8hmji~V*U z|H#-u#0?+F-q5xAm`sBgCRdx!1#!BEK+LsA?6VRZE2kqCmWGjK9k*zZn0kMuYWX_O z)v2x;6RK`a($fF)l&6HUJP7b$V|4c?-Vb$h(fXDmh zMPCzmuVuG4H!HM`$u6SjB3~c>g{iqdJoMQYUVLf}^Oup$`El#mk=Z0bkb0C&AWk`? zL$p;e=?>pO_>t_}oQ;}?VytSd!p$%FO`3On&E#Ki4#vse%%bGlD#+$@%*zl_vlb&U zaR(z`4yAEsJ@bJ!l~dM=4q3#jJa0$je5p_oyU!`8LteS~X2n0Q$!uNj$+0M_+H$Cu z*axw&j^1&yxK^lPT-M&g75S1EwbvK)PoU#Z6nf6QD4Z;94lY2GXRq#Ff|O7^R@Q7L zKdocO2+}C=52cMKM%nMJ!=l^NAD)LE+u@85jid}a^&be;b0fdH<9K)GZ1wF_pr*%7 zvt*`)6;+613sYzQj;SE0H?_N;uP5z)$ZKnvD9SAC=CqDsFXwX3z308b&2lReUo{)p z>3->8eL7KPF-4imf7piVn?W#;V#ajBY=p=026tbDOHC-fJ>3k(i^qQIlNodIm6tA` zJgPZvk$i=`q)dEQEa`oXl6k?CZ4mVAi4{iqWQyVyR=LIbOq2A7p|36#sBhpa&KOP@ v!R0S4Q@SPBkIGqZ|L^?`9`iX;SrGsLq)0Uq From 7c3b9f2db23c5d3ccd24ca2c08fdfaba9bde6478 Mon Sep 17 00:00:00 2001 From: Daniel Osorio Date: Thu, 2 Mar 2017 22:53:31 -0500 Subject: [PATCH 11/50] Peptides 1.19.2 --- R/data-AA.R | 104 ++++++++++++++++++++++++++++++++++++++++++++++++ R/data-H.R | 97 --------------------------------------------- README.md | 8 +--- man/AA.Rd | 112 ++++++++++++++++++++++++++++++++++++++++++++++++++++ man/H.Rd | 108 -------------------------------------------------- 5 files changed, 218 insertions(+), 211 deletions(-) create mode 100644 R/data-AA.R delete mode 100644 R/data-H.R create mode 100644 man/AA.Rd delete mode 100644 man/H.Rd diff --git a/R/data-AA.R b/R/data-AA.R new file mode 100644 index 0000000..d685b4e --- /dev/null +++ b/R/data-AA.R @@ -0,0 +1,104 @@ +#' @name AA +#' @docType data +#' @title Properties, scales and indices for the 20 naturally occurring amino acids from various sources +#' @description A list with a collection of properties, scales and indices for the 20 naturally occurring amino acids from various sources +#' @usage data(AA) +#' @format A list as follows: \itemize{ +#' \item{Hydrophobicity} \itemize{ +#' \item{Aboderin:} Aboderin, A. A. (1971). An empirical hydrophobicity scale for alpha-amino-acids and some of its applications. International Journal of Biochemistry, 2(11), 537-544. +#' \item{AbrahamLeo:} Abraham D.J., Leo A.J. Hydrophobicity (delta G1/2 cal). Proteins: Structure, Function and Genetics 2:130-152(1987). +#' \item{Argos:} Argos, P., Rao, J. K., & Hargrave, P. A. (1982). Structural Prediction of Membrane-Bound Proteins. European Journal of Biochemistry, 128(2-3), 565-575. +#' \item{BlackMould:} Black S.D., Mould D.R. Hydrophobicity of physiological L-alpha amino acids. Anal. Biochem. 193:72-82(1991). +#' \item{BullBreese:} Bull H.B., Breese K. Hydrophobicity (free energy of transfer to surface in kcal/mole). Arch. Biochem. Biophys. 161:665-670(1974). +#' \item{Casari:} Casari, G., & Sippl, M. J. (1992). Structure-derived hydrophobic potential: hydrophobic potential derived from X-ray structures of globular proteins is able to identify native folds. Journal of molecular biology, 224(3), 725-732. +#' \item{Chothia:} Chothia, C. (1976). The nature of the accessible and buried surfaces in proteins. Journal of molecular biology, 105(1), 1-12. +#' \item{Cid:} Cid, H., Bunster, M., Canales, M., & Gazitua, F. (1992). Hydrophobicity and structural classes in proteins. Protein engineering, 5(5), 373-375. +#' \item{Cowan3.4:} Cowan R., Whittaker R.G. Hydrophobicity indices at pH 3.4 determined by HPLC. Peptide Research 3:75-80(1990). +#' \item{Cowan7.5:} Cowan R., Whittaker R.G. Hydrophobicity indices at pH 7.5 determined by HPLC. Peptide Research 3:75-80(1990). +#' \item{Eisenberg:} Eisenberg D., Schwarz E., Komarony M., Wall R. Normalized consensus hydrophobicity scale. J. Mol. Biol. 179:125-142(1984). +#' \item{Engelman:} Engelman, D. M., Steitz, T. A., & Goldman, A. (1986). Identifying nonpolar transbilayer helices in amino acid sequences of membrane proteins. Annual review of biophysics and biophysical chemistry, 15(1), 321-353. +#' \item{Fasman:} Fasman, G. D. (Ed.). (1989). Prediction of protein structure and the principles of protein conformation. Springer. +#' \item{Fauchere:} Fauchere J.-L., Pliska V.E. Hydrophobicity scale (pi-r). Eur. J. Med. Chem. 18:369-375(1983). +#' \item{Goldsack:} Goldsack, D. E., & Chalifoux, R. C. (1973). Contribution of the free energy of mixing of hydrophobic side chains to the stability of the tertiary structure of proteins. Journal of theoretical biology, 39(3), 645-651. +#' \item{Guy:} Guy H.R. Hydrophobicity scale based on free energy of transfer (kcal/mole). Biophys J. 47:61-70(1985). +#' \item{HoppWoods:} Hopp T.P., Woods K.R. Hydrophilicity. Proc. Natl. Acad. Sci. U.S.A. 78:3824-3828(1981). +#' \item{Janin:} Janin J. Free energy of transfer from inside to outside of a globular protein. Nature 277:491-492(1979). +#' \item{Jones:} Jones, D. D. (1975). Amino acid properties and side-chain orientation in proteins: a cross correlation approach. Journal of theoretical biology, 50(1), 167-183. +#' \item{Juretic:} Juretic, D., Lucic, B., Zucic, D., & Trinajstic, N. (1998). Protein transmembrane structure: recognition and prediction by using hydrophobicity scales through preference functions. Theoretical and computational chemistry, 5, 405-445. +#' \item{Kidera:} Kidera, A., Konishi, Y., Oka, M., Ooi, T., & Scheraga, H. A. (1985). Statistical analysis of the physical properties of the 20 naturally occurring amino acids. Journal of Protein Chemistry, 4(1), 23-55. +#' \item{Kuhn:} Kuhn, L. A., Swanson, C. A., Pique, M. E., Tainer, J. A., & Getzoff, E. D. (1995). Atomic and residue hydrophilicity in the context of folded protein structures. Proteins: Structure, Function, and Bioinformatics, 23(4), 536-547. +#' \item{KyteDoolittle:} Kyte J., Doolittle R.F. Hydropathicity. J. Mol. Biol. 157:105-132(1982). +#' \item{Levitt:} Levitt, M. (1976). A simplified representation of protein conformations for rapid simulation of protein folding. Journal of molecular biology, 104(1), 59-107. +#' \item{Manavalan:} Manavalan P., Ponnuswamy Average surrounding hydrophobicity. P.K. Nature 275:673-674(1978). +#' \item{Miyazawa:} Miyazawa S., Jernigen R.L. Hydrophobicity scale (contact energy derived from 3D data). Macromolecules 18:534-552(1985). +#' \item{Parker:} Parker J.M.R., Guo D., Hodges R.S. Hydrophilicity scale derived from HPLC peptide retention times. Biochemistry 25:5425-5431(1986). +#' \item{Ponnuswamy:} Ponnuswamy, P. K. (1993). Hydrophobic charactesristics of folded proteins. Progress in biophysics and molecular biology, 59(1), 57-103. +#' \item{Prabhakaran:} Prabhakaran, M. (1990). The distribution of physical, chemical and conformational properties in signal and nascent peptides. Biochem. J, 269, 691-696. +#' \item{Rao:} Rao M.J.K., Argos P. Membrane buried helix parameter. Biochim. Biophys. Acta 869:197-214(1986). +#' \item{Rose:} Rose G.D., Geselowitz A.R., Lesser G.J., Lee R.H., Zehfus M.H. Mean fractional area loss (f) [average area buried/standard state area]. Science 229:834-838(1985) +#' \item{Roseman:} Roseman M.A. Hydrophobicity scale (pi-r). J. Mol. Biol. 200:513-522(1988). +#' \item{Sweet:} Sweet R.M., Eisenberg D. Optimized matching hydrophobicity (OMH). J. Mol. Biol. 171:479-488(1983). +#' \item{Tanford:} Tanford C. Hydrophobicity scale (Contribution of hydrophobic interactions to the stability of the globular conformation of proteins). J. Am. Chem. Soc. 84:4240-4274(1962). +#' \item{Welling:} Welling G.W., Weijer W.J., Van der Zee R., Welling-Wester S. Antigenicity value X 10. FEBS Lett. 188:215-218(1985). +#' \item{Wilson:} Wilson K.J., Honegger A., Stotzel R.P., Hughes G.J. Hydrophobic constants derived from HPLC peptide retention times. Biochem. J. 199:31-41(1981). +#' \item{Wolfenden:} Wolfenden R.V., Andersson L., Cullis P.M., Southgate C.C.F. Hydration potential (kcal/mole) at 25C. Biochemistry 20:849-855(1981). +#' \item{Zimmerman:} Zimmerman, J. M., Eliezer, N., & Simha, R. (1968). The characterization of amino acid sequences in proteins by statistical methods. Journal of theoretical biology, 21(2), 170-201. +#' } +#' \item{crucianiProperties:} \itemize{ +#' \item{PP1:} +#' \item{PP2:} +#' \item{PP3: } +#' } +#' \item{kideraFactors:} \itemize{ +#' \item{helix.bend.pref} +#' \item{side.chain.size} +#' \item{extended.str.pref} +#' \item{hydrophobicity} +#' \item{double.bend.pref} +#' \item{partial.spec.vol} +#' \item{flat.ext.pref} +#' \item{occurrence.alpha.reg} +#' \item{pK.C} +#' \item{surrounding.hydrop} +#' } +#' \item{pK}\itemize{ +#' \item{Bjellqvist} +#' \item{Dawson} +#' \item{EMBOSS} +#' \item{Lehninger} +#' \item{Murray} +#' \item{Rodwell} +#' \item{Sillero} +#' \item{Solomon} +#' \item{Stryer} +#' } +#' \item{zScales}\itemize{ +#' \item{Z1} +#' \item{Z2} +#' \item{Z3} +#' \item{Z4} +#' \item{Z5} +#' } +#' } +#' @source +#' \itemize{ +#' \item{Hydrophobicity}\itemize{ +#' \item ExPASy-Protscale (http://web.expasy.org/protscale/) +#' \item AAIndex Database (http://www.genome.jp/aaindex/) +#' } +#' } +#' @references +#' \itemize{ +#' \item{Hydrophobicity}\itemize{ +#' Nakai, K., Kidera, A., and Kanehisa, M.; Cluster analysis of amino acid indices for prediction of protein structure and function. Protein Eng. 2, 93-100 (1988). +#' +#' Tomii, K. and Kanehisa, M.; Analysis of amino acid indices and mutation matrices for sequence comparison and structure prediction of proteins. Protein Eng. 9, 27-36 (1996). +#' +#' Kawashima, S., Ogata, H., and Kanehisa, M.; AAindex: amino acid index database. Nucleic Acids Res. 27, 368-369 (1999). +#' +#' Kawashima, S. and Kanehisa, M.; AAindex: amino acid index database. Nucleic Acids Res. 28, 374 (2000). +#' +#' Kawashima, S., Pokarowski, P., Pokarowska, M., Kolinski, A., Katayama, T., and Kanehisa, M.; AAindex: amino acid index database, progress report 2008. Nucleic Acids Res. 36, D202-D205 (2008). +#' } +#' } +NULL diff --git a/R/data-H.R b/R/data-H.R deleted file mode 100644 index 986ceeb..0000000 --- a/R/data-H.R +++ /dev/null @@ -1,97 +0,0 @@ -#' @name H -#' @docType data -#' @title 38 Hydrophobicity scales for amino-acids from various sources -#' @description A list with 38 Hydrophobicity scales for amino acids from various sources -#' @usage data(H) -#' @format A list with 38 Hydrophobicity scales. -#' @details The hydrophobicity is an important stabilization force in protein folding; this force changes depending on the solvent in which the protein is found. -#' @source ExPASy-Protscale (http://web.expasy.org/protscale/) -#' -#' AAIndex Database (http://www.genome.jp/aaindex/) -#' @references Aboderin, A. A. (1971). An empirical hydrophobicity scale for alpha-amino-acids and some of its applications. International Journal of Biochemistry, 2(11), 537-544. -#' -#' Abraham D.J., Leo A.J. Hydrophobicity (delta G1/2 cal). Proteins: Structure, Function and Genetics 2:130-152(1987). -#' -#' Argos, P., Rao, J. K., & Hargrave, P. A. (1982). Structural Prediction of Membrane-Bound Proteins. European Journal of Biochemistry, 128(2-3), 565-575. -#' -#' Black S.D., Mould D.R. Hydrophobicity of physiological L-alpha amino acids. Anal. Biochem. 193:72-82(1991). -#' -#' Bull H.B., Breese K. Hydrophobicity (free energy of transfer to surface in kcal/mole). Arch. Biochem. Biophys. 161:665-670(1974). -#' -#' Casari, G., & Sippl, M. J. (1992). Structure-derived hydrophobic potential: hydrophobic potential derived from X-ray structures of globular proteins is able to identify native folds. Journal of molecular biology, 224(3), 725-732. -#' -#' Chothia, C. (1976). The nature of the accessible and buried surfaces in proteins. Journal of molecular biology, 105(1), 1-12. -#' -#' Cid, H., Bunster, M., Canales, M., & Gazitua, F. (1992). Hydrophobicity and structural classes in proteins. Protein engineering, 5(5), 373-375. -#' -#' Cowan R., Whittaker R.G. Hydrophobicity indices at pH 3.4 determined by HPLC. Peptide Research 3:75-80(1990). -#' -#' Cowan R., Whittaker R.G. Hydrophobicity indices at pH 7.5 determined by HPLC. Peptide Research 3:75-80(1990). -#' -#' Eisenberg D., Schwarz E., Komarony M., Wall R. Normalized consensus hydrophobicity scale. J. Mol. Biol. 179:125-142(1984). -#' -#' Engelman, D. M., Steitz, T. A., & Goldman, A. (1986). Identifying nonpolar transbilayer helices in amino acid sequences of membrane proteins. Annual review of biophysics and biophysical chemistry, 15(1), 321-353. -#' -#' Fasman, G. D. (Ed.). (1989). Prediction of protein structure and the principles of protein conformation. Springer. -#' -#' Fauchere J.-L., Pliska V.E. Hydrophobicity scale (pi-r). Eur. J. Med. Chem. 18:369-375(1983). -#' -#' Goldsack, D. E., & Chalifoux, R. C. (1973). Contribution of the free energy of mixing of hydrophobic side chains to the stability of the tertiary structure of proteins. Journal of theoretical biology, 39(3), 645-651. -#' -#' Guy H.R. Hydrophobicity scale based on free energy of transfer (kcal/mole). Biophys J. 47:61-70(1985). -#' -#' Hopp T.P., Woods K.R. Hydrophilicity. Proc. Natl. Acad. Sci. U.S.A. 78:3824-3828(1981). -#' -#' Janin J. Free energy of transfer from inside to outside of a globular protein. Nature 277:491-492(1979). -#' -#' Jones, D. D. (1975). Amino acid properties and side-chain orientation in proteins: a cross correlation approach. Journal of theoretical biology, 50(1), 167-183. -#' -#' Juretic, D., Lucic, B., Zucic, D., & Trinajstic, N. (1998). Protein transmembrane structure: recognition and prediction by using hydrophobicity scales through preference functions. Theoretical and computational chemistry, 5, 405-445. -#' -#' Kidera, A., Konishi, Y., Oka, M., Ooi, T., & Scheraga, H. A. (1985). Statistical analysis of the physical properties of the 20 naturally occurring amino acids. Journal of Protein Chemistry, 4(1), 23-55. -#' -#' Kuhn, L. A., Swanson, C. A., Pique, M. E., Tainer, J. A., & Getzoff, E. D. (1995). Atomic and residue hydrophilicity in the context of folded protein structures. Proteins: Structure, Function, and Bioinformatics, 23(4), 536-547. -#' -#' Kyte J., Doolittle R.F. Hydropathicity. J. Mol. Biol. 157:105-132(1982). -#' -#' Levitt, M. (1976). A simplified representation of protein conformations for rapid simulation of protein folding. Journal of molecular biology, 104(1), 59-107. -#' -#' Manavalan P., Ponnuswamy Average surrounding hydrophobicity. P.K. Nature 275:673-674(1978). -#' -#' Miyazawa S., Jernigen R.L. Hydrophobicity scale (contact energy derived from 3D data). Macromolecules 18:534-552(1985). -#' -#' Parker J.M.R., Guo D., Hodges R.S. Hydrophilicity scale derived from HPLC peptide retention times. Biochemistry 25:5425-5431(1986). -#' -#' Ponnuswamy, P. K. (1993). Hydrophobic charactesristics of folded proteins. Progress in biophysics and molecular biology, 59(1), 57-103. -#' -#' Prabhakaran, M. (1990). The distribution of physical, chemical and conformational properties in signal and nascent peptides. Biochem. J, 269, 691-696. -#' -#' Rao M.J.K., Argos P. Membrane buried helix parameter. Biochim. Biophys. Acta 869:197-214(1986). -#' -#' Rose G.D., Geselowitz A.R., Lesser G.J., Lee R.H., Zehfus M.H. Mean fractional area loss (f) [average area buried/standard state area]. Science 229:834-838(1985) -#' -#' Roseman M.A. Hydrophobicity scale (pi-r). J. Mol. Biol. 200:513-522(1988). -#' -#' Sweet R.M., Eisenberg D. Optimized matching hydrophobicity (OMH). J. Mol. Biol. 171:479-488(1983). -#' -#' Tanford C. Hydrophobicity scale (Contribution of hydrophobic interactions to the stability of the globular conformation of proteins). J. Am. Chem. Soc. 84:4240-4274(1962). -#' -#' Welling G.W., Weijer W.J., Van der Zee R., Welling-Wester S. Antigenicity value X 10. FEBS Lett. 188:215-218(1985). -#' -#' Wilson K.J., Honegger A., Stotzel R.P., Hughes G.J. Hydrophobic constants derived from HPLC peptide retention times. Biochem. J. 199:31-41(1981). -#' -#' Wolfenden R.V., Andersson L., Cullis P.M., Southgate C.C.F. Hydration potential (kcal/mole) at 25C. Biochemistry 20:849-855(1981). -#' -#' Zimmerman, J. M., Eliezer, N., & Simha, R. (1968). The characterization of amino acid sequences in proteins by statistical methods. Journal of theoretical biology, 21(2), 170-201. -#' -#' Nakai, K., Kidera, A., and Kanehisa, M.; Cluster analysis of amino acid indices for prediction of protein structure and function. Protein Eng. 2, 93-100 (1988). -#' -#' Tomii, K. and Kanehisa, M.; Analysis of amino acid indices and mutation matrices for sequence comparison and structure prediction of proteins. Protein Eng. 9, 27-36 (1996). -#' -#' Kawashima, S., Ogata, H., and Kanehisa, M.; AAindex: amino acid index database. Nucleic Acids Res. 27, 368-369 (1999). -#' -#' Kawashima, S. and Kanehisa, M.; AAindex: amino acid index database. Nucleic Acids Res. 28, 374 (2000). -#' -#' Kawashima, S., Pokarowski, P., Pokarowska, M., Kolinski, A., Katayama, T., and Kanehisa, M.; AAindex: amino acid index database, progress report 2008. Nucleic Acids Res. 36, D202-D205 (2008). - -NULL \ No newline at end of file diff --git a/README.md b/README.md index d4c2e17..d49d7e0 100755 --- a/README.md +++ b/README.md @@ -46,12 +46,8 @@ Available datasets ------------------- | Code | Description | |:----------- |:------------| -|CP | The 3 properties from Cruciani *et al.* (2004) | -|H | 38 Hydrophobicity values for amino acids form various sources | -|K | The 10 factors from Kidera *et al.* (1985)| -|pepdata | A data frame with 21 physicochemical properties and indices from 100 amino-acid sequences (50 antimicrobial and 50 non antimicrobial) | -|pK | 9 pKa scales for the side chain of charged amino acids from various sources | -|Z|The 5 Z-scales from Sandberg *et al.* (1998)| +|AA | | +|pepdata | A data frame with 21 physicochemical properties and indices from 100 amino-acid sequences (50 antimicrobial and 50 non antimicrobial) | Citation -------- diff --git a/man/AA.Rd b/man/AA.Rd new file mode 100644 index 0000000..daa7ddc --- /dev/null +++ b/man/AA.Rd @@ -0,0 +1,112 @@ +% Generated by roxygen2: do not edit by hand +% Please edit documentation in R/data-AA.R +\docType{data} +\name{AA} +\alias{AA} +\title{Properties, scales and indices for the 20 naturally occurring amino acids from various sources} +\format{A list as follows: \itemize{ +\item{Hydrophobicity} \itemize{ +\item{Aboderin:} Aboderin, A. A. (1971). An empirical hydrophobicity scale for alpha-amino-acids and some of its applications. International Journal of Biochemistry, 2(11), 537-544. +\item{AbrahamLeo:} Abraham D.J., Leo A.J. Hydrophobicity (delta G1/2 cal). Proteins: Structure, Function and Genetics 2:130-152(1987). +\item{Argos:} Argos, P., Rao, J. K., & Hargrave, P. A. (1982). Structural Prediction of Membrane-Bound Proteins. European Journal of Biochemistry, 128(2-3), 565-575. +\item{BlackMould:} Black S.D., Mould D.R. Hydrophobicity of physiological L-alpha amino acids. Anal. Biochem. 193:72-82(1991). +\item{BullBreese:} Bull H.B., Breese K. Hydrophobicity (free energy of transfer to surface in kcal/mole). Arch. Biochem. Biophys. 161:665-670(1974). +\item{Casari:} Casari, G., & Sippl, M. J. (1992). Structure-derived hydrophobic potential: hydrophobic potential derived from X-ray structures of globular proteins is able to identify native folds. Journal of molecular biology, 224(3), 725-732. +\item{Chothia:} Chothia, C. (1976). The nature of the accessible and buried surfaces in proteins. Journal of molecular biology, 105(1), 1-12. +\item{Cid:} Cid, H., Bunster, M., Canales, M., & Gazitua, F. (1992). Hydrophobicity and structural classes in proteins. Protein engineering, 5(5), 373-375. +\item{Cowan3.4:} Cowan R., Whittaker R.G. Hydrophobicity indices at pH 3.4 determined by HPLC. Peptide Research 3:75-80(1990). +\item{Cowan7.5:} Cowan R., Whittaker R.G. Hydrophobicity indices at pH 7.5 determined by HPLC. Peptide Research 3:75-80(1990). +\item{Eisenberg:} Eisenberg D., Schwarz E., Komarony M., Wall R. Normalized consensus hydrophobicity scale. J. Mol. Biol. 179:125-142(1984). +\item{Engelman:} Engelman, D. M., Steitz, T. A., & Goldman, A. (1986). Identifying nonpolar transbilayer helices in amino acid sequences of membrane proteins. Annual review of biophysics and biophysical chemistry, 15(1), 321-353. +\item{Fasman:} Fasman, G. D. (Ed.). (1989). Prediction of protein structure and the principles of protein conformation. Springer. +\item{Fauchere:} Fauchere J.-L., Pliska V.E. Hydrophobicity scale (pi-r). Eur. J. Med. Chem. 18:369-375(1983). +\item{Goldsack:} Goldsack, D. E., & Chalifoux, R. C. (1973). Contribution of the free energy of mixing of hydrophobic side chains to the stability of the tertiary structure of proteins. Journal of theoretical biology, 39(3), 645-651. +\item{Guy:} Guy H.R. Hydrophobicity scale based on free energy of transfer (kcal/mole). Biophys J. 47:61-70(1985). +\item{HoppWoods:} Hopp T.P., Woods K.R. Hydrophilicity. Proc. Natl. Acad. Sci. U.S.A. 78:3824-3828(1981). +\item{Janin:} Janin J. Free energy of transfer from inside to outside of a globular protein. Nature 277:491-492(1979). +\item{Jones:} Jones, D. D. (1975). Amino acid properties and side-chain orientation in proteins: a cross correlation approach. Journal of theoretical biology, 50(1), 167-183. +\item{Juretic:} Juretic, D., Lucic, B., Zucic, D., & Trinajstic, N. (1998). Protein transmembrane structure: recognition and prediction by using hydrophobicity scales through preference functions. Theoretical and computational chemistry, 5, 405-445. +\item{Kidera:} Kidera, A., Konishi, Y., Oka, M., Ooi, T., & Scheraga, H. A. (1985). Statistical analysis of the physical properties of the 20 naturally occurring amino acids. Journal of Protein Chemistry, 4(1), 23-55. +\item{Kuhn:} Kuhn, L. A., Swanson, C. A., Pique, M. E., Tainer, J. A., & Getzoff, E. D. (1995). Atomic and residue hydrophilicity in the context of folded protein structures. Proteins: Structure, Function, and Bioinformatics, 23(4), 536-547. +\item{KyteDoolittle:} Kyte J., Doolittle R.F. Hydropathicity. J. Mol. Biol. 157:105-132(1982). +\item{Levitt:} Levitt, M. (1976). A simplified representation of protein conformations for rapid simulation of protein folding. Journal of molecular biology, 104(1), 59-107. +\item{Manavalan:} Manavalan P., Ponnuswamy Average surrounding hydrophobicity. P.K. Nature 275:673-674(1978). +\item{Miyazawa:} Miyazawa S., Jernigen R.L. Hydrophobicity scale (contact energy derived from 3D data). Macromolecules 18:534-552(1985). +\item{Parker:} Parker J.M.R., Guo D., Hodges R.S. Hydrophilicity scale derived from HPLC peptide retention times. Biochemistry 25:5425-5431(1986). +\item{Ponnuswamy:} Ponnuswamy, P. K. (1993). Hydrophobic charactesristics of folded proteins. Progress in biophysics and molecular biology, 59(1), 57-103. +\item{Prabhakaran:} Prabhakaran, M. (1990). The distribution of physical, chemical and conformational properties in signal and nascent peptides. Biochem. J, 269, 691-696. +\item{Rao:} Rao M.J.K., Argos P. Membrane buried helix parameter. Biochim. Biophys. Acta 869:197-214(1986). +\item{Rose:} Rose G.D., Geselowitz A.R., Lesser G.J., Lee R.H., Zehfus M.H. Mean fractional area loss (f) [average area buried/standard state area]. Science 229:834-838(1985) +\item{Roseman:} Roseman M.A. Hydrophobicity scale (pi-r). J. Mol. Biol. 200:513-522(1988). +\item{Sweet:} Sweet R.M., Eisenberg D. Optimized matching hydrophobicity (OMH). J. Mol. Biol. 171:479-488(1983). +\item{Tanford:} Tanford C. Hydrophobicity scale (Contribution of hydrophobic interactions to the stability of the globular conformation of proteins). J. Am. Chem. Soc. 84:4240-4274(1962). +\item{Welling:} Welling G.W., Weijer W.J., Van der Zee R., Welling-Wester S. Antigenicity value X 10. FEBS Lett. 188:215-218(1985). +\item{Wilson:} Wilson K.J., Honegger A., Stotzel R.P., Hughes G.J. Hydrophobic constants derived from HPLC peptide retention times. Biochem. J. 199:31-41(1981). +\item{Wolfenden:} Wolfenden R.V., Andersson L., Cullis P.M., Southgate C.C.F. Hydration potential (kcal/mole) at 25C. Biochemistry 20:849-855(1981). +\item{Zimmerman:} Zimmerman, J. M., Eliezer, N., & Simha, R. (1968). The characterization of amino acid sequences in proteins by statistical methods. Journal of theoretical biology, 21(2), 170-201. +} +\item{crucianiProperties:} \itemize{ +\item{PP1:} +\item{PP2:} +\item{PP3: } +} +\item{kideraFactors:} \itemize{ +\item{helix.bend.pref} +\item{side.chain.size} +\item{extended.str.pref} +\item{hydrophobicity} +\item{double.bend.pref} +\item{partial.spec.vol} +\item{flat.ext.pref} +\item{occurrence.alpha.reg} +\item{pK.C} +\item{surrounding.hydrop} +} +\item{pK}\itemize{ +\item{Bjellqvist} +\item{Dawson} +\item{EMBOSS} +\item{Lehninger} +\item{Murray} +\item{Rodwell} +\item{Sillero} +\item{Solomon} +\item{Stryer} +} +\item{zScales}\itemize{ +\item{Z1} +\item{Z2} +\item{Z3} +\item{Z4} +\item{Z5} +} +}} +\source{ +\itemize{ +\item{Hydrophobicity}\itemize{ +\item ExPASy-Protscale (http://web.expasy.org/protscale/) +\item AAIndex Database (http://www.genome.jp/aaindex/) +} +} +} +\usage{ +data(AA) +} +\description{ +A list with a collection of properties, scales and indices for the 20 naturally occurring amino acids from various sources +} +\references{ +\itemize{ +\item{Hydrophobicity}\itemize{ +Nakai, K., Kidera, A., and Kanehisa, M.; Cluster analysis of amino acid indices for prediction of protein structure and function. Protein Eng. 2, 93-100 (1988). + +Tomii, K. and Kanehisa, M.; Analysis of amino acid indices and mutation matrices for sequence comparison and structure prediction of proteins. Protein Eng. 9, 27-36 (1996). + +Kawashima, S., Ogata, H., and Kanehisa, M.; AAindex: amino acid index database. Nucleic Acids Res. 27, 368-369 (1999). + +Kawashima, S. and Kanehisa, M.; AAindex: amino acid index database. Nucleic Acids Res. 28, 374 (2000). + +Kawashima, S., Pokarowski, P., Pokarowska, M., Kolinski, A., Katayama, T., and Kanehisa, M.; AAindex: amino acid index database, progress report 2008. Nucleic Acids Res. 36, D202-D205 (2008). +} +} +} diff --git a/man/H.Rd b/man/H.Rd deleted file mode 100644 index 745102b..0000000 --- a/man/H.Rd +++ /dev/null @@ -1,108 +0,0 @@ -% Generated by roxygen2: do not edit by hand -% Please edit documentation in R/data-H.R -\docType{data} -\name{H} -\alias{H} -\title{38 Hydrophobicity scales for amino-acids from various sources} -\format{A list with 38 Hydrophobicity scales.} -\source{ -ExPASy-Protscale (http://web.expasy.org/protscale/) - -AAIndex Database (http://www.genome.jp/aaindex/) -} -\usage{ -data(H) -} -\description{ -A list with 38 Hydrophobicity scales for amino acids from various sources -} -\details{ -The hydrophobicity is an important stabilization force in protein folding; this force changes depending on the solvent in which the protein is found. -} -\references{ -Aboderin, A. A. (1971). An empirical hydrophobicity scale for alpha-amino-acids and some of its applications. International Journal of Biochemistry, 2(11), 537-544. - -Abraham D.J., Leo A.J. Hydrophobicity (delta G1/2 cal). Proteins: Structure, Function and Genetics 2:130-152(1987). - -Argos, P., Rao, J. K., & Hargrave, P. A. (1982). Structural Prediction of Membrane-Bound Proteins. European Journal of Biochemistry, 128(2-3), 565-575. - -Black S.D., Mould D.R. Hydrophobicity of physiological L-alpha amino acids. Anal. Biochem. 193:72-82(1991). - -Bull H.B., Breese K. Hydrophobicity (free energy of transfer to surface in kcal/mole). Arch. Biochem. Biophys. 161:665-670(1974). - -Casari, G., & Sippl, M. J. (1992). Structure-derived hydrophobic potential: hydrophobic potential derived from X-ray structures of globular proteins is able to identify native folds. Journal of molecular biology, 224(3), 725-732. - -Chothia, C. (1976). The nature of the accessible and buried surfaces in proteins. Journal of molecular biology, 105(1), 1-12. - -Cid, H., Bunster, M., Canales, M., & Gazitua, F. (1992). Hydrophobicity and structural classes in proteins. Protein engineering, 5(5), 373-375. - -Cowan R., Whittaker R.G. Hydrophobicity indices at pH 3.4 determined by HPLC. Peptide Research 3:75-80(1990). - -Cowan R., Whittaker R.G. Hydrophobicity indices at pH 7.5 determined by HPLC. Peptide Research 3:75-80(1990). - -Eisenberg D., Schwarz E., Komarony M., Wall R. Normalized consensus hydrophobicity scale. J. Mol. Biol. 179:125-142(1984). - -Engelman, D. M., Steitz, T. A., & Goldman, A. (1986). Identifying nonpolar transbilayer helices in amino acid sequences of membrane proteins. Annual review of biophysics and biophysical chemistry, 15(1), 321-353. - -Fasman, G. D. (Ed.). (1989). Prediction of protein structure and the principles of protein conformation. Springer. - -Fauchere J.-L., Pliska V.E. Hydrophobicity scale (pi-r). Eur. J. Med. Chem. 18:369-375(1983). - -Goldsack, D. E., & Chalifoux, R. C. (1973). Contribution of the free energy of mixing of hydrophobic side chains to the stability of the tertiary structure of proteins. Journal of theoretical biology, 39(3), 645-651. - -Guy H.R. Hydrophobicity scale based on free energy of transfer (kcal/mole). Biophys J. 47:61-70(1985). - -Hopp T.P., Woods K.R. Hydrophilicity. Proc. Natl. Acad. Sci. U.S.A. 78:3824-3828(1981). - -Janin J. Free energy of transfer from inside to outside of a globular protein. Nature 277:491-492(1979). - -Jones, D. D. (1975). Amino acid properties and side-chain orientation in proteins: a cross correlation approach. Journal of theoretical biology, 50(1), 167-183. - -Juretic, D., Lucic, B., Zucic, D., & Trinajstic, N. (1998). Protein transmembrane structure: recognition and prediction by using hydrophobicity scales through preference functions. Theoretical and computational chemistry, 5, 405-445. - -Kidera, A., Konishi, Y., Oka, M., Ooi, T., & Scheraga, H. A. (1985). Statistical analysis of the physical properties of the 20 naturally occurring amino acids. Journal of Protein Chemistry, 4(1), 23-55. - -Kuhn, L. A., Swanson, C. A., Pique, M. E., Tainer, J. A., & Getzoff, E. D. (1995). Atomic and residue hydrophilicity in the context of folded protein structures. Proteins: Structure, Function, and Bioinformatics, 23(4), 536-547. - -Kyte J., Doolittle R.F. Hydropathicity. J. Mol. Biol. 157:105-132(1982). - -Levitt, M. (1976). A simplified representation of protein conformations for rapid simulation of protein folding. Journal of molecular biology, 104(1), 59-107. - -Manavalan P., Ponnuswamy Average surrounding hydrophobicity. P.K. Nature 275:673-674(1978). - -Miyazawa S., Jernigen R.L. Hydrophobicity scale (contact energy derived from 3D data). Macromolecules 18:534-552(1985). - -Parker J.M.R., Guo D., Hodges R.S. Hydrophilicity scale derived from HPLC peptide retention times. Biochemistry 25:5425-5431(1986). - -Ponnuswamy, P. K. (1993). Hydrophobic charactesristics of folded proteins. Progress in biophysics and molecular biology, 59(1), 57-103. - -Prabhakaran, M. (1990). The distribution of physical, chemical and conformational properties in signal and nascent peptides. Biochem. J, 269, 691-696. - -Rao M.J.K., Argos P. Membrane buried helix parameter. Biochim. Biophys. Acta 869:197-214(1986). - -Rose G.D., Geselowitz A.R., Lesser G.J., Lee R.H., Zehfus M.H. Mean fractional area loss (f) [average area buried/standard state area]. Science 229:834-838(1985) - -Roseman M.A. Hydrophobicity scale (pi-r). J. Mol. Biol. 200:513-522(1988). - -Sweet R.M., Eisenberg D. Optimized matching hydrophobicity (OMH). J. Mol. Biol. 171:479-488(1983). - -Tanford C. Hydrophobicity scale (Contribution of hydrophobic interactions to the stability of the globular conformation of proteins). J. Am. Chem. Soc. 84:4240-4274(1962). - -Welling G.W., Weijer W.J., Van der Zee R., Welling-Wester S. Antigenicity value X 10. FEBS Lett. 188:215-218(1985). - -Wilson K.J., Honegger A., Stotzel R.P., Hughes G.J. Hydrophobic constants derived from HPLC peptide retention times. Biochem. J. 199:31-41(1981). - -Wolfenden R.V., Andersson L., Cullis P.M., Southgate C.C.F. Hydration potential (kcal/mole) at 25C. Biochemistry 20:849-855(1981). - -Zimmerman, J. M., Eliezer, N., & Simha, R. (1968). The characterization of amino acid sequences in proteins by statistical methods. Journal of theoretical biology, 21(2), 170-201. - -Nakai, K., Kidera, A., and Kanehisa, M.; Cluster analysis of amino acid indices for prediction of protein structure and function. Protein Eng. 2, 93-100 (1988). - -Tomii, K. and Kanehisa, M.; Analysis of amino acid indices and mutation matrices for sequence comparison and structure prediction of proteins. Protein Eng. 9, 27-36 (1996). - -Kawashima, S., Ogata, H., and Kanehisa, M.; AAindex: amino acid index database. Nucleic Acids Res. 27, 368-369 (1999). - -Kawashima, S. and Kanehisa, M.; AAindex: amino acid index database. Nucleic Acids Res. 28, 374 (2000). - -Kawashima, S., Pokarowski, P., Pokarowska, M., Kolinski, A., Katayama, T., and Kanehisa, M.; AAindex: amino acid index database, progress report 2008. Nucleic Acids Res. 36, D202-D205 (2008). -} From b63fde04f1bd4b0c2d5df990253e46c077c38952 Mon Sep 17 00:00:00 2001 From: Daniel Osorio Date: Fri, 3 Mar 2017 07:03:45 -0500 Subject: [PATCH 12/50] Peptides 1.19.2 All datasets were unified into AA --- R/data-AA.R | 13 ++++++++----- R/data-CP.R | 8 -------- man/AA.Rd | 13 ++++++++----- 3 files changed, 16 insertions(+), 18 deletions(-) delete mode 100644 R/data-CP.R diff --git a/R/data-AA.R b/R/data-AA.R index d685b4e..637d32d 100644 --- a/R/data-AA.R +++ b/R/data-AA.R @@ -4,7 +4,7 @@ #' @description A list with a collection of properties, scales and indices for the 20 naturally occurring amino acids from various sources #' @usage data(AA) #' @format A list as follows: \itemize{ -#' \item{Hydrophobicity} \itemize{ +#' \item{Hydrophobicity} The hydrophobicity is an important stabilization force in protein folding; this force changes depending on the solvent in which the protein is found. \itemize{ #' \item{Aboderin:} Aboderin, A. A. (1971). An empirical hydrophobicity scale for alpha-amino-acids and some of its applications. International Journal of Biochemistry, 2(11), 537-544. #' \item{AbrahamLeo:} Abraham D.J., Leo A.J. Hydrophobicity (delta G1/2 cal). Proteins: Structure, Function and Genetics 2:130-152(1987). #' \item{Argos:} Argos, P., Rao, J. K., & Hargrave, P. A. (1982). Structural Prediction of Membrane-Bound Proteins. European Journal of Biochemistry, 128(2-3), 565-575. @@ -44,10 +44,10 @@ #' \item{Wolfenden:} Wolfenden R.V., Andersson L., Cullis P.M., Southgate C.C.F. Hydration potential (kcal/mole) at 25C. Biochemistry 20:849-855(1981). #' \item{Zimmerman:} Zimmerman, J. M., Eliezer, N., & Simha, R. (1968). The characterization of amino acid sequences in proteins by statistical methods. Journal of theoretical biology, 21(2), 170-201. #' } -#' \item{crucianiProperties:} \itemize{ -#' \item{PP1:} -#' \item{PP2:} -#' \item{PP3: } +#' \item{crucianiProperties:} The three Cruciani et. al (2004) properties, are the scaled principal component scores that summarize a broad set of descriptors calculated based on the interaction of each amino acid residue with several chemical groups (or "probes"), such as charged ions, methyl, hydroxyl groups, and so forth. \itemize{ +#' \item{PP1:} Polarity, +#' \item{PP2:} Hydrophobicity, +#' \item{PP3:} H-bonding #' } #' \item{kideraFactors:} \itemize{ #' \item{helix.bend.pref} @@ -100,5 +100,8 @@ #' #' Kawashima, S., Pokarowski, P., Pokarowska, M., Kolinski, A., Katayama, T., and Kanehisa, M.; AAindex: amino acid index database, progress report 2008. Nucleic Acids Res. 36, D202-D205 (2008). #' } +#' \item{crucianiProperties:} \itemize{ +#' Cruciani, G., Baroni, M., Carosati, E., Clementi, M., Valigi, R., and Clementi, S. (2004) Peptide studies by means of principal properties of amino acids derived from MIF descriptors. J. Chemom. 18, 146-155. +#' } #' } NULL diff --git a/R/data-CP.R b/R/data-CP.R deleted file mode 100644 index 7d967e7..0000000 --- a/R/data-CP.R +++ /dev/null @@ -1,8 +0,0 @@ -#' @name CP -#' @docType data -#' @title The 3 properties from Cruciani et. al (2004) -#' @description The three Cruciani et. al (2004) properties, are the scaled principal component scores that summarize a broad set of descriptors calculated based on the interaction of each amino acid residue with several chemical groups (or "probes"), such as charged ions, methyl, hydroxyl groups, and so forth -#' @usage data(CP) -#' @format A list with the three Cruciani et. al (2004) properties. Each PP represent an amino-acid property as follows: \itemize{\item{PP1:} Polarity, \item{PP2:} Hydrophobicity, \item{PP3:} H-bonding} -#' @references Cruciani, G., Baroni, M., Carosati, E., Clementi, M., Valigi, R., and Clementi, S. (2004) Peptide studies by means of principal properties of amino acids derived from MIF descriptors. J. Chemom. 18, 146-155. -NULL \ No newline at end of file diff --git a/man/AA.Rd b/man/AA.Rd index daa7ddc..f7704b8 100644 --- a/man/AA.Rd +++ b/man/AA.Rd @@ -5,7 +5,7 @@ \alias{AA} \title{Properties, scales and indices for the 20 naturally occurring amino acids from various sources} \format{A list as follows: \itemize{ -\item{Hydrophobicity} \itemize{ +\item{Hydrophobicity} The hydrophobicity is an important stabilization force in protein folding; this force changes depending on the solvent in which the protein is found. \itemize{ \item{Aboderin:} Aboderin, A. A. (1971). An empirical hydrophobicity scale for alpha-amino-acids and some of its applications. International Journal of Biochemistry, 2(11), 537-544. \item{AbrahamLeo:} Abraham D.J., Leo A.J. Hydrophobicity (delta G1/2 cal). Proteins: Structure, Function and Genetics 2:130-152(1987). \item{Argos:} Argos, P., Rao, J. K., & Hargrave, P. A. (1982). Structural Prediction of Membrane-Bound Proteins. European Journal of Biochemistry, 128(2-3), 565-575. @@ -45,10 +45,10 @@ \item{Wolfenden:} Wolfenden R.V., Andersson L., Cullis P.M., Southgate C.C.F. Hydration potential (kcal/mole) at 25C. Biochemistry 20:849-855(1981). \item{Zimmerman:} Zimmerman, J. M., Eliezer, N., & Simha, R. (1968). The characterization of amino acid sequences in proteins by statistical methods. Journal of theoretical biology, 21(2), 170-201. } -\item{crucianiProperties:} \itemize{ -\item{PP1:} -\item{PP2:} -\item{PP3: } +\item{crucianiProperties:} The three Cruciani et. al (2004) properties, are the scaled principal component scores that summarize a broad set of descriptors calculated based on the interaction of each amino acid residue with several chemical groups (or "probes"), such as charged ions, methyl, hydroxyl groups, and so forth. \itemize{ +\item{PP1:} Polarity, +\item{PP2:} Hydrophobicity, +\item{PP3:} H-bonding } \item{kideraFactors:} \itemize{ \item{helix.bend.pref} @@ -108,5 +108,8 @@ Kawashima, S. and Kanehisa, M.; AAindex: amino acid index database. Nucleic Acid Kawashima, S., Pokarowski, P., Pokarowska, M., Kolinski, A., Katayama, T., and Kanehisa, M.; AAindex: amino acid index database, progress report 2008. Nucleic Acids Res. 36, D202-D205 (2008). } +\item{crucianiProperties:} \itemize{ +Cruciani, G., Baroni, M., Carosati, E., Clementi, M., Valigi, R., and Clementi, S. (2004) Peptide studies by means of principal properties of amino acids derived from MIF descriptors. J. Chemom. 18, 146-155. +} } } From 3adc2d386f49ccbf24b4c5ced724251c31b198df Mon Sep 17 00:00:00 2001 From: Daniel Osorio Date: Fri, 3 Mar 2017 07:46:36 -0500 Subject: [PATCH 13/50] Peptides 1.19.3 All functions now use AA as source of data --- R/autocorrelation.R | 6 +++--- R/autocovariance.R | 6 +++--- R/charge.R | 23 +++++++++++------------ R/crosscovariance.R | 10 +++++----- R/crucianiProperties.R | 7 +++---- R/hmoment.R | 11 +++-------- R/hydrophobicity.R | 7 +++---- R/instaindex.R | 2 +- R/kideraFactors.R | 7 +++---- R/zScales.R | 7 +++---- man/CP.Rd | 16 ---------------- man/autoCorrelation.Rd | 6 +++--- man/autoCovariance.Rd | 6 +++--- man/crossCovariance.Rd | 10 +++++----- 14 files changed, 49 insertions(+), 75 deletions(-) delete mode 100644 man/CP.Rd diff --git a/R/autocorrelation.R b/R/autocorrelation.R index 1ba69af..3cba713 100644 --- a/R/autocorrelation.R +++ b/R/autocorrelation.R @@ -11,13 +11,13 @@ #' @references Cruciani, G., Baroni, M., Carosati, E., Clementi, M., Valigi, R., and Clementi, S. (2004) Peptide studies by means of principal properties of amino acids derived from MIF descriptors. J. Chemom. 18, 146-155. #' @examples #' # Loading a property to evaluate its autocorrelation -#' data(H) +#' data(AA) #' #' # Calculate the auto-correlation index for a lag=1 #' autoCorrelation( #' sequence = "SDKEVDEVDAALSDLEITLE", #' lag = 1, -#' property = H$KyteDoolittle, +#' property = AA$Hydrophobicity$KyteDoolittle, #' center = TRUE #' ) #' # [1] -0.3519908 @@ -26,7 +26,7 @@ #' autoCorrelation( #' sequence = "SDKEVDEVDAALSDLEITLE", #' lag = 5, -#' property = H$KyteDoolittle, +#' property = AA$Hydrophobicity$KyteDoolittle, #' center = TRUE #' ) #' # [1] 0.001133553 diff --git a/R/autocovariance.R b/R/autocovariance.R index d1d6a69..7f2736a 100644 --- a/R/autocovariance.R +++ b/R/autocovariance.R @@ -11,13 +11,13 @@ #' @references Cruciani, G., Baroni, M., Carosati, E., Clementi, M., Valigi, R., and Clementi, S. (2004) Peptide studies by means of principal properties of amino acids derived from MIF descriptors. J. Chemom. 18, 146-155. #' @examples #' # Loading a property to evaluate its autocorrelation -#' data(H) +#' data(AA) #' #' # Calculate the auto-covariance index for a lag=1 #' autoCovariance( #' sequence = "SDKEVDEVDAALSDLEITLE", #' lag = 1, -#' property = H$KyteDoolittle, +#' property = AA$Hydrophobicity$KyteDoolittle, #' center = TRUE #' ) #' # [1] -0.4140053 @@ -26,7 +26,7 @@ #' autoCovariance( #' sequence = "SDKEVDEVDAALSDLEITLE", #' lag = 5, -#' property = H$KyteDoolittle, +#' property = AA$Hydrophobicity$KyteDoolittle, #' center = TRUE #' ) #' # [1] 0.001000336 diff --git a/R/charge.R b/R/charge.R index 52924c1..7e13f8d 100755 --- a/R/charge.R +++ b/R/charge.R @@ -78,20 +78,19 @@ charge <- function(seq, pH = 7, pKscale = "Lehninger") { )), levels = LETTERS)) }) # Set pKscale - utils::data(pK, envir = environment()) - pK <- pK - pKs <- pK[[match.arg(pKscale, names(pK))]] + pK <- get(data("AA",envir = environment()))$pK + pK <- pK[[match.arg(pKscale, names(pK))]] charge <- lapply(aa, function(aa) { # Charge - cterm <- (-1 / (1 + 10 ^ (-1 * (pH - pKs["cTer"])))) - nterm <- (1 / (1 + 10 ^ (1 * (pH - pKs["nTer"])))) - carg <- aa["R"] * (1 / (1 + 10 ^ (1 * (pH - pKs["R"])))) - chis <- aa["H"] * (1 / (1 + 10 ^ (1 * (pH - pKs["H"])))) - clys <- aa["K"] * (1 / (1 + 10 ^ (1 * (pH - pKs["K"])))) - casp <- aa["D"] * (-1 / (1 + 10 ^ (-1 * (pH - pKs["D"])))) - cglu <- aa["E"] * (-1 / (1 + 10 ^ (-1 * (pH - pKs["E"])))) - ccys <- aa["C"] * (-1 / (1 + 10 ^ (-1 * (pH - pKs["C"])))) - ctyr <- aa["Y"] * (-1 / (1 + 10 ^ (-1 * (pH - pKs["Y"])))) + cterm <- (-1 / (1 + 10 ^ (-1 * (pH - pK["cTer"])))) + nterm <- (1 / (1 + 10 ^ (1 * (pH - pK["nTer"])))) + carg <- aa["R"] * (1 / (1 + 10 ^ (1 * (pH - pK["R"])))) + chis <- aa["H"] * (1 / (1 + 10 ^ (1 * (pH - pK["H"])))) + clys <- aa["K"] * (1 / (1 + 10 ^ (1 * (pH - pK["K"])))) + casp <- aa["D"] * (-1 / (1 + 10 ^ (-1 * (pH - pK["D"])))) + cglu <- aa["E"] * (-1 / (1 + 10 ^ (-1 * (pH - pK["E"])))) + ccys <- aa["C"] * (-1 / (1 + 10 ^ (-1 * (pH - pK["C"])))) + ctyr <- aa["Y"] * (-1 / (1 + 10 ^ (-1 * (pH - pK["Y"])))) # Compute the charge and return the value rounded to 3 decimals return(as.numeric(carg + clys + chis + nterm + casp + cglu + ctyr + ccys + cterm)) }) diff --git a/R/crosscovariance.R b/R/crosscovariance.R index 33cdc9c..ddf5203 100644 --- a/R/crosscovariance.R +++ b/R/crosscovariance.R @@ -12,14 +12,14 @@ #' @references Cruciani, G., Baroni, M., Carosati, E., Clementi, M., Valigi, R., and Clementi, S. (2004) Peptide studies by means of principal properties of amino acids derived from MIF descriptors. J. Chemom. 18, 146-155. #' @examples #' # Loading a property to evaluate its autocorrelation -#' data(H) +#' data(AA) #' #' # Calculate the cross-covariance index for a lag=1 #' crossCovariance( #' sequence = "SDKEVDEVDAALSDLEITLE", #' lag = 1, -#' property1 = H$KyteDoolittle, -#' property2 = H$Eisenberg, +#' property1 = AA$Hydrophobicity$KyteDoolittle, +#' property2 = AA$Hydrophobicity$Eisenberg, #' center = TRUE #' ) #' # [1] -0.3026609 @@ -28,8 +28,8 @@ #' crossCovariance( #' sequence = "SDKEVDEVDAALSDLEITLE", #' lag = 5, -#' property1 = H$KyteDoolittle, -#' property2 = H$Eisenberg, +#' property1 = AA$Hydrophobicity$KyteDoolittle, +#' property2 = AA$Hydrophobicity$Eisenberg, #' center = TRUE #' ) #' # [1] 0.02598035 diff --git a/R/crucianiProperties.R b/R/crucianiProperties.R index d6de42a..5f18824 100644 --- a/R/crucianiProperties.R +++ b/R/crucianiProperties.R @@ -11,14 +11,13 @@ crucianiProperties <- function(seq) { # Remove spaces and line breaks seq <- gsub("[[:space:]]+", "", as.vector(seq)) # Load Cruciani Properties - utils::data(CP, envir = environment()) - CP <- CP + properties <- get(data("AA",envir = environment()))$crucianiProperties # Split sequence seq <- strsplit(toupper(seq), split = "") # Calculate averages lapply(seq, function(seq) { - sapply(names(CP), function(property) { - (sum(CP[[property]][seq])/length(seq)) + sapply(names(properties), function(property) { + (sum(properties[[property]][seq])/length(seq)) }) }) } diff --git a/R/hmoment.R b/R/hmoment.R index a398211..dead587 100755 --- a/R/hmoment.R +++ b/R/hmoment.R @@ -27,16 +27,11 @@ hmoment <- function(seq, angle = 100, window = 11) { # Loading hydrophobicity scale seq <- gsub("[[:space:]]+", "", as.vector(seq)) - data(H, envir = environment()) - H <- H - h <- H[["Eisenberg"]] + h <- get(data("AA",envir = environment()))$Hydrophobicity$Eisenberg # Splitting the sequence in amino acids - aa <- lapply(seq, function(seq) { - unlist(strsplit(seq, "")) - }) + aa <- strsplit(seq,"") # Setting the sequence length - pep <- - lapply(aa, function(aa) { + pep <- lapply(aa, function(aa) { stats::embed(aa, min(c(length(aa), window))) }) # Applying the hmoment function to each amino acids window diff --git a/R/hydrophobicity.R b/R/hydrophobicity.R index 6c68a50..2803391 100755 --- a/R/hydrophobicity.R +++ b/R/hydrophobicity.R @@ -175,15 +175,14 @@ hydrophobicity <- function(seq, scale = "KyteDoolittle") { seq <- gsub("[[:space:]]+", "", as.vector(seq)) # Loading hydrophobicity scales - utils::data(H, envir = environment()) - H <- H + Hydrophobicity <- get(data("AA",envir = environment()))$Hydrophobicity # Setting the hydrophobicity scale - scale <- match.arg(scale, names(H)) + scale <- match.arg(scale, names(Hydrophobicity)) # Sum the hydrophobicity of each amino acid and divide them between the sequence length # Return the GRAVY value h <- lapply(seq, function(seq) { - (sum(H[[scale]][unlist(strsplit(seq, ""))], na.rm = TRUE) / nchar(seq)) + (sum(Hydrophobicity[[scale]][unlist(strsplit(seq, ""))], na.rm = TRUE) / nchar(seq)) }) return(unlist(h)) } diff --git a/R/instaindex.R b/R/instaindex.R index 1bc48aa..4d276b2 100755 --- a/R/instaindex.R +++ b/R/instaindex.R @@ -416,7 +416,7 @@ instaindex <- function(seq) { LG = 1, LA = 1, LL = 1, - "NA" = 1 + 'NA' = 1 ) # Divide the amino acid sequence in dipeptides seq <- gsub("[[:space:]]+", "", as.vector(seq)) diff --git a/R/kideraFactors.R b/R/kideraFactors.R index 6da79ab..a08b0d6 100644 --- a/R/kideraFactors.R +++ b/R/kideraFactors.R @@ -32,15 +32,14 @@ kideraFactors <- function (seq) { # Remove the break lines from the sequence seq <- gsub("[[:space:]]+", "", as.vector(seq)) # Load the KFactors data - data(K, envir = environment()) - K <- K + factors <- get(data("AA",envir = environment()))$kideraFactors # Compute the selected Kidera factor. seq <- lapply(seq, function(seq) { unlist(strsplit(seq, "")) }) kFactors <- lapply(seq, function(seq) { - sapply(names(K), function(factor) { - (sum(K[[factor]][seq], na.rm = TRUE) / length(seq)) + sapply(names(factors), function(factor) { + (sum(factors[[factor]][seq], na.rm = TRUE) / length(seq)) }) }) return(kFactors) diff --git a/R/zScales.R b/R/zScales.R index 1a287d8..e18ab3b 100644 --- a/R/zScales.R +++ b/R/zScales.R @@ -24,13 +24,12 @@ zScales <- function(seq) { seq <- strsplit(seq, "") # Load the Z-scales - utils::data(Z, envir = environment()) - Z <- Z + scales <- get(data("AA",envir = environment()))$zScales # Computes the Z-scales for given sequences lapply(seq, function(seq) { - sapply(names(Z), function(scale) { - (sum(Z[[scale]][seq], na.rm = TRUE) / length(seq)) + sapply(names(scales), function(scale) { + (sum(scales[[scale]][seq], na.rm = TRUE) / length(seq)) }) }) } \ No newline at end of file diff --git a/man/CP.Rd b/man/CP.Rd deleted file mode 100644 index 2b41ec0..0000000 --- a/man/CP.Rd +++ /dev/null @@ -1,16 +0,0 @@ -% Generated by roxygen2: do not edit by hand -% Please edit documentation in R/data-CP.R -\docType{data} -\name{CP} -\alias{CP} -\title{The 3 properties from Cruciani et. al (2004)} -\format{A list with the three Cruciani et. al (2004) properties. Each PP represent an amino-acid property as follows: \itemize{\item{PP1:} Polarity, \item{PP2:} Hydrophobicity, \item{PP3:} H-bonding}} -\usage{ -data(CP) -} -\description{ -The three Cruciani et. al (2004) properties, are the scaled principal component scores that summarize a broad set of descriptors calculated based on the interaction of each amino acid residue with several chemical groups (or "probes"), such as charged ions, methyl, hydroxyl groups, and so forth -} -\references{ -Cruciani, G., Baroni, M., Carosati, E., Clementi, M., Valigi, R., and Clementi, S. (2004) Peptide studies by means of principal properties of amino acids derived from MIF descriptors. J. Chemom. 18, 146-155. -} diff --git a/man/autoCorrelation.Rd b/man/autoCorrelation.Rd index 6f8f6b5..8f5de62 100644 --- a/man/autoCorrelation.Rd +++ b/man/autoCorrelation.Rd @@ -23,13 +23,13 @@ This function computes the Cruciani et al (2004) auto-correlation index. The \co } \examples{ # Loading a property to evaluate its autocorrelation -data(H) +data(AA) # Calculate the auto-correlation index for a lag=1 autoCorrelation( sequence = "SDKEVDEVDAALSDLEITLE", lag = 1, - property = H$KyteDoolittle, + property = AA$Hydrophobicity$KyteDoolittle, center = TRUE ) # [1] -0.3519908 @@ -38,7 +38,7 @@ autoCorrelation( autoCorrelation( sequence = "SDKEVDEVDAALSDLEITLE", lag = 5, - property = H$KyteDoolittle, + property = AA$Hydrophobicity$KyteDoolittle, center = TRUE ) # [1] 0.001133553 diff --git a/man/autoCovariance.Rd b/man/autoCovariance.Rd index cd28e17..8d62105 100644 --- a/man/autoCovariance.Rd +++ b/man/autoCovariance.Rd @@ -23,13 +23,13 @@ This function computes the Cruciani et al (2004) auto-corvariance index. The \co } \examples{ # Loading a property to evaluate its autocorrelation -data(H) +data(AA) # Calculate the auto-covariance index for a lag=1 autoCovariance( sequence = "SDKEVDEVDAALSDLEITLE", lag = 1, - property = H$KyteDoolittle, + property = AA$Hydrophobicity$KyteDoolittle, center = TRUE ) # [1] -0.4140053 @@ -38,7 +38,7 @@ autoCovariance( autoCovariance( sequence = "SDKEVDEVDAALSDLEITLE", lag = 5, - property = H$KyteDoolittle, + property = AA$Hydrophobicity$KyteDoolittle, center = TRUE ) # [1] 0.001000336 diff --git a/man/crossCovariance.Rd b/man/crossCovariance.Rd index 00f86a9..1388ea9 100644 --- a/man/crossCovariance.Rd +++ b/man/crossCovariance.Rd @@ -25,14 +25,14 @@ This function computes the Cruciani et al (2004) cross-covariance index. The lag } \examples{ # Loading a property to evaluate its autocorrelation -data(H) +data(AA) # Calculate the cross-covariance index for a lag=1 crossCovariance( sequence = "SDKEVDEVDAALSDLEITLE", lag = 1, - property1 = H$KyteDoolittle, - property2 = H$Eisenberg, + property1 = AA$Hydrophobicity$KyteDoolittle, + property2 = AA$Hydrophobicity$Eisenberg, center = TRUE ) # [1] -0.3026609 @@ -41,8 +41,8 @@ crossCovariance( crossCovariance( sequence = "SDKEVDEVDAALSDLEITLE", lag = 5, - property1 = H$KyteDoolittle, - property2 = H$Eisenberg, + property1 = AA$Hydrophobicity$KyteDoolittle, + property2 = AA$Hydrophobicity$Eisenberg, center = TRUE ) # [1] 0.02598035 From 4cf40529961f0606de610f9bbe0871a21dc0ff7c Mon Sep 17 00:00:00 2001 From: Daniel Osorio Date: Fri, 3 Mar 2017 08:58:43 -0500 Subject: [PATCH 14/50] Peptides 1.19.3 AA dated documentation was added --- R/data-AA.R | 81 +++++++++++++++++++++++++++++++---------------------- R/data-K.R | 18 ------------ R/data-Z.R | 13 --------- R/data-pK.R | 34 ---------------------- README.md | 2 +- man/AA.Rd | 81 +++++++++++++++++++++++++++++++---------------------- man/K.Rd | 26 ----------------- man/pK.Rd | 43 ---------------------------- 8 files changed, 97 insertions(+), 201 deletions(-) delete mode 100644 R/data-K.R delete mode 100644 R/data-Z.R delete mode 100644 R/data-pK.R delete mode 100644 man/K.Rd delete mode 100644 man/pK.Rd diff --git a/R/data-AA.R b/R/data-AA.R index 637d32d..37e0aa3 100644 --- a/R/data-AA.R +++ b/R/data-AA.R @@ -1,7 +1,7 @@ #' @name AA #' @docType data #' @title Properties, scales and indices for the 20 naturally occurring amino acids from various sources -#' @description A list with a collection of properties, scales and indices for the 20 naturally occurring amino acids from various sources +#' @description A list with a collection of properties, scales and indices for the 20 naturally occurring amino acids from various sources. #' @usage data(AA) #' @format A list as follows: \itemize{ #' \item{Hydrophobicity} The hydrophobicity is an important stabilization force in protein folding; this force changes depending on the solvent in which the protein is found. \itemize{ @@ -49,35 +49,35 @@ #' \item{PP2:} Hydrophobicity, #' \item{PP3:} H-bonding #' } -#' \item{kideraFactors:} \itemize{ -#' \item{helix.bend.pref} -#' \item{side.chain.size} -#' \item{extended.str.pref} -#' \item{hydrophobicity} -#' \item{double.bend.pref} -#' \item{partial.spec.vol} -#' \item{flat.ext.pref} -#' \item{occurrence.alpha.reg} -#' \item{pK.C} -#' \item{surrounding.hydrop} +#' \item{kideraFactors:} The Kidera Factors were originally derived by applying multivariate analysis to 188 physical properties of the 20 amino acids and using dimension reduction techniques. A 10-dimensional vector of orthogonal factors was then obtained for each amino acid.The first four factors are essentially pure physical properties; the remaining six factors are superpositions of several physical properties, and are labelled for convenience by the name of the most heavily weighted component \itemize{ +#' \item{helix.bend.pref:} Helix/bend preference +#' \item{side.chain.size:} Side-chain size +#' \item{extended.str.pref:} Extended structure preference +#' \item{hydrophobicity:} Hydrophobicity +#' \item{double.bend.pref:} Double-bend preference +#' \item{partial.spec.vol:} Partial specific volume +#' \item{flat.ext.pref:} Flat extended preference +#' \item{occurrence.alpha.reg:} Occurrence in alpha region +#' \item{pK.C:} pK-C +#' \item{surrounding.hydrop:} Surrounding hydrophobicity #' } #' \item{pK}\itemize{ -#' \item{Bjellqvist} -#' \item{Dawson} -#' \item{EMBOSS} -#' \item{Lehninger} -#' \item{Murray} -#' \item{Rodwell} -#' \item{Sillero} -#' \item{Solomon} -#' \item{Stryer} +#' \item{Bjellqvist:} Bjellqvist, B., Hughes, G.J., Pasquali, Ch., Paquet, N., Ravier, F., Sanchez, J.Ch., Frutige,r S., Hochstrasser D. (1993) The focusing positions of polypeptides in immobilized pH gradients can be predicted from their amino acid sequences. Electrophoresis, 14:1023-1031. +#' \item{Dawson:} Dawson, R. M. C.; Elliot, D. C.; Elliot, W. H.; Jones, K. M. Data for biochemical research. Oxford University Press, 1989; p. 592. +#' \item{EMBOSS:} EMBOSS data are from http://emboss.sourceforge.net/apps/release/5.0/emboss/apps/iep.html. +#' \item{Lehninger:} Nelson, D. L.; Cox, M. M. Lehninger Principles of Biochemistry, Fourth Edition; W. H. Freeman, 2004; p. 1100. +#' \item{Murray:} Murray, R.K., Granner, D.K., Rodwell, V.W. (2006) Harper's illustrated Biochemistry. 27th edition. Published by The McGraw-Hill Companies. +#' \item{Rodwell:} Rodwell, J. Heterogeneity of component bands in isoelectric focusing patterns. Analytical Biochemistry, 1982, 119 (2), 440-449. +#' \item{Sillero:} Sillero, A., Maldonado, A. (2006) Isoelectric point determination of proteins and other macromolecules: oscillating method. Comput Biol Med., 36:157-166. +#' \item{Solomon:} Solomon, T.W.G. (1998) Fundamentals of Organic Chemistry, 5th edition. Published by Wiley. +#' \item{Stryer:} Stryer L. (1999) Biochemia. czwarta edycja. Wydawnictwo Naukowe PWN. #' } -#' \item{zScales}\itemize{ -#' \item{Z1} -#' \item{Z2} -#' \item{Z3} -#' \item{Z4} -#' \item{Z5} +#' \item{zScales} The five Sandberg et al. (1998) Z-scales describe each amino acid with numerical values, descriptors, which represent the physicochemical properties of the amino acids including NMR data and thin-layer chromatography (TLC) data.\itemize{ +#' \item{Z1:} Lipophilicity +#' \item{Z2:} Steric properties (Steric bulk/Polarizability) +#' \item{Z3:} Electronic properties (Polarity / Charge) +#' \item{Z4:} Related to electronegativity, heat of formation, electrophilicity and hardness. +#' \item{Z5:} Related to electronegativity, heat of formation, electrophilicity and hardness. #' } #' } #' @source @@ -86,22 +86,37 @@ #' \item ExPASy-Protscale (http://web.expasy.org/protscale/) #' \item AAIndex Database (http://www.genome.jp/aaindex/) #' } +#' \item{pK}\itemize{ +#' \item Kiraga, J. (2008) Analysis and computer simulations of variability of isoelectric point of proteins in the proteomes. PhD thesis, University of Wroclaw, Poland. +#' } #' } #' @references #' \itemize{ #' \item{Hydrophobicity}\itemize{ -#' Nakai, K., Kidera, A., and Kanehisa, M.; Cluster analysis of amino acid indices for prediction of protein structure and function. Protein Eng. 2, 93-100 (1988). +#' \item Nakai, K., Kidera, A., and Kanehisa, M.; Cluster analysis of amino acid indices for prediction of protein structure and function. Protein Eng. 2, 93-100 (1988). #' -#' Tomii, K. and Kanehisa, M.; Analysis of amino acid indices and mutation matrices for sequence comparison and structure prediction of proteins. Protein Eng. 9, 27-36 (1996). +#' \item Tomii, K. and Kanehisa, M.; Analysis of amino acid indices and mutation matrices for sequence comparison and structure prediction of proteins. Protein Eng. 9, 27-36 (1996). #' -#' Kawashima, S., Ogata, H., and Kanehisa, M.; AAindex: amino acid index database. Nucleic Acids Res. 27, 368-369 (1999). +#' \item Kawashima, S., Ogata, H., and Kanehisa, M.; AAindex: amino acid index database. Nucleic Acids Res. 27, 368-369 (1999). #' -#' Kawashima, S. and Kanehisa, M.; AAindex: amino acid index database. Nucleic Acids Res. 28, 374 (2000). +#' \item Kawashima, S. and Kanehisa, M.; AAindex: amino acid index database. Nucleic Acids Res. 28, 374 (2000). #' -#' Kawashima, S., Pokarowski, P., Pokarowska, M., Kolinski, A., Katayama, T., and Kanehisa, M.; AAindex: amino acid index database, progress report 2008. Nucleic Acids Res. 36, D202-D205 (2008). +#' \item Kawashima, S., Pokarowski, P., Pokarowska, M., Kolinski, A., Katayama, T., and Kanehisa, M.; AAindex: amino acid index database, progress report 2008. Nucleic Acids Res. 36, D202-D205 (2008). #' } #' \item{crucianiProperties:} \itemize{ -#' Cruciani, G., Baroni, M., Carosati, E., Clementi, M., Valigi, R., and Clementi, S. (2004) Peptide studies by means of principal properties of amino acids derived from MIF descriptors. J. Chemom. 18, 146-155. +#' \item Cruciani, G., Baroni, M., Carosati, E., Clementi, M., Valigi, R., and Clementi, S. (2004) Peptide studies by means of principal properties of amino acids derived from MIF descriptors. J. Chemom. 18, 146-155. +#' } +#' \item{kideraFactors:} \itemize{ +#' \item Kidera, A., Konishi, Y., Oka, M., Ooi, T., & Scheraga, H. A. (1985). Statistical analysis of the physical properties of the 20 naturally occurring amino acids. Journal of Protein Chemistry, 4(1), 23-55. +#' } +#' \item{pK:} \itemize{ +#' \item Aronson, J. N. The Henderson-Hasselbalch equation revisited. Biochemical Education, 1983, 11 (2), 68. +#' \item Moore, D. S.. Amino acid and peptide net charges: A simple calculational procedure. Biochemical Education, 1986, 13 (1), 10-12. +#' \item Goloborodko, A.A.; Levitsky, L.I.; Ivanov, M.V.; and Gorshkov, M.V. (2013) "Pyteomics - a Python Framework for Exploratory Data Analysis and Rapid Software Prototyping in Proteomics", Journal of The American Society for Mass Spectrometry, 24(2), 301-304. +#' \item Kiraga, J. (2008) Analysis and computer simulations of variability of isoelectric point of proteins in the proteomes. PhD thesis, University of Wroclaw, Poland. +#' } +#' \item{zScales} \itemize{ +#' \item Sandberg M, Eriksson L, Jonsson J, Sjostrom M, Wold S: New chemical descriptors relevant for the design of biologically active peptides. A multivariate characterization of 87 amino acids. J Med Chem 1998, 41:2481-2491. #' } #' } NULL diff --git a/R/data-K.R b/R/data-K.R deleted file mode 100644 index 716cc0b..0000000 --- a/R/data-K.R +++ /dev/null @@ -1,18 +0,0 @@ -#' @name K -#' @docType data -#' @title The 10 factors from Kidera et al (1985) -#' @description The Kidera Factors were originally derived by applying multivariate analysis to 188 physical properties of the 20 amino acids and using dimension reduction techniques. A 10-dimensional vector of orthogonal factors was then obtained for each amino acid. -#' @usage data(K) -#' @format A list with the ten Kidera factors of the 20 amino acids. The first four factors are essentially pure physical properties; the remaining six factors are superpositions of several physical properties, and are labelled for convenience by the name of the most heavily weighted component. -#' \itemize{\item{Helix/bend preference}, -#' \item{Side-chain size}, -#' \item{Extended structure preference}, -#' \item{Hydrophobicity}, -#' \item{Double-bend preference}, -#' \item{Partial specific volume}, -#' \item{Flat extended preference}, -#' \item{Occurrence in alpha region}, -#' \item{pK-C}, -#' \item{Surrounding hydrophobicity}} -#' @references Kidera, A., Konishi, Y., Oka, M., Ooi, T., & Scheraga, H. A. (1985). Statistical analysis of the physical properties of the 20 naturally occurring amino acids. Journal of Protein Chemistry, 4(1), 23-55. -NULL \ No newline at end of file diff --git a/R/data-Z.R b/R/data-Z.R deleted file mode 100644 index 17dd191..0000000 --- a/R/data-Z.R +++ /dev/null @@ -1,13 +0,0 @@ -#' @name Z -#' @docType data -#' @title The 5 Z-scales from Sandberg et al. (1998) -#' @description The five Sandberg et al. (1998) Z-scales describe each amino acid with numerical values, descriptors, which represent the physicochemical properties of the amino acids including NMR data and thin-layer chromatography (TLC) data. -#' @usage data(Z) -#' @format A list with the five Sandberg et al. (1998) Z-scales. Each Z-scale represent an amino-acid property as follows: #' \itemize{ -#' \item{Z1:} Lipophilicity -#' \item{Z2:} Steric properties (Steric bulk/Polarizability) -#' \item{Z3:} Electronic properties (Polarity / Charge) -#' \item{Z4 and Z5:} They relate electronegativity, heat of formation, electrophilicity and hardness. -#' } -#' @references Sandberg M, Eriksson L, Jonsson J, Sjostrom M, Wold S: New chemical descriptors relevant for the design of biologically active peptides. A multivariate characterization of 87 amino acids. J Med Chem 1998, 41:2481-2491. -NULL \ No newline at end of file diff --git a/R/data-pK.R b/R/data-pK.R deleted file mode 100644 index 8977ca3..0000000 --- a/R/data-pK.R +++ /dev/null @@ -1,34 +0,0 @@ -#' @name pK -#' @docType data -#' @title 9 pKa scales for the side chain of charged amino acids from various sources -#' @description 9 pKa scales for the side chain of charged amino acids from various sources -#' @usage data(pK) -#' @format A list with the charged amino-acid, cTerm and nTerm for 9 pKa scales -#' @source Table 2 in Kiraga (2008) -#' @references Goloborodko, A.A.; Levitsky, L.I.; Ivanov, M.V.; and Gorshkov, M.V. (2013) "Pyteomics - a Python Framework for Exploratory Data Analysis and Rapid Software Prototyping in Proteomics", Journal of The American Society for Mass Spectrometry, 24(2), 301-304. -#' -#' Kiraga, J. (2008) Analysis and computer simulations of variability of isoelectric point of proteins in the proteomes. PhD thesis, University of Wroclaw, Poland. -#' -#' Bjellqvist, B., Hughes, G.J., Pasquali, Ch., Paquet, N., Ravier, F., Sanchez, J.Ch., Frutige,r S., Hochstrasser D. (1993) The focusing positions of polypeptides in immobilized pH gradients can be predicted from their amino acid sequences. Electrophoresis, 14:1023-1031. -#' -#' EMBOSS data are from http://emboss.sourceforge.net/apps/release/5.0/emboss/apps/iep.html. -#' -#' Murray, R.K., Granner, D.K., Rodwell, V.W. (2006) Harper's illustrated Biochemistry. 27th edition. Published by The McGraw-Hill Companies. -#' -#' Sillero, A., Maldonado, A. (2006) Isoelectric point determination of proteins and other macromolecules: oscillating method. Comput Biol Med., 36:157-166. -#' -#' Solomon, T.W.G. (1998) Fundamentals of Organic Chemistry, 5th edition. Published by Wiley. -#' -#' Stryer L. (1999) Biochemia. czwarta edycja. Wydawnictwo Naukowe PWN. -#' -#' Aronson, J. N. The Henderson-Hasselbalch equation revisited. Biochemical Education, 1983, 11 (2), 68. -#' -#' Moore, D. S.. Amino acid and peptide net charges: A simple calculational procedure. Biochemical Education, 1986, 13 (1), 10-12. -#' -#' Nelson, D. L.; Cox, M. M. Lehninger Principles of Biochemistry, Fourth Edition; W. H. Freeman, 2004; p. 1100. -#' -#' Dawson, R. M. C.; Elliot, D. C.; Elliot, W. H.; Jones, K. M. Data for biochemical research. Oxford University Press, 1989; p. 592. -#' -#' Rodwell, J. Heterogeneity of component bands in isoelectric focusing patterns. Analytical Biochemistry, 1982, 119 (2), 440-449. -#' -NULL \ No newline at end of file diff --git a/README.md b/README.md index d49d7e0..5814166 100755 --- a/README.md +++ b/README.md @@ -46,7 +46,7 @@ Available datasets ------------------- | Code | Description | |:----------- |:------------| -|AA | | +|AA | Properties, scales and indices for the 20 naturally occurring amino acids from various sources | |pepdata | A data frame with 21 physicochemical properties and indices from 100 amino-acid sequences (50 antimicrobial and 50 non antimicrobial) | Citation diff --git a/man/AA.Rd b/man/AA.Rd index f7704b8..a081707 100644 --- a/man/AA.Rd +++ b/man/AA.Rd @@ -50,35 +50,35 @@ \item{PP2:} Hydrophobicity, \item{PP3:} H-bonding } -\item{kideraFactors:} \itemize{ -\item{helix.bend.pref} -\item{side.chain.size} -\item{extended.str.pref} -\item{hydrophobicity} -\item{double.bend.pref} -\item{partial.spec.vol} -\item{flat.ext.pref} -\item{occurrence.alpha.reg} -\item{pK.C} -\item{surrounding.hydrop} +\item{kideraFactors:} The Kidera Factors were originally derived by applying multivariate analysis to 188 physical properties of the 20 amino acids and using dimension reduction techniques. A 10-dimensional vector of orthogonal factors was then obtained for each amino acid.The first four factors are essentially pure physical properties; the remaining six factors are superpositions of several physical properties, and are labelled for convenience by the name of the most heavily weighted component \itemize{ +\item{helix.bend.pref:} Helix/bend preference +\item{side.chain.size:} Side-chain size +\item{extended.str.pref:} Extended structure preference +\item{hydrophobicity:} Hydrophobicity +\item{double.bend.pref:} Double-bend preference +\item{partial.spec.vol:} Partial specific volume +\item{flat.ext.pref:} Flat extended preference +\item{occurrence.alpha.reg:} Occurrence in alpha region +\item{pK.C:} pK-C +\item{surrounding.hydrop:} Surrounding hydrophobicity } \item{pK}\itemize{ -\item{Bjellqvist} -\item{Dawson} -\item{EMBOSS} -\item{Lehninger} -\item{Murray} -\item{Rodwell} -\item{Sillero} -\item{Solomon} -\item{Stryer} -} -\item{zScales}\itemize{ -\item{Z1} -\item{Z2} -\item{Z3} -\item{Z4} -\item{Z5} +\item{Bjellqvist:} Bjellqvist, B., Hughes, G.J., Pasquali, Ch., Paquet, N., Ravier, F., Sanchez, J.Ch., Frutige,r S., Hochstrasser D. (1993) The focusing positions of polypeptides in immobilized pH gradients can be predicted from their amino acid sequences. Electrophoresis, 14:1023-1031. +\item{Dawson:} Dawson, R. M. C.; Elliot, D. C.; Elliot, W. H.; Jones, K. M. Data for biochemical research. Oxford University Press, 1989; p. 592. +\item{EMBOSS:} EMBOSS data are from http://emboss.sourceforge.net/apps/release/5.0/emboss/apps/iep.html. +\item{Lehninger:} Nelson, D. L.; Cox, M. M. Lehninger Principles of Biochemistry, Fourth Edition; W. H. Freeman, 2004; p. 1100. +\item{Murray:} Murray, R.K., Granner, D.K., Rodwell, V.W. (2006) Harper's illustrated Biochemistry. 27th edition. Published by The McGraw-Hill Companies. +\item{Rodwell:} Rodwell, J. Heterogeneity of component bands in isoelectric focusing patterns. Analytical Biochemistry, 1982, 119 (2), 440-449. +\item{Sillero:} Sillero, A., Maldonado, A. (2006) Isoelectric point determination of proteins and other macromolecules: oscillating method. Comput Biol Med., 36:157-166. +\item{Solomon:} Solomon, T.W.G. (1998) Fundamentals of Organic Chemistry, 5th edition. Published by Wiley. +\item{Stryer:} Stryer L. (1999) Biochemia. czwarta edycja. Wydawnictwo Naukowe PWN. +} +\item{zScales} The five Sandberg et al. (1998) Z-scales describe each amino acid with numerical values, descriptors, which represent the physicochemical properties of the amino acids including NMR data and thin-layer chromatography (TLC) data.\itemize{ +\item{Z1:} Lipophilicity +\item{Z2:} Steric properties (Steric bulk/Polarizability) +\item{Z3:} Electronic properties (Polarity / Charge) +\item{Z4:} Related to electronegativity, heat of formation, electrophilicity and hardness. +\item{Z5:} Related to electronegativity, heat of formation, electrophilicity and hardness. } }} \source{ @@ -87,6 +87,9 @@ \item ExPASy-Protscale (http://web.expasy.org/protscale/) \item AAIndex Database (http://www.genome.jp/aaindex/) } +\item{pK}\itemize{ +\item Kiraga, J. (2008) Analysis and computer simulations of variability of isoelectric point of proteins in the proteomes. PhD thesis, University of Wroclaw, Poland. +} } } \usage{ @@ -98,18 +101,30 @@ A list with a collection of properties, scales and indices for the 20 naturally \references{ \itemize{ \item{Hydrophobicity}\itemize{ -Nakai, K., Kidera, A., and Kanehisa, M.; Cluster analysis of amino acid indices for prediction of protein structure and function. Protein Eng. 2, 93-100 (1988). +\item Nakai, K., Kidera, A., and Kanehisa, M.; Cluster analysis of amino acid indices for prediction of protein structure and function. Protein Eng. 2, 93-100 (1988). -Tomii, K. and Kanehisa, M.; Analysis of amino acid indices and mutation matrices for sequence comparison and structure prediction of proteins. Protein Eng. 9, 27-36 (1996). +\item Tomii, K. and Kanehisa, M.; Analysis of amino acid indices and mutation matrices for sequence comparison and structure prediction of proteins. Protein Eng. 9, 27-36 (1996). -Kawashima, S., Ogata, H., and Kanehisa, M.; AAindex: amino acid index database. Nucleic Acids Res. 27, 368-369 (1999). +\item Kawashima, S., Ogata, H., and Kanehisa, M.; AAindex: amino acid index database. Nucleic Acids Res. 27, 368-369 (1999). -Kawashima, S. and Kanehisa, M.; AAindex: amino acid index database. Nucleic Acids Res. 28, 374 (2000). +\item Kawashima, S. and Kanehisa, M.; AAindex: amino acid index database. Nucleic Acids Res. 28, 374 (2000). -Kawashima, S., Pokarowski, P., Pokarowska, M., Kolinski, A., Katayama, T., and Kanehisa, M.; AAindex: amino acid index database, progress report 2008. Nucleic Acids Res. 36, D202-D205 (2008). +\item Kawashima, S., Pokarowski, P., Pokarowska, M., Kolinski, A., Katayama, T., and Kanehisa, M.; AAindex: amino acid index database, progress report 2008. Nucleic Acids Res. 36, D202-D205 (2008). } \item{crucianiProperties:} \itemize{ -Cruciani, G., Baroni, M., Carosati, E., Clementi, M., Valigi, R., and Clementi, S. (2004) Peptide studies by means of principal properties of amino acids derived from MIF descriptors. J. Chemom. 18, 146-155. +\item Cruciani, G., Baroni, M., Carosati, E., Clementi, M., Valigi, R., and Clementi, S. (2004) Peptide studies by means of principal properties of amino acids derived from MIF descriptors. J. Chemom. 18, 146-155. +} +\item{kideraFactors:} \itemize{ +\item Kidera, A., Konishi, Y., Oka, M., Ooi, T., & Scheraga, H. A. (1985). Statistical analysis of the physical properties of the 20 naturally occurring amino acids. Journal of Protein Chemistry, 4(1), 23-55. +} +\item{pK:} \itemize{ +\item Aronson, J. N. The Henderson-Hasselbalch equation revisited. Biochemical Education, 1983, 11 (2), 68. +\item Moore, D. S.. Amino acid and peptide net charges: A simple calculational procedure. Biochemical Education, 1986, 13 (1), 10-12. +\item Goloborodko, A.A.; Levitsky, L.I.; Ivanov, M.V.; and Gorshkov, M.V. (2013) "Pyteomics - a Python Framework for Exploratory Data Analysis and Rapid Software Prototyping in Proteomics", Journal of The American Society for Mass Spectrometry, 24(2), 301-304. +\item Kiraga, J. (2008) Analysis and computer simulations of variability of isoelectric point of proteins in the proteomes. PhD thesis, University of Wroclaw, Poland. +} +\item{zScales} \itemize{ +\item Sandberg M, Eriksson L, Jonsson J, Sjostrom M, Wold S: New chemical descriptors relevant for the design of biologically active peptides. A multivariate characterization of 87 amino acids. J Med Chem 1998, 41:2481-2491. } } } diff --git a/man/K.Rd b/man/K.Rd deleted file mode 100644 index 697d426..0000000 --- a/man/K.Rd +++ /dev/null @@ -1,26 +0,0 @@ -% Generated by roxygen2: do not edit by hand -% Please edit documentation in R/data-K.R -\docType{data} -\name{K} -\alias{K} -\title{The 10 factors from Kidera et al (1985)} -\format{A list with the ten Kidera factors of the 20 amino acids. The first four factors are essentially pure physical properties; the remaining six factors are superpositions of several physical properties, and are labelled for convenience by the name of the most heavily weighted component. -\itemize{\item{Helix/bend preference}, -\item{Side-chain size}, -\item{Extended structure preference}, -\item{Hydrophobicity}, -\item{Double-bend preference}, -\item{Partial specific volume}, -\item{Flat extended preference}, -\item{Occurrence in alpha region}, -\item{pK-C}, -\item{Surrounding hydrophobicity}}} -\usage{ -data(K) -} -\description{ -The Kidera Factors were originally derived by applying multivariate analysis to 188 physical properties of the 20 amino acids and using dimension reduction techniques. A 10-dimensional vector of orthogonal factors was then obtained for each amino acid. -} -\references{ -Kidera, A., Konishi, Y., Oka, M., Ooi, T., & Scheraga, H. A. (1985). Statistical analysis of the physical properties of the 20 naturally occurring amino acids. Journal of Protein Chemistry, 4(1), 23-55. -} diff --git a/man/pK.Rd b/man/pK.Rd deleted file mode 100644 index 2b368c9..0000000 --- a/man/pK.Rd +++ /dev/null @@ -1,43 +0,0 @@ -% Generated by roxygen2: do not edit by hand -% Please edit documentation in R/data-pK.R -\docType{data} -\name{pK} -\alias{pK} -\title{9 pKa scales for the side chain of charged amino acids from various sources} -\format{A list with the charged amino-acid, cTerm and nTerm for 9 pKa scales} -\source{ -Table 2 in Kiraga (2008) -} -\usage{ -data(pK) -} -\description{ -9 pKa scales for the side chain of charged amino acids from various sources -} -\references{ -Goloborodko, A.A.; Levitsky, L.I.; Ivanov, M.V.; and Gorshkov, M.V. (2013) "Pyteomics - a Python Framework for Exploratory Data Analysis and Rapid Software Prototyping in Proteomics", Journal of The American Society for Mass Spectrometry, 24(2), 301-304. - -Kiraga, J. (2008) Analysis and computer simulations of variability of isoelectric point of proteins in the proteomes. PhD thesis, University of Wroclaw, Poland. - -Bjellqvist, B., Hughes, G.J., Pasquali, Ch., Paquet, N., Ravier, F., Sanchez, J.Ch., Frutige,r S., Hochstrasser D. (1993) The focusing positions of polypeptides in immobilized pH gradients can be predicted from their amino acid sequences. Electrophoresis, 14:1023-1031. - -EMBOSS data are from http://emboss.sourceforge.net/apps/release/5.0/emboss/apps/iep.html. - -Murray, R.K., Granner, D.K., Rodwell, V.W. (2006) Harper's illustrated Biochemistry. 27th edition. Published by The McGraw-Hill Companies. - -Sillero, A., Maldonado, A. (2006) Isoelectric point determination of proteins and other macromolecules: oscillating method. Comput Biol Med., 36:157-166. - -Solomon, T.W.G. (1998) Fundamentals of Organic Chemistry, 5th edition. Published by Wiley. - -Stryer L. (1999) Biochemia. czwarta edycja. Wydawnictwo Naukowe PWN. - -Aronson, J. N. The Henderson-Hasselbalch equation revisited. Biochemical Education, 1983, 11 (2), 68. - -Moore, D. S.. Amino acid and peptide net charges: A simple calculational procedure. Biochemical Education, 1986, 13 (1), 10-12. - -Nelson, D. L.; Cox, M. M. Lehninger Principles of Biochemistry, Fourth Edition; W. H. Freeman, 2004; p. 1100. - -Dawson, R. M. C.; Elliot, D. C.; Elliot, W. H.; Jones, K. M. Data for biochemical research. Oxford University Press, 1989; p. 592. - -Rodwell, J. Heterogeneity of component bands in isoelectric focusing patterns. Analytical Biochemistry, 1982, 119 (2), 440-449. -} From 73809ecb1242ee5c6f5622acdd178c4e37184b9d Mon Sep 17 00:00:00 2001 From: Daniel Osorio Date: Fri, 3 Mar 2017 09:02:58 -0500 Subject: [PATCH 15/50] Peptides 1.19.4 Minor changes --- man/AA.Rd | 2 +- man/Z.Rd | 21 --------------------- 2 files changed, 1 insertion(+), 22 deletions(-) delete mode 100644 man/Z.Rd diff --git a/man/AA.Rd b/man/AA.Rd index a081707..0d420db 100644 --- a/man/AA.Rd +++ b/man/AA.Rd @@ -96,7 +96,7 @@ data(AA) } \description{ -A list with a collection of properties, scales and indices for the 20 naturally occurring amino acids from various sources +A list with a collection of properties, scales and indices for the 20 naturally occurring amino acids from various sources. } \references{ \itemize{ diff --git a/man/Z.Rd b/man/Z.Rd deleted file mode 100644 index 6b1631e..0000000 --- a/man/Z.Rd +++ /dev/null @@ -1,21 +0,0 @@ -% Generated by roxygen2: do not edit by hand -% Please edit documentation in R/data-Z.R -\docType{data} -\name{Z} -\alias{Z} -\title{The 5 Z-scales from Sandberg et al. (1998)} -\format{A list with the five Sandberg et al. (1998) Z-scales. Each Z-scale represent an amino-acid property as follows: #' \itemize{ -\item{Z1:} Lipophilicity -\item{Z2:} Steric properties (Steric bulk/Polarizability) -\item{Z3:} Electronic properties (Polarity / Charge) -\item{Z4 and Z5:} They relate electronegativity, heat of formation, electrophilicity and hardness. -}} -\usage{ -data(Z) -} -\description{ -The five Sandberg et al. (1998) Z-scales describe each amino acid with numerical values, descriptors, which represent the physicochemical properties of the amino acids including NMR data and thin-layer chromatography (TLC) data. -} -\references{ -Sandberg M, Eriksson L, Jonsson J, Sjostrom M, Wold S: New chemical descriptors relevant for the design of biologically active peptides. A multivariate characterization of 87 amino acids. J Med Chem 1998, 41:2481-2491. -} From ec45a9c45ee0dfcc66aa78d2dc8f40122ded37dd Mon Sep 17 00:00:00 2001 From: Daniel Osorio Date: Fri, 3 Mar 2017 12:27:00 -0500 Subject: [PATCH 16/50] Update 1.19.5 --- R/plotXVG.R | 2 +- R/readXVG.R | 16 +++++++++------- 2 files changed, 10 insertions(+), 8 deletions(-) diff --git a/R/plotXVG.R b/R/plotXVG.R index 8753854..53ebd71 100755 --- a/R/plotXVG.R +++ b/R/plotXVG.R @@ -30,7 +30,7 @@ plotXVG <- function(XVGfile, ...) { original_par <- par(no.readonly = TRUE) # Plot plot maximum 4 facets per row - graphics::par(mfcol = c((ncol(content) - 1) %/% 4 + 1, + graphics::par(mfcol = c((ncol(content) - 1.5) %/% 4 + 1, min((ncol(content) - 1), 4)), oma = c(0, 0, 2.5, 0)) for (i in seq_len(ncol(content) - 1)) { diff --git a/R/readXVG.R b/R/readXVG.R index fb7a7fe..981d0e7 100755 --- a/R/readXVG.R +++ b/R/readXVG.R @@ -29,7 +29,7 @@ readXVG <- function(file) { unquote <- function(x, ...) { gsub("\\\"|^\\s|\\s$", "", x, ...) } # Subsets a list for elments that match a regex and then removes that regex - perlgsub <- function(pattern, replacement, x, ...) { + perlgsub <- function(pattern, x, replacement = "", ...) { gsub(pattern = pattern, replacement = replacement, x = grep(pattern = pattern, x, value = TRUE, perl = TRUE, ... ), @@ -40,22 +40,24 @@ readXVG <- function(file) { content <- readLines(file) # Read colnames and title - variables <- unquote(perlgsub("^@ s[0-9]+ legend ", "", content)) - xvg_labels <- perlgsub("^@ \\s+[a-z]axis\\s+label ", "", content) + header <- grep('^[@#]', content, value = TRUE) + variables <- unquote(perlgsub("^@ s[0-9]+ legend ", header)) + x_axis_label <- unquote(perlgsub("^@ \\s+xaxis\\s+label ", header)) + x_axis_label <- perlgsub("(?!=\\w+)\\W+\\(\\w*\\)$", x_axis_label) + xvg_labels <- perlgsub("^@ \\s+[a-z]axis\\s+label ", header) xvg_labels <- unquote(unlist(strsplit(xvg_labels, ','))) - title <- unquote(perlgsub("^@ \\s+title ", "", content)) + title <- unquote(perlgsub("^@ \\s+title ", header)) # Extracting the data - content <- perlgsub('^\\s+', "", content) + content <- perlgsub('^\\s+', content) content <- as.data.frame( t(sapply( content, (function(x) {unlist(strsplit(x, "\\s+"))}), USE.NAMES = FALSE) - )) + ), stringsAsFactors = FALSE) # Asign colnames - x_axis_label <- perlgsub('(?!=\\w+)\\W+\\(\\w*\\)$', "", xvg_labels) colnames(content) <- c(x_axis_label, variables) # Add units and title as attribute From a87cc08babcec3fc687444ac5c8a8f3c44cfbbcc Mon Sep 17 00:00:00 2001 From: Daniel Osorio Date: Fri, 3 Mar 2017 19:18:37 -0500 Subject: [PATCH 17/50] Peptides 1.20.1 FASGAI vectors were included --- NAMESPACE | 1 + R/fasgaiVectors.R | 26 ++++++++++++++++++++++++++ README.md | 1 + data/AA.RData | Bin 6876 -> 7478 bytes man/fasgaiVectors.Rd | 17 +++++++++++++++++ 5 files changed, 45 insertions(+) create mode 100644 R/fasgaiVectors.R create mode 100644 man/fasgaiVectors.Rd diff --git a/NAMESPACE b/NAMESPACE index bd35ad9..c07934c 100755 --- a/NAMESPACE +++ b/NAMESPACE @@ -8,6 +8,7 @@ export(boman) export(charge) export(crossCovariance) export(crucianiProperties) +export(fasgaiVectors) export(hmoment) export(hydrophobicity) export(instaindex) diff --git a/R/fasgaiVectors.R b/R/fasgaiVectors.R new file mode 100644 index 0000000..1436e48 --- /dev/null +++ b/R/fasgaiVectors.R @@ -0,0 +1,26 @@ +#' @export fasgaiVectors +#' @title Compute the FASGAI vectors of a protein sequence +#' @description The FASGAI vectors (Factor Analysis Scales of Generalized Amino Acid Information) are based in involved hydrophobicity, alpha and turn propensities, bulky properties, composition characteristics, local flexibility, and electronic properties of 335 properties that can be utilized to represent the sequence structural features of peptides or protein motifs. +#' @param seq An amino-acids sequence +#' +#' @return + +#' +#' @examples +fasgaiVectors <- function(seq) { + # Remove spaces and line breaks + seq <- gsub("[[:space:]]+","",as.vector(seq)) + + # Split the sequence by amino-acids + seq <- strsplit(seq, "") + + # Load the FASGAI vectors + vectors <- get(data("AA",envir = environment()))$FASGAI + + # Computes the FASGAI vectors for given sequences + lapply(seq, function(seq) { + sapply(names(vectors), function(scale) { + (sum(vectors[[scale]][seq], na.rm = TRUE) / length(seq)) + }) + }) +} \ No newline at end of file diff --git a/README.md b/README.md index 5814166..87586e4 100755 --- a/README.md +++ b/README.md @@ -30,6 +30,7 @@ Available functions |charge | Compute the theoretical net charge of a protein sequence | |crossCovariance|Compute the cross-covariance index of a protein sequence| |crucianiProperties | Compute the Cruciani properties of a protein sequence | +|fasgaiVectors| Compute the FASGAI vectors of a protein sequence | |hmoment | Compute the hydrophobic moment of a protein sequence | |hydrophobicity | Compute the hydrophobicity index | |instaindex | Compute the instability index of a protein sequence | diff --git a/data/AA.RData b/data/AA.RData index 7c2bd0ec314cb0a9ee39e55f7ad5f91522c74066..c4587fc67c76a0885b81c738084d1a5e7cd60214 100644 GIT binary patch literal 7478 zcmV-69m(P!iwFP!000001MOXRTohNkUV4$HB6dYY>{zhHk{P5~P$>$=7|FCt!$BOtr=CzaNkICfgMO0tLpEH$r)PHwbE1Z{aQ~yP?b~xJO{u12R2JN@y z+hrT#K4V-r7dZqCro;j<^q?gu5NXjOS-JCxI)lyOJ}Ef9I>9m>K(CGm*}X{<3VN$ z0k*#8aUZ56R^9L(?ydT<*=by|`Yon|Sbe@7=9A`eYo>y4hX-G`T5Irry-WkJAmm4Q zT$vXd7^X9YJpO{vzXTq?sqgZBN6)i5d_OQBfm;yV7F%^0t2l9>QxDUL1a-SgA7#~~)^wUTF zIqn+zFPWEnCIR}Y7|)kM&t#JXXc^u&`SHwQvgA_vU&+yA`5E=l!yG0>?hN$7GaTuD zdLEN1os)cXbfovu^L6hRCT}gn`zhoV^B!{%`uhs>DgA!Z*Eb;NB=;n*r2k1j>_j`y z>flJv-+|t^i+SRqMy!Vj@8!jOh}Pk~iN~2srg04ZP{1Dyq?lJyb0%zJYHM@@FzV@ye%Jm@CorW z{!gU~TnTTGb(IM9;3rH4_+>6XFK}=09_p_Tz?(L6_JFe>6F&_5M;9`gW${$MI`Ul#Pp z9_Sh94^|iLQGXZn^QzY2P4Y&^OyXfUhu&b)dHEOp!5?b`eWZtZmh?9{4dEYQ1wDc5 z;OnH9Si{==rgeCeo%op_&omFxIOoc6o)7){7WXB=PEX}=;=q?V;(xF=xpJP@sYKu% zS;YGw@35nYf0BOVO89ea!<+CT`J(xZ&S_q(TTg!i-oyhdYs)Ly|0@03&oPgncb?Um zS9NRiQ*Far_}wIrgdf@G;Dv&}14rRG8Xr_&2miYEJXhyA4*ggcfASA#9p1TQ_W@tn z+YJ1A#7hLZ%z(dxaK`hj3G}lL^u;IGm!H5_40(OR8iMbTKL$tEg0E){@O%|tuXT9C z{!<~yMm$Vq2E711pfZOZHi2A%r_edufWMEmKs#3G7w~EpyqtKpFpg;4kpGtES1T>$ z-(*iio&-A&N3H;Rf$Z`k*oRla=N{s|I({vI7h-;_>(>_i-(=U9WByG;d(bP|hBxsL zrX0A#-V^*8X*iNSj<|vl_aUB5aW>#3^bhGJx=wM80^m;lN&27aQ?-+y2>!eVq(^EW z1$|PdUf>mfq)#l-FLm_^{0HRE74!+s%i69_Qh`%lJ_wwD#|P{1x__4s3UQr7>^6vaPh!f5M7t>r1u;ngM>)YJQ#p*?F{$NPvclK)oQ@D}VG@=H@3f%2k& zj}YI?p*R5g1Aar+1U#e~{zl?6-^v ztyfbXXBU>2S6f`~0l9W|fIWlyj+o~zwmM=@Mxpj`kVYHOcn6MQAK_!#A{exoWmaFiYczdx5Mhx86PFusZYq> z;1Ivz^2l!lxkdgI2RY{u=i=Ze6!0#AKB#k@DS*6w#ytEA{uKBLIQUbxBj@pK|5O1OUK;q$K=QPFjn`D2G-atM1m+FHrHX}cJ zZT~sj3P&BZkNAxW=PdET7I<%CEwy*5ktgEBk7rd|UQSi*c;Z0wn#vCODE7cZ5A&k^ zYR&U3^50nG6RO%mUwpv)m|Z(gq_W0+4S9X9YK&tO=zZ8tT8B6BT{@E9CcXQic77)5 z86loVcBnD@9{S)R<)qii9}D?5K>a1?YvSX`gJF%p=PR{MpVayt4!CIS9H0o2D5Y|o zn>q(5#UbKpo)QIW44jq0iZHr7SSAjfIzka43leG~WU|3Zi6l&d8bcRxm{=*rnUPC~ zB0NMY#;Kl*l%6zpQOp#}og91BI`8Y)8|Nl&(lCiUK%xw$8{Fi<64^8{eXF6nIPA-r zvAZ}TFhruH&oK5-$b!OZzLwtX5iyHe9-;^h^;al@=w}%W6Uzk%42CJ>61rkEEJ7&> zmj==+hf8bFq93C_JR*diG9NxGT;i%w$fV)nG64!t$&8wFdhH0YTs%W8`|`;nq_f1c z#WSfrLocy%szgc1dMV`ch_IRBY4qLoyp-aA5b;#8QfNZYM@${1@1qdx7IR|=Y@10O6};t=%XpyUKHLH$7_jYupl;y6?1ybf6w`hk=*+7puR zpZ|%*^xp_?k|!bPN{c(__s1j2i;Q4eYy%^W!D0i!c(@0AsXyTC;M;0bopxVPMfH!#>;4vlP6*7luB_#2_vjDG(1Zt-BI^{9Am&IGsMg_49%OimIg)3}B!Q(YWT2KqZm|MS@DzdR zk}?vmlQMrokr`P2l<8B9ejv|m4n>5tGjrtsGo${O@un4Hz=y`a;8Df6W`vc&(Dy`M zNZyJ35c$N42A1>-%?}`Y@JLX5BA7JECCbzcXO}H?^yb1ZHh_@h@;2*T}1L=G0T*OsE zF7xW_^Z@?DrO?W2=yB>_;`4MrA~)o*)gHWS{SH%Hv<#8Rq>+vR5_yngs8TYSs>7r~ z634(0u~hCDCY?C*`{&zJ@-C_DS_;k`R_3fl{Th@+k$%ld8b(LsoHWb=zDU%QFsf9t*i*+h;k#y?TU>@I3!ean<#9i zEqK@Z9R|3lJFbUN>M4|*gih`^_eLphqYieCKFQSYTu5|Mv!Ur5sI#v8$vj(Rm9Xk1I}agtDapJw;s2Fz0) zA1)twq)btF#6yOMw>k3^xRmkR8>@7%4e<+HPg6f$Rl*eU&ok-j+bgn|(p7zjUymzb z68QU7BEFu>t?ASm@h5~J!*TReZuoiio0&8%bpk@3nN$rNUflB_jX-kgzuKxLoGUx= z)mW>5k=!pUI;$m+djgz3VO(rg@A5qV6O;4W_rtwsjhRfoo=E^3dZbV#qToRRNL@oFz&g;D)oTB%{>cI)*!uuyN+2{1UB;m z?E5y46GQr^jPEBVOD*-vUzyJ}ol(<6OcJjTxIDFZzu(D4Yr5$xPK9xj&Yv?$8gZY- zVHq3uGVZ+^YNmi6Us{JZFUF&}1HdCqqb|a@2fW;JIcgMbuL;}BX*Mx;Ud0uH&3N(n zaW`$$17H~G74DiwO(~eU*j9Zd-yUmmT>~idGg#II=yeKWzNMrI?bP4o%x4WCXRpCd zDly-sV%zy=z@y}u23W4hPqPm_L%2Rys}q|Q+-2y4BIu_F$N*hO%ZhpZ!u`gNBPN|6 z4+48ifIccvPuCyrYY*PFeup8k7abUPYNtL>x^wW)I`v!_-!rg}M&b}VbL%+OV_&-O? z9DT&{AjLGtFo`5c-EK`Q%9_g?Ys!6nf_FELdY0d6dzS-)+bTI`Xg!ZUDdz*sD;8zx z1U#QR;CV^6n2UG%mVIA1d$sMZp5n=alV|VMNiGjKSp8<4j=a42f^UCK@xGk8XV;XVudoE^}z?U*%HQ?6&;ciwq$%_K`FtJMonyA8h< z`zb7~Xh7$~D;6JK9{D79z<|Am;~m$YvK0+!Q5ku<(e_IsliW91hn!YkIUM9#*1X02 zT|Vn)G;7;-t8xD)7h~7W{ju4+j|0zE?MPhe;k_*F*9ujWB`+@RZYJwe8BsE!e(zV^ zI;H&(chh|IMvs?ORxUb76JpSAna(aW(ug`IomoDMoFl_g-w}pl=ruqZ>7I z{PdBJ%8kdL+feLrCFbt)*8A-%ZDz0PTJMK?KX#wL=bFJU#rss39ltYWP&aB_`ZS#vKme1bv^6T9vdwZL)3_En6n*RyY1TL z;prALR+7?1@1?n3v#;0|*1`I25#IgwRXPlGYd!Ju9P6T05lM`6Ud6T(gH4wD1vL`;dWQ{(i459%A+UvC{Tq{Yg3a!v8Gql=ds+P6h#&G6<*mCmdr;}a zm`U%JX3j7PbkF!WGHc_`uKS-U1=#jHNI z^_F=-_aI4@`>5W{gQrgkod5NAd!rIsKR9S{vT9|s+^I>+QX=QOm^ZB+d$7yOj|W@L z+Scm**bVFx>xmBHs+a-a#&9~1#=p7s#>vG?awtb6n`QE8OX$7Bt}QGgu1>Y#7N1W) z6&NcEeRL;&m3_$%d&4$Fd&S@Av7uAnwTVy6dgWHNdE}6>BzD7{r7gYReq+`3eUI|k zvt{F>m)VzkxR#r#u1>O?dU-^n-ueqqY-{f1V^!X2f7-O1sNn;17DdIIZM9kMwfq-9 z|Cera#pSOymP|4%esfr*G(WTV#Y17^&zc|L9=@Pm;>UBta zan_a>YwDdbe|~G$k&(LDr<^P{y|bLTVy)kf6)T;FM>h9czqI1q>!xlqeoOr|<3d(W zP}B{ZSk}YbHlgp_`l~-p%6lKuv&gs6@X+W(;Z9BE!{QdCcKX^&mUwtm$He>ZUYoC* z<{uTi>G|83LqSo@m~+{~Z#NScj&i$pa(nB1J@3(H`;S{2<&=9Usn6_0!;}EK?{Bwm zY17QI&D70-Uiy~7@m5(6q>Jv%eOofN`w&H!!#+3OF+CsOoPPbN%RRRTp8KR{Z>2hA zxeQV0L}pJ8pR|6WNmtdjVhi*54Px(tN%O?Ly!BpQ>brJA#h9+LUiCazEqxrD*kOC3 z@#*jShDblWc{${`-uyn*Qw)nn6xp+(uLj(i-KXH*<_?XLswY(^Scg2dds#5C-Mpbo zRz==C*LcVAgM&Nj^sx$ERAl#jK>zu=j7_sXkB@x*ocY`>xMl8>dgcwTH23-LzTwI> z_l|uNkhiC$n3+7Y+kj<$KCEj%r+)nod~7q-#eQh`h7D02TU&-)zq_kXVb?LYPE73k zuAOv^(XxwH-u|6D#${Ao?QPz7|HU0go=yA|Cx6&&LyWZg{p7}7n|U~mliu{}WWD5m z+EDTC`CE58{d}je@JjiPxCTaxf6EvXXKK}=vA4}f%Od-zQ~4uTe&}p|J@ekS8G{za zCy($v*k#`8h_y@n+c$h|)@MU{veUu_FJH!o+j*Mk%s&3zpvVIS!@68QnwzS8v&Abh zZ|9Fqy&Z0tS#IuM-TKaM|HgTDFI_ow#2~(2`zx&i+NAVYFk`|whsT|drSw_EU3ht` z>i({uy8CVJfA?8<|3t}JpQp)T167gRjlKF5cb2waJAX;$pzcrZ@3E67+qP-D?cL3f zW&VqIuQYu4bgWT*=P=*iTh8t1XZrJAoAiuc9zTZKHRkJg z{nICIUv>TLyM@JNY2L>YcIMhIy%N^tV#mv7pK>0nh9(9d{py)ln+}1;hFe|JFRR`$ z=JfR6_EvTDIhB)l%vUrz?T+*xYsBk~`&;}L899CLl1+`D^_$RS_x5?0^(HJ#o@1S2 zGc%_!CDQ49Y5mA`yYx%btBW%Im!;>g7R~CtcVY5bcximA-U&uSK^~H<)cdAL?}D zWPHV;ue??`a`!!Um7aEN^{ZLa0kP$C9+rnKzu{Tg;mokbewR)<$y>c{H9z5bW^C(z z^IVs2Z*s7_bC0;S=;IzD}2eXgfoV`yRo4>JPnf;M?S$W0S?Dv(@jHtFg ztzRF#KI)C>fl6k{z23*CI1Muh@@TmzJ}vM?&w0)vvA6dG?9co5;?L`J`pSOtT%%W9 z-pxMXj$TrnLC&nehnE_1m8*LkuRq>*RZIQmA%T?=(~}lKyALR;EDd)qioB3NBWddQ zy{>GDb}U)jHPL3!*u?2uqg?FtB}vTK=9!T$`)@C>%j)vzo15m5t(Uz|ambiFy<^*x z+3tNaz1FOcE$bTn^l%%+ruc0$rs2dySyd^l~{Hu?pcX9?E+3eoIU(NUa1H`(lctLLf05T&+ AdjJ3c literal 6876 zcmV<28YAT&iwFP!000001MOUASQXd0rZ;ISVna|wL`5vvf@KB)v7iDfn8c_X*uvKB z-mn2h?7c;aUC<~IjV89lXzb3|(O}1hsG!nBkgf>G0p|V2139_(p6BK{$+Pd}2W!om znKiTD^{sEcUs>bpKE9{Xcq0uB4J{3AZ7mHg?V75NR?R<64IK@`+ICmhntx4eYPu-x zYf96a(t@>^QuoJd2!G5==ej>8Q)t(q_A=p^sZ6TuD(+Nqqlynz zJgDMHm7!D_MinorjG)R$stlouH&w<^Wh_(t%u%akP4cD$Q=U3*(}I+s%W6r+Kxj?fSDq3(7Irb6gP0AH(GZSa1%v<_fV z$PWp)GEeJZ2xAHb{6(RE20VVQy~^he-Op+YwNi;wFkMYnTV+Pi${zOlDFA zCBwX_>vlf#2IKOYl$*NY4f)Q5T)lyOQoEp5jF`75)1Vh}Am6x;dnd>z_W^Q^`N3sC zKfM?3<1S+&$KcXFan8TvTorFGk zjFPUW`?09fG08VaB|VSsZ+N}9c&i!Sk07sD_n33g-xr}z>GzYqz6v=fxhHug{ZIN~ z2l{#307tq%33}rO)`>fHVm(xRt{~<^)ei5C0?u3t&13L~0-ggC#P}5ndP?o^CY;|3cyR^5pY$~GwtVox zhs4u_KVA#C65b%|yaw9APnZhu%Uoey;9lW5G+yt3H$AshkbAYm`vLUmdjUW0E%>u0 z=5;pKxjaGcIPf{bn|lTQQ3ZVfyt((l5%YqnfF7aodnM=-j`RrRpLv9FQ(HbL$Q`c( zJ&+AKe*+weKjeZxWC`QJJcGQ8>m~S20q)26F_2@X7#64g%J*8n}-~eG0(Qed?-M>0rU!tbzTqGwG;Z|8wvgKCcu^W5Y|_b2Z9F?FX45B z{?rcd>tz2y&q7Z#rGoz8TYyJ^KeJl(oh)22^iNY^e(+6%`&lzVet8o?PWdLl8@yW7 z=a^5t5#~_={0qkP1ogt3fuDqarzm&C8=!|d@HblL2n~iOeggedf%~xzFc=S}64zxx zkL-q?f&O5%&>xL=v9PYH9o{5wRAv$n!!h&*^Fok+jX(Hf^`VcnvCfkICZ{3%Bdn+= za2|Y}^b)IAf85j#Z?Y3V3iFxPL7L}W8IJRzUti<8`>@l~1e`eVWsdkC>`ks*;B~wP zct;lTKFB-lDB_=_-?$RtSl#d@yhy%iJ)>h<7aO+IpNKc{z{>jaO7=gmQ~y5Z9`w%R z2J5O;eSWHLc#FTA7#Hwr7QCEzwm6Sy-jM&6)>m^i z<=+}ZO5pnpASL^f+>mVdjunzF6bn_SP>k7Q>!Al%* zy(7le{;ZJyU>_;)m5vg@f71p1b;k3%O;byL!Zrh5=D^1Uc_hX-wn1qMK4${n*BCsG zl84&u6Zl+Pj33$e?F5Cv+M3lZoMJ!b!aB+}#<4a0D9r`?m9D z^=c{L?8XZ6+7{<~K(1ZwVb7qw6V|!TknfI=ee~Bs zJ^2a66~sIQ`2CnOkT>}0#P-|3tq}Gj@$h%V&ygo|yn%efo}oMkF@FegGm&?b|FKj} z?RknvQk)U?9>q18Jm5sfR3dI5+Dnv&M*4~Tt#nN1={aNvk)1==AwErUe6_`|_m;z~k4tY(AxQKFvugzOCt z@f$9W{6>&lU}!_VPQfuDeb|3%EdfRHf zHAO#V=sykP30yhEFNr5o{Fy_kZg`9F7RnDK9!_>nOPs$(_6O+=w3C0SG5BID@}t-H zpR?8|HPJufH$0A6;)7OrZgVxYcdC&m;w;Q(zP%u)dn-o#CNGAy-j-eUH$w_(lcT_ zjqFeZ_&s#ML&{07lRp;nt&8^a(AUJrkq5)-gU?s0n?9-cJM3}Nz%@V_Bvr{2I5u(( zP)R~0)4ilhwCK93f|cQPdazs)IBlddQXV9>M9SrZRZ?lV6fJsgl5mMih9iBq5M@M& zOoBsgHyPb&;HI1@Q8+vGs(0MisW*-dJ!IihMSxTlOc!`4f~E555_(s?A(HS(j=cu8l}9MfY*N)(bA68WcB9x0n8iI&Wy z{`9;hs%cUcA?vMFC?dmWN~Y6$H}Y0V0zxFyBr35BZC?oul#Z`b90UE@`X_93$IO&U z={5AnN)%I+DjEiTf2mw9QxM2{{xW&El5RBgSIVbI6+u$5;S1UH=~7i~*TN*O-3h5J zE>@Jh1*Zb@x_**6kyIuhWJ^q5#iS(?jPqhrD;6UT{fT6bNEao;6Pcq;Y4_?IA%Dtb z7U!@ytN%K3K*lQtOXY+B+F^y8r9L^46+K_rbxEN$XA+2FVVSr*5Elr;JilkcDW ziN^Hb2yc=nG3ZL0JLvZ(BFT%4VA^a0BaOjk1JQW634Cch;OyjxTvO5q##OwZ#+At6 z`9INF^tZsf-tW*RW#{eP<5RWgr>gTmDI+6sa$pCDxbuiC27oJCas(zt*0FPgcG!p+ z3)rzkJBY=MD=}jklcAv{h)G8lCRw2B!z_R|c^cp`CE*n_hiNAz2|Z1g>iQXzlu4q2 zKXDPEon&t@9+aU84=P30DI!74kt|TP!<#(F@Dy_-&y-05OIgf7Er;A<2cGCD0@EdB zB%UW_{*WRwu>2|0rx@cvp4l9V2&rf0$p2?X{fF_U9b>?U=D+As#k^+3ox#xeL|#bV ziTn`x#Eu4*^b4&IAfaN0Hu~X;g!MwyM`=`3GrTFXLSJ$K*`UZ6s}1>wXPd}2kw^wR zNQgA@8k7Nrc|tqhX}*vr4`h)6?nHJtMAqnfwZj|ajUjoaox8w^@S+`$4DFb~&PJ|^ z$T;{68DFHQiGNV!fXM$xtf!>!iQJR1B!0m|&G062O*=$sXA<#0`f>y5l}EJ04ER$9 zCGF&(ovoCiK=XhymMPP$s6k0aDt0E5v8rx(i}RUw{L^|zMl0>8fxh4#0G|(#XPg%! zx1=vfUMVt9JKMpl#hve1AH{KikxQA}>V`Mr!iei8wjK&g{N9vUKXQc20}rxQBD zi9l`=UUQW)QV}Fm1Um_@qw&eUHiWzxvbGv^f2=uWG$NwZ92r{3kYgQC(y=k@G(?;l z;A!}~F?avnm=FEk!1^{EE1kfxq9;{HQCt5sRSem-FjdUx)lpK?V26gUj`N1N51YLI zidV-+-NaX?edm;)*a5HDsllsLysw>b{Fk7PlvObW7OyCxjucl1q_o<#$JSt^n6#H* zOYC3p>d4N;E~DSQddCJOy*fn!5&iosU)>aLs{iiQJ3yf5>w;}H@b{m8by35hq&*ic zA>(#<#fBQ@Z!k^&ry8c=H2oXAI%$~3coiy1!~Bt6|0`epUp~rc@KmW>9yUW3PO&dN zcgf68(JeiXk%LE%p@rYjOB$l6S@Oj0^+wjLgA!VT^?j8=Gi$n|!!a_sT&hxvhf29} z`lp`9M5tzou+mpU1zHTVi#0}Kv;pRu8Da}$?o|R-19C4@q5%>Q%#d);C{V%;-xwPv@nK6|=T9_4{uVI=BvflrVu0|w8FEJuO(wT>8qULP=FMRy z6giV-_kYiJ! zokPO3=stp*negXe)^YEUaHEZJBQqQyE@F^aMs5$TkYZ+-M{qCE2c^^vZ;Jhi8!LbV zj}O_3Zc}`Kj5mOphOi2)P~rz|$(;|}MY*O#8JLq?8QgRTm$8lD#)F%RV)W{UHzh8M zAMS*kS=6iaVOqE?xZ99-iUl99FXy7ZC-)nLw~*M%YG58wZUnhq@!=5;3Dw+23Y)15 z-t~TmE>3EF(L=2D6l>06t(REq{a^HAI`m&z*-Zjfk%2OaLgrm_PFiDFi)lb6)9Uhm zhDZV9s=2R*7iey%srU5_ z-qk$jalZ97#~%l`S8>d+MxK3A&jgrMEX>jjcrvH|lag-n=aTxCeO(y6s_o96k|~2z zqW5T~ln3mue)WZ>qP+F|FMmq)xsbN__UseP&~0n^S7|HO?)|O1%edsHgRfYKM+E}g{sQn25ZeEShy1p1W|La?hv;-vxb6 z^>5RD-0G^SS2Az8?%2P2vYE5_ss$%JMqEz#5T0Jtzstepiw-V}dYIe4{~o;wPHT?0 z)fj438FixBw(}Z>xv#PgIIp;PFvz{EwbiYizUyYRYTtgVfy={l32WzUX*Ku#fKyf5 zlb3kG@r)e%`Hf`Zs&8nT*}w*@n5_>t<^^E7Q-bRN(Qfq_Yh@9v;}Pl8Z(pVT z01ul<7iL=&t&F_S$mUkW9vy7B#4pg*Ev_Z^)F|8Y;fneDBj3j7Y88xFsFUqu_4(m* zY27^rEZv(H>h$dXfpKG&vnTF6`sT~+H$HZmlj!ooAkyXiXq9r~iX^MNjW=iH*t*F! zPf~t+IC=Btw);{J_(V)~>E?QQzG>XOh^x*ihmZPq$b28%#jStB>VOqnt#?*A+GpP` zK3TagL)rH3iROpm%$}b8GVQr+n0w)bQTAK4dge?Y`s-sKw?2#F)1A&9@S7LBtk9!z zb1kdEk;RM89&kJOW0wni0^!ZyeGS0?)UKF{61%_Do( zQQvOQV~_fr8d^N($ob{7b1HW3i`bhuv6120uOD4Le0NnurBC?K_^6;gX9KPL8eg5F z8El-CZt!&{pQVX=BEQL7n78(F^uW?P@sr;y$(&&rI3(l!sH_b;Qu@W+88slxS6ly) z!?UMxQ`bj+$iMX=_tr|ySvx0Y#jiTD^}0zx_aJH3kkP$c2Zv1!oHyvJJu!D}Ztpie zR<)v4?zH<$Q={g&nY64Pzu$4i`~B9lVy)kfU(Y_Ym}D=hitqnrJg0eY!mI1AoZY;o z2XZvzvkX6M4!wEM-O4ob(lkqM(U}*=0~6$-_mUD<+Le5>CwzUJcjDC^>pS;dll;)Q zS8i3id-fTN6V@j!Y2)+ybMvlmdz2@fDw`0u)UMRiz1*0;G}&z0g^|sA>nu1L+uGUJ zyxjVS^yxVL9N&Il1TRmm!^|zIT3F=Rw}`NqygRkge8Vdd}R(zq98T85Ng$oAmwR-1b9{CwZ4J6<`Qo2GiT**iIJ$Cj2p_E(L~Hn~*WB<=EVo_FK?#RG?Q6B~8B zXdTclwa5G!6HnVe=yD{r&qD6(v+Gs2c7EI4Z`xJMP zbzC!Vapu784{zqPQJ%;@{Wwr7@M9X`*pQsoq>z#&rwlf zdlqkO{E_=l$l7`dXDe>h8N(%gSrfksZI?mbhy|=ZuKwax19-fzIrUN;=pI#%bmDeo;yoVI9dN>+_HZ{`RqI8;mfXi zRXUs;zR2(VF=vJKOY3=epJXQ3^qcFxY+H-{<(&>)I=`uS@My{M(fg<8UD}_0_*(Qn zNkaaHre$`A66NI;aK5EAYNoz@|N zl~SW)ra`-YR92bk?N}IfHh;$bXckiBS#CRBpN`25nLGEGt4p$0!d} Date: Mon, 6 Mar 2017 08:40:41 -0500 Subject: [PATCH 18/50] Peptides 1.20.2 FASGAI vectors were added in AA fasgaiVectors function was fully documented --- R/data-AA.R | 11 +++++++++++ R/fasgaiVectors.R | 12 +++++++----- man/AA.Rd | 11 +++++++++++ man/fasgaiVectors.Rd | 13 +++++++++++-- 4 files changed, 40 insertions(+), 7 deletions(-) diff --git a/R/data-AA.R b/R/data-AA.R index 37e0aa3..802d5df 100644 --- a/R/data-AA.R +++ b/R/data-AA.R @@ -79,6 +79,14 @@ #' \item{Z4:} Related to electronegativity, heat of formation, electrophilicity and hardness. #' \item{Z5:} Related to electronegativity, heat of formation, electrophilicity and hardness. #' } +#' \item{FASGAI} Factor Analysis Scale of Generalized Amino Acid Information (FASGAI) proposed by Liang and Li (2007), is a set of amino acid descriptors, that reflects hydrophobicity, alpha and turn propensities, bulky properties, compositional characteristics, local flexibility, and electronic properties, was derived from multi-dimensional properties of 20 naturally occurring amino acids. \itemize{ +#' \item{F1:} Hydrophobicity index +#' \item{F2:} Alpha and turn propensities +#' \item{F3:} Bulky properties +#' \item{F4:} Compositional characteristic index +#' \item{F5:} Local flexibility +#' \item{F6:} Electronic properties +#' } #' } #' @source #' \itemize{ @@ -118,5 +126,8 @@ #' \item{zScales} \itemize{ #' \item Sandberg M, Eriksson L, Jonsson J, Sjostrom M, Wold S: New chemical descriptors relevant for the design of biologically active peptides. A multivariate characterization of 87 amino acids. J Med Chem 1998, 41:2481-2491. #' } +#' \item{FASGAI} \itemize{ +#' \item Liang, G., & Li, Z. (2007). Factor analysis scale of generalized amino acid information as the source of a new set of descriptors for elucidating the structure and activity relationships of cationic antimicrobial peptides. Molecular Informatics, 26(6), 754-763. +#' } #' } NULL diff --git a/R/fasgaiVectors.R b/R/fasgaiVectors.R index 1436e48..0513f4d 100644 --- a/R/fasgaiVectors.R +++ b/R/fasgaiVectors.R @@ -1,12 +1,14 @@ #' @export fasgaiVectors #' @title Compute the FASGAI vectors of a protein sequence -#' @description The FASGAI vectors (Factor Analysis Scales of Generalized Amino Acid Information) are based in involved hydrophobicity, alpha and turn propensities, bulky properties, composition characteristics, local flexibility, and electronic properties of 335 properties that can be utilized to represent the sequence structural features of peptides or protein motifs. +#' @description The FASGAI vectors (Factor Analysis Scales of Generalized Amino Acid Information) is a set of amino acid descriptors, that reflects hydrophobicity, alpha and turn propensities, bulky properties, compositional characteristics, local flexibility, and electronic properties, that can be utilized to represent the sequence structural features of peptides or protein motifs. #' @param seq An amino-acids sequence -#' -#' @return - -#' +#' @return The computed average of FASGAI factors of all the amino acids in the corresponding peptide sequence. Each factor represent an amino-acid property as follows: \itemize{ \item{F1:} Hydrophobicity index, \item{F2:} Alpha and turn propensities, \item{F3:} Bulky properties, \item{F4:} Compositional characteristic index, \item{F5:} Local flexibility, \item{F6:} Electronic properties} +#' @references Liang, G., & Li, Z. (2007). Factor analysis scale of generalized amino acid information as the source of a new set of descriptors for elucidating the structure and activity relationships of cationic antimicrobial peptides. Molecular Informatics, 26(6), 754-763. #' @examples +#' fasgaiVectors(seq = "QWGRRCCGWGPGRRYCVRWC") +#' [[1]] +#' F1 F2 F3 F4 F5 F6 +#' -0.13675 -0.45485 -0.11695 -0.45800 -0.38015 0.52740 fasgaiVectors <- function(seq) { # Remove spaces and line breaks seq <- gsub("[[:space:]]+","",as.vector(seq)) diff --git a/man/AA.Rd b/man/AA.Rd index 0d420db..c05d90e 100644 --- a/man/AA.Rd +++ b/man/AA.Rd @@ -80,6 +80,14 @@ \item{Z4:} Related to electronegativity, heat of formation, electrophilicity and hardness. \item{Z5:} Related to electronegativity, heat of formation, electrophilicity and hardness. } +\item{FASGAI} Factor Analysis Scale of Generalized Amino Acid Information (FASGAI) proposed by Liang and Li (2007), is a set of amino acid descriptors, that reflects hydrophobicity, alpha and turn propensities, bulky properties, compositional characteristics, local flexibility, and electronic properties, was derived from multi-dimensional properties of 20 naturally occurring amino acids. \itemize{ +\item{F1:} Hydrophobicity index +\item{F2:} Alpha and turn propensities +\item{F3:} Bulky properties +\item{F4:} Compositional characteristic index +\item{F5:} Local flexibility +\item{F6:} Electronic properties +} }} \source{ \itemize{ @@ -126,5 +134,8 @@ A list with a collection of properties, scales and indices for the 20 naturally \item{zScales} \itemize{ \item Sandberg M, Eriksson L, Jonsson J, Sjostrom M, Wold S: New chemical descriptors relevant for the design of biologically active peptides. A multivariate characterization of 87 amino acids. J Med Chem 1998, 41:2481-2491. } +\item{FASGAI} \itemize{ +\item Liang, G., & Li, Z. (2007). Factor analysis scale of generalized amino acid information as the source of a new set of descriptors for elucidating the structure and activity relationships of cationic antimicrobial peptides. Molecular Informatics, 26(6), 754-763. +} } } diff --git a/man/fasgaiVectors.Rd b/man/fasgaiVectors.Rd index a4cae84..e98e1a4 100644 --- a/man/fasgaiVectors.Rd +++ b/man/fasgaiVectors.Rd @@ -10,8 +10,17 @@ fasgaiVectors(seq) \item{seq}{An amino-acids sequence} } \value{ - +The computed average of FASGAI factors of all the amino acids in the corresponding peptide sequence. Each factor represent an amino-acid property as follows: \itemize{ \item{F1:} Hydrophobicity index, \item{F2:} Alpha and turn propensities, \item{F3:} Bulky properties, \item{F4:} Compositional characteristic index, \item{F5:} Local flexibility, \item{F6:} Electronic properties} } \description{ -The FASGAI vectors (Factor Analysis Scales of Generalized Amino Acid Information) are based in involved hydrophobicity, alpha and turn propensities, bulky properties, composition characteristics, local flexibility, and electronic properties of 335 properties that can be utilized to represent the sequence structural features of peptides or protein motifs. +The FASGAI vectors (Factor Analysis Scales of Generalized Amino Acid Information) is a set of amino acid descriptors, that reflects hydrophobicity, alpha and turn propensities, bulky properties, compositional characteristics, local flexibility, and electronic properties, that can be utilized to represent the sequence structural features of peptides or protein motifs. +} +\examples{ +fasgaiVectors(seq = "QWGRRCCGWGPGRRYCVRWC") +[[1]] + F1 F2 F3 F4 F5 F6 +-0.13675 -0.45485 -0.11695 -0.45800 -0.38015 0.52740 +} +\references{ +Liang, G., & Li, Z. (2007). Factor analysis scale of generalized amino acid information as the source of a new set of descriptors for elucidating the structure and activity relationships of cationic antimicrobial peptides. Molecular Informatics, 26(6), 754-763. } From cda86e02438e726fac8b0f703746d7c0767edfab Mon Sep 17 00:00:00 2001 From: Daniel Osorio Date: Mon, 6 Mar 2017 14:31:58 -0500 Subject: [PATCH 19/50] Peptides 1.20.3 Minor changes in fasgaiVectors function documentation --- R/fasgaiVectors.R | 6 +++--- man/fasgaiVectors.Rd | 6 +++--- 2 files changed, 6 insertions(+), 6 deletions(-) diff --git a/R/fasgaiVectors.R b/R/fasgaiVectors.R index 0513f4d..bb33335 100644 --- a/R/fasgaiVectors.R +++ b/R/fasgaiVectors.R @@ -6,9 +6,9 @@ #' @references Liang, G., & Li, Z. (2007). Factor analysis scale of generalized amino acid information as the source of a new set of descriptors for elucidating the structure and activity relationships of cationic antimicrobial peptides. Molecular Informatics, 26(6), 754-763. #' @examples #' fasgaiVectors(seq = "QWGRRCCGWGPGRRYCVRWC") -#' [[1]] -#' F1 F2 F3 F4 F5 F6 -#' -0.13675 -0.45485 -0.11695 -0.45800 -0.38015 0.52740 +#' # [[1]] +#' # F1 F2 F3 F4 F5 F6 +#' # -0.13675 -0.45485 -0.11695 -0.45800 -0.38015 0.52740 fasgaiVectors <- function(seq) { # Remove spaces and line breaks seq <- gsub("[[:space:]]+","",as.vector(seq)) diff --git a/man/fasgaiVectors.Rd b/man/fasgaiVectors.Rd index e98e1a4..3a539e2 100644 --- a/man/fasgaiVectors.Rd +++ b/man/fasgaiVectors.Rd @@ -17,9 +17,9 @@ The FASGAI vectors (Factor Analysis Scales of Generalized Amino Acid Information } \examples{ fasgaiVectors(seq = "QWGRRCCGWGPGRRYCVRWC") -[[1]] - F1 F2 F3 F4 F5 F6 --0.13675 -0.45485 -0.11695 -0.45800 -0.38015 0.52740 +# [[1]] +# F1 F2 F3 F4 F5 F6 +# -0.13675 -0.45485 -0.11695 -0.45800 -0.38015 0.52740 } \references{ Liang, G., & Li, Z. (2007). Factor analysis scale of generalized amino acid information as the source of a new set of descriptors for elucidating the structure and activity relationships of cationic antimicrobial peptides. Molecular Informatics, 26(6), 754-763. From 0562b1670f544bcfd7ff9223583eae47b4e775ed Mon Sep 17 00:00:00 2001 From: Daniel Osorio Date: Mon, 6 Mar 2017 19:00:07 -0500 Subject: [PATCH 20/50] Peptides 1.20.4 All test were changed to testthat --- DESCRIPTION | 12 +++--- NEWS => NEWS.md | 12 ++++++ R/autocorrelation.R | 6 +-- R/autocovariance.R | 6 +-- R/charge.R | 2 +- R/crosscovariance.R | 10 ++--- R/crucianiProperties.R | 2 +- R/data-AA.R | 4 +- R/fasgaiVectors.R | 2 +- R/hmoment.R | 2 +- R/hydrophobicity.R | 2 +- R/kideraFactors.R | 2 +- R/sysdata.rda | Bin 0 -> 7482 bytes R/zScales.R | 2 +- data/AA.RData | Bin 7478 -> 0 bytes data/AAdata.RData | Bin 0 -> 7482 bytes data/datalist | 2 +- inst/tests/runalltest.R | 14 ------- inst/tests/runit.aacomp.R | 23 ----------- inst/tests/runit.aindex.R | 13 ------- inst/tests/runit.boman.R | 13 ------- inst/tests/runit.charge.R | 17 -------- inst/tests/runit.hmoment.R | 16 -------- inst/tests/runit.hydrophobicity.R | 12 ------ inst/tests/runit.instaindex.R | 13 ------- inst/tests/runit.lengthpep.R | 12 ------ inst/tests/runit.mw.R | 11 ------ inst/tests/runit.pI.R | 12 ------ man/{AA.Rd => AAdata.Rd} | 6 +-- man/autoCorrelation.Rd | 6 +-- man/autoCovariance.Rd | 6 +-- man/crossCovariance.Rd | 10 ++--- tests/doRUnit.R | 62 ------------------------------ tests/testthat.R | 4 ++ tests/testthat/test.aacomp.R | 29 ++++++++++++++ tests/testthat/test.aindex.R | 15 ++++++++ tests/testthat/test.boman.R | 14 +++++++ tests/testthat/test.charge.R | 57 +++++++++++++++++++++++++++ 38 files changed, 171 insertions(+), 260 deletions(-) rename NEWS => NEWS.md (99%) create mode 100644 R/sysdata.rda delete mode 100644 data/AA.RData create mode 100644 data/AAdata.RData delete mode 100644 inst/tests/runalltest.R delete mode 100644 inst/tests/runit.aacomp.R delete mode 100644 inst/tests/runit.aindex.R delete mode 100644 inst/tests/runit.boman.R delete mode 100644 inst/tests/runit.charge.R delete mode 100644 inst/tests/runit.hmoment.R delete mode 100644 inst/tests/runit.hydrophobicity.R delete mode 100644 inst/tests/runit.instaindex.R delete mode 100644 inst/tests/runit.lengthpep.R delete mode 100644 inst/tests/runit.mw.R delete mode 100644 inst/tests/runit.pI.R rename man/{AA.Rd => AAdata.Rd} (99%) delete mode 100644 tests/doRUnit.R create mode 100644 tests/testthat.R create mode 100644 tests/testthat/test.aacomp.R create mode 100644 tests/testthat/test.aindex.R create mode 100644 tests/testthat/test.boman.R create mode 100644 tests/testthat/test.charge.R diff --git a/DESCRIPTION b/DESCRIPTION index a68b535..62ec2ba 100644 --- a/DESCRIPTION +++ b/DESCRIPTION @@ -1,14 +1,12 @@ Package: Peptides -Version: 1.2.1 -Date: 2017-02-20 +Version: 1.20.4 +Date: 2017-03-10 Title: Calculate Indices and Theoretical Physicochemical Properties of Protein Sequences -Author: Daniel Osorio, Paola Rondon-Villarreal and Rodrigo Torres. +Authors@R: c(person("Daniel","Osorio",email="dcosorioh@unal.edu.co",role=c("aut","cre")),person("Paola","Rondon-Villarreal",role=c("aut","ths")),person("Rodrigo","Torres",role=c("aut","ths")),person("J. Sebastian","Paez",role=c("ctb"))) Maintainer: Daniel Osorio URL: https://github.com/dosorio/Peptides/ Suggests: - RUnit -Description: Calculate physicochemical properties and indices from amino-acid - sequences of peptides and proteins. Include also the option to read and plot - output files from the 'GROMACS' molecular dynamics package. + testthat +Description: Includes functions to calculate several physicochemical properties and indices for amino-acid sequences as well as to read and plot 'XVG' output files from the 'GROMACS' molecular dynamics package. License: GPL-2 RoxygenNote: 6.0.1 diff --git a/NEWS b/NEWS.md similarity index 99% rename from NEWS rename to NEWS.md index 01b90bd..391992b 100644 --- a/NEWS +++ b/NEWS.md @@ -1,30 +1,42 @@ NEWS ==== **Peptides v.1.2.1** + * Four new functions were added: autoCorrelation, autoCovariance, crossCovariance and crucianiProperties + * Functions related with XVG files were updated. + * Documentation was changed to roxygen2 **Peptides v.1.1.2** + * All functions were re-vectorized to support set of peptides as input + * Kidera function now returns all factors in a unique output **Peptides v.1.1.1** + * The mw function now computes the molecular weight using monoisotopic values + * A problem with blank spaces was solved **Peptides v.1.1.0** + * The kidera function and Kfactors dataset was included. **Peptides v.1.0.4** + * A instaindex function bug has been fixed. + * A problem with line breaks in sequences was solved. **Peptides v.1.0.3** * A membpos function bug has been fixed. + * The results now are not rounded. **Peptides v.1.0.2** + * Hydrophobicity function now can compute the GRAVY index with one of the 38 scales includes in Peptides (*new): 1. **Aboderin:** Aboderin, A. A. (1971). An empirical hydrophobicity scale for α-amino-acids and some of its applications. International Journal of Biochemistry, 2(11), 537-544. diff --git a/R/autocorrelation.R b/R/autocorrelation.R index 3cba713..087cd9d 100644 --- a/R/autocorrelation.R +++ b/R/autocorrelation.R @@ -11,13 +11,13 @@ #' @references Cruciani, G., Baroni, M., Carosati, E., Clementi, M., Valigi, R., and Clementi, S. (2004) Peptide studies by means of principal properties of amino acids derived from MIF descriptors. J. Chemom. 18, 146-155. #' @examples #' # Loading a property to evaluate its autocorrelation -#' data(AA) +#' data(AAdata) #' #' # Calculate the auto-correlation index for a lag=1 #' autoCorrelation( #' sequence = "SDKEVDEVDAALSDLEITLE", #' lag = 1, -#' property = AA$Hydrophobicity$KyteDoolittle, +#' property = AAdata$Hydrophobicity$KyteDoolittle, #' center = TRUE #' ) #' # [1] -0.3519908 @@ -26,7 +26,7 @@ #' autoCorrelation( #' sequence = "SDKEVDEVDAALSDLEITLE", #' lag = 5, -#' property = AA$Hydrophobicity$KyteDoolittle, +#' property = AAdata$Hydrophobicity$KyteDoolittle, #' center = TRUE #' ) #' # [1] 0.001133553 diff --git a/R/autocovariance.R b/R/autocovariance.R index 7f2736a..47a9418 100644 --- a/R/autocovariance.R +++ b/R/autocovariance.R @@ -11,13 +11,13 @@ #' @references Cruciani, G., Baroni, M., Carosati, E., Clementi, M., Valigi, R., and Clementi, S. (2004) Peptide studies by means of principal properties of amino acids derived from MIF descriptors. J. Chemom. 18, 146-155. #' @examples #' # Loading a property to evaluate its autocorrelation -#' data(AA) +#' data(AAdata) #' #' # Calculate the auto-covariance index for a lag=1 #' autoCovariance( #' sequence = "SDKEVDEVDAALSDLEITLE", #' lag = 1, -#' property = AA$Hydrophobicity$KyteDoolittle, +#' property = AAdata$Hydrophobicity$KyteDoolittle, #' center = TRUE #' ) #' # [1] -0.4140053 @@ -26,7 +26,7 @@ #' autoCovariance( #' sequence = "SDKEVDEVDAALSDLEITLE", #' lag = 5, -#' property = AA$Hydrophobicity$KyteDoolittle, +#' property = AAdata$Hydrophobicity$KyteDoolittle, #' center = TRUE #' ) #' # [1] 0.001000336 diff --git a/R/charge.R b/R/charge.R index 7e13f8d..28b2fad 100755 --- a/R/charge.R +++ b/R/charge.R @@ -78,7 +78,7 @@ charge <- function(seq, pH = 7, pKscale = "Lehninger") { )), levels = LETTERS)) }) # Set pKscale - pK <- get(data("AA",envir = environment()))$pK + pK <- AAdata$pK pK <- pK[[match.arg(pKscale, names(pK))]] charge <- lapply(aa, function(aa) { # Charge diff --git a/R/crosscovariance.R b/R/crosscovariance.R index ddf5203..154c226 100644 --- a/R/crosscovariance.R +++ b/R/crosscovariance.R @@ -12,14 +12,14 @@ #' @references Cruciani, G., Baroni, M., Carosati, E., Clementi, M., Valigi, R., and Clementi, S. (2004) Peptide studies by means of principal properties of amino acids derived from MIF descriptors. J. Chemom. 18, 146-155. #' @examples #' # Loading a property to evaluate its autocorrelation -#' data(AA) +#' data(AAdata) #' #' # Calculate the cross-covariance index for a lag=1 #' crossCovariance( #' sequence = "SDKEVDEVDAALSDLEITLE", #' lag = 1, -#' property1 = AA$Hydrophobicity$KyteDoolittle, -#' property2 = AA$Hydrophobicity$Eisenberg, +#' property1 = AAdata$Hydrophobicity$KyteDoolittle, +#' property2 = AAdata$Hydrophobicity$Eisenberg, #' center = TRUE #' ) #' # [1] -0.3026609 @@ -28,8 +28,8 @@ #' crossCovariance( #' sequence = "SDKEVDEVDAALSDLEITLE", #' lag = 5, -#' property1 = AA$Hydrophobicity$KyteDoolittle, -#' property2 = AA$Hydrophobicity$Eisenberg, +#' property1 = AAdata$Hydrophobicity$KyteDoolittle, +#' property2 = AAdata$Hydrophobicity$Eisenberg, #' center = TRUE #' ) #' # [1] 0.02598035 diff --git a/R/crucianiProperties.R b/R/crucianiProperties.R index 5f18824..74dbb74 100644 --- a/R/crucianiProperties.R +++ b/R/crucianiProperties.R @@ -11,7 +11,7 @@ crucianiProperties <- function(seq) { # Remove spaces and line breaks seq <- gsub("[[:space:]]+", "", as.vector(seq)) # Load Cruciani Properties - properties <- get(data("AA",envir = environment()))$crucianiProperties + properties <- AAdata$crucianiProperties # Split sequence seq <- strsplit(toupper(seq), split = "") # Calculate averages diff --git a/R/data-AA.R b/R/data-AA.R index 802d5df..c523ab9 100644 --- a/R/data-AA.R +++ b/R/data-AA.R @@ -1,8 +1,8 @@ -#' @name AA +#' @name AAdata #' @docType data #' @title Properties, scales and indices for the 20 naturally occurring amino acids from various sources #' @description A list with a collection of properties, scales and indices for the 20 naturally occurring amino acids from various sources. -#' @usage data(AA) +#' @usage data(AAdata) #' @format A list as follows: \itemize{ #' \item{Hydrophobicity} The hydrophobicity is an important stabilization force in protein folding; this force changes depending on the solvent in which the protein is found. \itemize{ #' \item{Aboderin:} Aboderin, A. A. (1971). An empirical hydrophobicity scale for alpha-amino-acids and some of its applications. International Journal of Biochemistry, 2(11), 537-544. diff --git a/R/fasgaiVectors.R b/R/fasgaiVectors.R index bb33335..c9ce363 100644 --- a/R/fasgaiVectors.R +++ b/R/fasgaiVectors.R @@ -17,7 +17,7 @@ fasgaiVectors <- function(seq) { seq <- strsplit(seq, "") # Load the FASGAI vectors - vectors <- get(data("AA",envir = environment()))$FASGAI + vectors <- AAdata$FASGAI # Computes the FASGAI vectors for given sequences lapply(seq, function(seq) { diff --git a/R/hmoment.R b/R/hmoment.R index dead587..ae8d03f 100755 --- a/R/hmoment.R +++ b/R/hmoment.R @@ -27,7 +27,7 @@ hmoment <- function(seq, angle = 100, window = 11) { # Loading hydrophobicity scale seq <- gsub("[[:space:]]+", "", as.vector(seq)) - h <- get(data("AA",envir = environment()))$Hydrophobicity$Eisenberg + h <- AAdata$Hydrophobicity$Eisenberg # Splitting the sequence in amino acids aa <- strsplit(seq,"") # Setting the sequence length diff --git a/R/hydrophobicity.R b/R/hydrophobicity.R index 2803391..80e473e 100755 --- a/R/hydrophobicity.R +++ b/R/hydrophobicity.R @@ -175,7 +175,7 @@ hydrophobicity <- function(seq, scale = "KyteDoolittle") { seq <- gsub("[[:space:]]+", "", as.vector(seq)) # Loading hydrophobicity scales - Hydrophobicity <- get(data("AA",envir = environment()))$Hydrophobicity + Hydrophobicity <- AAdata$Hydrophobicity # Setting the hydrophobicity scale scale <- match.arg(scale, names(Hydrophobicity)) # Sum the hydrophobicity of each amino acid and divide them between the sequence length diff --git a/R/kideraFactors.R b/R/kideraFactors.R index a08b0d6..2054155 100644 --- a/R/kideraFactors.R +++ b/R/kideraFactors.R @@ -32,7 +32,7 @@ kideraFactors <- function (seq) { # Remove the break lines from the sequence seq <- gsub("[[:space:]]+", "", as.vector(seq)) # Load the KFactors data - factors <- get(data("AA",envir = environment()))$kideraFactors + factors <- AAdata$kideraFactors # Compute the selected Kidera factor. seq <- lapply(seq, function(seq) { unlist(strsplit(seq, "")) diff --git a/R/sysdata.rda b/R/sysdata.rda new file mode 100644 index 0000000000000000000000000000000000000000..bb2f75c0dc2d8f70b780f8a53578e1d595dfaf6f GIT binary patch literal 7482 zcmV-A9mV1wiwFP!000001MOXRTohNkUV4$HB6dYY>{zhHk{P5~P$>$=70=A5!ILR=S<}t_1|6A3g_k9)PK>e9gg<6zXbQS zLHlj_cG-rw&luOu`1@Hq+-HmPHuUCNzs5i=o+b&aDOjmL9+f)IRPdp~NGiBe!G#Lm zRB)q$2Ni};VJHB5nSLTHVhUrWpkG~-FFM-Ez>btz((etbh-w(`3;8ujeP{iZPiuitIs_~xv=nouO z1Jr*;`=#_=ZNvK?Za?2rEfMg%*PEG}w?2f~amcubL(VKF12{gg3K)@4c!2puzsbh% z^HZ2q_2tMU<{FO+li$_CujZ0)OlYBLfXVvln7W23K>L}hB@N_1u4NvVKev03F^Ngx zl??Mv)9eD~9s1=hDK~Ay8}gkAxq1irq|tehPWTyvJOG{=NczO241<^$o~5$vw#{>3`A> zJJHUwIylnvcc3@!VxD-Y5$hqsdwDS*qIGz0;&JAZX&i$;6!1re&Pl$Dcs{}90LKTo zuTl+Phcbq)gLepeyA;o#;_>F7pXhx|1<#L|LiAq|ucx#QZ^HQ_j~7<}{7Fv}Z_5WC zd_p{p|5ND#SHc@)T_r+2_z6=1ewoY93)~yLhx+RS@TT{c@^Y_rct3_7{mA3Ty$65R z!MM)GJeSAI9S1%~cyn){KdPV)fH(IMIAUBd70@Hpe{Xnw!jT?<{4-C{Z(7R-dAU>R zLl0y_&fft?;t#pt4_SPFFfSqR!h8vSQ-J5ue+=Z9DF)t{A2{f7j(9ln9g_D#?bP4I zBiIf&HiQulV_O9|CS#tp#ds({y)pC(jCGYE?rX!hr>e)dr!ohw#D_4y3Oo=zhD<@Fu)SzGyz9bD9_H*3+MWH}SyA+VV>Fze>OMbIc>? zoo99CRo&YBRNL?temBV@;Yap4c%k6$z)^UP#s}5c!N0CO&((R3LqFEVpZo(_hj%X7 zeZUv?HUqyN@e)BUGvMzaobfzs0{yH5eentQ_Tg3Vxrex~j$cdQg_s}f`n3iBH`(>&n19pI9`uT~ z;Y~b*DF^Pb_XK}N8jfU-Bd#FCeTZjMoDFyh{X=?*u2Wp20Ju|slK!XqRPE#^f5{e{{i`P1${#EvbO7!RNz#X4+7`k@xeO0?%(BuLfq*8 zC?8}yY61(>+4lT=#X5j*v^&o8jjn?=dV_6`IDGpX8ok4I;1em>4)CjV^XH%I3cMY_ zOS<6xF6dW>3w-{ALj=!P+KYMrO=q;%3GeSVRV(=k+X#4B0UvYZk(lAUHI5eGbLQZE z^}*vPd8o}kp3m8$|H!^?!z&Ed&QddR3hh|&^C(*%=dIvJY0TTNY%A^bpRl6Z`jTw{ zIi#d1jDNNX>RSVE8{CiQRkr+f6(vpKx(e+I_4K}GXwMqg@jl{<(!LU*@flh)fU%#K(3t~V9%hwBj&kIkni@8y$ zYlQaNX(vCSxPp*}0KXq|9`Xi1olyS(xD~>FBp&{O_&M@~PSufb*fW&pAmk4rZYJ<< z@;{bpsXb5eNQyJU-lMoClLwsWoQ{Ya2=)@?p^<(fe=D8Sb$SokL1gF9eTYv}9AE43 zMm$_)3H=Q}xXOa!FTC6dJld$X{w6;PQw98RRFPi_@fuba=dee)Vu~yA?XWs^#z%>E z>JzdzIK*$bJn|bsZjnF5LC!hExj6U<1-wh359(ZJ3LvkaF%Q3jKLvgQ4*nM*{|f#@ z8dute_aEj%kpBI5^C6Ir{6EfzsMJpR7V@+yub$$>$m0?66)=AadG}SYM~$J6jNrG1 z|Bn^HUu%JO%Fuo)`V+Wvh+h&CfOgPH&9RhrTXBD z&B%{l+keis!chn9BYva8IZJ%71>W0OOYNO%jN$-BB zou5g1Mu?}89cm1}hdy{nIq7xs$3nghP=5*fn)o>KU|1vY`ATimC$)Zu11=gn2PlFh zN~s*@rp^IMafo=Dr$m7o17~HhB8)B%mWczWj!;C%f`pm~nQX99A_@JQ743Q}5GmJeHvY@b}j|ics%!khkm$)hvGHH0YOn|~uGNb04UOPf87tavOzI^fs z=`8VV@l0yZ&`YeGDp3-$UJAK9B5bC38hv*?FQqsjL_Afj6q?ZU5mQI$`zVAyFjAMl zU}NArQzD_yFd8kEPgW?Y8;txVGMQ9PARGEiWnl_>(8OOMn=FwBNrZ}V(rMEqN_Erx zAXcx0)DtEvO5TD~fq7dyNu5Y4lMk{bB(Gx75(&n2A*mIU5r_5!GDoC~lHrNW(W10R zwT+NJWiSh4SQyoR9XTN5m4c?}zz2(#I0XGTC^>;lP=63fBN9uCIL_2LuS1rFejp`{ z_Jrj7=YOIx{Wrp!JK&HOSjJ$eYYAe|k%dVXsP-@m;7y(ecuYxnh0I}ENl8LagQdE5 z#w2Bui0~&&BD9k1J^F((G~q#|$T~$Nh&hr4s&#mi2N|AXj^vp#Nnj}p8K~uuTdcqn zJVju-q>O~?q|BdCWCoT$W%?AOAILMCLlGhE%pCdu%&7lmylKT4@S*W9cvLa28DV8G z^gWRml6N9ML_V>ifhGMy^8-kzkfDusxFUYO5cE+hm9z|RimcF14j>y88DsSz|L|-R z*(MUnUmO2N=1O$*pa86E2J}Z$iE);w{J}_y_I$K>8j# z7jc!4%e*=}J%ImkDYWt$dYt-~_&nW@$PIaHwFmE7zrz$4Ekh(SX{2L-L>}ZAs+3Ho z>M&`L#4#{LER{QkNoSLTuD&EPT@-B2>fmYeyFPdQU7rv6UB~*=?JNDj(Sj#cU#>2H87d~MEld?l`g9yAX|P@0Pseo= zJcmWzf5oR`Q#aw$Y27*HC$_^UcC7R16z^-ppZ_JOBV|=cfyE~Zs3XO-15#S;+hS=j zQcT*4u_X2{_;h6FVwKVFKD~XNBYiqW0TKQCD?i-=ZmR$4)7wFyXm>$d5&r)7KV8r; zIMSMnrjT)ad}3V<^EVi#|6L7JcbNVSKAkj7eS8WXNyGe+UjHjU{a?Pybnq03Og4Rn zG>l?jhOXk7U!q%vZX*Vd@}-I2#8VO?ubJ|M<_$;G%!6W@f{lC>K{IQbqf=k0OeRq( zgj0n~G3`sszTwJQ0<7w3(?FobFuPbYBt{!!yjdc)K;~X0U^OQ9G9?-y@xT%Z2le?Q ztIN|bl_4dv!;JwtO$iE=aHFb^1(Vp=Ql&AZuF4YVeluK*?%Lv$y}g?a}2^J z%xB241z*o0VOnq>!Ocwgb1>_;4@kJtL%)$3j*W{LB$koegDa$%8O9OZOSGYsw&6{& zKVe}7a8O|*TfuFL4aii+Fw+oLp&3fp(3af!z+I4QN|b>)$(6xPhj1BN4{kiTsVGLT zZFp1SvaoR{+{}VrrHyIfw%{H>-YFJ*s(k#o=yX_`^X5Nic z@2lIMDK1v;+k1&iHXC|<`q9h1nwp&*kd!7m_r)@kVf^qh1XN8rM>LoFtUqr`f%@ z0rQl{hsy^ZDO1!P@sQ!+ZO%LeE@k}o#ws0bL;M2Q)6|bwl`uv8^Gv$>_KGZ~bXDKs z*W(J91pa=Nh_B~zYdUpC{0Sk*a2)-V8-8B>W+qKboq&*MCRGE67xz3!BamGBueNFl z=gLleHP$L%B=^gT&T0wdo&cv$7#CaByFAbT#N@p8{c!JDV%-E>A7q?{{+1nr`}vQ(>H>^XE*G zM%<@ySjNV^jC-$!nknGNm)7CUi}7gg0PslDsEaV}0WY^)jv7VVYr^(&noZ1|S8;`4 zGhRG?+)W$x02oGkg}bIvQwnA-wpCxrx5rvs*8s}=43>2PdYyupZz*X)JM}j?^H~GP z*=w+qO3Zhu*mnLI@F;nv0hTNB)9gdf5U$VF>cnORcNzMi2>R&(GCn~Cg0gz92l-pQl)Mv{dA+*zJX$yaJQkmv#*Eq&@b;7 z{?8FJM<1~~NHNVZOd<(Vw_DSSvgY!}nsQ&C;N6X*p5?dN-sQmHwn~l}TF;|T%J~5E zibYvE0ng_ScwW*i=Hi{cW#1RhUTwRpr+D(<*8*A?>{E-#o+5LUY{wDB)fZ+gty!{VOT)Wv6eQg2N^wXQN*0M z*NKgJlfSaMO;mW^uhxw^4$ED%PqBAoxX;2qX9u)wJ7!JQl`Tn&Fr{^hMtic#C?y%$?K=-Wla z=tj*PKYiq*a^vymHWYhYiMji{^?v(Go7toqg>@?}=6GwU~f+x+5*<+Jy^{CfAv-rlCICL71!KQ_vD z#ldRNle=`T8atfx+^Z|O(Nem#VQSjwpBC*rwPm=}nK_klg!R#l%iU(!<67X9tmMV+ zJ5@h8eZBI^?^i~b+Eo$gm=Gvl@0^lT2H(@$GT`$L=q#NSF!EHV3VbO zfzB?`O}Q7Q*&a_;E;tzRJ|$2B?mRcXf4Xr*|Bs`TicKr;w8-0ZZ$^%ti*(CG#ZN~Qw`{T9mwd=Od`kar&es-L zL_Z3@;go#zgnzrtkHMW?2E?ujSh=;;uBt8$*$;}(RIblZ*e0BAd?ecP#f5KEUrC3$ z7LFh3uvNEb&a@%_c;@ZWXK_rLykx<5g>$-h?d}o%wdC5=D{eB&(dp6E z&bwOYWt?v`|9VW5InlYX+q*2dKEcQ5Rqny z@VNL1^-R`%|Mc3?gw^4d-eE&xB7^o`2yEe3|HfpUV6!`E#@~1JUKYPM;)lFNdF!st z9#r};X41Q*nKMiR-7`Lp%-Xm!xnK0dkprju=ovlj@bX3UlnoJ|^6!7jy}wFl)~*Rz zF{_Vly=7j|JxG$}KB{-~;OSEW=YRd(-l&Au4-Q(KtXkPDcWTnIl*sum=1r@|9_+I6 zNW|@525_<2jYYU5rt5a>b z#plyc1;)xkAKi&xWnc2c-mnePUhy}2Z0OW?ZQ>KNUb$6m9yw$ziQRB#X-n_7-&l2h z-=jSCY}xqeW%i{WuH|N`tCK9JULMh?xBkKt+nPK1Se3WhpEfNgYWTpMMN#o)TWywm zE&s*O|E1eparvu_C6f$`-yBvc&Cl$;@oh-Qsrl9(-p&2R8#dc|+O)UHFOKnNx`Zx| zdL7bUoVDe}ntErN7jhFeSk5 z``fKs+BCClGj(&Im%e3iyj9i%>7qMx-FOCQH3 zcG#Y1eEPe-A<_?TUJf~~H@{Ey6vLtsMfPmys{war_bIryxkIC*>PgiJ)*(;rUKUJj zH*e^YRgpK(HQsUj;NXrreXK$k71=!>(0{%zW7Dk9<0GFxXFhieZkhX}o_T{S&3(SR zZ@6;Jy<^`5}~VWvdBK_RQ|}7A3B>~&%C#7 z#-N4q$s;@ucA2+2V(k+D_6=W~_1Tb~?6k1K%a`%tcAh3WvyXo_DDptTurAk+=B6s& zZ1GCW+xcTtZ-*OZmYe%mx4yI6zj5B(OIHpZF^I3%{z|KWHYq(8%$RV_;c@3+W3N8Nou%#9&R>!_sQZ)qd+g-Nwr$#O zdw26=ng8P5D-9n$9cxtIIn1~BmUBD$nf|=jCOxB<$B&`*P3Bb;E#2mFb?C;M-_0_c zI@f+=|MZF5S6x5*Zeej*n)k7Uow@c)uY`5E*zvO2r<}*Cp^3pqzk24?rbFPd;a1o5 z%c^&bIX(Tiy;U83PUYks^A(LwyCeO_8u5DL{uaMQMo!Y_~lW$F2=MYDP@9y=qV>)eEvcbl%>WBqc$*E@bT zyWaP!rGA(E7L5E}nLRS$!#11Bo3kU@|Fk`R_xMijr7vCHYtgOL4QAWV zhdSLj8DDYeE3Xxf+Z`~%};oq z8QZ$wJlEyhn;b0fc;xD(&BcR9iC2s|I4$q$!R(_qXYUio=5K6RW`87JR$ehS`+cP} zBdV=W>(@uGk9uQzppsc~ulMmOPQwg>JX$V_PYZm}bDncZ?Cm`P`}4lN`13lQzOtV@ z*XR|Oce4+;qn8wCkTWar;iZOLyP(c)l$ECNMNPJ^rS`5?gNS{OT(RuA}{36 zNSgY6uPa-k9ZS}BO|%&_HgWpaC>J|@NfI-*d1j=`{@V-evbsF_=B9aM>t*j#95N

c+-7ZwU@L|LSAuot%M3HoJH5SM$C90C8jl^hIv~ E0D$s9$^ZZW literal 0 HcmV?d00001 diff --git a/R/zScales.R b/R/zScales.R index e18ab3b..dee1975 100644 --- a/R/zScales.R +++ b/R/zScales.R @@ -24,7 +24,7 @@ zScales <- function(seq) { seq <- strsplit(seq, "") # Load the Z-scales - scales <- get(data("AA",envir = environment()))$zScales + scales <- AAdata$zScales # Computes the Z-scales for given sequences lapply(seq, function(seq) { diff --git a/data/AA.RData b/data/AA.RData deleted file mode 100644 index c4587fc67c76a0885b81c738084d1a5e7cd60214..0000000000000000000000000000000000000000 GIT binary patch literal 0 HcmV?d00001 literal 7478 zcmV-69m(P!iwFP!000001MOXRTohNkUV4$HB6dYY>{zhHk{P5~P$>$=7|FCt!$BOtr=CzaNkICfgMO0tLpEH$r)PHwbE1Z{aQ~yP?b~xJO{u12R2JN@y z+hrT#K4V-r7dZqCro;j<^q?gu5NXjOS-JCxI)lyOJ}Ef9I>9m>K(CGm*}X{<3VN$ z0k*#8aUZ56R^9L(?ydT<*=by|`Yon|Sbe@7=9A`eYo>y4hX-G`T5Irry-WkJAmm4Q zT$vXd7^X9YJpO{vzXTq?sqgZBN6)i5d_OQBfm;yV7F%^0t2l9>QxDUL1a-SgA7#~~)^wUTF zIqn+zFPWEnCIR}Y7|)kM&t#JXXc^u&`SHwQvgA_vU&+yA`5E=l!yG0>?hN$7GaTuD zdLEN1os)cXbfovu^L6hRCT}gn`zhoV^B!{%`uhs>DgA!Z*Eb;NB=;n*r2k1j>_j`y z>flJv-+|t^i+SRqMy!Vj@8!jOh}Pk~iN~2srg04ZP{1Dyq?lJyb0%zJYHM@@FzV@ye%Jm@CorW z{!gU~TnTTGb(IM9;3rH4_+>6XFK}=09_p_Tz?(L6_JFe>6F&_5M;9`gW${$MI`Ul#Pp z9_Sh94^|iLQGXZn^QzY2P4Y&^OyXfUhu&b)dHEOp!5?b`eWZtZmh?9{4dEYQ1wDc5 z;OnH9Si{==rgeCeo%op_&omFxIOoc6o)7){7WXB=PEX}=;=q?V;(xF=xpJP@sYKu% zS;YGw@35nYf0BOVO89ea!<+CT`J(xZ&S_q(TTg!i-oyhdYs)Ly|0@03&oPgncb?Um zS9NRiQ*Far_}wIrgdf@G;Dv&}14rRG8Xr_&2miYEJXhyA4*ggcfASA#9p1TQ_W@tn z+YJ1A#7hLZ%z(dxaK`hj3G}lL^u;IGm!H5_40(OR8iMbTKL$tEg0E){@O%|tuXT9C z{!<~yMm$Vq2E711pfZOZHi2A%r_edufWMEmKs#3G7w~EpyqtKpFpg;4kpGtES1T>$ z-(*iio&-A&N3H;Rf$Z`k*oRla=N{s|I({vI7h-;_>(>_i-(=U9WByG;d(bP|hBxsL zrX0A#-V^*8X*iNSj<|vl_aUB5aW>#3^bhGJx=wM80^m;lN&27aQ?-+y2>!eVq(^EW z1$|PdUf>mfq)#l-FLm_^{0HRE74!+s%i69_Qh`%lJ_wwD#|P{1x__4s3UQr7>^6vaPh!f5M7t>r1u;ngM>)YJQ#p*?F{$NPvclK)oQ@D}VG@=H@3f%2k& zj}YI?p*R5g1Aar+1U#e~{zl?6-^v ztyfbXXBU>2S6f`~0l9W|fIWlyj+o~zwmM=@Mxpj`kVYHOcn6MQAK_!#A{exoWmaFiYczdx5Mhx86PFusZYq> z;1Ivz^2l!lxkdgI2RY{u=i=Ze6!0#AKB#k@DS*6w#ytEA{uKBLIQUbxBj@pK|5O1OUK;q$K=QPFjn`D2G-atM1m+FHrHX}cJ zZT~sj3P&BZkNAxW=PdET7I<%CEwy*5ktgEBk7rd|UQSi*c;Z0wn#vCODE7cZ5A&k^ zYR&U3^50nG6RO%mUwpv)m|Z(gq_W0+4S9X9YK&tO=zZ8tT8B6BT{@E9CcXQic77)5 z86loVcBnD@9{S)R<)qii9}D?5K>a1?YvSX`gJF%p=PR{MpVayt4!CIS9H0o2D5Y|o zn>q(5#UbKpo)QIW44jq0iZHr7SSAjfIzka43leG~WU|3Zi6l&d8bcRxm{=*rnUPC~ zB0NMY#;Kl*l%6zpQOp#}og91BI`8Y)8|Nl&(lCiUK%xw$8{Fi<64^8{eXF6nIPA-r zvAZ}TFhruH&oK5-$b!OZzLwtX5iyHe9-;^h^;al@=w}%W6Uzk%42CJ>61rkEEJ7&> zmj==+hf8bFq93C_JR*diG9NxGT;i%w$fV)nG64!t$&8wFdhH0YTs%W8`|`;nq_f1c z#WSfrLocy%szgc1dMV`ch_IRBY4qLoyp-aA5b;#8QfNZYM@${1@1qdx7IR|=Y@10O6};t=%XpyUKHLH$7_jYupl;y6?1ybf6w`hk=*+7puR zpZ|%*^xp_?k|!bPN{c(__s1j2i;Q4eYy%^W!D0i!c(@0AsXyTC;M;0bopxVPMfH!#>;4vlP6*7luB_#2_vjDG(1Zt-BI^{9Am&IGsMg_49%OimIg)3}B!Q(YWT2KqZm|MS@DzdR zk}?vmlQMrokr`P2l<8B9ejv|m4n>5tGjrtsGo${O@un4Hz=y`a;8Df6W`vc&(Dy`M zNZyJ35c$N42A1>-%?}`Y@JLX5BA7JECCbzcXO}H?^yb1ZHh_@h@;2*T}1L=G0T*OsE zF7xW_^Z@?DrO?W2=yB>_;`4MrA~)o*)gHWS{SH%Hv<#8Rq>+vR5_yngs8TYSs>7r~ z634(0u~hCDCY?C*`{&zJ@-C_DS_;k`R_3fl{Th@+k$%ld8b(LsoHWb=zDU%QFsf9t*i*+h;k#y?TU>@I3!ean<#9i zEqK@Z9R|3lJFbUN>M4|*gih`^_eLphqYieCKFQSYTu5|Mv!Ur5sI#v8$vj(Rm9Xk1I}agtDapJw;s2Fz0) zA1)twq)btF#6yOMw>k3^xRmkR8>@7%4e<+HPg6f$Rl*eU&ok-j+bgn|(p7zjUymzb z68QU7BEFu>t?ASm@h5~J!*TReZuoiio0&8%bpk@3nN$rNUflB_jX-kgzuKxLoGUx= z)mW>5k=!pUI;$m+djgz3VO(rg@A5qV6O;4W_rtwsjhRfoo=E^3dZbV#qToRRNL@oFz&g;D)oTB%{>cI)*!uuyN+2{1UB;m z?E5y46GQr^jPEBVOD*-vUzyJ}ol(<6OcJjTxIDFZzu(D4Yr5$xPK9xj&Yv?$8gZY- zVHq3uGVZ+^YNmi6Us{JZFUF&}1HdCqqb|a@2fW;JIcgMbuL;}BX*Mx;Ud0uH&3N(n zaW`$$17H~G74DiwO(~eU*j9Zd-yUmmT>~idGg#II=yeKWzNMrI?bP4o%x4WCXRpCd zDly-sV%zy=z@y}u23W4hPqPm_L%2Rys}q|Q+-2y4BIu_F$N*hO%ZhpZ!u`gNBPN|6 z4+48ifIccvPuCyrYY*PFeup8k7abUPYNtL>x^wW)I`v!_-!rg}M&b}VbL%+OV_&-O? z9DT&{AjLGtFo`5c-EK`Q%9_g?Ys!6nf_FELdY0d6dzS-)+bTI`Xg!ZUDdz*sD;8zx z1U#QR;CV^6n2UG%mVIA1d$sMZp5n=alV|VMNiGjKSp8<4j=a42f^UCK@xGk8XV;XVudoE^}z?U*%HQ?6&;ciwq$%_K`FtJMonyA8h< z`zb7~Xh7$~D;6JK9{D79z<|Am;~m$YvK0+!Q5ku<(e_IsliW91hn!YkIUM9#*1X02 zT|Vn)G;7;-t8xD)7h~7W{ju4+j|0zE?MPhe;k_*F*9ujWB`+@RZYJwe8BsE!e(zV^ zI;H&(chh|IMvs?ORxUb76JpSAna(aW(ug`IomoDMoFl_g-w}pl=ruqZ>7I z{PdBJ%8kdL+feLrCFbt)*8A-%ZDz0PTJMK?KX#wL=bFJU#rss39ltYWP&aB_`ZS#vKme1bv^6T9vdwZL)3_En6n*RyY1TL z;prALR+7?1@1?n3v#;0|*1`I25#IgwRXPlGYd!Ju9P6T05lM`6Ud6T(gH4wD1vL`;dWQ{(i459%A+UvC{Tq{Yg3a!v8Gql=ds+P6h#&G6<*mCmdr;}a zm`U%JX3j7PbkF!WGHc_`uKS-U1=#jHNI z^_F=-_aI4@`>5W{gQrgkod5NAd!rIsKR9S{vT9|s+^I>+QX=QOm^ZB+d$7yOj|W@L z+Scm**bVFx>xmBHs+a-a#&9~1#=p7s#>vG?awtb6n`QE8OX$7Bt}QGgu1>Y#7N1W) z6&NcEeRL;&m3_$%d&4$Fd&S@Av7uAnwTVy6dgWHNdE}6>BzD7{r7gYReq+`3eUI|k zvt{F>m)VzkxR#r#u1>O?dU-^n-ueqqY-{f1V^!X2f7-O1sNn;17DdIIZM9kMwfq-9 z|Cera#pSOymP|4%esfr*G(WTV#Y17^&zc|L9=@Pm;>UBta zan_a>YwDdbe|~G$k&(LDr<^P{y|bLTVy)kf6)T;FM>h9czqI1q>!xlqeoOr|<3d(W zP}B{ZSk}YbHlgp_`l~-p%6lKuv&gs6@X+W(;Z9BE!{QdCcKX^&mUwtm$He>ZUYoC* z<{uTi>G|83LqSo@m~+{~Z#NScj&i$pa(nB1J@3(H`;S{2<&=9Usn6_0!;}EK?{Bwm zY17QI&D70-Uiy~7@m5(6q>Jv%eOofN`w&H!!#+3OF+CsOoPPbN%RRRTp8KR{Z>2hA zxeQV0L}pJ8pR|6WNmtdjVhi*54Px(tN%O?Ly!BpQ>brJA#h9+LUiCazEqxrD*kOC3 z@#*jShDblWc{${`-uyn*Qw)nn6xp+(uLj(i-KXH*<_?XLswY(^Scg2dds#5C-Mpbo zRz==C*LcVAgM&Nj^sx$ERAl#jK>zu=j7_sXkB@x*ocY`>xMl8>dgcwTH23-LzTwI> z_l|uNkhiC$n3+7Y+kj<$KCEj%r+)nod~7q-#eQh`h7D02TU&-)zq_kXVb?LYPE73k zuAOv^(XxwH-u|6D#${Ao?QPz7|HU0go=yA|Cx6&&LyWZg{p7}7n|U~mliu{}WWD5m z+EDTC`CE58{d}je@JjiPxCTaxf6EvXXKK}=vA4}f%Od-zQ~4uTe&}p|J@ekS8G{za zCy($v*k#`8h_y@n+c$h|)@MU{veUu_FJH!o+j*Mk%s&3zpvVIS!@68QnwzS8v&Abh zZ|9Fqy&Z0tS#IuM-TKaM|HgTDFI_ow#2~(2`zx&i+NAVYFk`|whsT|drSw_EU3ht` z>i({uy8CVJfA?8<|3t}JpQp)T167gRjlKF5cb2waJAX;$pzcrZ@3E67+qP-D?cL3f zW&VqIuQYu4bgWT*=P=*iTh8t1XZrJAoAiuc9zTZKHRkJg z{nICIUv>TLyM@JNY2L>YcIMhIy%N^tV#mv7pK>0nh9(9d{py)ln+}1;hFe|JFRR`$ z=JfR6_EvTDIhB)l%vUrz?T+*xYsBk~`&;}L899CLl1+`D^_$RS_x5?0^(HJ#o@1S2 zGc%_!CDQ49Y5mA`yYx%btBW%Im!;>g7R~CtcVY5bcximA-U&uSK^~H<)cdAL?}D zWPHV;ue??`a`!!Um7aEN^{ZLa0kP$C9+rnKzu{Tg;mokbewR)<$y>c{H9z5bW^C(z z^IVs2Z*s7_bC0;S=;IzD}2eXgfoV`yRo4>JPnf;M?S$W0S?Dv(@jHtFg ztzRF#KI)C>fl6k{z23*CI1Muh@@TmzJ}vM?&w0)vvA6dG?9co5;?L`J`pSOtT%%W9 z-pxMXj$TrnLC&nehnE_1m8*LkuRq>*RZIQmA%T?=(~}lKyALR;EDd)qioB3NBWddQ zy{>GDb}U)jHPL3!*u?2uqg?FtB}vTK=9!T$`)@C>%j)vzo15m5t(Uz|ambiFy<^*x z+3tNaz1FOcE$bTn^l%%+ruc0$rs2dySyd^l~{Hu?pcX9?E+3eoIU(NUa1H`(lctLLf05T&+ AdjJ3c diff --git a/data/AAdata.RData b/data/AAdata.RData new file mode 100644 index 0000000000000000000000000000000000000000..bb2f75c0dc2d8f70b780f8a53578e1d595dfaf6f GIT binary patch literal 7482 zcmV-A9mV1wiwFP!000001MOXRTohNkUV4$HB6dYY>{zhHk{P5~P$>$=70=A5!ILR=S<}t_1|6A3g_k9)PK>e9gg<6zXbQS zLHlj_cG-rw&luOu`1@Hq+-HmPHuUCNzs5i=o+b&aDOjmL9+f)IRPdp~NGiBe!G#Lm zRB)q$2Ni};VJHB5nSLTHVhUrWpkG~-FFM-Ez>btz((etbh-w(`3;8ujeP{iZPiuitIs_~xv=nouO z1Jr*;`=#_=ZNvK?Za?2rEfMg%*PEG}w?2f~amcubL(VKF12{gg3K)@4c!2puzsbh% z^HZ2q_2tMU<{FO+li$_CujZ0)OlYBLfXVvln7W23K>L}hB@N_1u4NvVKev03F^Ngx zl??Mv)9eD~9s1=hDK~Ay8}gkAxq1irq|tehPWTyvJOG{=NczO241<^$o~5$vw#{>3`A> zJJHUwIylnvcc3@!VxD-Y5$hqsdwDS*qIGz0;&JAZX&i$;6!1re&Pl$Dcs{}90LKTo zuTl+Phcbq)gLepeyA;o#;_>F7pXhx|1<#L|LiAq|ucx#QZ^HQ_j~7<}{7Fv}Z_5WC zd_p{p|5ND#SHc@)T_r+2_z6=1ewoY93)~yLhx+RS@TT{c@^Y_rct3_7{mA3Ty$65R z!MM)GJeSAI9S1%~cyn){KdPV)fH(IMIAUBd70@Hpe{Xnw!jT?<{4-C{Z(7R-dAU>R zLl0y_&fft?;t#pt4_SPFFfSqR!h8vSQ-J5ue+=Z9DF)t{A2{f7j(9ln9g_D#?bP4I zBiIf&HiQulV_O9|CS#tp#ds({y)pC(jCGYE?rX!hr>e)dr!ohw#D_4y3Oo=zhD<@Fu)SzGyz9bD9_H*3+MWH}SyA+VV>Fze>OMbIc>? zoo99CRo&YBRNL?temBV@;Yap4c%k6$z)^UP#s}5c!N0CO&((R3LqFEVpZo(_hj%X7 zeZUv?HUqyN@e)BUGvMzaobfzs0{yH5eentQ_Tg3Vxrex~j$cdQg_s}f`n3iBH`(>&n19pI9`uT~ z;Y~b*DF^Pb_XK}N8jfU-Bd#FCeTZjMoDFyh{X=?*u2Wp20Ju|slK!XqRPE#^f5{e{{i`P1${#EvbO7!RNz#X4+7`k@xeO0?%(BuLfq*8 zC?8}yY61(>+4lT=#X5j*v^&o8jjn?=dV_6`IDGpX8ok4I;1em>4)CjV^XH%I3cMY_ zOS<6xF6dW>3w-{ALj=!P+KYMrO=q;%3GeSVRV(=k+X#4B0UvYZk(lAUHI5eGbLQZE z^}*vPd8o}kp3m8$|H!^?!z&Ed&QddR3hh|&^C(*%=dIvJY0TTNY%A^bpRl6Z`jTw{ zIi#d1jDNNX>RSVE8{CiQRkr+f6(vpKx(e+I_4K}GXwMqg@jl{<(!LU*@flh)fU%#K(3t~V9%hwBj&kIkni@8y$ zYlQaNX(vCSxPp*}0KXq|9`Xi1olyS(xD~>FBp&{O_&M@~PSufb*fW&pAmk4rZYJ<< z@;{bpsXb5eNQyJU-lMoClLwsWoQ{Ya2=)@?p^<(fe=D8Sb$SokL1gF9eTYv}9AE43 zMm$_)3H=Q}xXOa!FTC6dJld$X{w6;PQw98RRFPi_@fuba=dee)Vu~yA?XWs^#z%>E z>JzdzIK*$bJn|bsZjnF5LC!hExj6U<1-wh359(ZJ3LvkaF%Q3jKLvgQ4*nM*{|f#@ z8dute_aEj%kpBI5^C6Ir{6EfzsMJpR7V@+yub$$>$m0?66)=AadG}SYM~$J6jNrG1 z|Bn^HUu%JO%Fuo)`V+Wvh+h&CfOgPH&9RhrTXBD z&B%{l+keis!chn9BYva8IZJ%71>W0OOYNO%jN$-BB zou5g1Mu?}89cm1}hdy{nIq7xs$3nghP=5*fn)o>KU|1vY`ATimC$)Zu11=gn2PlFh zN~s*@rp^IMafo=Dr$m7o17~HhB8)B%mWczWj!;C%f`pm~nQX99A_@JQ743Q}5GmJeHvY@b}j|ics%!khkm$)hvGHH0YOn|~uGNb04UOPf87tavOzI^fs z=`8VV@l0yZ&`YeGDp3-$UJAK9B5bC38hv*?FQqsjL_Afj6q?ZU5mQI$`zVAyFjAMl zU}NArQzD_yFd8kEPgW?Y8;txVGMQ9PARGEiWnl_>(8OOMn=FwBNrZ}V(rMEqN_Erx zAXcx0)DtEvO5TD~fq7dyNu5Y4lMk{bB(Gx75(&n2A*mIU5r_5!GDoC~lHrNW(W10R zwT+NJWiSh4SQyoR9XTN5m4c?}zz2(#I0XGTC^>;lP=63fBN9uCIL_2LuS1rFejp`{ z_Jrj7=YOIx{Wrp!JK&HOSjJ$eYYAe|k%dVXsP-@m;7y(ecuYxnh0I}ENl8LagQdE5 z#w2Bui0~&&BD9k1J^F((G~q#|$T~$Nh&hr4s&#mi2N|AXj^vp#Nnj}p8K~uuTdcqn zJVju-q>O~?q|BdCWCoT$W%?AOAILMCLlGhE%pCdu%&7lmylKT4@S*W9cvLa28DV8G z^gWRml6N9ML_V>ifhGMy^8-kzkfDusxFUYO5cE+hm9z|RimcF14j>y88DsSz|L|-R z*(MUnUmO2N=1O$*pa86E2J}Z$iE);w{J}_y_I$K>8j# z7jc!4%e*=}J%ImkDYWt$dYt-~_&nW@$PIaHwFmE7zrz$4Ekh(SX{2L-L>}ZAs+3Ho z>M&`L#4#{LER{QkNoSLTuD&EPT@-B2>fmYeyFPdQU7rv6UB~*=?JNDj(Sj#cU#>2H87d~MEld?l`g9yAX|P@0Pseo= zJcmWzf5oR`Q#aw$Y27*HC$_^UcC7R16z^-ppZ_JOBV|=cfyE~Zs3XO-15#S;+hS=j zQcT*4u_X2{_;h6FVwKVFKD~XNBYiqW0TKQCD?i-=ZmR$4)7wFyXm>$d5&r)7KV8r; zIMSMnrjT)ad}3V<^EVi#|6L7JcbNVSKAkj7eS8WXNyGe+UjHjU{a?Pybnq03Og4Rn zG>l?jhOXk7U!q%vZX*Vd@}-I2#8VO?ubJ|M<_$;G%!6W@f{lC>K{IQbqf=k0OeRq( zgj0n~G3`sszTwJQ0<7w3(?FobFuPbYBt{!!yjdc)K;~X0U^OQ9G9?-y@xT%Z2le?Q ztIN|bl_4dv!;JwtO$iE=aHFb^1(Vp=Ql&AZuF4YVeluK*?%Lv$y}g?a}2^J z%xB241z*o0VOnq>!Ocwgb1>_;4@kJtL%)$3j*W{LB$koegDa$%8O9OZOSGYsw&6{& zKVe}7a8O|*TfuFL4aii+Fw+oLp&3fp(3af!z+I4QN|b>)$(6xPhj1BN4{kiTsVGLT zZFp1SvaoR{+{}VrrHyIfw%{H>-YFJ*s(k#o=yX_`^X5Nic z@2lIMDK1v;+k1&iHXC|<`q9h1nwp&*kd!7m_r)@kVf^qh1XN8rM>LoFtUqr`f%@ z0rQl{hsy^ZDO1!P@sQ!+ZO%LeE@k}o#ws0bL;M2Q)6|bwl`uv8^Gv$>_KGZ~bXDKs z*W(J91pa=Nh_B~zYdUpC{0Sk*a2)-V8-8B>W+qKboq&*MCRGE67xz3!BamGBueNFl z=gLleHP$L%B=^gT&T0wdo&cv$7#CaByFAbT#N@p8{c!JDV%-E>A7q?{{+1nr`}vQ(>H>^XE*G zM%<@ySjNV^jC-$!nknGNm)7CUi}7gg0PslDsEaV}0WY^)jv7VVYr^(&noZ1|S8;`4 zGhRG?+)W$x02oGkg}bIvQwnA-wpCxrx5rvs*8s}=43>2PdYyupZz*X)JM}j?^H~GP z*=w+qO3Zhu*mnLI@F;nv0hTNB)9gdf5U$VF>cnORcNzMi2>R&(GCn~Cg0gz92l-pQl)Mv{dA+*zJX$yaJQkmv#*Eq&@b;7 z{?8FJM<1~~NHNVZOd<(Vw_DSSvgY!}nsQ&C;N6X*p5?dN-sQmHwn~l}TF;|T%J~5E zibYvE0ng_ScwW*i=Hi{cW#1RhUTwRpr+D(<*8*A?>{E-#o+5LUY{wDB)fZ+gty!{VOT)Wv6eQg2N^wXQN*0M z*NKgJlfSaMO;mW^uhxw^4$ED%PqBAoxX;2qX9u)wJ7!JQl`Tn&Fr{^hMtic#C?y%$?K=-Wla z=tj*PKYiq*a^vymHWYhYiMji{^?v(Go7toqg>@?}=6GwU~f+x+5*<+Jy^{CfAv-rlCICL71!KQ_vD z#ldRNle=`T8atfx+^Z|O(Nem#VQSjwpBC*rwPm=}nK_klg!R#l%iU(!<67X9tmMV+ zJ5@h8eZBI^?^i~b+Eo$gm=Gvl@0^lT2H(@$GT`$L=q#NSF!EHV3VbO zfzB?`O}Q7Q*&a_;E;tzRJ|$2B?mRcXf4Xr*|Bs`TicKr;w8-0ZZ$^%ti*(CG#ZN~Qw`{T9mwd=Od`kar&es-L zL_Z3@;go#zgnzrtkHMW?2E?ujSh=;;uBt8$*$;}(RIblZ*e0BAd?ecP#f5KEUrC3$ z7LFh3uvNEb&a@%_c;@ZWXK_rLykx<5g>$-h?d}o%wdC5=D{eB&(dp6E z&bwOYWt?v`|9VW5InlYX+q*2dKEcQ5Rqny z@VNL1^-R`%|Mc3?gw^4d-eE&xB7^o`2yEe3|HfpUV6!`E#@~1JUKYPM;)lFNdF!st z9#r};X41Q*nKMiR-7`Lp%-Xm!xnK0dkprju=ovlj@bX3UlnoJ|^6!7jy}wFl)~*Rz zF{_Vly=7j|JxG$}KB{-~;OSEW=YRd(-l&Au4-Q(KtXkPDcWTnIl*sum=1r@|9_+I6 zNW|@525_<2jYYU5rt5a>b z#plyc1;)xkAKi&xWnc2c-mnePUhy}2Z0OW?ZQ>KNUb$6m9yw$ziQRB#X-n_7-&l2h z-=jSCY}xqeW%i{WuH|N`tCK9JULMh?xBkKt+nPK1Se3WhpEfNgYWTpMMN#o)TWywm zE&s*O|E1eparvu_C6f$`-yBvc&Cl$;@oh-Qsrl9(-p&2R8#dc|+O)UHFOKnNx`Zx| zdL7bUoVDe}ntErN7jhFeSk5 z``fKs+BCClGj(&Im%e3iyj9i%>7qMx-FOCQH3 zcG#Y1eEPe-A<_?TUJf~~H@{Ey6vLtsMfPmys{war_bIryxkIC*>PgiJ)*(;rUKUJj zH*e^YRgpK(HQsUj;NXrreXK$k71=!>(0{%zW7Dk9<0GFxXFhieZkhX}o_T{S&3(SR zZ@6;Jy<^`5}~VWvdBK_RQ|}7A3B>~&%C#7 z#-N4q$s;@ucA2+2V(k+D_6=W~_1Tb~?6k1K%a`%tcAh3WvyXo_DDptTurAk+=B6s& zZ1GCW+xcTtZ-*OZmYe%mx4yI6zj5B(OIHpZF^I3%{z|KWHYq(8%$RV_;c@3+W3N8Nou%#9&R>!_sQZ)qd+g-Nwr$#O zdw26=ng8P5D-9n$9cxtIIn1~BmUBD$nf|=jCOxB<$B&`*P3Bb;E#2mFb?C;M-_0_c zI@f+=|MZF5S6x5*Zeej*n)k7Uow@c)uY`5E*zvO2r<}*Cp^3pqzk24?rbFPd;a1o5 z%c^&bIX(Tiy;U83PUYks^A(LwyCeO_8u5DL{uaMQMo!Y_~lW$F2=MYDP@9y=qV>)eEvcbl%>WBqc$*E@bT zyWaP!rGA(E7L5E}nLRS$!#11Bo3kU@|Fk`R_xMijr7vCHYtgOL4QAWV zhdSLj8DDYeE3Xxf+Z`~%};oq z8QZ$wJlEyhn;b0fc;xD(&BcR9iC2s|I4$q$!R(_qXYUio=5K6RW`87JR$ehS`+cP} zBdV=W>(@uGk9uQzppsc~ulMmOPQwg>JX$V_PYZm}bDncZ?Cm`P`}4lN`13lQzOtV@ z*XR|Oce4+;qn8wCkTWar;iZOLyP(c)l$ECNMNPJ^rS`5?gNS{OT(RuA}{36 zNSgY6uPa-k9ZS}BO|%&_HgWpaC>J|@NfI-*d1j=`{@V-evbsF_=B9aM>t*j#95N

c+-7ZwU@L|LSAuot%M3HoJH5SM$C90C8jl^hIv~ E0D$s9$^ZZW literal 0 HcmV?d00001 diff --git a/data/datalist b/data/datalist index 5445c9b..0fb67fe 100755 --- a/data/datalist +++ b/data/datalist @@ -1,2 +1,2 @@ -AA +AAdata pepdata \ No newline at end of file diff --git a/inst/tests/runalltest.R b/inst/tests/runalltest.R deleted file mode 100644 index 3e78d00..0000000 --- a/inst/tests/runalltest.R +++ /dev/null @@ -1,14 +0,0 @@ -require(Peptides) -require(RUnit) - -#options(warn=1) - -testSuite <- defineTestSuite(name="RUnit", - dirs=".", - testFileRegexp="runit.*\\.R$", - rngKind="default", - rngNormalKind="default") - -testData <- runTestSuite(testSuite, verbose=0L) -printTextProtocol(testData, showDetails=FALSE) - diff --git a/inst/tests/runit.aacomp.R b/inst/tests/runit.aacomp.R deleted file mode 100644 index 9eee6c4..0000000 --- a/inst/tests/runit.aacomp.R +++ /dev/null @@ -1,23 +0,0 @@ -test.aacomp <- function(){ - # CHECK OUTPUT CLASS - checkTrue(is.matrix(aacomp("QWGRRCCGWGPGRRYCVRWC")[[1]])) - - # COMPARED TO PEPSTATS - # http://emboss.bioinformatics.nl/cgi-bin/emboss/pepstats - # Property Residues Number Mole% - # Tiny (A+C+G+S+T) 8 40.000 - # Small (A+B+C+D+G+N+P+S+T+V) 10 50.000 - # Aliphatic (A+I+L+V) 1 5.000 - # Aromatic (F+H+W+Y) 4 20.000 - # Non-polar (A+C+F+G+I+L+M+P+V+W+Y) 14 70.000 - # Polar (D+E+H+K+N+Q+R+S+T+Z) 6 30.000 - # Charged (B+D+E+H+K+R+Z) 5 25.000 - # Basic (H+K+R) 5 25.000 - # Acidic (B+D+E+Z) 0 0.000 - - # CHECK VALUES - checkEquals(aacomp("QWGRRCCGWGPGRRYCVRWC")[[1]][1:9],c(8,10,1,4,14,6,5,5,0)) - - #CHECK PERCENTAGES - checkEquals(aacomp("QWGRRCCGWGPGRRYCVRWC")[[1]][10:18],c(40,50,5,20,70,30,25,25,0)) -} diff --git a/inst/tests/runit.aindex.R b/inst/tests/runit.aindex.R deleted file mode 100644 index 3b14877..0000000 --- a/inst/tests/runit.aindex.R +++ /dev/null @@ -1,13 +0,0 @@ -test.aindex <- function(){ - # COMPARED TO ExPASy ALIPHATIC INDEX - # http://web.expasy.org/protparam/ - - # SEQUENCE: DAYAQWLKDGGPSSGRPPPS - # Aliphatic index: 29.50 - - # CHECK VALUES - checkEquals(aindex("DAYAQWLKDGGPSSGRPPPS"),29.50) - - # CHECK OUTPUT CLASS - checkTrue(is.numeric(aindex("DAYAQWLKDGGPSSGRPPPS"))) -} \ No newline at end of file diff --git a/inst/tests/runit.boman.R b/inst/tests/runit.boman.R deleted file mode 100644 index 6873624..0000000 --- a/inst/tests/runit.boman.R +++ /dev/null @@ -1,13 +0,0 @@ -test.boman <- function(){ - - # COMPARED TO YADAMP DATABASE - # http://yadamp.unisa.it/showItem.aspx?yadampid=845&x=0,4373912 - # SEQUENCE: FLPVLAGLTPSIVPKLVCLLTKKC - # BOMAN INDEX -1.24 - - # CHECK VALUES - checkEquals(boman("FLPVLAGLTPSIVPKLVCLLTKKC"),-1.24,tolerance = 0.01) - - # CHECK OUTPUT CLASS - checkTrue(is.numeric(boman("FLPVLAGLTPSIVPKLVCLLTKKC"))) -} \ No newline at end of file diff --git a/inst/tests/runit.charge.R b/inst/tests/runit.charge.R deleted file mode 100644 index bf3ecc6..0000000 --- a/inst/tests/runit.charge.R +++ /dev/null @@ -1,17 +0,0 @@ -test.charge <- function(){ - # COMPARED TO EMBOSS PEPSTATS - # http://emboss.bioinformatics.nl/cgi-bin/emboss/pepstats - # SEQUENCE: FLPVLAGLTPSIVPKLVCLLTKKC - # Charge = 3.0 - checkEquals(round(charge(seq = "FLPVLAGLTPSIVPKLVCLLTKKC",pH = 7,pKscale = "EMBOSS")),3) - - # COMPARED TO YADAMP - # http://yadamp.unisa.it/showItem.aspx?yadampid=845&x=0,7055475 - # SEQUENCE: FLPVLAGLTPSIVPKLVCLLTKKC - checkEquals(charge("FLPVLAGLTPSIVPKLVCLLTKKC",5,pKscale = "Lehn"),3,tolerance = 0.01) - checkEquals(charge("FLPVLAGLTPSIVPKLVCLLTKKC",7,pKscale = "Lehn"),2.9,tolerance = 0.01) - checkEquals(charge("FLPVLAGLTPSIVPKLVCLLTKKC",9,pKscale = "Lehn"),1.0,tolerance = 0.01) - - # CHECK OUTPUT CLASS - checkTrue(is.numeric(charge("FLPVLAGLTPSIVPKLVCLLTKKC",7,pKscale = "Bjellqvist"))) -} \ No newline at end of file diff --git a/inst/tests/runit.hmoment.R b/inst/tests/runit.hmoment.R deleted file mode 100644 index 6458604..0000000 --- a/inst/tests/runit.hmoment.R +++ /dev/null @@ -1,16 +0,0 @@ -test.hmoment <- function(){ - # COMPARED TO EMBOSS:HMOMENT - # http://emboss.bioinformatics.nl/cgi-bin/emboss/hmoment - # SEQUENCE: FLPVLAGLTPSIVPKLVCLLTKKC - # ALPHA-HELIX 100º : 0.56 - # BETA-SHEET 160º : 0.25 - - # ALPHA HELIX VALUE - checkEquals(hmoment(seq = "FLPVLAGLTPSIVPKLVCLLTKKC",angle = 100,window = 11), 0.520,tolerance = 0.01) - - # BETA SHEET VALUE - checkEquals(hmoment(seq = "FLPVLAGLTPSIVPKLVCLLTKKC",angle = 160,window = 11), 0.271,tolerance = 0.01) - - # CHECK OUTPUT CLASS - checkTrue(is.numeric(hmoment("FLPVLAGLTPSIVPKLVCLLTKKC",100))) -} \ No newline at end of file diff --git a/inst/tests/runit.hydrophobicity.R b/inst/tests/runit.hydrophobicity.R deleted file mode 100644 index 812504c..0000000 --- a/inst/tests/runit.hydrophobicity.R +++ /dev/null @@ -1,12 +0,0 @@ -test.hydrophobicity <- function(){ - # COMPARED TO GRAVY Grand average of hydropathicity (GRAVY) ExPASy - # http://web.expasy.org/cgi-bin/protparam/protparam - # SEQUENCE: QWGRRCCGWGPGRRYCVRWC - # GRAVY: -0.950 - - # CHECK GRAVY VALUE - checkEquals(hydrophobicity(seq = "QWGRRCCGWGPGRRYCVRWC",scale = "Kyte"),-0.950) - - # CHECK OUTPUT CLASS - checkTrue(is.numeric(hydrophobicity("QWGRRCCGWGPGRRYCVRWC","Kyte"))) -} \ No newline at end of file diff --git a/inst/tests/runit.instaindex.R b/inst/tests/runit.instaindex.R deleted file mode 100644 index 555022a..0000000 --- a/inst/tests/runit.instaindex.R +++ /dev/null @@ -1,13 +0,0 @@ -test.instaindex <- function(){ - # COMPARED TO ExPASy INSTAINDEX - # http://web.expasy.org/protparam/ - # SEQUENCE: QWGRRCCGWGPGRRYCVRWC - # The instability index (II) is computed to be 83.68 - - - # CHECK INSTAINDEX VALUE - checkEquals(instaindex("QWGRRCCGWGPGRRYCVRWC"),83.68) - - # CHECK OUTPUT CLASS - checkTrue(is.numeric(instaindex("QWGRRCCGWGPGRRYCVRWC"))) -} \ No newline at end of file diff --git a/inst/tests/runit.lengthpep.R b/inst/tests/runit.lengthpep.R deleted file mode 100644 index 614834c..0000000 --- a/inst/tests/runit.lengthpep.R +++ /dev/null @@ -1,12 +0,0 @@ -test.lengthpep <- function(){ - # COMPARED TO ExPASy ProtParam - # http://web.expasy.org/protparam - # SEQUENCE: QWGRRCCGWGPGRRYCVRWC - # Number of amino acids: 20 - - # CHECK VALUE - checkEquals(lengthpep("QWGRRCCGWGPGRRYCVRWC"),20) - - # CHECK OUTPUT CLASS - checkTrue(is.numeric(lengthpep("QWGRRCCGWGPGRRYCVRWC"))) -} \ No newline at end of file diff --git a/inst/tests/runit.mw.R b/inst/tests/runit.mw.R deleted file mode 100644 index d9ba5ae..0000000 --- a/inst/tests/runit.mw.R +++ /dev/null @@ -1,11 +0,0 @@ -mw.membpos <- function(){ - # COMPARED TO ExPASy Compute pI/Mw tool - # http://web.expasy.org/compute_pi/ - # SEQUENCE: QWGRRCCGWGPGRRYCVRWC - - # CHECK MW VALUE - checkEquals(mw("QWGRRCCGWGPGRRYCVRWC"), 2485.91,tolerance = 0.01) - - # CHECK OUTPUT CLASS - checkTrue(is.numeric(mw("QWGRRCCGWGPGRRYCVRWC"))) -} \ No newline at end of file diff --git a/inst/tests/runit.pI.R b/inst/tests/runit.pI.R deleted file mode 100644 index 2deb21b..0000000 --- a/inst/tests/runit.pI.R +++ /dev/null @@ -1,12 +0,0 @@ -test.pI<- function(){ - # COMPARED TO ExPASy ProtParam - # http://web.expasy.org/cgi-bin/protparam/protparam - # SEQUENCE: QWGRRCCGWGPGRRYCVRWC - # Theoretical pI: 9.88 - - # CHECK pI VALUE - checkEquals(pI(seq = "QWGRRCCGWGPGRRYCVRWC",pKscale = "Bjellqvist"),9.88,tolerance = 0.01) - - # CHECK OUTPUT CLASS - checkTrue(is.numeric(pI("QWGRRCCGWGPGRRYCVRWC","Bjellqvist"))) -} \ No newline at end of file diff --git a/man/AA.Rd b/man/AAdata.Rd similarity index 99% rename from man/AA.Rd rename to man/AAdata.Rd index c05d90e..762e48e 100644 --- a/man/AA.Rd +++ b/man/AAdata.Rd @@ -1,8 +1,8 @@ % Generated by roxygen2: do not edit by hand % Please edit documentation in R/data-AA.R \docType{data} -\name{AA} -\alias{AA} +\name{AAdata} +\alias{AAdata} \title{Properties, scales and indices for the 20 naturally occurring amino acids from various sources} \format{A list as follows: \itemize{ \item{Hydrophobicity} The hydrophobicity is an important stabilization force in protein folding; this force changes depending on the solvent in which the protein is found. \itemize{ @@ -101,7 +101,7 @@ } } \usage{ -data(AA) +data(AAdata) } \description{ A list with a collection of properties, scales and indices for the 20 naturally occurring amino acids from various sources. diff --git a/man/autoCorrelation.Rd b/man/autoCorrelation.Rd index 8f5de62..46a4248 100644 --- a/man/autoCorrelation.Rd +++ b/man/autoCorrelation.Rd @@ -23,13 +23,13 @@ This function computes the Cruciani et al (2004) auto-correlation index. The \co } \examples{ # Loading a property to evaluate its autocorrelation -data(AA) +data(AAdata) # Calculate the auto-correlation index for a lag=1 autoCorrelation( sequence = "SDKEVDEVDAALSDLEITLE", lag = 1, - property = AA$Hydrophobicity$KyteDoolittle, + property = AAdata$Hydrophobicity$KyteDoolittle, center = TRUE ) # [1] -0.3519908 @@ -38,7 +38,7 @@ autoCorrelation( autoCorrelation( sequence = "SDKEVDEVDAALSDLEITLE", lag = 5, - property = AA$Hydrophobicity$KyteDoolittle, + property = AAdata$Hydrophobicity$KyteDoolittle, center = TRUE ) # [1] 0.001133553 diff --git a/man/autoCovariance.Rd b/man/autoCovariance.Rd index 8d62105..d555523 100644 --- a/man/autoCovariance.Rd +++ b/man/autoCovariance.Rd @@ -23,13 +23,13 @@ This function computes the Cruciani et al (2004) auto-corvariance index. The \co } \examples{ # Loading a property to evaluate its autocorrelation -data(AA) +data(AAdata) # Calculate the auto-covariance index for a lag=1 autoCovariance( sequence = "SDKEVDEVDAALSDLEITLE", lag = 1, - property = AA$Hydrophobicity$KyteDoolittle, + property = AAdata$Hydrophobicity$KyteDoolittle, center = TRUE ) # [1] -0.4140053 @@ -38,7 +38,7 @@ autoCovariance( autoCovariance( sequence = "SDKEVDEVDAALSDLEITLE", lag = 5, - property = AA$Hydrophobicity$KyteDoolittle, + property = AAdata$Hydrophobicity$KyteDoolittle, center = TRUE ) # [1] 0.001000336 diff --git a/man/crossCovariance.Rd b/man/crossCovariance.Rd index 1388ea9..cdc9d81 100644 --- a/man/crossCovariance.Rd +++ b/man/crossCovariance.Rd @@ -25,14 +25,14 @@ This function computes the Cruciani et al (2004) cross-covariance index. The lag } \examples{ # Loading a property to evaluate its autocorrelation -data(AA) +data(AAdata) # Calculate the cross-covariance index for a lag=1 crossCovariance( sequence = "SDKEVDEVDAALSDLEITLE", lag = 1, - property1 = AA$Hydrophobicity$KyteDoolittle, - property2 = AA$Hydrophobicity$Eisenberg, + property1 = AAdata$Hydrophobicity$KyteDoolittle, + property2 = AAdata$Hydrophobicity$Eisenberg, center = TRUE ) # [1] -0.3026609 @@ -41,8 +41,8 @@ crossCovariance( crossCovariance( sequence = "SDKEVDEVDAALSDLEITLE", lag = 5, - property1 = AA$Hydrophobicity$KyteDoolittle, - property2 = AA$Hydrophobicity$Eisenberg, + property1 = AAdata$Hydrophobicity$KyteDoolittle, + property2 = AAdata$Hydrophobicity$Eisenberg, center = TRUE ) # [1] 0.02598035 diff --git a/tests/doRUnit.R b/tests/doRUnit.R deleted file mode 100644 index b852597..0000000 --- a/tests/doRUnit.R +++ /dev/null @@ -1,62 +0,0 @@ -# taken from: -# http://rwiki.sciviews.org/doku.php?id=developers:runit - -## unit tests will not be done if RUnit is not available -if(require("RUnit", quietly=TRUE)) { - - ## --- Setup --- - - pkg <- "Peptides" # <-- Change to package name! - if(Sys.getenv("RCMDCHECK") == "FALSE") { - ## Path to unit tests for standalone running under Makefile (not R CMD check) - ## PKG/tests/../inst/unitTests - path <- file.path(getwd(), "..", "inst", "tests") - } else { - ## Path to unit tests for R CMD check - ## PKG.Rcheck/tests/../PKG/unitTests - path <- system.file(package=pkg, "tests") - } - cat("\nRunning unit tests\n") - print(list(pkg=pkg, getwd=getwd(), pathToUnitTests=path)) - - library(package=pkg, character.only=TRUE) - - ## If desired, load the name space to allow testing of private functions - ## if (is.element(pkg, loadedNamespaces())) - ## attach(loadNamespace(pkg), name=paste("namespace", pkg, sep=":"), pos=3) - ## - ## or simply call PKG:::myPrivateFunction() in tests - - ## --- Testing --- - - ## Define tests - testSuite <- defineTestSuite(name=paste(pkg, "unit testing"), - dirs=path) - ## Run - tests <- runTestSuite(testSuite) - - ## Default report name - pathReport <- file.path(path, "report") - - ## Report to stdout and text files - cat("------------------- UNIT TEST SUMMARY ---------------------\n\n") - printTextProtocol(tests, showDetails=FALSE) - printTextProtocol(tests, showDetails=FALSE, - fileName=paste(pathReport, "Summary.txt", sep="")) - printTextProtocol(tests, showDetails=TRUE, - fileName=paste(pathReport, ".txt", sep="")) - - ## Report to HTML file - printHTMLProtocol(tests, fileName=paste(pathReport, ".html", sep="")) - - ## Return stop() to cause R CMD check stop in case of - ## - failures i.e. FALSE to unit tests or - ## - errors i.e. R errors - tmp <- getErrors(tests) - if(tmp$nFail > 0 | tmp$nErr > 0) { - stop(paste("\n\nunit testing failed (#test failures: ", tmp$nFail, - ", #R errors: ", tmp$nErr, ")\n\n", sep="")) - } -} else { - warning("cannot run unit tests -- package RUnit is not available") -} diff --git a/tests/testthat.R b/tests/testthat.R new file mode 100644 index 0000000..46925b8 --- /dev/null +++ b/tests/testthat.R @@ -0,0 +1,4 @@ +library(testthat) +library(Peptides) + +test_check("Peptides") diff --git a/tests/testthat/test.aacomp.R b/tests/testthat/test.aacomp.R new file mode 100644 index 0000000..d8b94e5 --- /dev/null +++ b/tests/testthat/test.aacomp.R @@ -0,0 +1,29 @@ +# CHECK OUTPUT CLASS +test_that("aacomp function: output value should be a matrix",{ + expect_true(is.matrix(aacomp("QWGRRCCGWGPGRRYCVRWC")[[1]])) +}) + + +# COMPARED TO PEPSTATS +# http://emboss.bioinformatics.nl/cgi-bin/emboss/pepstats +# Property Residues Number Mole% +# Tiny (A+C+G+S+T) 8 40.000 +# Small (A+B+C+D+G+N+P+S+T+V) 10 50.000 +# Aliphatic (A+I+L+V) 1 5.000 +# Aromatic (F+H+W+Y) 4 20.000 +# Non-polar (A+C+F+G+I+L+M+P+V+W+Y) 14 70.000 +# Polar (D+E+H+K+N+Q+R+S+T+Z) 6 30.000 +# Charged (B+D+E+H+K+R+Z) 5 25.000 +# Basic (H+K+R) 5 25.000 +# Acidic (B+D+E+Z) 0 0.000 + +# CHECK VALUES +test_that("aacomp function: absolute frequencies are wrong",{ + expect_equal(aacomp("QWGRRCCGWGPGRRYCVRWC")[[1]][1:9],c(8,10,1,4,14,6,5,5,0)) +}) + +#CHECK PERCENTAGES +test_that("aacomp function: relative frequencies are wrong",{ + expect_equal(aacomp("QWGRRCCGWGPGRRYCVRWC")[[1]][10:18],c(40,50,5,20,70,30,25,25,0)) +}) + diff --git a/tests/testthat/test.aindex.R b/tests/testthat/test.aindex.R new file mode 100644 index 0000000..3cbd662 --- /dev/null +++ b/tests/testthat/test.aindex.R @@ -0,0 +1,15 @@ +# COMPARED TO ExPASy ALIPHATIC INDEX +# http://web.expasy.org/protparam/ + +# SEQUENCE: DAYAQWLKDGGPSSGRPPPS +# Aliphatic index: 29.50 + +# CHECK VALUES +test_that("aindex function: output value is wrong",{ + expect_equal(aindex(seq = "DAYAQWLKDGGPSSGRPPPS"),29.50) +}) + +# # CHECK OUTPUT CLASS +test_that("aindex function: output class is wrong",{ + expect_true(is.numeric(aindex(seq = "DAYAQWLKDGGPSSGRPPPS"))) +}) diff --git a/tests/testthat/test.boman.R b/tests/testthat/test.boman.R new file mode 100644 index 0000000..50a9a5c --- /dev/null +++ b/tests/testthat/test.boman.R @@ -0,0 +1,14 @@ +# COMPARED TO YADAMP DATABASE +# http://yadamp.unisa.it/showItem.aspx?yadampid=845&x=0,4373912 +# SEQUENCE: FLPVLAGLTPSIVPKLVCLLTKKC +# BOMAN INDEX -1.24 + +# CHECK VALUES +test_that("boman function: output value is wrong",{ + expect_equal(boman(seq = "FLPVLAGLTPSIVPKLVCLLTKKC"),-1.24, tolerance=0.01) +}) + +# CHECK OUTPUT CLASS +test_that("boman function: output class is wrong",{ + expect_true(is.numeric(boman(seq = "FLPVLAGLTPSIVPKLVCLLTKKC"))) +}) \ No newline at end of file diff --git a/tests/testthat/test.charge.R b/tests/testthat/test.charge.R new file mode 100644 index 0000000..0295f50 --- /dev/null +++ b/tests/testthat/test.charge.R @@ -0,0 +1,57 @@ +# COMPARED TO EMBOSS PEPSTATS +# http://emboss.bioinformatics.nl/cgi-bin/emboss/pepstats +# SEQUENCE: FLPVLAGLTPSIVPKLVCLLTKKC +# Charge = 3.0 +test_that("charge function: output value is wrong", { + expect_equal( + object = charge( + seq = "FLPVLAGLTPSIVPKLVCLLTKKC", + pH = 7, + pKscale = "EMBOSS" + ), + expected = 3.0, + tolerance = 0.1 + ) +}) + +# COMPARED TO YADAMP +# http://yadamp.unisa.it/showItem.aspx?yadampid=845&x=0,7055475 +# SEQUENCE: FLPVLAGLTPSIVPKLVCLLTKKC +test_that("charge function: output value is wrong", { + expect_equal( + object = charge( + seq = "FLPVLAGLTPSIVPKLVCLLTKKC", + pH = 5, + pKscale = "Lehninger" + ), + expected = 3.0, + tolerance = 0.1 + ) +}) +test_that("charge function: output value is wrong", { + expect_equal( + object = charge( + seq = "FLPVLAGLTPSIVPKLVCLLTKKC", + pH = 7, + pKscale = "Lehninger" + ), + expected = 2.9, + tolerance = 0.1 + ) +}) +test_that("charge function: output value is wrong", { + expect_equal( + object = charge( + seq = "FLPVLAGLTPSIVPKLVCLLTKKC", + pH = 9, + pKscale = "Lehninger" + ), + expected = 1.0, + tolerance = 0.1 + ) +}) + +# CHECK OUTPUT CLASS +test_that("charge function: output class is wrong",{ + expect_true(object = is.numeric(charge(seq = "FLPVLAGLTPSIVPKLVCLLTKKC",pH = 7,pKscale = "Bjellqvist"))) +}) \ No newline at end of file From 4dab4e0f58ed2508058676609f4449e343bae677 Mon Sep 17 00:00:00 2001 From: Daniel Osorio Date: Mon, 6 Mar 2017 20:00:49 -0500 Subject: [PATCH 21/50] Peptides 1.20.5 All test were migrated to testthat --- tests/testthat/test.hmoment.R | 21 +++++++++++++++++++++ tests/testthat/test.hydrophobicity.R | 14 ++++++++++++++ tests/testthat/test.instaindex.R | 15 +++++++++++++++ tests/testthat/test.lengthpep.R | 14 ++++++++++++++ tests/testthat/test.mw.R | 19 +++++++++++++++++++ tests/testthat/test.pI.R | 14 ++++++++++++++ 6 files changed, 97 insertions(+) create mode 100644 tests/testthat/test.hmoment.R create mode 100644 tests/testthat/test.hydrophobicity.R create mode 100644 tests/testthat/test.instaindex.R create mode 100644 tests/testthat/test.lengthpep.R create mode 100644 tests/testthat/test.mw.R create mode 100644 tests/testthat/test.pI.R diff --git a/tests/testthat/test.hmoment.R b/tests/testthat/test.hmoment.R new file mode 100644 index 0000000..92b50be --- /dev/null +++ b/tests/testthat/test.hmoment.R @@ -0,0 +1,21 @@ +# COMPARED TO EMBOSS:HMOMENT +# http://emboss.bioinformatics.nl/cgi-bin/emboss/hmoment +# SEQUENCE: FLPVLAGLTPSIVPKLVCLLTKKC +# ALPHA-HELIX 100º : 0.56 +# BETA-SHEET 160º : 0.25 + +# ALPHA HELIX VALUE +test_that("hmoment function: output value is wrong",{ + expect_equal(hmoment(seq = "FLPVLAGLTPSIVPKLVCLLTKKC",angle = 100,window = 11), 0.520,tolerance = 0.01) +}) + +# BETA SHEET VALUE +test_that("hmoment function: output value is wrong",{ + expect_equal(hmoment(seq = "FLPVLAGLTPSIVPKLVCLLTKKC",angle = 160,window = 11), 0.271,tolerance = 0.01) +}) + + +# CHECK OUTPUT CLASS +test_that("hmoment function: output class is wrong",{ + expect_true(is.numeric(hmoment(seq = "FLPVLAGLTPSIVPKLVCLLTKKC",angle = 100))) +}) \ No newline at end of file diff --git a/tests/testthat/test.hydrophobicity.R b/tests/testthat/test.hydrophobicity.R new file mode 100644 index 0000000..e486d64 --- /dev/null +++ b/tests/testthat/test.hydrophobicity.R @@ -0,0 +1,14 @@ +# COMPARED TO GRAVY Grand average of hydropathicity (GRAVY) ExPASy +# http://web.expasy.org/cgi-bin/protparam/protparam +# SEQUENCE: QWGRRCCGWGPGRRYCVRWC +# GRAVY: -0.950 + +# CHECK GRAVY VALUE +test_that("hidrophobicity function: the computed value is wrong",{ + expect_equal(hydrophobicity(seq = "QWGRRCCGWGPGRRYCVRWC",scale = "Kyte"),-0.950) +}) + +# CHECK OUTPUT CLASS +test_that("hidrophobicity function: the computed value is wrong",{ + expect_true(is.numeric(hydrophobicity(seq = "QWGRRCCGWGPGRRYCVRWC", scale = "Kyte" ))) +}) diff --git a/tests/testthat/test.instaindex.R b/tests/testthat/test.instaindex.R new file mode 100644 index 0000000..145cc6d --- /dev/null +++ b/tests/testthat/test.instaindex.R @@ -0,0 +1,15 @@ +# COMPARED TO ExPASy INSTAINDEX +# http://web.expasy.org/protparam/ +# SEQUENCE: QWGRRCCGWGPGRRYCVRWC +# The instability index (II) is computed to be 83.68 + + +# CHECK INSTAINDEX VALUE +test_that("instaindex function: the computed value is wrong",{ + expect_equal(instaindex(seq = "QWGRRCCGWGPGRRYCVRWC"), 83.68) +}) + +# CHECK OUTPUT CLASS +test_that("instaindex function: the output class is wrong",{ + expect_true(is.numeric(instaindex(seq = "QWGRRCCGWGPGRRYCVRWC"))) +}) \ No newline at end of file diff --git a/tests/testthat/test.lengthpep.R b/tests/testthat/test.lengthpep.R new file mode 100644 index 0000000..c67e105 --- /dev/null +++ b/tests/testthat/test.lengthpep.R @@ -0,0 +1,14 @@ +# COMPARED TO ExPASy ProtParam +# http://web.expasy.org/protparam +# SEQUENCE: QWGRRCCGWGPGRRYCVRWC +# Number of amino acids: 20 + +# CHECK VALUE +test_that("lengthpep function: the computed value is wrong",{ + expect_equal(lengthpep(seq = "QWGRRCCGWGPGRRYCVRWC"),20) +}) + +# CHECK OUTPUT CLASS +test_that("lengthpep function: the output class is wrong",{ + expect_true(is.numeric(lengthpep(seq = "QWGRRCCGWGPGRRYCVRWC"))) +}) diff --git a/tests/testthat/test.mw.R b/tests/testthat/test.mw.R new file mode 100644 index 0000000..c70b4bd --- /dev/null +++ b/tests/testthat/test.mw.R @@ -0,0 +1,19 @@ +# COMPARED TO ExPASy Compute pI/Mw tool +# http://web.expasy.org/compute_pi/ +# SEQUENCE: QWGRRCCGWGPGRRYCVRWC +# AVERAGE: 2485.91 - MONOISOTOPIC: 2484.12 + +# CHECK MW VALUE - AVERAGE +test_that("mw function: the computed value is wrong",{ + expect_equal(object = mw(seq = "QWGRRCCGWGPGRRYCVRWC",monoisotopic = FALSE), expected = 2485.91, tolerance= 0.01) +}) + +# CHECK MW VALUE - MONOISOTOPIC +test_that("mw function: the computed value is wrong",{ + expect_equal(object = mw(seq = "QWGRRCCGWGPGRRYCVRWC",monoisotopic = TRUE), expected = 2484.12, tolerance= 0.01) +}) + +# CHECK OUTPUT CLASS +test_that("mw function: the output class is wrong",{ + expect_true(object = is.numeric(mw(seq = "QWGRRCCGWGPGRRYCVRWC"))) +}) diff --git a/tests/testthat/test.pI.R b/tests/testthat/test.pI.R new file mode 100644 index 0000000..9cd3777 --- /dev/null +++ b/tests/testthat/test.pI.R @@ -0,0 +1,14 @@ +# COMPARED TO ExPASy ProtParam +# http://web.expasy.org/cgi-bin/protparam/protparam +# SEQUENCE: QWGRRCCGWGPGRRYCVRWC +# Theoretical pI: 9.88 + +# CHECK pI VALUE +test_that("pI function: the computed value is wrong",{ + expect_equal(object = pI(seq = "QWGRRCCGWGPGRRYCVRWC",pKscale = "Bjellqvist"),expected = 9.88, tolerance = 0.01) +}) + +# CHECK OUTPUT CLASS +test_that("pI function: the output class is wrong",{ + expect_true(object = is.numeric(pI(seq = "QWGRRCCGWGPGRRYCVRWC",pKscale = "Bjellqvist"))) +}) From 262095c9637b7b91b2a99e4c46c50729e1b550e8 Mon Sep 17 00:00:00 2001 From: Daniel Osorio Date: Mon, 6 Mar 2017 21:12:31 -0500 Subject: [PATCH 22/50] Peptides 1.20.6 Minor changes in NEWS and README --- NEWS.md | 14 ++++++++++++++ README.md | 2 +- 2 files changed, 15 insertions(+), 1 deletion(-) diff --git a/NEWS.md b/NEWS.md index 391992b..768b31a 100644 --- a/NEWS.md +++ b/NEWS.md @@ -1,5 +1,19 @@ NEWS ==== +**Peptides v.1.20.X** + +* All datasets were unified into AAdata + +* zScales function was added + +* All test were migrated to testthat + +* fasgaiVectors function was added + +**Peptides v.1.2.2** + +* crucianiProperties function was added. + **Peptides v.1.2.1** * Four new functions were added: autoCorrelation, autoCovariance, crossCovariance and crucianiProperties diff --git a/README.md b/README.md index 87586e4..9fa97a9 100755 --- a/README.md +++ b/README.md @@ -1,6 +1,6 @@ Peptides ======== -R package to calculate indices and theoretical physicochemical properties of peptides and protein sequences. Include also the option to read and plot output files from the GROMACS molecular dynamics package. +R package to calculate several physicochemical properties and indices for amino-acid sequences as well as to read and plot 'XVG' output files from the 'GROMACS' molecular dynamics package Install ------- From faf986a571e3226b0256041c1f7690b0e38c8fa7 Mon Sep 17 00:00:00 2001 From: Daniel Osorio Date: Tue, 7 Mar 2017 19:14:10 -0500 Subject: [PATCH 23/50] Peptides 1.20.7 T-scales were added to AAdata --- R/sysdata.rda | Bin 7482 -> 7797 bytes 1 file changed, 0 insertions(+), 0 deletions(-) diff --git a/R/sysdata.rda b/R/sysdata.rda index bb2f75c0dc2d8f70b780f8a53578e1d595dfaf6f..542979b6a1a3c05ecf57b237213ad12767d59951 100644 GIT binary patch literal 7797 zcmV-*9*W@~iwFP!000001MOXRSQJ;gUy3woDq?Sl*s)-XZ3Yprpi&f!G3o-Vtgb9B zpxAqlk{C6LMv26zu_cz+ov~wYV8I5cARz;?UTz;vWNA=6@pN|AS_qbKz+33-& zMWfNW1EH|-QJ>7kO@zDmE&7DT-RDxHbr*y*ZFS?LLgHC%#W{jTSTrNWbD!Nz-e{kl z_J~T+NCKJ51=z;A$9=hiIBml}3a_<~%}5cFv~RKK!y8NOa36G!+i@jQI}-SY<$8nn z^Tj%VnUL?3aOIxpV3@+?O87IOe+oQ))!yavhMwmQq<-Mu1GhX3hCB&ZUMBS`SC04W zLVuv-tD*iQ+ApN{>Kop_x&LrQT*&ae(UqH(^-T!3d5>8qr;O>`OW=6RHgL$D+@HCh zjO%_IadIM;ti2qS$X$?d;j-IX`&V3I<(-DQ2DtR^4`^$+9JHS%F02{)-74;0@gs*@ zFUN6@B_+eX(KS1ldxL&?P0CH*@P>S+L9X6FKB-<(D;C^al*!Nw8IW&0C%lv7Q}_V6 z#`q9kLO;Eio)a#h|B@uR=k7pX<>UDx=$Tg}0eXh_WobMMm@I{4=~oIgS$;%4^ssHHhJqA-VY$JnD@BT(BJ2vPwDrQzP-}IIb zN^&O}Ll3-yoWB8%#2+%jAJV1%;GRO>*?b9plY{5ce;nkP%Lm?=9|Y)efp|Fa9g_E4 z{nX#YBluP*YrzPIu`NQ5$(ZMxVm#!a-VAyL#=2;N`3QBpl3&qEl2frJ z@CL7D`W)j)w7@vZfq%i0-k@K2bMTYU?__dEya9Sx0Dq%-j?myl;wR8QC3qh50EhnI zN^xI0^vI9UGteKrA=;z<&X?v@y~CU2jmk9QVK|50;8G>|m;K2fZwh^6gn5?qH#rUA zAK{svz;*C-(o4Ka<$lvUyva`dD2->D2WgxOML5rfetnJm5@Dw&OE?MO%L4H~*qcJJ z#Op*Ect<+%KFB-lDB_=_--H6`T;K2}yhy%iKBIG*7pvCOAH$n?U}*!kd8akUs_`Z!OjH)$n|o zRIhhC4~SOK!{(4n@Dw`dYfAU=)@a8T{Q_RigO?M}X5)y)4f$_r zeznz8{!R8Y}|bpSz9ws`#}SFU0&<)vwL`-(=SpWByG+d(bQT zhBxsLt{Aw(-edlZ6qIC-Bd);WKE$&r&IY_#|Bzmy>lD|>0q)eFr2nZtSwHy+^XJth zJyN-3`lL!d;}w6VPi)XHRrLw{2jtIX`h@0Xeb*<+z^N)91kS(XgH?Flzsm<%-01%( zALLu>0t-|4mePF1JArSsI4JRr_Wg8vgKvpAe9KEZy~DSX5-Ipr@T+tPke+J~yq&;H z+Ts3o=vSvxQvQQeq{LTR$|e6zTeQ~(@9!{4FZl^y8+h3QA1maMSmL}1N^9^rEAYM= z;Bk~Z)NH53=bEDb$i8nTDGc7hMmKS?c5J12l&^vF#_*%mk?dE#v3~kbcv)qA$v1=? zQqmO0KVKL1O@OyO?#J_DQ|Y=$NmIBkqFq)`@2ijY>~J0LBfd!fTYbZu**WBwrZ@uS zMFAfc-^`#m0Qv)dL*5)bq#XW6;xpubL41eBKjA+S4uMye!VW6LxIz3w-|!aeL*538 zlDu`PC*kbIOY+(j*E>P3U7cXhpuRQcxi*mRmXPCqkkfW3JD`8SOKAQS;fWNRpnpx# zUJL!?Clps;c?j_PaVH^f@YAvSTfi+B_9OA|cf`+;Cv>EWe8ZlhJO`FPgt!^w-Q<5P z)Khz&;*k_*guO>`O)d*K(K(ff8!&r`^3X^>k-wGB={miK>>#pp=sv`!DUPpqcq1Mz z+CYE94=!3${6&&G#-mLu>u>U-aAm*`rAU4$#A|p%oWmX!@+qz)wZj`!86O4usZYq> z5D>o+vdC`)xkdhz067;B=Mvy2WOx@qA5^){T zYpu~v5!z2ie*#wl@k`=~6n_>_>KooH-a`3-#KXzXsfX*A$^Ia{fqL>U)c{|tPk!{u z{&T)DN&~cy_>G8jp7>xxytj^?+B@aQ6LFEov)EjcQ?Z3a9B5t>9gvUW2t151FFLN! zJ3gvb%DT||u$%M_Z{oXDlHMl0`>t|+Cg~X# zPa`|j41Nz|@Q`BC>*SAxd{;yL8R%=`IO~L0&^-Z5t`W;TVXyzKI4pwNCp*Xj2 z4b;d(PS^EtBF*p`e_u3a0O~i+~nbMjS^?3ZXxQ3 z5TzWaMs7-a(#%agO&;pv+@;cacjvA+H+NTtD?$SmnhA7+d*}p(YO0Rupm~5=HC_=KtY8(Rl#?ebG}@-6L9AT~ zX~ZTgO5TD~fqPv!Nu5Y4mkqMTl2eWcqDm|5loA1V5D(aY`~0%8^D+P1I|u?$TcN>pkLYZ)UQMa z&-{hXqJIS5m41g2DLZfPPM;1te>!ye7iDC@1_xGvu$4z-F#ud<$q|?oS;xu^T4BR7 z7O-N6RuHp{E0(d0!BEu_#GoS!lPpmEVHUufJPq)elJK(3VOmK^LQjLGymH1QWs=D7 z$0iY4N%j`~K^dCxpi*R=A`-+L$pY0oyvc(MPq9GqOqnFGlvxI9G2|92@R+9vOqY}q zyH3jdK1F6=`BSD(KKg+?vl$c-($CD1|Idv2593WM#()ovf96rexaQc(VCZ`yFC_0o zeu#WxMFUUzh2{s4P?n*Mc7!}>zF_(&nU3@fZ;GtYP7WX&6dB`9Nu$F%YqdYt-~_&nW@$PIaH^#|`tzrz9-Z9)_(Wt4NEA~e`JOrsc2)#1uug>z7d zTp8*duAD&*x*Ce82(4c&*f~5x^RM??hfELFsKY|kfyy9d1bO~!gVm9ND#hW;=CIP^3nq2n|v=%T-|^a%YW#+pN_CK-g$y~q6-qj{gq?zf7j;&e%GZjwnIiABJ@4w^I zv8fyTbXs>#`H3y?iLI-AI>q~%N#}nH>PT5-DX{oNhB{JQTOp;@u{o9oBgLe-97|&V zhEGR!E>;=+?$cXVDe2QG3W(_6-}&j*a8vzvpWXrjMY{_&mErF{|LIJ_prkby^&sPp z_{6Fj<{vOj|EC(J>M;EWd^%~E8u%0{NyGe^UjI8k{SRMd(Ql$crJ6ET8BVb;lm7B) zpQ2kP?nC+w^P`F1+)EJ>S~2CZ=1qoF%!6{8f=zwZ!P6?5qfttMq*(}<^OvZ*q zM5igChBgKy_ckStFq#ZAS~S3vVS@!XMo8?a_7|Gj{~)}{T%d(>9Kt5tN64|YR4*W5 znz@hQW+wavn03NCB-|LG-^dKd#zhsVn?0XkqbNO!j8JiKFz)+pPW*2bo<&0`MXNeRV(`oIgU>{)ZcnqC^)}q`*Xkd z+}ny;w{`O=BSk1&H{Yb<7U2q{oq|B`wY%-^DrISwMcUnV6FzcpMrrreZOP^5YxnIv zBP3Z4JU*r?Cp^RK5sT+C4W$c-y4`pqg~DOadIgVaq(4p)O7GL{UR;xVAmJlq1CPfO zwHT$IA-1Jn4BZReO6$I#;;7`{0W^a=1Iv{h~~& z7cwh4b!z+}7GyYxe#(qEseLn-qNh$k$TOF$gTq^R6s!|SA@!H0S_v154t+M#HgKr$ z)6%wD2^8)Frw?x*Rlntvbut z{k3wx=^fsb42xt6mgGsv4M+xL*D2|i0qUBYBj0 z@pAPu8ICu^_@$K%6r87|L+AsxO#!@Kyan*4q&7;*pv-lu&!`gI$FfCjP^EXpHH9WZ z$rc}3P13D4@{k8bs5Mk+7)C$XbcSD$T*dA-@o@F?bR~RDBXE&@4*L(lES-Jjp~33O z&fyA0u=X_-jcO_`e_L_f-FL#aI?)fa8*gg&bHC;qfg4!ev)kj7fmS8+(+vV2&Fb~2 zphN8GYu$^!%AK*I>DJEj@%@r!Y&S?M4%}V-Vw6E>af7*E{PNi6Z1TceGmmluHmw$4 zBrjXN<7&sABNCqUyV&sgu^dH`hj&3lqi@Fy3JgBb$bLm1(|Zl`xI;JE@Ubtlmz6h* zj>!7Ou6FA|ne%t5w-1f*o!9MnuSU&BtSp;&G3}=7mfb7I*|^xQn0M5D@P)V!;VF5& z+U{MtVDFNs`XKJ*7N@9xYe`1t3UgF@8e~g6Bc>;EKd2QM6A2;$(e2SRqaY63&zyw`m95nl&^PO zwi^DeXCp4L%Z&z(4Xr;vwIb}Zpyi+UH~B8@S*da33FnZePDMRlT zn~grPCg1a1?Da=Yb~%>X&sg5R`q$OJ>p17f3)Ozg-zlDT{?cs64O@S&tS+(>h;aM{kWy8EqhGaI46H>@r)mz_T6^4tB*zF@n-Qi4-E5Ly1U%#@K%HK zW=?samQQr@33{NrVL*Jw3}e;9_iC#XQ@+f_afl-m@|03@hhK(pYK1N+|j-F;vLCh&QBBfjPP5^AHDtH>n}E6|JZg` ze9u&~$e!((o7W#F<6jklJyb9!|v|5)iaFV#)&9Idl2#^%YXFOr`r2lme$J=AG~ zVdsp=1AcqxM-#J^phhEXj4RQOB@hzsUTBr}nt*{kiSg9WmmX7B+qJXWg@% zSJ>^*!V{To49*NaJg`<^Z?du1Ubi@&>-(Z+$%cr6xnJha?AX4eXG~wkg-Pe!RW`#@W6E8(HpzN< zvi6*dv2|z0WX5f3H}~QgU*Bh$yEnPNntsT)!?TTte2x#upLO8O(wP}0TX#n6h#ynk zeDzlkF6_UvBBInMd_Zhe@b*(d4gG6e8gDSc@>+`7SFL>($8V4PI%|H`>I*aa6yA;< z_hwPrRP!K@m+yzBf4e2AN6hV^y{GsZnLcRs^hwObHIW~(Z+^(Ux!hp-)-ma^D-LY9 zVwKY|Sds2AtZRb_Qziz@>HFpO=sQhr?Y2H#wyb{Uq{PLKqvp6-)hi#lyWO()yBkm6 z*!bCqt&1ZvJ6?*p0pY8(K%6pJXpAIGK7R zC{7i2_gegN$AYi7hp&n8j=$7tO`Gnk67E}e$t-Jj*XiZLxHZ=nHS&4=xo!Kmor>d* z7mbct>{#g8zt~bdKh9>-*&(&N8qYhlv4M-PZE@pWDU&mz2lvjHA02PG!G4MNlArto zp1RMH7eD*9V4O+*i@l=8>e%*6Uxc)tlx^qf(;z^;W?fS+`Je8gi z9DT_?j`y@`dZ+uW8Y@1G%X%BqInS^5;INoI5ia#Y2kn@f+@`O$Dq-*1)(JP?Jhxgs zIUqW2?W5PRdxE365hq>^zFJ?NJIwvU;Z04ljeLe5?>TB!v`glm#BMVZOdbb1e08-+ zBm4R`%_gl2@;0`a5O14)OF94Atk(r2I}T8{+v|Jj4cGbJB>DH+jT)up=E@{+jCGrHy6Sl6m{V)?l8J9Z%t9G>QkZ83Y` z!sStyPt@6baCg7f2HkAK=I1#)>eX|OA!lE|+r51sKc+o$pU^1tes!yw=NkBadDCRs z${Pnh56t?pk(?VptwXQH{=R(wz&1U4{QSPzBsa%_5o^{&w{Bt+a`F1sZn^D8Tsbth z`KJ-uH0qhaI7}JFJOSmcJcer+s}-mr=^g{%!0Q z-b@)N-!^B%HkTi+<>sC%-n^rx>4INhj@V&g+pvz0{d=1{$LJ&3Lzlg4YjrX0#>T0A z=EWxs@!H*P_KL_=3jd@9OzDU9z-U*R#CIwQT`)vaX*ww`X6q`06dsH4bd{xYOLJV@^2TYkS~vxB0@U zr&r2uZvDQa|GJ*nA4c>{P^|KOkQClqjM`-8-7UYZvgN8d3)A{^ynpjYhtQ;^&6;m~ zbNPKyz=CbdOm06IXqIo)#7 zEXSceQ^#&ve)0I5dHF>tJ_qh>$#h(FF1+38)@Ln0WZV-6CQR7>*+cJUt%42=w!L6n zRK9t{(J8-fFKg|4BqQs9pKN%_HRW$B<=>d~wEi_JYRdM7YwJAhF{bXeO|#D$jhUA; z)9$hTw2a)xQ7$J7YecQyYFwCFo|hJ|I5m5PY8Fhuejoww~NDZzqo^A;5DPf9n~_X2i-nXODJ8@>0ph~e#;vfHwXzTRahLh4&L^&y3EF8%lxQQ z*;5lIebwdM`WWYeRqYe(`;1JOvLV{d!B~;Vjckw><+khUT!-{_cR#;u71d<%+s95X z$4_b9{O~J}?rGjDzlkeqAM;>uGxgf|jngKZKQlae%wN%d_^P(wn6)a%+cgcHc>26zHpZH~l%$|MNwP%81+z!|E6GBctdtZ1hqxZgb9<2hjeDA*iTL<@l H(slp{zhHk{P5~P$>$=70=A5!ILR=S<}t_1|6A3g_k9)PK>e9gg<6zXbQS zLHlj_cG-rw&luOu`1@Hq+-HmPHuUCNzs5i=o+b&aDOjmL9+f)IRPdp~NGiBe!G#Lm zRB)q$2Ni};VJHB5nSLTHVhUrWpkG~-FFM-Ez>btz((etbh-w(`3;8ujeP{iZPiuitIs_~xv=nouO z1Jr*;`=#_=ZNvK?Za?2rEfMg%*PEG}w?2f~amcubL(VKF12{gg3K)@4c!2puzsbh% z^HZ2q_2tMU<{FO+li$_CujZ0)OlYBLfXVvln7W23K>L}hB@N_1u4NvVKev03F^Ngx zl??Mv)9eD~9s1=hDK~Ay8}gkAxq1irq|tehPWTyvJOG{=NczO241<^$o~5$vw#{>3`A> zJJHUwIylnvcc3@!VxD-Y5$hqsdwDS*qIGz0;&JAZX&i$;6!1re&Pl$Dcs{}90LKTo zuTl+Phcbq)gLepeyA;o#;_>F7pXhx|1<#L|LiAq|ucx#QZ^HQ_j~7<}{7Fv}Z_5WC zd_p{p|5ND#SHc@)T_r+2_z6=1ewoY93)~yLhx+RS@TT{c@^Y_rct3_7{mA3Ty$65R z!MM)GJeSAI9S1%~cyn){KdPV)fH(IMIAUBd70@Hpe{Xnw!jT?<{4-C{Z(7R-dAU>R zLl0y_&fft?;t#pt4_SPFFfSqR!h8vSQ-J5ue+=Z9DF)t{A2{f7j(9ln9g_D#?bP4I zBiIf&HiQulV_O9|CS#tp#ds({y)pC(jCGYE?rX!hr>e)dr!ohw#D_4y3Oo=zhD<@Fu)SzGyz9bD9_H*3+MWH}SyA+VV>Fze>OMbIc>? zoo99CRo&YBRNL?temBV@;Yap4c%k6$z)^UP#s}5c!N0CO&((R3LqFEVpZo(_hj%X7 zeZUv?HUqyN@e)BUGvMzaobfzs0{yH5eentQ_Tg3Vxrex~j$cdQg_s}f`n3iBH`(>&n19pI9`uT~ z;Y~b*DF^Pb_XK}N8jfU-Bd#FCeTZjMoDFyh{X=?*u2Wp20Ju|slK!XqRPE#^f5{e{{i`P1${#EvbO7!RNz#X4+7`k@xeO0?%(BuLfq*8 zC?8}yY61(>+4lT=#X5j*v^&o8jjn?=dV_6`IDGpX8ok4I;1em>4)CjV^XH%I3cMY_ zOS<6xF6dW>3w-{ALj=!P+KYMrO=q;%3GeSVRV(=k+X#4B0UvYZk(lAUHI5eGbLQZE z^}*vPd8o}kp3m8$|H!^?!z&Ed&QddR3hh|&^C(*%=dIvJY0TTNY%A^bpRl6Z`jTw{ zIi#d1jDNNX>RSVE8{CiQRkr+f6(vpKx(e+I_4K}GXwMqg@jl{<(!LU*@flh)fU%#K(3t~V9%hwBj&kIkni@8y$ zYlQaNX(vCSxPp*}0KXq|9`Xi1olyS(xD~>FBp&{O_&M@~PSufb*fW&pAmk4rZYJ<< z@;{bpsXb5eNQyJU-lMoClLwsWoQ{Ya2=)@?p^<(fe=D8Sb$SokL1gF9eTYv}9AE43 zMm$_)3H=Q}xXOa!FTC6dJld$X{w6;PQw98RRFPi_@fuba=dee)Vu~yA?XWs^#z%>E z>JzdzIK*$bJn|bsZjnF5LC!hExj6U<1-wh359(ZJ3LvkaF%Q3jKLvgQ4*nM*{|f#@ z8dute_aEj%kpBI5^C6Ir{6EfzsMJpR7V@+yub$$>$m0?66)=AadG}SYM~$J6jNrG1 z|Bn^HUu%JO%Fuo)`V+Wvh+h&CfOgPH&9RhrTXBD z&B%{l+keis!chn9BYva8IZJ%71>W0OOYNO%jN$-BB zou5g1Mu?}89cm1}hdy{nIq7xs$3nghP=5*fn)o>KU|1vY`ATimC$)Zu11=gn2PlFh zN~s*@rp^IMafo=Dr$m7o17~HhB8)B%mWczWj!;C%f`pm~nQX99A_@JQ743Q}5GmJeHvY@b}j|ics%!khkm$)hvGHH0YOn|~uGNb04UOPf87tavOzI^fs z=`8VV@l0yZ&`YeGDp3-$UJAK9B5bC38hv*?FQqsjL_Afj6q?ZU5mQI$`zVAyFjAMl zU}NArQzD_yFd8kEPgW?Y8;txVGMQ9PARGEiWnl_>(8OOMn=FwBNrZ}V(rMEqN_Erx zAXcx0)DtEvO5TD~fq7dyNu5Y4lMk{bB(Gx75(&n2A*mIU5r_5!GDoC~lHrNW(W10R zwT+NJWiSh4SQyoR9XTN5m4c?}zz2(#I0XGTC^>;lP=63fBN9uCIL_2LuS1rFejp`{ z_Jrj7=YOIx{Wrp!JK&HOSjJ$eYYAe|k%dVXsP-@m;7y(ecuYxnh0I}ENl8LagQdE5 z#w2Bui0~&&BD9k1J^F((G~q#|$T~$Nh&hr4s&#mi2N|AXj^vp#Nnj}p8K~uuTdcqn zJVju-q>O~?q|BdCWCoT$W%?AOAILMCLlGhE%pCdu%&7lmylKT4@S*W9cvLa28DV8G z^gWRml6N9ML_V>ifhGMy^8-kzkfDusxFUYO5cE+hm9z|RimcF14j>y88DsSz|L|-R z*(MUnUmO2N=1O$*pa86E2J}Z$iE);w{J}_y_I$K>8j# z7jc!4%e*=}J%ImkDYWt$dYt-~_&nW@$PIaHwFmE7zrz$4Ekh(SX{2L-L>}ZAs+3Ho z>M&`L#4#{LER{QkNoSLTuD&EPT@-B2>fmYeyFPdQU7rv6UB~*=?JNDj(Sj#cU#>2H87d~MEld?l`g9yAX|P@0Pseo= zJcmWzf5oR`Q#aw$Y27*HC$_^UcC7R16z^-ppZ_JOBV|=cfyE~Zs3XO-15#S;+hS=j zQcT*4u_X2{_;h6FVwKVFKD~XNBYiqW0TKQCD?i-=ZmR$4)7wFyXm>$d5&r)7KV8r; zIMSMnrjT)ad}3V<^EVi#|6L7JcbNVSKAkj7eS8WXNyGe+UjHjU{a?Pybnq03Og4Rn zG>l?jhOXk7U!q%vZX*Vd@}-I2#8VO?ubJ|M<_$;G%!6W@f{lC>K{IQbqf=k0OeRq( zgj0n~G3`sszTwJQ0<7w3(?FobFuPbYBt{!!yjdc)K;~X0U^OQ9G9?-y@xT%Z2le?Q ztIN|bl_4dv!;JwtO$iE=aHFb^1(Vp=Ql&AZuF4YVeluK*?%Lv$y}g?a}2^J z%xB241z*o0VOnq>!Ocwgb1>_;4@kJtL%)$3j*W{LB$koegDa$%8O9OZOSGYsw&6{& zKVe}7a8O|*TfuFL4aii+Fw+oLp&3fp(3af!z+I4QN|b>)$(6xPhj1BN4{kiTsVGLT zZFp1SvaoR{+{}VrrHyIfw%{H>-YFJ*s(k#o=yX_`^X5Nic z@2lIMDK1v;+k1&iHXC|<`q9h1nwp&*kd!7m_r)@kVf^qh1XN8rM>LoFtUqr`f%@ z0rQl{hsy^ZDO1!P@sQ!+ZO%LeE@k}o#ws0bL;M2Q)6|bwl`uv8^Gv$>_KGZ~bXDKs z*W(J91pa=Nh_B~zYdUpC{0Sk*a2)-V8-8B>W+qKboq&*MCRGE67xz3!BamGBueNFl z=gLleHP$L%B=^gT&T0wdo&cv$7#CaByFAbT#N@p8{c!JDV%-E>A7q?{{+1nr`}vQ(>H>^XE*G zM%<@ySjNV^jC-$!nknGNm)7CUi}7gg0PslDsEaV}0WY^)jv7VVYr^(&noZ1|S8;`4 zGhRG?+)W$x02oGkg}bIvQwnA-wpCxrx5rvs*8s}=43>2PdYyupZz*X)JM}j?^H~GP z*=w+qO3Zhu*mnLI@F;nv0hTNB)9gdf5U$VF>cnORcNzMi2>R&(GCn~Cg0gz92l-pQl)Mv{dA+*zJX$yaJQkmv#*Eq&@b;7 z{?8FJM<1~~NHNVZOd<(Vw_DSSvgY!}nsQ&C;N6X*p5?dN-sQmHwn~l}TF;|T%J~5E zibYvE0ng_ScwW*i=Hi{cW#1RhUTwRpr+D(<*8*A?>{E-#o+5LUY{wDB)fZ+gty!{VOT)Wv6eQg2N^wXQN*0M z*NKgJlfSaMO;mW^uhxw^4$ED%PqBAoxX;2qX9u)wJ7!JQl`Tn&Fr{^hMtic#C?y%$?K=-Wla z=tj*PKYiq*a^vymHWYhYiMji{^?v(Go7toqg>@?}=6GwU~f+x+5*<+Jy^{CfAv-rlCICL71!KQ_vD z#ldRNle=`T8atfx+^Z|O(Nem#VQSjwpBC*rwPm=}nK_klg!R#l%iU(!<67X9tmMV+ zJ5@h8eZBI^?^i~b+Eo$gm=Gvl@0^lT2H(@$GT`$L=q#NSF!EHV3VbO zfzB?`O}Q7Q*&a_;E;tzRJ|$2B?mRcXf4Xr*|Bs`TicKr;w8-0ZZ$^%ti*(CG#ZN~Qw`{T9mwd=Od`kar&es-L zL_Z3@;go#zgnzrtkHMW?2E?ujSh=;;uBt8$*$;}(RIblZ*e0BAd?ecP#f5KEUrC3$ z7LFh3uvNEb&a@%_c;@ZWXK_rLykx<5g>$-h?d}o%wdC5=D{eB&(dp6E z&bwOYWt?v`|9VW5InlYX+q*2dKEcQ5Rqny z@VNL1^-R`%|Mc3?gw^4d-eE&xB7^o`2yEe3|HfpUV6!`E#@~1JUKYPM;)lFNdF!st z9#r};X41Q*nKMiR-7`Lp%-Xm!xnK0dkprju=ovlj@bX3UlnoJ|^6!7jy}wFl)~*Rz zF{_Vly=7j|JxG$}KB{-~;OSEW=YRd(-l&Au4-Q(KtXkPDcWTnIl*sum=1r@|9_+I6 zNW|@525_<2jYYU5rt5a>b z#plyc1;)xkAKi&xWnc2c-mnePUhy}2Z0OW?ZQ>KNUb$6m9yw$ziQRB#X-n_7-&l2h z-=jSCY}xqeW%i{WuH|N`tCK9JULMh?xBkKt+nPK1Se3WhpEfNgYWTpMMN#o)TWywm zE&s*O|E1eparvu_C6f$`-yBvc&Cl$;@oh-Qsrl9(-p&2R8#dc|+O)UHFOKnNx`Zx| zdL7bUoVDe}ntErN7jhFeSk5 z``fKs+BCClGj(&Im%e3iyj9i%>7qMx-FOCQH3 zcG#Y1eEPe-A<_?TUJf~~H@{Ey6vLtsMfPmys{war_bIryxkIC*>PgiJ)*(;rUKUJj zH*e^YRgpK(HQsUj;NXrreXK$k71=!>(0{%zW7Dk9<0GFxXFhieZkhX}o_T{S&3(SR zZ@6;Jy<^`5}~VWvdBK_RQ|}7A3B>~&%C#7 z#-N4q$s;@ucA2+2V(k+D_6=W~_1Tb~?6k1K%a`%tcAh3WvyXo_DDptTurAk+=B6s& zZ1GCW+xcTtZ-*OZmYe%mx4yI6zj5B(OIHpZF^I3%{z|KWHYq(8%$RV_;c@3+W3N8Nou%#9&R>!_sQZ)qd+g-Nwr$#O zdw26=ng8P5D-9n$9cxtIIn1~BmUBD$nf|=jCOxB<$B&`*P3Bb;E#2mFb?C;M-_0_c zI@f+=|MZF5S6x5*Zeej*n)k7Uow@c)uY`5E*zvO2r<}*Cp^3pqzk24?rbFPd;a1o5 z%c^&bIX(Tiy;U83PUYks^A(LwyCeO_8u5DL{uaMQMo!Y_~lW$F2=MYDP@9y=qV>)eEvcbl%>WBqc$*E@bT zyWaP!rGA(E7L5E}nLRS$!#11Bo3kU@|Fk`R_xMijr7vCHYtgOL4QAWV zhdSLj8DDYeE3Xxf+Z`~%};oq z8QZ$wJlEyhn;b0fc;xD(&BcR9iC2s|I4$q$!R(_qXYUio=5K6RW`87JR$ehS`+cP} zBdV=W>(@uGk9uQzppsc~ulMmOPQwg>JX$V_PYZm}bDncZ?Cm`P`}4lN`13lQzOtV@ z*XR|Oce4+;qn8wCkTWar;iZOLyP(c)l$ECNMNPJ^rS`5?gNS{OT(RuA}{36 zNSgY6uPa-k9ZS}BO|%&_HgWpaC>J|@NfI-*d1j=`{@V-evbsF_=B9aM>t*j#95N

c+-7ZwU@L|LSAuot%M3HoJH5SM$C90C8jl^hIv~ E0D$s9$^ZZW From 3ee8b69d41cbf986a1fdbfd80012561178b4ead5 Mon Sep 17 00:00:00 2001 From: Daniel Osorio Date: Wed, 8 Mar 2017 09:01:15 -0500 Subject: [PATCH 24/50] Peptides 1.21.0 tScales function was added --- DESCRIPTION | 4 ++-- NAMESPACE | 1 + R/tScales.R | 28 ++++++++++++++++++++++++++++ README.md | 3 ++- man/tScales.Rd | 26 ++++++++++++++++++++++++++ 5 files changed, 59 insertions(+), 3 deletions(-) create mode 100644 R/tScales.R create mode 100644 man/tScales.Rd diff --git a/DESCRIPTION b/DESCRIPTION index 62ec2ba..2527623 100644 --- a/DESCRIPTION +++ b/DESCRIPTION @@ -1,8 +1,8 @@ Package: Peptides -Version: 1.20.4 +Version: 1.21.0 Date: 2017-03-10 Title: Calculate Indices and Theoretical Physicochemical Properties of Protein Sequences -Authors@R: c(person("Daniel","Osorio",email="dcosorioh@unal.edu.co",role=c("aut","cre")),person("Paola","Rondon-Villarreal",role=c("aut","ths")),person("Rodrigo","Torres",role=c("aut","ths")),person("J. Sebastian","Paez",role=c("ctb"))) +Authors@R: c(person("Daniel","Osorio",email="dcosorioh@unal.edu.co",role=c("aut","cre")),person("Paola","Rondon-Villarreal",role=c("aut","ths")),person("Rodrigo","Torres",role=c("aut","ths")),person("J. Sebastian","Paez",email="jpaezpae@purdue.edu",role=c("ctb"))) Maintainer: Daniel Osorio URL: https://github.com/dosorio/Peptides/ Suggests: diff --git a/NAMESPACE b/NAMESPACE index c07934c..4f975b2 100755 --- a/NAMESPACE +++ b/NAMESPACE @@ -19,6 +19,7 @@ export(mw) export(pI) export(plotXVG) export(readXVG) +export(tScales) export(zScales) importFrom(graphics,par) importFrom(graphics,title) diff --git a/R/tScales.R b/R/tScales.R new file mode 100644 index 0000000..3ec51b6 --- /dev/null +++ b/R/tScales.R @@ -0,0 +1,28 @@ +#' @export tScales +#' @title Compute the T-scales of a protein sequence +#' @description T-scales are based on 67 common topological descriptors of 135 amino acids. These topological descriptors are based on the connectivity table of amino acids alone, and to not explicitly consider 3D properties of each structure. +#' @references Tian F, Zhou P, Li Z: T-scale as a novel vector of topological descriptors for amino acids and its application in QSARs of peptides. J Mol Struct. 2007, 830: 106-115. 10.1016/j.molstruc.2006.07.004. +#' @param seq An amino-acids sequence +#' @return The computed average of T-scales of all the amino acids in the corresponding peptide sequence. +#' @examples tScales(seq = "QWGRRCCGWGPGRRYCVRWC") +#' # [[1]] +#' # T1 T2 T3 T4 T5 +#' # -3.2700 -0.0035 -0.3855 -0.1475 0.7585 + +tScales <- function(seq){ + # Remove spaces and line breaks + seq <- gsub("[[:space:]]+","",as.vector(seq)) + + # Split the sequence by amino-acids + seq <- strsplit(seq, "") + + # Load the T-scales + scales <- AAdata$tScales + + # Computes the T-scales for given sequences + lapply(seq, function(seq) { + sapply(names(scales), function(scale) { + (sum(scales[[scale]][seq], na.rm = TRUE) / length(seq)) + }) + }) +} \ No newline at end of file diff --git a/README.md b/README.md index 9fa97a9..2df5801 100755 --- a/README.md +++ b/README.md @@ -41,13 +41,14 @@ Available functions |pI | Compute the isoelectic point (pI) of a protein sequence | |plotXVG | Plot time series from GROMACS XVG files | |readXVG | Read XVG files from GROMACS molecular dynamics package | +|tScales| Compute the T-scales of a protein sequence| |zScales| Compute the Z-scales of a protein sequence | Available datasets ------------------- | Code | Description | |:----------- |:------------| -|AA | Properties, scales and indices for the 20 naturally occurring amino acids from various sources | +|AAdata | Properties, scales and indices for the 20 naturally occurring amino acids from various sources | |pepdata | A data frame with 21 physicochemical properties and indices from 100 amino-acid sequences (50 antimicrobial and 50 non antimicrobial) | Citation diff --git a/man/tScales.Rd b/man/tScales.Rd new file mode 100644 index 0000000..7152aa0 --- /dev/null +++ b/man/tScales.Rd @@ -0,0 +1,26 @@ +% Generated by roxygen2: do not edit by hand +% Please edit documentation in R/tScales.R +\name{tScales} +\alias{tScales} +\title{Compute the T-scales of a protein sequence} +\usage{ +tScales(seq) +} +\arguments{ +\item{seq}{An amino-acids sequence} +} +\value{ +The computed average of T-scales of all the amino acids in the corresponding peptide sequence. +} +\description{ +T-scales are based on 67 common topological descriptors of 135 amino acids. These topological descriptors are based on the connectivity table of amino acids alone, and to not explicitly consider 3D properties of each structure. +} +\examples{ +tScales(seq = "QWGRRCCGWGPGRRYCVRWC") +# [[1]] +# T1 T2 T3 T4 T5 +# -3.2700 -0.0035 -0.3855 -0.1475 0.7585 +} +\references{ +Tian F, Zhou P, Li Z: T-scale as a novel vector of topological descriptors for amino acids and its application in QSARs of peptides. J Mol Struct. 2007, 830: 106-115. 10.1016/j.molstruc.2006.07.004. +} From 465a714c202845377ed40a9fe05c132c1c7240b2 Mon Sep 17 00:00:00 2001 From: Daniel Osorio Date: Wed, 8 Mar 2017 21:56:05 -0500 Subject: [PATCH 25/50] vhseScales function and data were added --- R/sysdata.rda | Bin 7797 -> 8253 bytes R/vhseScales.R | 17 +++++++++++++++++ data/AAdata.RData | Bin 7482 -> 7945 bytes 3 files changed, 17 insertions(+) create mode 100644 R/vhseScales.R diff --git a/R/sysdata.rda b/R/sysdata.rda index 542979b6a1a3c05ecf57b237213ad12767d59951..15199fb0b9c64e82766337ee35915d50e104038d 100644 GIT binary patch literal 8253 zcmV-DAj01tiwFP!000001MOXRTvSK9UV4$H66_5TI~HuwB?+WjLdih4}UmWj@(gpVy zH-dyX~n1#!yC?abP9JC*glSUqN;70kgI zc+!C%9eB}!4;>7ogF$pKln#c_!7w`TrUPF(2%v+JbPz-bpU^>I%|CAleC|QJl2fr` z+KVP*bO%C7^CNyai(3e{?pS{qk#L7gkJVieGPS3h9}$vIX-}LcXoN*G(|q5Cx zL#{DCgbe7XGU++tEc!1+l6&qZ^i>g_FNL0YMiO9Pcwdmlvw+D`NR@u2K$GPgoQED3 zFewVZLLb~iN%zz9m{h4w@-0wF@1y7S?`M;@f#H1@@``znI|2QD8v2xeKk4i9kaLoI zl2_9Iq#w4RoqKvX(({+0H?ClwxSeb=+5}g|A&HN7rF@Fuh%Z=MPJG3(!yWKCVKtkGKN#U!kO@3=VI?xlF=K$OrzU zr^#;1gFSeM>@?|5GzPAOH;i>rhV!sbxC+>pInul!JjHvczg_`vdT)s&_XdaeZRpW5 z2|wW_>}Mm4>t~qfawWMFV9ycW!c*vvD(C~?EtCOAj0>&;dW8D#siaQ?(j$<6?k@Vx zVC_Lk?nG1QfoG8O7r>G1haA`sSyF#+k09@CzJz^~kLS^U9ORfQ0^XP(1n6;r>~OMo zNZtz!Q-6~k!M8(MA5J)&Z4q)z&OF}|;~^jCEumN7tc&Kjua(rESVwA4v<0qY4`F^~ zb|CB^vP(o$sXc?k`y%;&(6i9fT#2MV#D=gVU_bN5wSz1|5%f=eX?%$Fr002iNq$9J zNlwLjz#Dco)8`mZqBX`*KH>{D^ajJin?sz0ekYSVvKyd>1=w#i&k-7&NcIWzPX(UG zJiwtpxJulY1wHaT^bGU|Z;bY+zl)@K)!^_Zd80Cu>@d`!H@I|3{$>B!40PvAQ2b<#_`dF_5PIK0VEd?Sr#ng?l|3#F*%LBBr7eaZ0CQze`P*vkUh zfABYja>=d}Ww1N4$nJx@!;d2Slk}TVEY%GSZ^Db@i{>+`)4ZsEp8go#WCvE(mRIus zMbp~Pakrp%?&-~|#ZjwjBkNk7kg)H8Il08S`gU;*WukX(bdd~^yM}7P$ zK45To=aAnAeBp0%i0hGE!sIdo@eaZn&+}H$&qmM}ui;<5hP`4g=@Z@@_725kQ1W)t zdEN}qS4rm$4sZB>B9d%mhlw`O3(y0iE%dMzVFE50Dcn0>|4cw;}*J5@d=12XwHj96gUtf;- zHx2DUuNWHMWQTC&z#aY`i)W;vB!3)v1(x?AJDc)sz>D<{=_R^Od5wJFPW?&xpU$Tm zrhUTVdG$z-)GnDm(L2xVihrh0?9ng!`ULRyuRAq;C%b=ik|bdUoBv zY7er!(f?6AB9p+ZA?6C*0o&{pxyL;y<`XOZG}zxfH+Yi1s?*{aq#-q>Fb{wR6l&_0=bHq^^Nd7C|+%V%O zysWmq_@N-A(bw5(D+;DIZCBM)-S_*W_}66V<6i-hlZ_#6u(fMDbRt({*|e`9b98(0#~H zQy$;o@J2pdw1@si99*=c{EH-a%#OCGt-mRb!c_r3lp@8Ykgws5QHMV&6j5GDYKJ${ z8z04nsZYq?5RktSaw%>ExdnepfSe1+a|wtOGQ5kS5A?2c`H%Do`N`mfcOjJ zUm>1IE(p;3^=0Np>RTp9PeLhBwQ%5I>OYaPo5+;ra#gKS*!jJjIvl z!d`4larD~pbG|uBBeakFjfgr=_Fz-Iw}FBBJJsNcxJ%<%Y%R&D*hVrOXkHVY!AEfc z9wwL&HS#d|l%WbW&X{>8YMB4|jL#QLEnDttaYMUdl*Cc(6hL0~pm9j>4& z7K5WTiYR3Wy>f`M1}*wArbD8`=qcMFGolm&)M}M7DoVwm7^;|7Q>WJslZVTv$yIMZ zd6;sBe5QOlwP)@t*GyJu2w7isczAT=bomte?mE62d2pC~vRuQOF!7gDN16JoSsz$v zkKbZr7BF3*pwF-vDG#5Z)=)QC1SwQ1WjKLs9;8%7s_8+iAhl|OB0N;VPK;JgnWE5W zo0bN#b|s_7O({$j2MN0ybegc#nGbX4%$Vek2mKJgRs#n)DmRUcL zl16)se1HE>bf*7Cc#}M_q$@4%px>Vek{3C_wAcnt8i&OO%z3y9e5pSW>=ekjCejD` zl|4`WO2**HKQUPJx4^sB?=T@{=j+?;?P2$~hwkqvBWpG|umXgwJR*+);4)8+z@*GN zR&LM=8^&0`iXB=(%otaUv5di>?+Ieik%vhhsNq-^z?&ish?tV_GUhO?q$HuI!BSnD zF-c4k8UENLLMzE$qCbeCi3loX)+r-FmLqwf28TCAkP#^sNS=vF0#BJSP|G2=Sb@hP zMX+>98L{i6%4=z z$%y2zf`p7lQAP|Xj1yY%PUD3lc`z0^;7-PlfXo`*Z*X|Sc;iT(Y2_|(BD`qDBS$M{ zu(DC8B4Zr(3^`wsr>^8vr>^MSwXSbzP#G7TBYBB`d~+T*uF#fonUSH+$_9VL+l+vtBfu3OEFiLff90p!Ax!mOeR>-R6zwk9Qii{O|EDtzgOb)< zG=hw~;1l&V%->*`{&zKu{xJO;d^%~Ey7&|-NyGdzz5Z8z`X9c^y8k4FN;P$wGLmv% z<^$x@-)6VWy@vH45kM2a)lfxPc+Hf@nl~R-GY`sX3byc9hfc3)j;aAll}e#ev#MI9 zp7OTkfGEuj2CH`3G-GBl+%Db*#Ar*5H+$q3$la?1td-UfY@R7C%V~xBfQC7poMcB(k9#+$g!Pt zUI1a5g^v(sCj14sb;2tUZcNZ`3a&lQF;r+R$hj2MBE4pyJF)J0fcH{Ev3y21@BtF z!weUVM|WdK-Pw^lJLBzPfF>q9X0S zy(fhfn?Xm%_T+@em_6e0T#m7HAz8N@Z?sS{;&H#w(aj7eNJ8{J-R{NpxVsWQLLTsV zFiG1HH#iC2Cfr@%QYvk4EE-`O;)l4NrhUAsm@AZ?=hC&eS7dP|%X<$wwEEhF3)pbbJxD~~G~?@@#Nc_AJB zS>UPbNrATamaWnWG*^lKl6IMHWN3JE823U_m3F{i67Gd*YLMP6oWm?EgEjLI*7qd| zCyw+_snkzgmR9ODKXGqrI-{nCxMWEm2)SDEez`@6({<^+2qH`a~%SEzAtcT?` z*alN<27Sf0E5&kzHqvu!8%#tG#k%lf5j7AUYBL>0N4%#Qq7@C`{W&2y0KF(S_!F(x zzePV18BX$2c|>Vg5))p6faRuK1= z8niONaPa=)sKZD$507N?@JKcfk7V=k$akX-mTa_;R-sr8tq&lo7RBg5;i64u8NZ(> zazuF{Yrl}z57gcin<$NJQ8_5*;K7mYAWlAfUd z1cv0Ba)z|&FHz`7?@&J`p`=-#@TPXrj-laAo1?JJVra7-qWBk)wTO9=^e=7BUJTr5 z2>_PJ{BAR5qA(&i#&WlWKQ@(M{Zjge)Q11{cr$%Vxoz6So~XHmBcrT?b09-5mU8K& zFNhLNlv0`(OMoxwAFLl`)+hZZ6r|^`8k%*fN7V&&pXpy((nI)=H$>Jt$tijHwD}3V zeYP1&M(zIMZS*MWGPkw+iu_=@q6oqXre=u@^GbZ%{7H4O35}Lu$`>iall(15~bGAN#h8D$zo|b zl$qO&Qp$sOS3ezX6kgtB?x#OJ@H>^d@cQRRxPhBii%(ORt=@5|Yu}HP9`--i^vSRJ ziWG0(;;3d{j~yHwdZ3xpiVrPrH!b82UhTlgKh0ZK-6}RJ_b12q+7Hf|zf-+^c$ELV zUPt>iYyI)cs!8WEuX$|Qy>h(0yTgikN4$odO?VxdR@krO-lYrnE{VC5)34ul^D%C# z4!4vIY+4y}$)*CGQ-Z_!5de%3MXP13& zv}$wGA|JoSX+Kqn4HrH#02#IJlZRN5>n-P9HOM_^oowF~6-T@;M!U<$jA@E|pF* zmv^r7Wu0%j&iVeV*$+iK#ZzvdS?;*%5I8io`tj0<-nnrN)AwD!m)fLGV@uxvZs}^9 zK2tZ&DH>Nk^ZQ31Z9CM{&${^p%fxF3Mg%O~T|M;BR--ePuD=c4Zmc-pOu3~FOwFvP<%u95K2`kBw2Wpj5&zl_f@&L1-0 z^qF7NPxhZk?dtWx;vK0GZjX}pd>pWpKXT*lm!EFF@}}dg#J=g4(S6HCXw++$U2dAY z_Ug23XHVt&aq4gPC#_%Ka%ajOzob!f({)0hnGRr1*^z4_gGI-gB z=3A>exjwsI^lRl;8S0idk2Kg9XaDf{r>T#Xg9a3g8Sc8lxO?`Lf&aMY=h!=FgiK>(4hLk z(QA{sO&#CngY8G#e%Ua3^%V0ruQv=04IOsuMD@+H+~ERoo;tkC#yc5@{vjK8`FWe8 z1^!R#RcweVp8HwB=UqE@^@;mPadz@)FO~hs^tft|tu1mhj=eYMTztdN<8l%k?MNJ3$7=N#chBy>xgx64FLGdf zOz8IGAx#78o}XYe(dKfRY@v~5&9YImn)WxJct*x3B#s5Sf@$8oOms`!4N z#tTNb#yq|F)ZNopu_s%mnql>NeZbthdQ-&$}5Tw;yOhviG32*R-U!~;mSI{+TOo7W8ZM& zXNTSG*1oWxzI0XK=B3Nrhr~1q{Ay9fZ%-O|P5U|Zr;OuS*`cxLof3E-+m<(b&#JrP z_4wSEVciP@-Ww7Tw+GRTE%HqKMjq`udR44@&Yt96Gn3381Ur9msYNrV#`diyuM6=twV#;i zkab--|MINo#iP0oRCn6zfBps6{q}{a=k|ME^}0TEr}F5Kjk zv$(Oy&Ngw4+%JFpY7Mqx^AgW)E7pJm$i04L1L>yMKG5 zUJeoS3!U%x>pRDob86h{_P#f7GVgm$Y?gDUj%~fuP5eK*X1;9Y)dQad=YHQz&P|x! zrQhN}e||u4hdzCNENeB{(`8W9nl-WQTiA!4yRx-cLFbPz9vs*EMH}Txi^V4#{DM08 zjLxVy)6=&1t`nR0-5d9MNBE5{YvPsFFDEqU+}Ou`wDLk=2gili(gw-5&DpTc{kzKr z1*gk5@2F?7;OC5wcUU_#ZQ$orW?$$MdpK|SvR55#&t+cSIPJrEi7CT|?(Q^uMf9qL zL2c_lvFWuYJ;i-qy+@A{qnw9Y8O{9Vvkzl_%pct8-2R+Y&C~V1Nx56TY2@d6-o}1i z-|7~Zw*@uGy>jyOo_%JCb=sb89^C3dx4F~C{^okS-t`~ z7u7dOvC98$O5_J(%qC0UUPT?1ZCA}%nE7GXJJ-H<4o_*>s`bVf7s^V57HnH)e&g;a zi@F|>0X^6Mwz-e>ciWxPGkW-Z6XDWuc17W$jh<%)eSP7x88(w=xeV`{K5odhY?nfmkgs`mbe zvvUsw$VR4JR{mq9{42}8c0b3&Ox?b4ZG(G##x~rxY4$0TvGYY zx-qM_nwF$j7iI=6PS0B*o6&Q@sAS z!Zn|*B}d$v|76psUqbokH_9WIoF7`*?$^N!0#6=t4{!dY`J9{gGZR|$nLS|1riQ!A z+wVJba$QmX5%Q%Yc2CJYv-{cp3p01h6Y{>UU+S_iQB__s>ev zcbH|*2)S{xzEHWM+b?y;1T1f6+9WKbQel0_E_BMDElE%RfJ=S@qV{6&w`>*L&t zS9MNu`fyaz)D5wo&ZdfFZd8-Z7|&go<~nC}y7kEg+n5%MUp{cnm@u_{>qF1HduRHt z{3@ZebKKp%t<-B1H%^~o_1O5>uYrorBUg3&%CcQ?;l@Ghf0=#hi=92IVvdX+kmb46 v<6%Hf*zDPdJo+XXC+zT8KQZjsz;?UTz;vWNA=6@pN|AS_qbKz+33-& zMWfNW1EH|-QJ>7kO@zDmE&7DT-RDxHbr*y*ZFS?LLgHC%#W{jTSTrNWbD!Nz-e{kl z_J~T+NCKJ51=z;A$9=hiIBml}3a_<~%}5cFv~RKK!y8NOa36G!+i@jQI}-SY<$8nn z^Tj%VnUL?3aOIxpV3@+?O87IOe+oQ))!yavhMwmQq<-Mu1GhX3hCB&ZUMBS`SC04W zLVuv-tD*iQ+ApN{>Kop_x&LrQT*&ae(UqH(^-T!3d5>8qr;O>`OW=6RHgL$D+@HCh zjO%_IadIM;ti2qS$X$?d;j-IX`&V3I<(-DQ2DtR^4`^$+9JHS%F02{)-74;0@gs*@ zFUN6@B_+eX(KS1ldxL&?P0CH*@P>S+L9X6FKB-<(D;C^al*!Nw8IW&0C%lv7Q}_V6 z#`q9kLO;Eio)a#h|B@uR=k7pX<>UDx=$Tg}0eXh_WobMMm@I{4=~oIgS$;%4^ssHHhJqA-VY$JnD@BT(BJ2vPwDrQzP-}IIb zN^&O}Ll3-yoWB8%#2+%jAJV1%;GRO>*?b9plY{5ce;nkP%Lm?=9|Y)efp|Fa9g_E4 z{nX#YBluP*YrzPIu`NQ5$(ZMxVm#!a-VAyL#=2;N`3QBpl3&qEl2frJ z@CL7D`W)j)w7@vZfq%i0-k@K2bMTYU?__dEya9Sx0Dq%-j?myl;wR8QC3qh50EhnI zN^xI0^vI9UGteKrA=;z<&X?v@y~CU2jmk9QVK|50;8G>|m;K2fZwh^6gn5?qH#rUA zAK{svz;*C-(o4Ka<$lvUyva`dD2->D2WgxOML5rfetnJm5@Dw&OE?MO%L4H~*qcJJ z#Op*Ect<+%KFB-lDB_=_--H6`T;K2}yhy%iKBIG*7pvCOAH$n?U}*!kd8akUs_`Z!OjH)$n|o zRIhhC4~SOK!{(4n@Dw`dYfAU=)@a8T{Q_RigO?M}X5)y)4f$_r zeznz8{!R8Y}|bpSz9ws`#}SFU0&<)vwL`-(=SpWByG+d(bQT zhBxsLt{Aw(-edlZ6qIC-Bd);WKE$&r&IY_#|Bzmy>lD|>0q)eFr2nZtSwHy+^XJth zJyN-3`lL!d;}w6VPi)XHRrLw{2jtIX`h@0Xeb*<+z^N)91kS(XgH?Flzsm<%-01%( zALLu>0t-|4mePF1JArSsI4JRr_Wg8vgKvpAe9KEZy~DSX5-Ipr@T+tPke+J~yq&;H z+Ts3o=vSvxQvQQeq{LTR$|e6zTeQ~(@9!{4FZl^y8+h3QA1maMSmL}1N^9^rEAYM= z;Bk~Z)NH53=bEDb$i8nTDGc7hMmKS?c5J12l&^vF#_*%mk?dE#v3~kbcv)qA$v1=? zQqmO0KVKL1O@OyO?#J_DQ|Y=$NmIBkqFq)`@2ijY>~J0LBfd!fTYbZu**WBwrZ@uS zMFAfc-^`#m0Qv)dL*5)bq#XW6;xpubL41eBKjA+S4uMye!VW6LxIz3w-|!aeL*538 zlDu`PC*kbIOY+(j*E>P3U7cXhpuRQcxi*mRmXPCqkkfW3JD`8SOKAQS;fWNRpnpx# zUJL!?Clps;c?j_PaVH^f@YAvSTfi+B_9OA|cf`+;Cv>EWe8ZlhJO`FPgt!^w-Q<5P z)Khz&;*k_*guO>`O)d*K(K(ff8!&r`^3X^>k-wGB={miK>>#pp=sv`!DUPpqcq1Mz z+CYE94=!3${6&&G#-mLu>u>U-aAm*`rAU4$#A|p%oWmX!@+qz)wZj`!86O4usZYq> z5D>o+vdC`)xkdhz067;B=Mvy2WOx@qA5^){T zYpu~v5!z2ie*#wl@k`=~6n_>_>KooH-a`3-#KXzXsfX*A$^Ia{fqL>U)c{|tPk!{u z{&T)DN&~cy_>G8jp7>xxytj^?+B@aQ6LFEov)EjcQ?Z3a9B5t>9gvUW2t151FFLN! zJ3gvb%DT||u$%M_Z{oXDlHMl0`>t|+Cg~X# zPa`|j41Nz|@Q`BC>*SAxd{;yL8R%=`IO~L0&^-Z5t`W;TVXyzKI4pwNCp*Xj2 z4b;d(PS^EtBF*p`e_u3a0O~i+~nbMjS^?3ZXxQ3 z5TzWaMs7-a(#%agO&;pv+@;cacjvA+H+NTtD?$SmnhA7+d*}p(YO0Rupm~5=HC_=KtY8(Rl#?ebG}@-6L9AT~ zX~ZTgO5TD~fqPv!Nu5Y4mkqMTl2eWcqDm|5loA1V5D(aY`~0%8^D+P1I|u?$TcN>pkLYZ)UQMa z&-{hXqJIS5m41g2DLZfPPM;1te>!ye7iDC@1_xGvu$4z-F#ud<$q|?oS;xu^T4BR7 z7O-N6RuHp{E0(d0!BEu_#GoS!lPpmEVHUufJPq)elJK(3VOmK^LQjLGymH1QWs=D7 z$0iY4N%j`~K^dCxpi*R=A`-+L$pY0oyvc(MPq9GqOqnFGlvxI9G2|92@R+9vOqY}q zyH3jdK1F6=`BSD(KKg+?vl$c-($CD1|Idv2593WM#()ovf96rexaQc(VCZ`yFC_0o zeu#WxMFUUzh2{s4P?n*Mc7!}>zF_(&nU3@fZ;GtYP7WX&6dB`9Nu$F%YqdYt-~_&nW@$PIaH^#|`tzrz9-Z9)_(Wt4NEA~e`JOrsc2)#1uug>z7d zTp8*duAD&*x*Ce82(4c&*f~5x^RM??hfELFsKY|kfyy9d1bO~!gVm9ND#hW;=CIP^3nq2n|v=%T-|^a%YW#+pN_CK-g$y~q6-qj{gq?zf7j;&e%GZjwnIiABJ@4w^I zv8fyTbXs>#`H3y?iLI-AI>q~%N#}nH>PT5-DX{oNhB{JQTOp;@u{o9oBgLe-97|&V zhEGR!E>;=+?$cXVDe2QG3W(_6-}&j*a8vzvpWXrjMY{_&mErF{|LIJ_prkby^&sPp z_{6Fj<{vOj|EC(J>M;EWd^%~E8u%0{NyGe^UjI8k{SRMd(Ql$crJ6ET8BVb;lm7B) zpQ2kP?nC+w^P`F1+)EJ>S~2CZ=1qoF%!6{8f=zwZ!P6?5qfttMq*(}<^OvZ*q zM5igChBgKy_ckStFq#ZAS~S3vVS@!XMo8?a_7|Gj{~)}{T%d(>9Kt5tN64|YR4*W5 znz@hQW+wavn03NCB-|LG-^dKd#zhsVn?0XkqbNO!j8JiKFz)+pPW*2bo<&0`MXNeRV(`oIgU>{)ZcnqC^)}q`*Xkd z+}ny;w{`O=BSk1&H{Yb<7U2q{oq|B`wY%-^DrISwMcUnV6FzcpMrrreZOP^5YxnIv zBP3Z4JU*r?Cp^RK5sT+C4W$c-y4`pqg~DOadIgVaq(4p)O7GL{UR;xVAmJlq1CPfO zwHT$IA-1Jn4BZReO6$I#;;7`{0W^a=1Iv{h~~& z7cwh4b!z+}7GyYxe#(qEseLn-qNh$k$TOF$gTq^R6s!|SA@!H0S_v154t+M#HgKr$ z)6%wD2^8)Frw?x*Rlntvbut z{k3wx=^fsb42xt6mgGsv4M+xL*D2|i0qUBYBj0 z@pAPu8ICu^_@$K%6r87|L+AsxO#!@Kyan*4q&7;*pv-lu&!`gI$FfCjP^EXpHH9WZ z$rc}3P13D4@{k8bs5Mk+7)C$XbcSD$T*dA-@o@F?bR~RDBXE&@4*L(lES-Jjp~33O z&fyA0u=X_-jcO_`e_L_f-FL#aI?)fa8*gg&bHC;qfg4!ev)kj7fmS8+(+vV2&Fb~2 zphN8GYu$^!%AK*I>DJEj@%@r!Y&S?M4%}V-Vw6E>af7*E{PNi6Z1TceGmmluHmw$4 zBrjXN<7&sABNCqUyV&sgu^dH`hj&3lqi@Fy3JgBb$bLm1(|Zl`xI;JE@Ubtlmz6h* zj>!7Ou6FA|ne%t5w-1f*o!9MnuSU&BtSp;&G3}=7mfb7I*|^xQn0M5D@P)V!;VF5& z+U{MtVDFNs`XKJ*7N@9xYe`1t3UgF@8e~g6Bc>;EKd2QM6A2;$(e2SRqaY63&zyw`m95nl&^PO zwi^DeXCp4L%Z&z(4Xr;vwIb}Zpyi+UH~B8@S*da33FnZePDMRlT zn~grPCg1a1?Da=Yb~%>X&sg5R`q$OJ>p17f3)Ozg-zlDT{?cs64O@S&tS+(>h;aM{kWy8EqhGaI46H>@r)mz_T6^4tB*zF@n-Qi4-E5Ly1U%#@K%HK zW=?samQQr@33{NrVL*Jw3}e;9_iC#XQ@+f_afl-m@|03@hhK(pYK1N+|j-F;vLCh&QBBfjPP5^AHDtH>n}E6|JZg` ze9u&~$e!((o7W#F<6jklJyb9!|v|5)iaFV#)&9Idl2#^%YXFOr`r2lme$J=AG~ zVdsp=1AcqxM-#J^phhEXj4RQOB@hzsUTBr}nt*{kiSg9WmmX7B+qJXWg@% zSJ>^*!V{To49*NaJg`<^Z?du1Ubi@&>-(Z+$%cr6xnJha?AX4eXG~wkg-Pe!RW`#@W6E8(HpzN< zvi6*dv2|z0WX5f3H}~QgU*Bh$yEnPNntsT)!?TTte2x#upLO8O(wP}0TX#n6h#ynk zeDzlkF6_UvBBInMd_Zhe@b*(d4gG6e8gDSc@>+`7SFL>($8V4PI%|H`>I*aa6yA;< z_hwPrRP!K@m+yzBf4e2AN6hV^y{GsZnLcRs^hwObHIW~(Z+^(Ux!hp-)-ma^D-LY9 zVwKY|Sds2AtZRb_Qziz@>HFpO=sQhr?Y2H#wyb{Uq{PLKqvp6-)hi#lyWO()yBkm6 z*!bCqt&1ZvJ6?*p0pY8(K%6pJXpAIGK7R zC{7i2_gegN$AYi7hp&n8j=$7tO`Gnk67E}e$t-Jj*XiZLxHZ=nHS&4=xo!Kmor>d* z7mbct>{#g8zt~bdKh9>-*&(&N8qYhlv4M-PZE@pWDU&mz2lvjHA02PG!G4MNlArto zp1RMH7eD*9V4O+*i@l=8>e%*6Uxc)tlx^qf(;z^;W?fS+`Je8gi z9DT_?j`y@`dZ+uW8Y@1G%X%BqInS^5;INoI5ia#Y2kn@f+@`O$Dq-*1)(JP?Jhxgs zIUqW2?W5PRdxE365hq>^zFJ?NJIwvU;Z04ljeLe5?>TB!v`glm#BMVZOdbb1e08-+ zBm4R`%_gl2@;0`a5O14)OF94Atk(r2I}T8{+v|Jj4cGbJB>DH+jT)up=E@{+jCGrHy6Sl6m{V)?l8J9Z%t9G>QkZ83Y` z!sStyPt@6baCg7f2HkAK=I1#)>eX|OA!lE|+r51sKc+o$pU^1tes!yw=NkBadDCRs z${Pnh56t?pk(?VptwXQH{=R(wz&1U4{QSPzBsa%_5o^{&w{Bt+a`F1sZn^D8Tsbth z`KJ-uH0qhaI7}JFJOSmcJcer+s}-mr=^g{%!0Q z-b@)N-!^B%HkTi+<>sC%-n^rx>4INhj@V&g+pvz0{d=1{$LJ&3Lzlg4YjrX0#>T0A z=EWxs@!H*P_KL_=3jd@9OzDU9z-U*R#CIwQT`)vaX*ww`X6q`06dsH4bd{xYOLJV@^2TYkS~vxB0@U zr&r2uZvDQa|GJ*nA4c>{P^|KOkQClqjM`-8-7UYZvgN8d3)A{^ynpjYhtQ;^&6;m~ zbNPKyz=CbdOm06IXqIo)#7 zEXSceQ^#&ve)0I5dHF>tJ_qh>$#h(FF1+38)@Ln0WZV-6CQR7>*+cJUt%42=w!L6n zRK9t{(J8-fFKg|4BqQs9pKN%_HRW$B<=>d~wEi_JYRdM7YwJAhF{bXeO|#D$jhUA; z)9$hTw2a)xQ7$J7YecQyYFwCFo|hJ|I5m5PY8Fhuejoww~NDZzqo^A;5DPf9n~_X2i-nXODJ8@>0ph~e#;vfHwXzTRahLh4&L^&y3EF8%lxQQ z*;5lIebwdM`WWYeRqYe(`;1JOvLV{d!B~;Vjckw><+khUT!-{_cR#;u71d<%+s95X z$4_b9{O~J}?rGjDzlkeqAM;>uGxgf|jngKZKQlae%wN%d_^P(wn6)a%+cgcHc>26zHpZH~l%$|MNwP%81+z!|E6GBctdtZ1hqxZgb9<2hjeDA*iTL<@l H(slp0o zbM~EYzInegqxXPO-D{1iC6mbvWkyDZGDD-PLu13Le+*>CGK;Fx)Ws!G9xkuCp z2VQjGMh6~rFpv%g(ZNtU7(xfb=)j#0Jn6uP4o1>}A02!_2fkJRyd&_rN9~HvMvZAN z8jaB%2u00~du1(ZF5J0S>(kKKdt7Ri?t+l6J>BfMka$*m;v7LEES!q7l+ApH_>Koqwa{J+mxPak#qbD~rdv!3kWxshh$IR(m8gRU2>pv_$Z!hUEg1RB!t>o^OK5TU> zZ9Ml#QZn2tU9)qzSLm0Qq}=okZ^(B#+Or55)ZWis?aCgdB>32!9%6y8Fv zF+PMe=%*6tIpG5OFG-SnE*|=-0M8dg&%7WB&@;R*OXFF3K}5R44fssHFGN^EK~hleeDXeIN3Qd5=2{{e2Gllzur0Sxl6#U@ z(*L9%wxXQ}HE^WouR(8I$2@UcC)NYmdnGX+sCRg;lW-Q2XdHt-rILI+q0K73j2+-pK@o?fhB=33p zslSOw@a<66gAop6TZ9~wG0(Tac*w!K;{YbmuS)|T26t$-`>A)`98mw40a{ib(#lb!fZ8qYKj(l{52QO|*XeTn-LVW%fcI0@j(0`WiCn?k9? z>qHrNM+Wge$UE#P;-947ghHvVZ+H`4BwsY2QJv<+n&;_{;Y~cSyt=%S{Vy6oBOWGNLN7oMh*r?U7LZHu6sq%erTchmv}22Y0k7u4%ZX>RaYW;W{I@i} z+UhC)CVLw4#OyqjLN4?I+2#4L56^?o-Nt=2{923`Vt%aY*Jl22vg=DR|E8cl=oNj# zn|KIU3fy7uF@Hu1O0vfhS731;;@K2u1756uNH5WKifiNocj`~l|8zcCKluss=hY=W zQoUsQq{ey1EB;KM*q~o(>J#`6$e+vf3C+v;u1}JIQ%ybyoPWm$Yw)^%mk+YI(f?6C z$hX%87N+oRrTL0?1m9@$i^MlN_t)tSzAfVLZ7=Ec4&P2nq~P1ZuhPX&dag6@b_6f! zg!?<8UmZ_L`45f}5?^U6m;5&!(Ow6z!A!H-g3vS0aT`sqL6W!3d1-vn|< zNmCgAd;^?s4!rGgKb{v`NY_P5n!_#W&w=F+A#TQaH~Aln z^wgfGcqGLcVee5~lgkE9RHqVg17Jld?f{w6;PR{{J`isY9nLtMX1_6O+=oG1TM9q`3Q21=xZ>r~KlAdAl zG_pg@;rB2G4=E+RPX1WPw+YUlfxad_jyxFN41B&^-}Fhf-{FXh<}Uu~K!rvbf_g0% ze~mm?K6$7@jWZ@Lnjm!;UGA@v2TU5Kj!*@%GZ89Pe~m&Brob6fS9zFRqeRWjHCP=U ztdyf_gvYfuv)LkC-zGm(& zj|d1>Xy`M{J=Cheu&S@6H+w`(rOlHgCWGZ63<8tE>JSB8F&iAAQG_c4 z=#@j1RcO(VF&+{TOix)2nI5hfpjNAt;o&L<#Zbl6sye-Pm^?&2Rjzvf$-|V>qs*(ngYrlb$_D|?>$mB`?k zztCCqkHEXy?=T`|=jqw){bBd_ht3};qgrfmUi z5}}o3uhAcrp$QKvMb;@ILCldXP`$&OJjn1A3nb5!NdilmWuTTqZm|N7d5XYvNg1*0 zq|EP8WCoT$W%?ALAILMCNf9Ca%pCdu%&7liylKT4@S*X~JgOMi99tO-eNW_t;7PyG`~VWlGPKc-kT1;_OdloFk)GjAkrmp>0c3+BW4saMAD(R@+e9KctRNxM zD9R`U3gd)Uywi9gPaeo32i%G52#BoF{d$Kt$QwuUOe=SR6X8WG9ywYugO!a!1(9*^ z88W^|PZR&3$N`c6cbHE}-xIkfV~OqHp=Wp#xuzAOv@(hKAMM;gdgVT?Fa!RSK}jn) zXk{y9D9|{djAhC+%db(Ak&2bcWUT5N-fTS6ihr8#$Y`Y%HP9ErUEuQ;@{H>&a!dMx zl@yL3&-Y7$Tvm2nOuT@(9RE}@3C`{P!74wuCdbt z_>b_2R$fDoQ~wg5r~47PA&;&8;9c!^)WSuZV1-H<>Ey2n33Lk8C??S9FlC^^DIi#` z3~>rm&L9U}9Ytig)~^=m6c(=e@P6yy>46$`Xt3H}8K4X&&!26eI>KM2_+9I^p>j>Q zQm%3e3snR-O;xLK-fDtM9`022jt_6PQwIb@Xf%qD0ELrW6&fse(kRI7XB;}ji9oI! zR&|#;A|y~5667R(j_kdCZ2@_+;9JRbf4nVaG$Nu@9~oN6kmK8-q`D>SG(?Ar=z5#!8SEN9oH@J92R;19iNU( z-Potox^v1;Y=cj1U*pp$-q%v9|1GE^WtFAC;u9I_NO5h4lvanZnfMNPy)i5=O=|AApNyF5^r%*{6=Fjx{-}&i(_^Mj{Cn{8`DN~hU6#FtAAfNU= zx@GD%tp5lfn)oe-DuP3*raacX>9DGKP)<{@nYTJ{T2*sY^--!+3XPgo)hhMm_bvN` zYo;?;wbP~vqs1`0cuOQkn`6A$Ahtl}UO8YjC-*WX8X)n&1_=jsq>?w3=$B|piR^G= zfKF3_0wvstb+BL(8(WITf1w%jkBA{4q1uoV1Ek;0kvoEDGP$jjaUEu}XbUqL8x|3r zri2>W7?9lClsLj@GR$bv08@qy7Tg#ivBTsqG_(Ifc$2w63+Fh5O}KZEV{7TWfP`u0 zK7yN>@E2g#32%^aV}yPqGaMTiaY!s9w}+5NF*A%KxR+={DSgA6Vt;I51#l3tku7tZ zVgoYK9A+BADl|i}4Q-F6e+aj!;e_tkC76%=Uq?L8wT zSq?fewkIb%#q1G-=dui?3yHejcq4?O5l{OCj&7XPCy+wwPc5_(E)*a6c$BUGaN)-# z9kmiD+yhQ;F)lW0cX^)umdkwR^XA5b`dqqno{I+?x~)ZjW)4?0-lYopOF}C8GtX7m zlLBq;EnBG*Xs#UnCG9fZP~Y(8Fz$tf3hjWuDm)0*R3W`ZxQJO;1~&5;?E9*O6G!@| zSn4M(Lo4-~pSX8bol(_8T%x28glw&NzuqcD>$>SvElF;LOf8BnF0k$8beovFEEDp;W;`YQgv<8Y0Wg^K zif}=vrqtX_Y^%OhYLB=JO_yvu9u@<(Ti1vF-c= z;8FNM2dt3qtJ{a3BU~S9)rtKQ;Vkq)KJ?QqWPq-sWyO+y5q_4&5tk~B2gaV_p^tL4 z)AgI1`h$11-(gBD#+|VpcgA+y8QXDZY{$JPJL)BS&wI?-xIqw~u|>*Iq+l^w2?!$7 zHg_z;kb?9SbR&I}PZ^BWx83(M2Q6?x^Uld#ej%1ApSjI}*4YH)fQna6~r@V)@OQL0`lqpL|oD}4w zBtj(jh$ghXJ*;I))+BEP1y4!-X?!H3fAT093-70GPAT~d{i1hxLynj}pyY{#kY5V^ zQ}P?|q~%a7Sd3+oY`gnRN@fGT^gIRcsXxj4LrHR!Jok>0we$;b$~5OnfL991FO6s5 z0Plim052rz3EGC9{ zbBKD#;0-2kKIsce%A%weniq?JFXNfzm!x=_|VEK zTIoV^O3S@z`893RLG`ri{l#0>NRmSm9$U#p$^TpR4ex5d!yFe)dGffy_lK1}fADTI++aQMk1~wv252Gzl=2XzXVo=@CS1vuKw3@Gt$B2p z2ZXCNbkZ=CU^1KG6ChWyyG`9)d^}tTRb%bPy#E&Ve-K(adCNlr)svmV6pBFYJE~gL zR9#+Mb==!KXnXyr2RY3)ciP*(wMO6u)%NK1=%l|@*}Mz`|A#aCJuK`JbNX8E;&1Y1 zEN`)`yL>|bq!~L6l1lyeRX!hW5K`KB&X+$u@;aNm;MUj2xq+KkiO-XluG)3AYv0ck z9{0c4!tkbR#}4)nJlxcN`KM-go8)sxZgk*dp64vBY#9}v{gd5C?FVPg z+pXR?JluP3uM_>6w*GuY#l(y0H(j>wTQT0o*>?Hd<8DJP#J&wn$?w@g~7DwL8 z>ep|l=@_S#$6Ck+HYtxh{?X<$GK;L|8T*}=o;wgYpty09o7=osPi@q?^+xl)_fE&I zn)zL$StXyGsMwOQ(8Fs{%1>otg9VSzY;UCMR31?{wocEdT{@(EyX&&m$h96#xx^kf z8ap(x{^Hc~(2oO_eKElFyQCjqdOtF2J*DS-TSwzo5iy2Q)5c60ey7xY%x`N7JkG^j zf7pDFL%IEoWu0q(Tl>4Nvv*uD`LSTPc-HAF^IbP=eTODjK3x*zo*msF_28`s$&G6_ zGWYc1maMYuGiB54f^nrYc0BoP`_Z0WwVF*ZkGpwzgwK+Fl|zqiGdOSV_}kE(hKfr~ zl^g3Nr;Pl5-qvFqhA3UQV`&F@Z^K<#n@qc12$-0WG~a!z_^tD2OV6F%a42NMqi!#b zE*Tk9aqDJCPQMO|&swL3O!+A2>V$5xj(hrwc75;U<$ZTz>$^AgUM+DjA2K-c<*cPQ zA6&nF^umEdpB1-~J&f_bo9H;+_;q@wZK1({QF8}#C)y3@vTd8kP`8*-ibtJ{o>&<* z`j~HG7i8=f;nin%x#K5p&BvYn+Ae=tL?Wl0RkrC!e~X2_0WPl54TZzFLV+#&OfUwAe7;?U{ju5Of$m>zisG(YIuT zM!jz7wI7>`vP66+W?V7ncijtfTLQUvf@5bi}VsdPz`6 z*M6}p{FiQQwymO*k_(68Q ztz>w{+O0`_qHhoXWQwhst)9Z)=}Z5aY*n3SAuaEV!*aW5eSWwSTpG zcxC#*;f61cIa{xLWixHbO5ZI@mO2lKZ0x&wVcBob8oEvWIr*owQyH0oQJ3svc@L`= z@x5o(S^jo>_Uqv8`92>F360(#?%XhB@UA(@9X|6^B^+4SKH=u8XI85w`$fgBd-yVD ze_#~%`EM_VTx}%J8{u~0=;r1*MqVRN^c}r2$~kL)Vy_tqrjPtveRH*WQ~O3XEhnuH z@HDmwinGnQrJQ$d=F7rST?eW=9q_*NitB#&@|25*TyMDD8oFC~;!3h}hU-AJLF9`G z;p112v*;{tDzLVSTO;?%9Y0In!^`N&ncgeMmVMq?)uZ;%Wee}dCbZj}V1E3o-oeT@ z&z}tZ#b|b~%891=!}1;Y(5L;b&FGbTV|}}i5-Z17#@hwoZ}lX1T$@>g7A%Xr{9FAk zzwGPZ-k_Il=)C+^5Bv3UHC<=}&HZ+C^`QF&9iooq3}5=Dqt(Uq8=IznIyWw9*wB5Q zW-X6cxxlY&y=Rua)}$sm&#n99NnCiVp%w-+e);Ot$i2CPJ6$}Km8^Nb!80Ly>vs*k z94}egtnXXd{MvTE`q|gdoZElUB(8SbbItr)KI%4S>e$~L?{+-=sMkE<)RQX}H@AJ? z)pvd0>kq>FCMZ^V-%kqrM2y^Q?%AuLqq6PF*$dJ??RxL#j#eQ_En2qT^y+d+vETgd zOHFUzA7xg@CCsPihTpdIsrAE7`_!}^9^ZvJG?-PEzi^Z5`9W(he>L55(oBcpeN)G6 zUUu=stGNZmDPD);w`MskJQvpKbo;ZGZ!_ig zcUH9bK9-q%*he-p<(l$eE99%q`&$1T898O=f_3#D^cmY=`{r3^jmFMR`r7W1{j|)y zN0H7ai|RzK+GbpoTA82jw1#+dig4+g-Ku9izQ-JX04g?lJF5@*2y{Cqtbt9gQp7 z|FP#1C*h{YwxZ)s&3>|M*e|y9>)WMai!Ti=Z};oq`Mzh4I)^lS)@*kC!}QqZeP#_< zyt%=?()I_>pIKkfe}sI=h<%f@&+mJ2=<Ivn`yZusUjL)*B#*Kpm$`!SaS_f|5tFEvy-8wJwRL<1IN#FE1 zw;|f8aAoHN`%gzDOxYOa+R9jw$c<{89_hO0>YP>?o$h>b*($R6qSucc(ka z_ulEAD^|xAcaFY)prv|U+@@)hEuI>l{MA>{dF0BDtIgXL=5HFb;g?xgzuDchBJ%j? z0U55_Tps&m1<#sw)TM8NVeBrK4MD*tpOzF|%lzcvdiQpITE6!m`A0`QReJycJy9QP literal 7482 zcmV-A9mV1wiwFP!000001MOXRTohNkUV4$HB6dYY>{zhHk{P5~P$>$=70=A5!ILR=S<}t_1|6A3g_k9)PK>e9gg<6zXbQS zLHlj_cG-rw&luOu`1@Hq+-HmPHuUCNzs5i=o+b&aDOjmL9+f)IRPdp~NGiBe!G#Lm zRB)q$2Ni};VJHB5nSLTHVhUrWpkG~-FFM-Ez>btz((etbh-w(`3;8ujeP{iZPiuitIs_~xv=nouO z1Jr*;`=#_=ZNvK?Za?2rEfMg%*PEG}w?2f~amcubL(VKF12{gg3K)@4c!2puzsbh% z^HZ2q_2tMU<{FO+li$_CujZ0)OlYBLfXVvln7W23K>L}hB@N_1u4NvVKev03F^Ngx zl??Mv)9eD~9s1=hDK~Ay8}gkAxq1irq|tehPWTyvJOG{=NczO241<^$o~5$vw#{>3`A> zJJHUwIylnvcc3@!VxD-Y5$hqsdwDS*qIGz0;&JAZX&i$;6!1re&Pl$Dcs{}90LKTo zuTl+Phcbq)gLepeyA;o#;_>F7pXhx|1<#L|LiAq|ucx#QZ^HQ_j~7<}{7Fv}Z_5WC zd_p{p|5ND#SHc@)T_r+2_z6=1ewoY93)~yLhx+RS@TT{c@^Y_rct3_7{mA3Ty$65R z!MM)GJeSAI9S1%~cyn){KdPV)fH(IMIAUBd70@Hpe{Xnw!jT?<{4-C{Z(7R-dAU>R zLl0y_&fft?;t#pt4_SPFFfSqR!h8vSQ-J5ue+=Z9DF)t{A2{f7j(9ln9g_D#?bP4I zBiIf&HiQulV_O9|CS#tp#ds({y)pC(jCGYE?rX!hr>e)dr!ohw#D_4y3Oo=zhD<@Fu)SzGyz9bD9_H*3+MWH}SyA+VV>Fze>OMbIc>? zoo99CRo&YBRNL?temBV@;Yap4c%k6$z)^UP#s}5c!N0CO&((R3LqFEVpZo(_hj%X7 zeZUv?HUqyN@e)BUGvMzaobfzs0{yH5eentQ_Tg3Vxrex~j$cdQg_s}f`n3iBH`(>&n19pI9`uT~ z;Y~b*DF^Pb_XK}N8jfU-Bd#FCeTZjMoDFyh{X=?*u2Wp20Ju|slK!XqRPE#^f5{e{{i`P1${#EvbO7!RNz#X4+7`k@xeO0?%(BuLfq*8 zC?8}yY61(>+4lT=#X5j*v^&o8jjn?=dV_6`IDGpX8ok4I;1em>4)CjV^XH%I3cMY_ zOS<6xF6dW>3w-{ALj=!P+KYMrO=q;%3GeSVRV(=k+X#4B0UvYZk(lAUHI5eGbLQZE z^}*vPd8o}kp3m8$|H!^?!z&Ed&QddR3hh|&^C(*%=dIvJY0TTNY%A^bpRl6Z`jTw{ zIi#d1jDNNX>RSVE8{CiQRkr+f6(vpKx(e+I_4K}GXwMqg@jl{<(!LU*@flh)fU%#K(3t~V9%hwBj&kIkni@8y$ zYlQaNX(vCSxPp*}0KXq|9`Xi1olyS(xD~>FBp&{O_&M@~PSufb*fW&pAmk4rZYJ<< z@;{bpsXb5eNQyJU-lMoClLwsWoQ{Ya2=)@?p^<(fe=D8Sb$SokL1gF9eTYv}9AE43 zMm$_)3H=Q}xXOa!FTC6dJld$X{w6;PQw98RRFPi_@fuba=dee)Vu~yA?XWs^#z%>E z>JzdzIK*$bJn|bsZjnF5LC!hExj6U<1-wh359(ZJ3LvkaF%Q3jKLvgQ4*nM*{|f#@ z8dute_aEj%kpBI5^C6Ir{6EfzsMJpR7V@+yub$$>$m0?66)=AadG}SYM~$J6jNrG1 z|Bn^HUu%JO%Fuo)`V+Wvh+h&CfOgPH&9RhrTXBD z&B%{l+keis!chn9BYva8IZJ%71>W0OOYNO%jN$-BB zou5g1Mu?}89cm1}hdy{nIq7xs$3nghP=5*fn)o>KU|1vY`ATimC$)Zu11=gn2PlFh zN~s*@rp^IMafo=Dr$m7o17~HhB8)B%mWczWj!;C%f`pm~nQX99A_@JQ743Q}5GmJeHvY@b}j|ics%!khkm$)hvGHH0YOn|~uGNb04UOPf87tavOzI^fs z=`8VV@l0yZ&`YeGDp3-$UJAK9B5bC38hv*?FQqsjL_Afj6q?ZU5mQI$`zVAyFjAMl zU}NArQzD_yFd8kEPgW?Y8;txVGMQ9PARGEiWnl_>(8OOMn=FwBNrZ}V(rMEqN_Erx zAXcx0)DtEvO5TD~fq7dyNu5Y4lMk{bB(Gx75(&n2A*mIU5r_5!GDoC~lHrNW(W10R zwT+NJWiSh4SQyoR9XTN5m4c?}zz2(#I0XGTC^>;lP=63fBN9uCIL_2LuS1rFejp`{ z_Jrj7=YOIx{Wrp!JK&HOSjJ$eYYAe|k%dVXsP-@m;7y(ecuYxnh0I}ENl8LagQdE5 z#w2Bui0~&&BD9k1J^F((G~q#|$T~$Nh&hr4s&#mi2N|AXj^vp#Nnj}p8K~uuTdcqn zJVju-q>O~?q|BdCWCoT$W%?AOAILMCLlGhE%pCdu%&7lmylKT4@S*W9cvLa28DV8G z^gWRml6N9ML_V>ifhGMy^8-kzkfDusxFUYO5cE+hm9z|RimcF14j>y88DsSz|L|-R z*(MUnUmO2N=1O$*pa86E2J}Z$iE);w{J}_y_I$K>8j# z7jc!4%e*=}J%ImkDYWt$dYt-~_&nW@$PIaHwFmE7zrz$4Ekh(SX{2L-L>}ZAs+3Ho z>M&`L#4#{LER{QkNoSLTuD&EPT@-B2>fmYeyFPdQU7rv6UB~*=?JNDj(Sj#cU#>2H87d~MEld?l`g9yAX|P@0Pseo= zJcmWzf5oR`Q#aw$Y27*HC$_^UcC7R16z^-ppZ_JOBV|=cfyE~Zs3XO-15#S;+hS=j zQcT*4u_X2{_;h6FVwKVFKD~XNBYiqW0TKQCD?i-=ZmR$4)7wFyXm>$d5&r)7KV8r; zIMSMnrjT)ad}3V<^EVi#|6L7JcbNVSKAkj7eS8WXNyGe+UjHjU{a?Pybnq03Og4Rn zG>l?jhOXk7U!q%vZX*Vd@}-I2#8VO?ubJ|M<_$;G%!6W@f{lC>K{IQbqf=k0OeRq( zgj0n~G3`sszTwJQ0<7w3(?FobFuPbYBt{!!yjdc)K;~X0U^OQ9G9?-y@xT%Z2le?Q ztIN|bl_4dv!;JwtO$iE=aHFb^1(Vp=Ql&AZuF4YVeluK*?%Lv$y}g?a}2^J z%xB241z*o0VOnq>!Ocwgb1>_;4@kJtL%)$3j*W{LB$koegDa$%8O9OZOSGYsw&6{& zKVe}7a8O|*TfuFL4aii+Fw+oLp&3fp(3af!z+I4QN|b>)$(6xPhj1BN4{kiTsVGLT zZFp1SvaoR{+{}VrrHyIfw%{H>-YFJ*s(k#o=yX_`^X5Nic z@2lIMDK1v;+k1&iHXC|<`q9h1nwp&*kd!7m_r)@kVf^qh1XN8rM>LoFtUqr`f%@ z0rQl{hsy^ZDO1!P@sQ!+ZO%LeE@k}o#ws0bL;M2Q)6|bwl`uv8^Gv$>_KGZ~bXDKs z*W(J91pa=Nh_B~zYdUpC{0Sk*a2)-V8-8B>W+qKboq&*MCRGE67xz3!BamGBueNFl z=gLleHP$L%B=^gT&T0wdo&cv$7#CaByFAbT#N@p8{c!JDV%-E>A7q?{{+1nr`}vQ(>H>^XE*G zM%<@ySjNV^jC-$!nknGNm)7CUi}7gg0PslDsEaV}0WY^)jv7VVYr^(&noZ1|S8;`4 zGhRG?+)W$x02oGkg}bIvQwnA-wpCxrx5rvs*8s}=43>2PdYyupZz*X)JM}j?^H~GP z*=w+qO3Zhu*mnLI@F;nv0hTNB)9gdf5U$VF>cnORcNzMi2>R&(GCn~Cg0gz92l-pQl)Mv{dA+*zJX$yaJQkmv#*Eq&@b;7 z{?8FJM<1~~NHNVZOd<(Vw_DSSvgY!}nsQ&C;N6X*p5?dN-sQmHwn~l}TF;|T%J~5E zibYvE0ng_ScwW*i=Hi{cW#1RhUTwRpr+D(<*8*A?>{E-#o+5LUY{wDB)fZ+gty!{VOT)Wv6eQg2N^wXQN*0M z*NKgJlfSaMO;mW^uhxw^4$ED%PqBAoxX;2qX9u)wJ7!JQl`Tn&Fr{^hMtic#C?y%$?K=-Wla z=tj*PKYiq*a^vymHWYhYiMji{^?v(Go7toqg>@?}=6GwU~f+x+5*<+Jy^{CfAv-rlCICL71!KQ_vD z#ldRNle=`T8atfx+^Z|O(Nem#VQSjwpBC*rwPm=}nK_klg!R#l%iU(!<67X9tmMV+ zJ5@h8eZBI^?^i~b+Eo$gm=Gvl@0^lT2H(@$GT`$L=q#NSF!EHV3VbO zfzB?`O}Q7Q*&a_;E;tzRJ|$2B?mRcXf4Xr*|Bs`TicKr;w8-0ZZ$^%ti*(CG#ZN~Qw`{T9mwd=Od`kar&es-L zL_Z3@;go#zgnzrtkHMW?2E?ujSh=;;uBt8$*$;}(RIblZ*e0BAd?ecP#f5KEUrC3$ z7LFh3uvNEb&a@%_c;@ZWXK_rLykx<5g>$-h?d}o%wdC5=D{eB&(dp6E z&bwOYWt?v`|9VW5InlYX+q*2dKEcQ5Rqny z@VNL1^-R`%|Mc3?gw^4d-eE&xB7^o`2yEe3|HfpUV6!`E#@~1JUKYPM;)lFNdF!st z9#r};X41Q*nKMiR-7`Lp%-Xm!xnK0dkprju=ovlj@bX3UlnoJ|^6!7jy}wFl)~*Rz zF{_Vly=7j|JxG$}KB{-~;OSEW=YRd(-l&Au4-Q(KtXkPDcWTnIl*sum=1r@|9_+I6 zNW|@525_<2jYYU5rt5a>b z#plyc1;)xkAKi&xWnc2c-mnePUhy}2Z0OW?ZQ>KNUb$6m9yw$ziQRB#X-n_7-&l2h z-=jSCY}xqeW%i{WuH|N`tCK9JULMh?xBkKt+nPK1Se3WhpEfNgYWTpMMN#o)TWywm zE&s*O|E1eparvu_C6f$`-yBvc&Cl$;@oh-Qsrl9(-p&2R8#dc|+O)UHFOKnNx`Zx| zdL7bUoVDe}ntErN7jhFeSk5 z``fKs+BCClGj(&Im%e3iyj9i%>7qMx-FOCQH3 zcG#Y1eEPe-A<_?TUJf~~H@{Ey6vLtsMfPmys{war_bIryxkIC*>PgiJ)*(;rUKUJj zH*e^YRgpK(HQsUj;NXrreXK$k71=!>(0{%zW7Dk9<0GFxXFhieZkhX}o_T{S&3(SR zZ@6;Jy<^`5}~VWvdBK_RQ|}7A3B>~&%C#7 z#-N4q$s;@ucA2+2V(k+D_6=W~_1Tb~?6k1K%a`%tcAh3WvyXo_DDptTurAk+=B6s& zZ1GCW+xcTtZ-*OZmYe%mx4yI6zj5B(OIHpZF^I3%{z|KWHYq(8%$RV_;c@3+W3N8Nou%#9&R>!_sQZ)qd+g-Nwr$#O zdw26=ng8P5D-9n$9cxtIIn1~BmUBD$nf|=jCOxB<$B&`*P3Bb;E#2mFb?C;M-_0_c zI@f+=|MZF5S6x5*Zeej*n)k7Uow@c)uY`5E*zvO2r<}*Cp^3pqzk24?rbFPd;a1o5 z%c^&bIX(Tiy;U83PUYks^A(LwyCeO_8u5DL{uaMQMo!Y_~lW$F2=MYDP@9y=qV>)eEvcbl%>WBqc$*E@bT zyWaP!rGA(E7L5E}nLRS$!#11Bo3kU@|Fk`R_xMijr7vCHYtgOL4QAWV zhdSLj8DDYeE3Xxf+Z`~%};oq z8QZ$wJlEyhn;b0fc;xD(&BcR9iC2s|I4$q$!R(_qXYUio=5K6RW`87JR$ehS`+cP} zBdV=W>(@uGk9uQzppsc~ulMmOPQwg>JX$V_PYZm}bDncZ?Cm`P`}4lN`13lQzOtV@ z*XR|Oce4+;qn8wCkTWar;iZOLyP(c)l$ECNMNPJ^rS`5?gNS{OT(RuA}{36 zNSgY6uPa-k9ZS}BO|%&_HgWpaC>J|@NfI-*d1j=`{@V-evbsF_=B9aM>t*j#95N

c+-7ZwU@L|LSAuot%M3HoJH5SM$C90C8jl^hIv~ E0D$s9$^ZZW From 7697d15f7f5de91b2ad4f2be4e4bed992c66ace1 Mon Sep 17 00:00:00 2001 From: Daniel Osorio Date: Wed, 8 Mar 2017 21:58:13 -0500 Subject: [PATCH 26/50] vhseScales was added to README file --- README.md | 1 + 1 file changed, 1 insertion(+) diff --git a/README.md b/README.md index 2df5801..f9935bb 100755 --- a/README.md +++ b/README.md @@ -42,6 +42,7 @@ Available functions |plotXVG | Plot time series from GROMACS XVG files | |readXVG | Read XVG files from GROMACS molecular dynamics package | |tScales| Compute the T-scales of a protein sequence| +|vhseScales|Compute the VHSE-scales of a protein sequence| |zScales| Compute the Z-scales of a protein sequence | Available datasets From c09dc00efeed0fed286bb90c9e123422426a0a5a Mon Sep 17 00:00:00 2001 From: Daniel Osorio Date: Thu, 9 Mar 2017 14:36:05 -0500 Subject: [PATCH 27/50] vhseScales function and data were documented --- NAMESPACE | 1 + R/data-AA.R | 8 ++++++++ R/vhseScales.R | 15 +++++++++++++++ man/AAdata.Rd | 8 ++++++++ man/vhseScales.Rd | 31 +++++++++++++++++++++++++++++++ 5 files changed, 63 insertions(+) create mode 100644 man/vhseScales.Rd diff --git a/NAMESPACE b/NAMESPACE index 4f975b2..acfe8d0 100755 --- a/NAMESPACE +++ b/NAMESPACE @@ -20,6 +20,7 @@ export(pI) export(plotXVG) export(readXVG) export(tScales) +export(vhseScales) export(zScales) importFrom(graphics,par) importFrom(graphics,title) diff --git a/R/data-AA.R b/R/data-AA.R index c523ab9..7394cfa 100644 --- a/R/data-AA.R +++ b/R/data-AA.R @@ -87,6 +87,11 @@ #' \item{F5:} Local flexibility #' \item{F6:} Electronic properties #' } +#' \item{VHSE} The principal components score Vectors of Hydrophobic, Steric, and Electronic properties, is derived from principal components analysis (PCA) on independent families of 18 hydrophobic properties, 17 steric properties, and 15 electronic properties, respectively, which are included in total 50 physicochemical variables of 20 coded amino acids. \itemize{ +#' \item{VHSE1 and VHSE2:} Hydrophobic properties +#' \item{VHSE3 and VHSE4:} Steric properties +#' \item{VHSE5 to VHSE8:} Electronic properties +#' } #' } #' @source #' \itemize{ @@ -129,5 +134,8 @@ #' \item{FASGAI} \itemize{ #' \item Liang, G., & Li, Z. (2007). Factor analysis scale of generalized amino acid information as the source of a new set of descriptors for elucidating the structure and activity relationships of cationic antimicrobial peptides. Molecular Informatics, 26(6), 754-763. #' } +#' \item{VHSE} \itemize{ +#' \item Mei, H. U., Liao, Z. H., Zhou, Y., & Li, S. Z. (2005). A new set of amino acid descriptors and its application in peptide QSARs. Peptide Science, 80(6), 775-786. +#' } #' } NULL diff --git a/R/vhseScales.R b/R/vhseScales.R index 1bf2808..0243f13 100644 --- a/R/vhseScales.R +++ b/R/vhseScales.R @@ -1,3 +1,18 @@ +#' @export vhseScales +#' @title Compute the VHSE-scales of a protein sequence +#' @description VHSE-scales (principal components score Vectors of Hydrophobic, Steric, and Electronic properties), is derived from principal components analysis (PCA) on independent families of 18 hydrophobic properties, 17 steric properties, and 15 electronic properties, respectively, which are included in total 50 physicochemical variables of 20 coded amino acids. +#' @references Mei, H. U., Liao, Z. H., Zhou, Y., & Li, S. Z. (2005). A new set of amino acid descriptors and its application in peptide QSARs. Peptide Science, 80(6), 775-786. +#' @param seq An amino-acids sequence +#' @return The computed average of VHSE-scales of all the amino acids in the corresponding peptide sequence. Each VSHE-scale represent an amino-acid property as follows: \itemize{ +#' \item{VHSE1 and VHSE2:} Hydrophobic properties +#' \item{VHSE3 and VHSE4:} Steric properties +#' \item{VHSE5 to VHSE8:} Electronic properties +#' } +#' @examples vhseScales(seq = "QWGRRCCGWGPGRRYCVRWC") +#' # [[1]] +#' # VHSE1 VHSE2 VHSE3 VHSE4 VHSE5 VHSE6 VHSE7 VHSE8 +#' #-0.1150 0.0630 -0.0055 0.7955 0.4355 0.2485 0.1740 -0.0960 +#' vhseScales <- function(seq){ # Remove spaces and line breaks seq <- gsub("[[:space:]]+","",as.vector(seq)) diff --git a/man/AAdata.Rd b/man/AAdata.Rd index 762e48e..1fac3ce 100644 --- a/man/AAdata.Rd +++ b/man/AAdata.Rd @@ -88,6 +88,11 @@ \item{F5:} Local flexibility \item{F6:} Electronic properties } +\item{VHSE} The principal components score Vectors of Hydrophobic, Steric, and Electronic properties, is derived from principal components analysis (PCA) on independent families of 18 hydrophobic properties, 17 steric properties, and 15 electronic properties, respectively, which are included in total 50 physicochemical variables of 20 coded amino acids. \itemize{ +\item{VHSE1 and VHSE2:} Hydrophobic properties +\item{VHSE3 and VHSE4:} Steric properties +\item{VHSE5 to VHSE8:} Electronic properties +} }} \source{ \itemize{ @@ -137,5 +142,8 @@ A list with a collection of properties, scales and indices for the 20 naturally \item{FASGAI} \itemize{ \item Liang, G., & Li, Z. (2007). Factor analysis scale of generalized amino acid information as the source of a new set of descriptors for elucidating the structure and activity relationships of cationic antimicrobial peptides. Molecular Informatics, 26(6), 754-763. } +\item{VHSE} \itemize{ +\item Mei, H. U., Liao, Z. H., Zhou, Y., & Li, S. Z. (2005). A new set of amino acid descriptors and its application in peptide QSARs. Peptide Science, 80(6), 775-786. +} } } diff --git a/man/vhseScales.Rd b/man/vhseScales.Rd new file mode 100644 index 0000000..c579b9e --- /dev/null +++ b/man/vhseScales.Rd @@ -0,0 +1,31 @@ +% Generated by roxygen2: do not edit by hand +% Please edit documentation in R/vhseScales.R +\name{vhseScales} +\alias{vhseScales} +\title{Compute the VHSE-scales of a protein sequence} +\usage{ +vhseScales(seq) +} +\arguments{ +\item{seq}{An amino-acids sequence} +} +\value{ +The computed average of VHSE-scales of all the amino acids in the corresponding peptide sequence. Each VSHE-scale represent an amino-acid property as follows: \itemize{ +\item{VHSE1 and VHSE2:} Hydrophobic properties +\item{VHSE3 and VHSE4:} Steric properties +\item{VHSE5 to VHSE8:} Electronic properties +} +} +\description{ +VHSE-scales (principal components score Vectors of Hydrophobic, Steric, and Electronic properties), is derived from principal components analysis (PCA) on independent families of 18 hydrophobic properties, 17 steric properties, and 15 electronic properties, respectively, which are included in total 50 physicochemical variables of 20 coded amino acids. +} +\examples{ +vhseScales(seq = "QWGRRCCGWGPGRRYCVRWC") +# [[1]] +# VHSE1 VHSE2 VHSE3 VHSE4 VHSE5 VHSE6 VHSE7 VHSE8 +#-0.1150 0.0630 -0.0055 0.7955 0.4355 0.2485 0.1740 -0.0960 + +} +\references{ +Mei, H. U., Liao, Z. H., Zhou, Y., & Li, S. Z. (2005). A new set of amino acid descriptors and its application in peptide QSARs. Peptide Science, 80(6), 775-786. +} From c3491a7c297c990ae90b941e63f5bb74ffd22c20 Mon Sep 17 00:00:00 2001 From: Daniel Osorio Date: Thu, 9 Mar 2017 14:44:49 -0500 Subject: [PATCH 28/50] AAdata dataset was removed --- R/data-AA.R | 141 ------------------------------------------- data/AAdata.RData | Bin 7945 -> 0 bytes data/datalist | 1 - man/AAdata.Rd | 149 ---------------------------------------------- 4 files changed, 291 deletions(-) delete mode 100644 R/data-AA.R delete mode 100644 data/AAdata.RData delete mode 100644 man/AAdata.Rd diff --git a/R/data-AA.R b/R/data-AA.R deleted file mode 100644 index 7394cfa..0000000 --- a/R/data-AA.R +++ /dev/null @@ -1,141 +0,0 @@ -#' @name AAdata -#' @docType data -#' @title Properties, scales and indices for the 20 naturally occurring amino acids from various sources -#' @description A list with a collection of properties, scales and indices for the 20 naturally occurring amino acids from various sources. -#' @usage data(AAdata) -#' @format A list as follows: \itemize{ -#' \item{Hydrophobicity} The hydrophobicity is an important stabilization force in protein folding; this force changes depending on the solvent in which the protein is found. \itemize{ -#' \item{Aboderin:} Aboderin, A. A. (1971). An empirical hydrophobicity scale for alpha-amino-acids and some of its applications. International Journal of Biochemistry, 2(11), 537-544. -#' \item{AbrahamLeo:} Abraham D.J., Leo A.J. Hydrophobicity (delta G1/2 cal). Proteins: Structure, Function and Genetics 2:130-152(1987). -#' \item{Argos:} Argos, P., Rao, J. K., & Hargrave, P. A. (1982). Structural Prediction of Membrane-Bound Proteins. European Journal of Biochemistry, 128(2-3), 565-575. -#' \item{BlackMould:} Black S.D., Mould D.R. Hydrophobicity of physiological L-alpha amino acids. Anal. Biochem. 193:72-82(1991). -#' \item{BullBreese:} Bull H.B., Breese K. Hydrophobicity (free energy of transfer to surface in kcal/mole). Arch. Biochem. Biophys. 161:665-670(1974). -#' \item{Casari:} Casari, G., & Sippl, M. J. (1992). Structure-derived hydrophobic potential: hydrophobic potential derived from X-ray structures of globular proteins is able to identify native folds. Journal of molecular biology, 224(3), 725-732. -#' \item{Chothia:} Chothia, C. (1976). The nature of the accessible and buried surfaces in proteins. Journal of molecular biology, 105(1), 1-12. -#' \item{Cid:} Cid, H., Bunster, M., Canales, M., & Gazitua, F. (1992). Hydrophobicity and structural classes in proteins. Protein engineering, 5(5), 373-375. -#' \item{Cowan3.4:} Cowan R., Whittaker R.G. Hydrophobicity indices at pH 3.4 determined by HPLC. Peptide Research 3:75-80(1990). -#' \item{Cowan7.5:} Cowan R., Whittaker R.G. Hydrophobicity indices at pH 7.5 determined by HPLC. Peptide Research 3:75-80(1990). -#' \item{Eisenberg:} Eisenberg D., Schwarz E., Komarony M., Wall R. Normalized consensus hydrophobicity scale. J. Mol. Biol. 179:125-142(1984). -#' \item{Engelman:} Engelman, D. M., Steitz, T. A., & Goldman, A. (1986). Identifying nonpolar transbilayer helices in amino acid sequences of membrane proteins. Annual review of biophysics and biophysical chemistry, 15(1), 321-353. -#' \item{Fasman:} Fasman, G. D. (Ed.). (1989). Prediction of protein structure and the principles of protein conformation. Springer. -#' \item{Fauchere:} Fauchere J.-L., Pliska V.E. Hydrophobicity scale (pi-r). Eur. J. Med. Chem. 18:369-375(1983). -#' \item{Goldsack:} Goldsack, D. E., & Chalifoux, R. C. (1973). Contribution of the free energy of mixing of hydrophobic side chains to the stability of the tertiary structure of proteins. Journal of theoretical biology, 39(3), 645-651. -#' \item{Guy:} Guy H.R. Hydrophobicity scale based on free energy of transfer (kcal/mole). Biophys J. 47:61-70(1985). -#' \item{HoppWoods:} Hopp T.P., Woods K.R. Hydrophilicity. Proc. Natl. Acad. Sci. U.S.A. 78:3824-3828(1981). -#' \item{Janin:} Janin J. Free energy of transfer from inside to outside of a globular protein. Nature 277:491-492(1979). -#' \item{Jones:} Jones, D. D. (1975). Amino acid properties and side-chain orientation in proteins: a cross correlation approach. Journal of theoretical biology, 50(1), 167-183. -#' \item{Juretic:} Juretic, D., Lucic, B., Zucic, D., & Trinajstic, N. (1998). Protein transmembrane structure: recognition and prediction by using hydrophobicity scales through preference functions. Theoretical and computational chemistry, 5, 405-445. -#' \item{Kidera:} Kidera, A., Konishi, Y., Oka, M., Ooi, T., & Scheraga, H. A. (1985). Statistical analysis of the physical properties of the 20 naturally occurring amino acids. Journal of Protein Chemistry, 4(1), 23-55. -#' \item{Kuhn:} Kuhn, L. A., Swanson, C. A., Pique, M. E., Tainer, J. A., & Getzoff, E. D. (1995). Atomic and residue hydrophilicity in the context of folded protein structures. Proteins: Structure, Function, and Bioinformatics, 23(4), 536-547. -#' \item{KyteDoolittle:} Kyte J., Doolittle R.F. Hydropathicity. J. Mol. Biol. 157:105-132(1982). -#' \item{Levitt:} Levitt, M. (1976). A simplified representation of protein conformations for rapid simulation of protein folding. Journal of molecular biology, 104(1), 59-107. -#' \item{Manavalan:} Manavalan P., Ponnuswamy Average surrounding hydrophobicity. P.K. Nature 275:673-674(1978). -#' \item{Miyazawa:} Miyazawa S., Jernigen R.L. Hydrophobicity scale (contact energy derived from 3D data). Macromolecules 18:534-552(1985). -#' \item{Parker:} Parker J.M.R., Guo D., Hodges R.S. Hydrophilicity scale derived from HPLC peptide retention times. Biochemistry 25:5425-5431(1986). -#' \item{Ponnuswamy:} Ponnuswamy, P. K. (1993). Hydrophobic charactesristics of folded proteins. Progress in biophysics and molecular biology, 59(1), 57-103. -#' \item{Prabhakaran:} Prabhakaran, M. (1990). The distribution of physical, chemical and conformational properties in signal and nascent peptides. Biochem. J, 269, 691-696. -#' \item{Rao:} Rao M.J.K., Argos P. Membrane buried helix parameter. Biochim. Biophys. Acta 869:197-214(1986). -#' \item{Rose:} Rose G.D., Geselowitz A.R., Lesser G.J., Lee R.H., Zehfus M.H. Mean fractional area loss (f) [average area buried/standard state area]. Science 229:834-838(1985) -#' \item{Roseman:} Roseman M.A. Hydrophobicity scale (pi-r). J. Mol. Biol. 200:513-522(1988). -#' \item{Sweet:} Sweet R.M., Eisenberg D. Optimized matching hydrophobicity (OMH). J. Mol. Biol. 171:479-488(1983). -#' \item{Tanford:} Tanford C. Hydrophobicity scale (Contribution of hydrophobic interactions to the stability of the globular conformation of proteins). J. Am. Chem. Soc. 84:4240-4274(1962). -#' \item{Welling:} Welling G.W., Weijer W.J., Van der Zee R., Welling-Wester S. Antigenicity value X 10. FEBS Lett. 188:215-218(1985). -#' \item{Wilson:} Wilson K.J., Honegger A., Stotzel R.P., Hughes G.J. Hydrophobic constants derived from HPLC peptide retention times. Biochem. J. 199:31-41(1981). -#' \item{Wolfenden:} Wolfenden R.V., Andersson L., Cullis P.M., Southgate C.C.F. Hydration potential (kcal/mole) at 25C. Biochemistry 20:849-855(1981). -#' \item{Zimmerman:} Zimmerman, J. M., Eliezer, N., & Simha, R. (1968). The characterization of amino acid sequences in proteins by statistical methods. Journal of theoretical biology, 21(2), 170-201. -#' } -#' \item{crucianiProperties:} The three Cruciani et. al (2004) properties, are the scaled principal component scores that summarize a broad set of descriptors calculated based on the interaction of each amino acid residue with several chemical groups (or "probes"), such as charged ions, methyl, hydroxyl groups, and so forth. \itemize{ -#' \item{PP1:} Polarity, -#' \item{PP2:} Hydrophobicity, -#' \item{PP3:} H-bonding -#' } -#' \item{kideraFactors:} The Kidera Factors were originally derived by applying multivariate analysis to 188 physical properties of the 20 amino acids and using dimension reduction techniques. A 10-dimensional vector of orthogonal factors was then obtained for each amino acid.The first four factors are essentially pure physical properties; the remaining six factors are superpositions of several physical properties, and are labelled for convenience by the name of the most heavily weighted component \itemize{ -#' \item{helix.bend.pref:} Helix/bend preference -#' \item{side.chain.size:} Side-chain size -#' \item{extended.str.pref:} Extended structure preference -#' \item{hydrophobicity:} Hydrophobicity -#' \item{double.bend.pref:} Double-bend preference -#' \item{partial.spec.vol:} Partial specific volume -#' \item{flat.ext.pref:} Flat extended preference -#' \item{occurrence.alpha.reg:} Occurrence in alpha region -#' \item{pK.C:} pK-C -#' \item{surrounding.hydrop:} Surrounding hydrophobicity -#' } -#' \item{pK}\itemize{ -#' \item{Bjellqvist:} Bjellqvist, B., Hughes, G.J., Pasquali, Ch., Paquet, N., Ravier, F., Sanchez, J.Ch., Frutige,r S., Hochstrasser D. (1993) The focusing positions of polypeptides in immobilized pH gradients can be predicted from their amino acid sequences. Electrophoresis, 14:1023-1031. -#' \item{Dawson:} Dawson, R. M. C.; Elliot, D. C.; Elliot, W. H.; Jones, K. M. Data for biochemical research. Oxford University Press, 1989; p. 592. -#' \item{EMBOSS:} EMBOSS data are from http://emboss.sourceforge.net/apps/release/5.0/emboss/apps/iep.html. -#' \item{Lehninger:} Nelson, D. L.; Cox, M. M. Lehninger Principles of Biochemistry, Fourth Edition; W. H. Freeman, 2004; p. 1100. -#' \item{Murray:} Murray, R.K., Granner, D.K., Rodwell, V.W. (2006) Harper's illustrated Biochemistry. 27th edition. Published by The McGraw-Hill Companies. -#' \item{Rodwell:} Rodwell, J. Heterogeneity of component bands in isoelectric focusing patterns. Analytical Biochemistry, 1982, 119 (2), 440-449. -#' \item{Sillero:} Sillero, A., Maldonado, A. (2006) Isoelectric point determination of proteins and other macromolecules: oscillating method. Comput Biol Med., 36:157-166. -#' \item{Solomon:} Solomon, T.W.G. (1998) Fundamentals of Organic Chemistry, 5th edition. Published by Wiley. -#' \item{Stryer:} Stryer L. (1999) Biochemia. czwarta edycja. Wydawnictwo Naukowe PWN. -#' } -#' \item{zScales} The five Sandberg et al. (1998) Z-scales describe each amino acid with numerical values, descriptors, which represent the physicochemical properties of the amino acids including NMR data and thin-layer chromatography (TLC) data.\itemize{ -#' \item{Z1:} Lipophilicity -#' \item{Z2:} Steric properties (Steric bulk/Polarizability) -#' \item{Z3:} Electronic properties (Polarity / Charge) -#' \item{Z4:} Related to electronegativity, heat of formation, electrophilicity and hardness. -#' \item{Z5:} Related to electronegativity, heat of formation, electrophilicity and hardness. -#' } -#' \item{FASGAI} Factor Analysis Scale of Generalized Amino Acid Information (FASGAI) proposed by Liang and Li (2007), is a set of amino acid descriptors, that reflects hydrophobicity, alpha and turn propensities, bulky properties, compositional characteristics, local flexibility, and electronic properties, was derived from multi-dimensional properties of 20 naturally occurring amino acids. \itemize{ -#' \item{F1:} Hydrophobicity index -#' \item{F2:} Alpha and turn propensities -#' \item{F3:} Bulky properties -#' \item{F4:} Compositional characteristic index -#' \item{F5:} Local flexibility -#' \item{F6:} Electronic properties -#' } -#' \item{VHSE} The principal components score Vectors of Hydrophobic, Steric, and Electronic properties, is derived from principal components analysis (PCA) on independent families of 18 hydrophobic properties, 17 steric properties, and 15 electronic properties, respectively, which are included in total 50 physicochemical variables of 20 coded amino acids. \itemize{ -#' \item{VHSE1 and VHSE2:} Hydrophobic properties -#' \item{VHSE3 and VHSE4:} Steric properties -#' \item{VHSE5 to VHSE8:} Electronic properties -#' } -#' } -#' @source -#' \itemize{ -#' \item{Hydrophobicity}\itemize{ -#' \item ExPASy-Protscale (http://web.expasy.org/protscale/) -#' \item AAIndex Database (http://www.genome.jp/aaindex/) -#' } -#' \item{pK}\itemize{ -#' \item Kiraga, J. (2008) Analysis and computer simulations of variability of isoelectric point of proteins in the proteomes. PhD thesis, University of Wroclaw, Poland. -#' } -#' } -#' @references -#' \itemize{ -#' \item{Hydrophobicity}\itemize{ -#' \item Nakai, K., Kidera, A., and Kanehisa, M.; Cluster analysis of amino acid indices for prediction of protein structure and function. Protein Eng. 2, 93-100 (1988). -#' -#' \item Tomii, K. and Kanehisa, M.; Analysis of amino acid indices and mutation matrices for sequence comparison and structure prediction of proteins. Protein Eng. 9, 27-36 (1996). -#' -#' \item Kawashima, S., Ogata, H., and Kanehisa, M.; AAindex: amino acid index database. Nucleic Acids Res. 27, 368-369 (1999). -#' -#' \item Kawashima, S. and Kanehisa, M.; AAindex: amino acid index database. Nucleic Acids Res. 28, 374 (2000). -#' -#' \item Kawashima, S., Pokarowski, P., Pokarowska, M., Kolinski, A., Katayama, T., and Kanehisa, M.; AAindex: amino acid index database, progress report 2008. Nucleic Acids Res. 36, D202-D205 (2008). -#' } -#' \item{crucianiProperties:} \itemize{ -#' \item Cruciani, G., Baroni, M., Carosati, E., Clementi, M., Valigi, R., and Clementi, S. (2004) Peptide studies by means of principal properties of amino acids derived from MIF descriptors. J. Chemom. 18, 146-155. -#' } -#' \item{kideraFactors:} \itemize{ -#' \item Kidera, A., Konishi, Y., Oka, M., Ooi, T., & Scheraga, H. A. (1985). Statistical analysis of the physical properties of the 20 naturally occurring amino acids. Journal of Protein Chemistry, 4(1), 23-55. -#' } -#' \item{pK:} \itemize{ -#' \item Aronson, J. N. The Henderson-Hasselbalch equation revisited. Biochemical Education, 1983, 11 (2), 68. -#' \item Moore, D. S.. Amino acid and peptide net charges: A simple calculational procedure. Biochemical Education, 1986, 13 (1), 10-12. -#' \item Goloborodko, A.A.; Levitsky, L.I.; Ivanov, M.V.; and Gorshkov, M.V. (2013) "Pyteomics - a Python Framework for Exploratory Data Analysis and Rapid Software Prototyping in Proteomics", Journal of The American Society for Mass Spectrometry, 24(2), 301-304. -#' \item Kiraga, J. (2008) Analysis and computer simulations of variability of isoelectric point of proteins in the proteomes. PhD thesis, University of Wroclaw, Poland. -#' } -#' \item{zScales} \itemize{ -#' \item Sandberg M, Eriksson L, Jonsson J, Sjostrom M, Wold S: New chemical descriptors relevant for the design of biologically active peptides. A multivariate characterization of 87 amino acids. J Med Chem 1998, 41:2481-2491. -#' } -#' \item{FASGAI} \itemize{ -#' \item Liang, G., & Li, Z. (2007). Factor analysis scale of generalized amino acid information as the source of a new set of descriptors for elucidating the structure and activity relationships of cationic antimicrobial peptides. Molecular Informatics, 26(6), 754-763. -#' } -#' \item{VHSE} \itemize{ -#' \item Mei, H. U., Liao, Z. H., Zhou, Y., & Li, S. Z. (2005). A new set of amino acid descriptors and its application in peptide QSARs. Peptide Science, 80(6), 775-786. -#' } -#' } -NULL diff --git a/data/AAdata.RData b/data/AAdata.RData deleted file mode 100644 index cdd2bf47419544a24074f5b9fb6ade59b0a5f58a..0000000000000000000000000000000000000000 GIT binary patch literal 0 HcmV?d00001 literal 7945 zcmV+kANJrMiwFP!000001MOXRSX9TmUOFgECD=P+$AT@I0o zbM~EYzInegqxXPO-D{1iC6mbvWkyDZGDD-PLu13Le+*>CGK;Fx)Ws!G9xkuCp z2VQjGMh6~rFpv%g(ZNtU7(xfb=)j#0Jn6uP4o1>}A02!_2fkJRyd&_rN9~HvMvZAN z8jaB%2u00~du1(ZF5J0S>(kKKdt7Ri?t+l6J>BfMka$*m;v7LEES!q7l+ApH_>Koqwa{J+mxPak#qbD~rdv!3kWxshh$IR(m8gRU2>pv_$Z!hUEg1RB!t>o^OK5TU> zZ9Ml#QZn2tU9)qzSLm0Qq}=okZ^(B#+Or55)ZWis?aCgdB>32!9%6y8Fv zF+PMe=%*6tIpG5OFG-SnE*|=-0M8dg&%7WB&@;R*OXFF3K}5R44fssHFGN^EK~hleeDXeIN3Qd5=2{{e2Gllzur0Sxl6#U@ z(*L9%wxXQ}HE^WouR(8I$2@UcC)NYmdnGX+sCRg;lW-Q2XdHt-rILI+q0K73j2+-pK@o?fhB=33p zslSOw@a<66gAop6TZ9~wG0(Tac*w!K;{YbmuS)|T26t$-`>A)`98mw40a{ib(#lb!fZ8qYKj(l{52QO|*XeTn-LVW%fcI0@j(0`WiCn?k9? z>qHrNM+Wge$UE#P;-947ghHvVZ+H`4BwsY2QJv<+n&;_{;Y~cSyt=%S{Vy6oBOWGNLN7oMh*r?U7LZHu6sq%erTchmv}22Y0k7u4%ZX>RaYW;W{I@i} z+UhC)CVLw4#OyqjLN4?I+2#4L56^?o-Nt=2{923`Vt%aY*Jl22vg=DR|E8cl=oNj# zn|KIU3fy7uF@Hu1O0vfhS731;;@K2u1756uNH5WKifiNocj`~l|8zcCKluss=hY=W zQoUsQq{ey1EB;KM*q~o(>J#`6$e+vf3C+v;u1}JIQ%ybyoPWm$Yw)^%mk+YI(f?6C z$hX%87N+oRrTL0?1m9@$i^MlN_t)tSzAfVLZ7=Ec4&P2nq~P1ZuhPX&dag6@b_6f! zg!?<8UmZ_L`45f}5?^U6m;5&!(Ow6z!A!H-g3vS0aT`sqL6W!3d1-vn|< zNmCgAd;^?s4!rGgKb{v`NY_P5n!_#W&w=F+A#TQaH~Aln z^wgfGcqGLcVee5~lgkE9RHqVg17Jld?f{w6;PR{{J`isY9nLtMX1_6O+=oG1TM9q`3Q21=xZ>r~KlAdAl zG_pg@;rB2G4=E+RPX1WPw+YUlfxad_jyxFN41B&^-}Fhf-{FXh<}Uu~K!rvbf_g0% ze~mm?K6$7@jWZ@Lnjm!;UGA@v2TU5Kj!*@%GZ89Pe~m&Brob6fS9zFRqeRWjHCP=U ztdyf_gvYfuv)LkC-zGm(& zj|d1>Xy`M{J=Cheu&S@6H+w`(rOlHgCWGZ63<8tE>JSB8F&iAAQG_c4 z=#@j1RcO(VF&+{TOix)2nI5hfpjNAt;o&L<#Zbl6sye-Pm^?&2Rjzvf$-|V>qs*(ngYrlb$_D|?>$mB`?k zztCCqkHEXy?=T`|=jqw){bBd_ht3};qgrfmUi z5}}o3uhAcrp$QKvMb;@ILCldXP`$&OJjn1A3nb5!NdilmWuTTqZm|N7d5XYvNg1*0 zq|EP8WCoT$W%?ALAILMCNf9Ca%pCdu%&7liylKT4@S*X~JgOMi99tO-eNW_t;7PyG`~VWlGPKc-kT1;_OdloFk)GjAkrmp>0c3+BW4saMAD(R@+e9KctRNxM zD9R`U3gd)Uywi9gPaeo32i%G52#BoF{d$Kt$QwuUOe=SR6X8WG9ywYugO!a!1(9*^ z88W^|PZR&3$N`c6cbHE}-xIkfV~OqHp=Wp#xuzAOv@(hKAMM;gdgVT?Fa!RSK}jn) zXk{y9D9|{djAhC+%db(Ak&2bcWUT5N-fTS6ihr8#$Y`Y%HP9ErUEuQ;@{H>&a!dMx zl@yL3&-Y7$Tvm2nOuT@(9RE}@3C`{P!74wuCdbt z_>b_2R$fDoQ~wg5r~47PA&;&8;9c!^)WSuZV1-H<>Ey2n33Lk8C??S9FlC^^DIi#` z3~>rm&L9U}9Ytig)~^=m6c(=e@P6yy>46$`Xt3H}8K4X&&!26eI>KM2_+9I^p>j>Q zQm%3e3snR-O;xLK-fDtM9`022jt_6PQwIb@Xf%qD0ELrW6&fse(kRI7XB;}ji9oI! zR&|#;A|y~5667R(j_kdCZ2@_+;9JRbf4nVaG$Nu@9~oN6kmK8-q`D>SG(?Ar=z5#!8SEN9oH@J92R;19iNU( z-Potox^v1;Y=cj1U*pp$-q%v9|1GE^WtFAC;u9I_NO5h4lvanZnfMNPy)i5=O=|AApNyF5^r%*{6=Fjx{-}&i(_^Mj{Cn{8`DN~hU6#FtAAfNU= zx@GD%tp5lfn)oe-DuP3*raacX>9DGKP)<{@nYTJ{T2*sY^--!+3XPgo)hhMm_bvN` zYo;?;wbP~vqs1`0cuOQkn`6A$Ahtl}UO8YjC-*WX8X)n&1_=jsq>?w3=$B|piR^G= zfKF3_0wvstb+BL(8(WITf1w%jkBA{4q1uoV1Ek;0kvoEDGP$jjaUEu}XbUqL8x|3r zri2>W7?9lClsLj@GR$bv08@qy7Tg#ivBTsqG_(Ifc$2w63+Fh5O}KZEV{7TWfP`u0 zK7yN>@E2g#32%^aV}yPqGaMTiaY!s9w}+5NF*A%KxR+={DSgA6Vt;I51#l3tku7tZ zVgoYK9A+BADl|i}4Q-F6e+aj!;e_tkC76%=Uq?L8wT zSq?fewkIb%#q1G-=dui?3yHejcq4?O5l{OCj&7XPCy+wwPc5_(E)*a6c$BUGaN)-# z9kmiD+yhQ;F)lW0cX^)umdkwR^XA5b`dqqno{I+?x~)ZjW)4?0-lYopOF}C8GtX7m zlLBq;EnBG*Xs#UnCG9fZP~Y(8Fz$tf3hjWuDm)0*R3W`ZxQJO;1~&5;?E9*O6G!@| zSn4M(Lo4-~pSX8bol(_8T%x28glw&NzuqcD>$>SvElF;LOf8BnF0k$8beovFEEDp;W;`YQgv<8Y0Wg^K zif}=vrqtX_Y^%OhYLB=JO_yvu9u@<(Ti1vF-c= z;8FNM2dt3qtJ{a3BU~S9)rtKQ;Vkq)KJ?QqWPq-sWyO+y5q_4&5tk~B2gaV_p^tL4 z)AgI1`h$11-(gBD#+|VpcgA+y8QXDZY{$JPJL)BS&wI?-xIqw~u|>*Iq+l^w2?!$7 zHg_z;kb?9SbR&I}PZ^BWx83(M2Q6?x^Uld#ej%1ApSjI}*4YH)fQna6~r@V)@OQL0`lqpL|oD}4w zBtj(jh$ghXJ*;I))+BEP1y4!-X?!H3fAT093-70GPAT~d{i1hxLynj}pyY{#kY5V^ zQ}P?|q~%a7Sd3+oY`gnRN@fGT^gIRcsXxj4LrHR!Jok>0we$;b$~5OnfL991FO6s5 z0Plim052rz3EGC9{ zbBKD#;0-2kKIsce%A%weniq?JFXNfzm!x=_|VEK zTIoV^O3S@z`893RLG`ri{l#0>NRmSm9$U#p$^TpR4ex5d!yFe)dGffy_lK1}fADTI++aQMk1~wv252Gzl=2XzXVo=@CS1vuKw3@Gt$B2p z2ZXCNbkZ=CU^1KG6ChWyyG`9)d^}tTRb%bPy#E&Ve-K(adCNlr)svmV6pBFYJE~gL zR9#+Mb==!KXnXyr2RY3)ciP*(wMO6u)%NK1=%l|@*}Mz`|A#aCJuK`JbNX8E;&1Y1 zEN`)`yL>|bq!~L6l1lyeRX!hW5K`KB&X+$u@;aNm;MUj2xq+KkiO-XluG)3AYv0ck z9{0c4!tkbR#}4)nJlxcN`KM-go8)sxZgk*dp64vBY#9}v{gd5C?FVPg z+pXR?JluP3uM_>6w*GuY#l(y0H(j>wTQT0o*>?Hd<8DJP#J&wn$?w@g~7DwL8 z>ep|l=@_S#$6Ck+HYtxh{?X<$GK;L|8T*}=o;wgYpty09o7=osPi@q?^+xl)_fE&I zn)zL$StXyGsMwOQ(8Fs{%1>otg9VSzY;UCMR31?{wocEdT{@(EyX&&m$h96#xx^kf z8ap(x{^Hc~(2oO_eKElFyQCjqdOtF2J*DS-TSwzo5iy2Q)5c60ey7xY%x`N7JkG^j zf7pDFL%IEoWu0q(Tl>4Nvv*uD`LSTPc-HAF^IbP=eTODjK3x*zo*msF_28`s$&G6_ zGWYc1maMYuGiB54f^nrYc0BoP`_Z0WwVF*ZkGpwzgwK+Fl|zqiGdOSV_}kE(hKfr~ zl^g3Nr;Pl5-qvFqhA3UQV`&F@Z^K<#n@qc12$-0WG~a!z_^tD2OV6F%a42NMqi!#b zE*Tk9aqDJCPQMO|&swL3O!+A2>V$5xj(hrwc75;U<$ZTz>$^AgUM+DjA2K-c<*cPQ zA6&nF^umEdpB1-~J&f_bo9H;+_;q@wZK1({QF8}#C)y3@vTd8kP`8*-ibtJ{o>&<* z`j~HG7i8=f;nin%x#K5p&BvYn+Ae=tL?Wl0RkrC!e~X2_0WPl54TZzFLV+#&OfUwAe7;?U{ju5Of$m>zisG(YIuT zM!jz7wI7>`vP66+W?V7ncijtfTLQUvf@5bi}VsdPz`6 z*M6}p{FiQQwymO*k_(68Q ztz>w{+O0`_qHhoXWQwhst)9Z)=}Z5aY*n3SAuaEV!*aW5eSWwSTpG zcxC#*;f61cIa{xLWixHbO5ZI@mO2lKZ0x&wVcBob8oEvWIr*owQyH0oQJ3svc@L`= z@x5o(S^jo>_Uqv8`92>F360(#?%XhB@UA(@9X|6^B^+4SKH=u8XI85w`$fgBd-yVD ze_#~%`EM_VTx}%J8{u~0=;r1*MqVRN^c}r2$~kL)Vy_tqrjPtveRH*WQ~O3XEhnuH z@HDmwinGnQrJQ$d=F7rST?eW=9q_*NitB#&@|25*TyMDD8oFC~;!3h}hU-AJLF9`G z;p112v*;{tDzLVSTO;?%9Y0In!^`N&ncgeMmVMq?)uZ;%Wee}dCbZj}V1E3o-oeT@ z&z}tZ#b|b~%891=!}1;Y(5L;b&FGbTV|}}i5-Z17#@hwoZ}lX1T$@>g7A%Xr{9FAk zzwGPZ-k_Il=)C+^5Bv3UHC<=}&HZ+C^`QF&9iooq3}5=Dqt(Uq8=IznIyWw9*wB5Q zW-X6cxxlY&y=Rua)}$sm&#n99NnCiVp%w-+e);Ot$i2CPJ6$}Km8^Nb!80Ly>vs*k z94}egtnXXd{MvTE`q|gdoZElUB(8SbbItr)KI%4S>e$~L?{+-=sMkE<)RQX}H@AJ? z)pvd0>kq>FCMZ^V-%kqrM2y^Q?%AuLqq6PF*$dJ??RxL#j#eQ_En2qT^y+d+vETgd zOHFUzA7xg@CCsPihTpdIsrAE7`_!}^9^ZvJG?-PEzi^Z5`9W(he>L55(oBcpeN)G6 zUUu=stGNZmDPD);w`MskJQvpKbo;ZGZ!_ig zcUH9bK9-q%*he-p<(l$eE99%q`&$1T898O=f_3#D^cmY=`{r3^jmFMR`r7W1{j|)y zN0H7ai|RzK+GbpoTA82jw1#+dig4+g-Ku9izQ-JX04g?lJF5@*2y{Cqtbt9gQp7 z|FP#1C*h{YwxZ)s&3>|M*e|y9>)WMai!Ti=Z};oq`Mzh4I)^lS)@*kC!}QqZeP#_< zyt%=?()I_>pIKkfe}sI=h<%f@&+mJ2=<Ivn`yZusUjL)*B#*Kpm$`!SaS_f|5tFEvy-8wJwRL<1IN#FE1 zw;|f8aAoHN`%gzDOxYOa+R9jw$c<{89_hO0>YP>?o$h>b*($R6qSucc(ka z_ulEAD^|xAcaFY)prv|U+@@)hEuI>l{MA>{dF0BDtIgXL=5HFb;g?xgzuDchBJ%j? z0U55_Tps&m1<#sw)TM8NVeBrK4MD*tpOzF|%lzcvdiQpITE6!m`A0`QReJycJy9QP diff --git a/data/datalist b/data/datalist index 0fb67fe..2444b89 100755 --- a/data/datalist +++ b/data/datalist @@ -1,2 +1 @@ -AAdata pepdata \ No newline at end of file diff --git a/man/AAdata.Rd b/man/AAdata.Rd deleted file mode 100644 index 1fac3ce..0000000 --- a/man/AAdata.Rd +++ /dev/null @@ -1,149 +0,0 @@ -% Generated by roxygen2: do not edit by hand -% Please edit documentation in R/data-AA.R -\docType{data} -\name{AAdata} -\alias{AAdata} -\title{Properties, scales and indices for the 20 naturally occurring amino acids from various sources} -\format{A list as follows: \itemize{ -\item{Hydrophobicity} The hydrophobicity is an important stabilization force in protein folding; this force changes depending on the solvent in which the protein is found. \itemize{ -\item{Aboderin:} Aboderin, A. A. (1971). An empirical hydrophobicity scale for alpha-amino-acids and some of its applications. International Journal of Biochemistry, 2(11), 537-544. -\item{AbrahamLeo:} Abraham D.J., Leo A.J. Hydrophobicity (delta G1/2 cal). Proteins: Structure, Function and Genetics 2:130-152(1987). -\item{Argos:} Argos, P., Rao, J. K., & Hargrave, P. A. (1982). Structural Prediction of Membrane-Bound Proteins. European Journal of Biochemistry, 128(2-3), 565-575. -\item{BlackMould:} Black S.D., Mould D.R. Hydrophobicity of physiological L-alpha amino acids. Anal. Biochem. 193:72-82(1991). -\item{BullBreese:} Bull H.B., Breese K. Hydrophobicity (free energy of transfer to surface in kcal/mole). Arch. Biochem. Biophys. 161:665-670(1974). -\item{Casari:} Casari, G., & Sippl, M. J. (1992). Structure-derived hydrophobic potential: hydrophobic potential derived from X-ray structures of globular proteins is able to identify native folds. Journal of molecular biology, 224(3), 725-732. -\item{Chothia:} Chothia, C. (1976). The nature of the accessible and buried surfaces in proteins. Journal of molecular biology, 105(1), 1-12. -\item{Cid:} Cid, H., Bunster, M., Canales, M., & Gazitua, F. (1992). Hydrophobicity and structural classes in proteins. Protein engineering, 5(5), 373-375. -\item{Cowan3.4:} Cowan R., Whittaker R.G. Hydrophobicity indices at pH 3.4 determined by HPLC. Peptide Research 3:75-80(1990). -\item{Cowan7.5:} Cowan R., Whittaker R.G. Hydrophobicity indices at pH 7.5 determined by HPLC. Peptide Research 3:75-80(1990). -\item{Eisenberg:} Eisenberg D., Schwarz E., Komarony M., Wall R. Normalized consensus hydrophobicity scale. J. Mol. Biol. 179:125-142(1984). -\item{Engelman:} Engelman, D. M., Steitz, T. A., & Goldman, A. (1986). Identifying nonpolar transbilayer helices in amino acid sequences of membrane proteins. Annual review of biophysics and biophysical chemistry, 15(1), 321-353. -\item{Fasman:} Fasman, G. D. (Ed.). (1989). Prediction of protein structure and the principles of protein conformation. Springer. -\item{Fauchere:} Fauchere J.-L., Pliska V.E. Hydrophobicity scale (pi-r). Eur. J. Med. Chem. 18:369-375(1983). -\item{Goldsack:} Goldsack, D. E., & Chalifoux, R. C. (1973). Contribution of the free energy of mixing of hydrophobic side chains to the stability of the tertiary structure of proteins. Journal of theoretical biology, 39(3), 645-651. -\item{Guy:} Guy H.R. Hydrophobicity scale based on free energy of transfer (kcal/mole). Biophys J. 47:61-70(1985). -\item{HoppWoods:} Hopp T.P., Woods K.R. Hydrophilicity. Proc. Natl. Acad. Sci. U.S.A. 78:3824-3828(1981). -\item{Janin:} Janin J. Free energy of transfer from inside to outside of a globular protein. Nature 277:491-492(1979). -\item{Jones:} Jones, D. D. (1975). Amino acid properties and side-chain orientation in proteins: a cross correlation approach. Journal of theoretical biology, 50(1), 167-183. -\item{Juretic:} Juretic, D., Lucic, B., Zucic, D., & Trinajstic, N. (1998). Protein transmembrane structure: recognition and prediction by using hydrophobicity scales through preference functions. Theoretical and computational chemistry, 5, 405-445. -\item{Kidera:} Kidera, A., Konishi, Y., Oka, M., Ooi, T., & Scheraga, H. A. (1985). Statistical analysis of the physical properties of the 20 naturally occurring amino acids. Journal of Protein Chemistry, 4(1), 23-55. -\item{Kuhn:} Kuhn, L. A., Swanson, C. A., Pique, M. E., Tainer, J. A., & Getzoff, E. D. (1995). Atomic and residue hydrophilicity in the context of folded protein structures. Proteins: Structure, Function, and Bioinformatics, 23(4), 536-547. -\item{KyteDoolittle:} Kyte J., Doolittle R.F. Hydropathicity. J. Mol. Biol. 157:105-132(1982). -\item{Levitt:} Levitt, M. (1976). A simplified representation of protein conformations for rapid simulation of protein folding. Journal of molecular biology, 104(1), 59-107. -\item{Manavalan:} Manavalan P., Ponnuswamy Average surrounding hydrophobicity. P.K. Nature 275:673-674(1978). -\item{Miyazawa:} Miyazawa S., Jernigen R.L. Hydrophobicity scale (contact energy derived from 3D data). Macromolecules 18:534-552(1985). -\item{Parker:} Parker J.M.R., Guo D., Hodges R.S. Hydrophilicity scale derived from HPLC peptide retention times. Biochemistry 25:5425-5431(1986). -\item{Ponnuswamy:} Ponnuswamy, P. K. (1993). Hydrophobic charactesristics of folded proteins. Progress in biophysics and molecular biology, 59(1), 57-103. -\item{Prabhakaran:} Prabhakaran, M. (1990). The distribution of physical, chemical and conformational properties in signal and nascent peptides. Biochem. J, 269, 691-696. -\item{Rao:} Rao M.J.K., Argos P. Membrane buried helix parameter. Biochim. Biophys. Acta 869:197-214(1986). -\item{Rose:} Rose G.D., Geselowitz A.R., Lesser G.J., Lee R.H., Zehfus M.H. Mean fractional area loss (f) [average area buried/standard state area]. Science 229:834-838(1985) -\item{Roseman:} Roseman M.A. Hydrophobicity scale (pi-r). J. Mol. Biol. 200:513-522(1988). -\item{Sweet:} Sweet R.M., Eisenberg D. Optimized matching hydrophobicity (OMH). J. Mol. Biol. 171:479-488(1983). -\item{Tanford:} Tanford C. Hydrophobicity scale (Contribution of hydrophobic interactions to the stability of the globular conformation of proteins). J. Am. Chem. Soc. 84:4240-4274(1962). -\item{Welling:} Welling G.W., Weijer W.J., Van der Zee R., Welling-Wester S. Antigenicity value X 10. FEBS Lett. 188:215-218(1985). -\item{Wilson:} Wilson K.J., Honegger A., Stotzel R.P., Hughes G.J. Hydrophobic constants derived from HPLC peptide retention times. Biochem. J. 199:31-41(1981). -\item{Wolfenden:} Wolfenden R.V., Andersson L., Cullis P.M., Southgate C.C.F. Hydration potential (kcal/mole) at 25C. Biochemistry 20:849-855(1981). -\item{Zimmerman:} Zimmerman, J. M., Eliezer, N., & Simha, R. (1968). The characterization of amino acid sequences in proteins by statistical methods. Journal of theoretical biology, 21(2), 170-201. -} -\item{crucianiProperties:} The three Cruciani et. al (2004) properties, are the scaled principal component scores that summarize a broad set of descriptors calculated based on the interaction of each amino acid residue with several chemical groups (or "probes"), such as charged ions, methyl, hydroxyl groups, and so forth. \itemize{ -\item{PP1:} Polarity, -\item{PP2:} Hydrophobicity, -\item{PP3:} H-bonding -} -\item{kideraFactors:} The Kidera Factors were originally derived by applying multivariate analysis to 188 physical properties of the 20 amino acids and using dimension reduction techniques. A 10-dimensional vector of orthogonal factors was then obtained for each amino acid.The first four factors are essentially pure physical properties; the remaining six factors are superpositions of several physical properties, and are labelled for convenience by the name of the most heavily weighted component \itemize{ -\item{helix.bend.pref:} Helix/bend preference -\item{side.chain.size:} Side-chain size -\item{extended.str.pref:} Extended structure preference -\item{hydrophobicity:} Hydrophobicity -\item{double.bend.pref:} Double-bend preference -\item{partial.spec.vol:} Partial specific volume -\item{flat.ext.pref:} Flat extended preference -\item{occurrence.alpha.reg:} Occurrence in alpha region -\item{pK.C:} pK-C -\item{surrounding.hydrop:} Surrounding hydrophobicity -} -\item{pK}\itemize{ -\item{Bjellqvist:} Bjellqvist, B., Hughes, G.J., Pasquali, Ch., Paquet, N., Ravier, F., Sanchez, J.Ch., Frutige,r S., Hochstrasser D. (1993) The focusing positions of polypeptides in immobilized pH gradients can be predicted from their amino acid sequences. Electrophoresis, 14:1023-1031. -\item{Dawson:} Dawson, R. M. C.; Elliot, D. C.; Elliot, W. H.; Jones, K. M. Data for biochemical research. Oxford University Press, 1989; p. 592. -\item{EMBOSS:} EMBOSS data are from http://emboss.sourceforge.net/apps/release/5.0/emboss/apps/iep.html. -\item{Lehninger:} Nelson, D. L.; Cox, M. M. Lehninger Principles of Biochemistry, Fourth Edition; W. H. Freeman, 2004; p. 1100. -\item{Murray:} Murray, R.K., Granner, D.K., Rodwell, V.W. (2006) Harper's illustrated Biochemistry. 27th edition. Published by The McGraw-Hill Companies. -\item{Rodwell:} Rodwell, J. Heterogeneity of component bands in isoelectric focusing patterns. Analytical Biochemistry, 1982, 119 (2), 440-449. -\item{Sillero:} Sillero, A., Maldonado, A. (2006) Isoelectric point determination of proteins and other macromolecules: oscillating method. Comput Biol Med., 36:157-166. -\item{Solomon:} Solomon, T.W.G. (1998) Fundamentals of Organic Chemistry, 5th edition. Published by Wiley. -\item{Stryer:} Stryer L. (1999) Biochemia. czwarta edycja. Wydawnictwo Naukowe PWN. -} -\item{zScales} The five Sandberg et al. (1998) Z-scales describe each amino acid with numerical values, descriptors, which represent the physicochemical properties of the amino acids including NMR data and thin-layer chromatography (TLC) data.\itemize{ -\item{Z1:} Lipophilicity -\item{Z2:} Steric properties (Steric bulk/Polarizability) -\item{Z3:} Electronic properties (Polarity / Charge) -\item{Z4:} Related to electronegativity, heat of formation, electrophilicity and hardness. -\item{Z5:} Related to electronegativity, heat of formation, electrophilicity and hardness. -} -\item{FASGAI} Factor Analysis Scale of Generalized Amino Acid Information (FASGAI) proposed by Liang and Li (2007), is a set of amino acid descriptors, that reflects hydrophobicity, alpha and turn propensities, bulky properties, compositional characteristics, local flexibility, and electronic properties, was derived from multi-dimensional properties of 20 naturally occurring amino acids. \itemize{ -\item{F1:} Hydrophobicity index -\item{F2:} Alpha and turn propensities -\item{F3:} Bulky properties -\item{F4:} Compositional characteristic index -\item{F5:} Local flexibility -\item{F6:} Electronic properties -} -\item{VHSE} The principal components score Vectors of Hydrophobic, Steric, and Electronic properties, is derived from principal components analysis (PCA) on independent families of 18 hydrophobic properties, 17 steric properties, and 15 electronic properties, respectively, which are included in total 50 physicochemical variables of 20 coded amino acids. \itemize{ -\item{VHSE1 and VHSE2:} Hydrophobic properties -\item{VHSE3 and VHSE4:} Steric properties -\item{VHSE5 to VHSE8:} Electronic properties -} -}} -\source{ -\itemize{ -\item{Hydrophobicity}\itemize{ -\item ExPASy-Protscale (http://web.expasy.org/protscale/) -\item AAIndex Database (http://www.genome.jp/aaindex/) -} -\item{pK}\itemize{ -\item Kiraga, J. (2008) Analysis and computer simulations of variability of isoelectric point of proteins in the proteomes. PhD thesis, University of Wroclaw, Poland. -} -} -} -\usage{ -data(AAdata) -} -\description{ -A list with a collection of properties, scales and indices for the 20 naturally occurring amino acids from various sources. -} -\references{ -\itemize{ -\item{Hydrophobicity}\itemize{ -\item Nakai, K., Kidera, A., and Kanehisa, M.; Cluster analysis of amino acid indices for prediction of protein structure and function. Protein Eng. 2, 93-100 (1988). - -\item Tomii, K. and Kanehisa, M.; Analysis of amino acid indices and mutation matrices for sequence comparison and structure prediction of proteins. Protein Eng. 9, 27-36 (1996). - -\item Kawashima, S., Ogata, H., and Kanehisa, M.; AAindex: amino acid index database. Nucleic Acids Res. 27, 368-369 (1999). - -\item Kawashima, S. and Kanehisa, M.; AAindex: amino acid index database. Nucleic Acids Res. 28, 374 (2000). - -\item Kawashima, S., Pokarowski, P., Pokarowska, M., Kolinski, A., Katayama, T., and Kanehisa, M.; AAindex: amino acid index database, progress report 2008. Nucleic Acids Res. 36, D202-D205 (2008). -} -\item{crucianiProperties:} \itemize{ -\item Cruciani, G., Baroni, M., Carosati, E., Clementi, M., Valigi, R., and Clementi, S. (2004) Peptide studies by means of principal properties of amino acids derived from MIF descriptors. J. Chemom. 18, 146-155. -} -\item{kideraFactors:} \itemize{ -\item Kidera, A., Konishi, Y., Oka, M., Ooi, T., & Scheraga, H. A. (1985). Statistical analysis of the physical properties of the 20 naturally occurring amino acids. Journal of Protein Chemistry, 4(1), 23-55. -} -\item{pK:} \itemize{ -\item Aronson, J. N. The Henderson-Hasselbalch equation revisited. Biochemical Education, 1983, 11 (2), 68. -\item Moore, D. S.. Amino acid and peptide net charges: A simple calculational procedure. Biochemical Education, 1986, 13 (1), 10-12. -\item Goloborodko, A.A.; Levitsky, L.I.; Ivanov, M.V.; and Gorshkov, M.V. (2013) "Pyteomics - a Python Framework for Exploratory Data Analysis and Rapid Software Prototyping in Proteomics", Journal of The American Society for Mass Spectrometry, 24(2), 301-304. -\item Kiraga, J. (2008) Analysis and computer simulations of variability of isoelectric point of proteins in the proteomes. PhD thesis, University of Wroclaw, Poland. -} -\item{zScales} \itemize{ -\item Sandberg M, Eriksson L, Jonsson J, Sjostrom M, Wold S: New chemical descriptors relevant for the design of biologically active peptides. A multivariate characterization of 87 amino acids. J Med Chem 1998, 41:2481-2491. -} -\item{FASGAI} \itemize{ -\item Liang, G., & Li, Z. (2007). Factor analysis scale of generalized amino acid information as the source of a new set of descriptors for elucidating the structure and activity relationships of cationic antimicrobial peptides. Molecular Informatics, 26(6), 754-763. -} -\item{VHSE} \itemize{ -\item Mei, H. U., Liao, Z. H., Zhou, Y., & Li, S. Z. (2005). A new set of amino acid descriptors and its application in peptide QSARs. Peptide Science, 80(6), 775-786. -} -} -} From eb767983de8ce1f8a9b547f9c3c4d5662ce199e1 Mon Sep 17 00:00:00 2001 From: Daniel Osorio Date: Thu, 9 Mar 2017 14:45:10 -0500 Subject: [PATCH 29/50] kideraFactors output was renamed as KF# --- R/kideraFactors.R | 31 +++++++++++++------------------ man/kideraFactors.Rd | 31 +++++++++++++------------------ 2 files changed, 26 insertions(+), 36 deletions(-) diff --git a/R/kideraFactors.R b/R/kideraFactors.R index 2054155..bde2eac 100644 --- a/R/kideraFactors.R +++ b/R/kideraFactors.R @@ -5,28 +5,23 @@ #' @param seq An amino-acids sequence #' @return A list with the average of the ten Kidera factors. #' The first four factors are essentially pure physical properties; the remaining six factors are superpositions of several physical properties, and are labelled for convenience by the name of the most heavily weighted component. -#' \itemize{\item{Helix/bend preference}, -#' \item{Side-chain size}, -#' \item{Extended structure preference}, -#' \item{Hydrophobicity}, -#' \item{Double-bend preference}, -#' \item{Partial specific volume}, -#' \item{Flat extended preference}, -#' \item{Occurrence in alpha region}, -#' \item{pK-C}, -#' \item{Surrounding hydrophobicity}} +#' \itemize{ +#' \item{KF1:} Helix/bend preference, +#' \item{KF2:} Side-chain size, +#' \item{KF3:} Extended structure preference, +#' \item{KF4:} Hydrophobicity, +#' \item{KF5:} Double-bend preference, +#' \item{KF6:} Partial specific volume, +#' \item{KF7:} Flat extended preference, +#' \item{KF8:} Occurrence in alpha region, +#' \item{KF9:} pK-C, +#' \item{KF10:} Surrounding hydrophobicity} #' @references Kidera, A., Konishi, Y., Oka, M., Ooi, T., & Scheraga, H. A. (1985). Statistical analysis of the physical properties of the 20 naturally occurring amino acids. Journal of Protein Chemistry, 4(1), 23-55. #' @examples #' kideraFactors(seq = "KLKLLLLLKLK") #' # [[1]] -#' # helix.bend.pref side.chain.size extended.str.pref -#' # -0.78545455 0.29818182 -0.23636364 -#' # hydrophobicity double.bend.pref partial.spec.vol -#' # -0.08181818 0.21000000 -1.89363636 -#' # flat.ext.pref occurrence.alpha.reg pK.C -#' # 1.02909091 -0.51272727 0.11181818 -#' # surrounding.hydrop -#' # 0.81000000 +#' KF1 KF2 KF3 KF4 KF5 KF6 KF7 KF8 KF9 KF10 +#' -0.78545455 0.29818182 -0.23636364 -0.08181818 0.21000000 -1.89363636 1.02909091 -0.51272727 0.11181818 0.81000000 kideraFactors <- function (seq) { # Remove the break lines from the sequence diff --git a/man/kideraFactors.Rd b/man/kideraFactors.Rd index c4b17b8..ada9fed 100644 --- a/man/kideraFactors.Rd +++ b/man/kideraFactors.Rd @@ -12,16 +12,17 @@ kideraFactors(seq) \value{ A list with the average of the ten Kidera factors. The first four factors are essentially pure physical properties; the remaining six factors are superpositions of several physical properties, and are labelled for convenience by the name of the most heavily weighted component. -\itemize{\item{Helix/bend preference}, -\item{Side-chain size}, -\item{Extended structure preference}, -\item{Hydrophobicity}, -\item{Double-bend preference}, -\item{Partial specific volume}, -\item{Flat extended preference}, -\item{Occurrence in alpha region}, -\item{pK-C}, -\item{Surrounding hydrophobicity}} +\itemize{ +\item{KF1:} Helix/bend preference, +\item{KF2:} Side-chain size, +\item{KF3:} Extended structure preference, +\item{KF4:} Hydrophobicity, +\item{KF5:} Double-bend preference, +\item{KF6:} Partial specific volume, +\item{KF7:} Flat extended preference, +\item{KF8:} Occurrence in alpha region, +\item{KF9:} pK-C, +\item{KF10:} Surrounding hydrophobicity} } \description{ The Kidera Factors were originally derived by applying multivariate analysis to 188 physical properties of the 20 amino acids and using dimension reduction techniques. This function calculates the average of the ten Kidera factors for a protein sequence. @@ -29,14 +30,8 @@ The Kidera Factors were originally derived by applying multivariate analysis to \examples{ kideraFactors(seq = "KLKLLLLLKLK") # [[1]] -# helix.bend.pref side.chain.size extended.str.pref -# -0.78545455 0.29818182 -0.23636364 -# hydrophobicity double.bend.pref partial.spec.vol -# -0.08181818 0.21000000 -1.89363636 -# flat.ext.pref occurrence.alpha.reg pK.C -# 1.02909091 -0.51272727 0.11181818 -# surrounding.hydrop -# 0.81000000 + KF1 KF2 KF3 KF4 KF5 KF6 KF7 KF8 KF9 KF10 +-0.78545455 0.29818182 -0.23636364 -0.08181818 0.21000000 -1.89363636 1.02909091 -0.51272727 0.11181818 0.81000000 } \references{ Kidera, A., Konishi, Y., Oka, M., Ooi, T., & Scheraga, H. A. (1985). Statistical analysis of the physical properties of the 20 naturally occurring amino acids. Journal of Protein Chemistry, 4(1), 23-55. From 2deac15eaa4a5e1fc98cd4ea7099561195e4dc2a Mon Sep 17 00:00:00 2001 From: Daniel Osorio Date: Thu, 9 Mar 2017 14:45:41 -0500 Subject: [PATCH 30/50] Several amino acids descriptors were added --- R/sysdata.rda | Bin 8253 -> 9770 bytes 1 file changed, 0 insertions(+), 0 deletions(-) diff --git a/R/sysdata.rda b/R/sysdata.rda index 15199fb0b9c64e82766337ee35915d50e104038d..df37dab7b1d30f93da27da1e481fcdf2cd979321 100644 GIT binary patch literal 9770 zcmV+_Ce_&=iwFP!000001MPixSQXdT?x9FgnkDvLuvcu+Br}MLU5ZhY81)D!D1uUK zv6tAQCdL?B)M$)JY>CmI#;7y)61&(NVnIZdt_aBGFz>tZoS1w4o}1@OobTfgX7;o* z=iO_sy~?}S@oV3=S<${l4F-d?!N$hgU~QAXYiphV&&ptHaLnJ@d3pvKqm20%l+15A zVe6j1b;;kBl1mLP_>&FVpLEBg;7_`*9XIfJrq-5nPMH2q%5G?9Ej9fuldEG}6W6EX zx@vfS4ehydNnGcE^G@3Ja&=r+742&LWV3HmB+NKGC^CP?&Ghm(XywTrKkoG4PJ8Zn zamSZC9k}Doole~8%$;uB>B^n%-08?2AMW^brx$nnaOVT=^v?hHg5XQn>tyU-(66p) z)30Dh$*8>3H*rQ4<@}|h?~Yh|Ns3!ga6-9nI$U|Da$&#ezyU&|OdogKdvmEzWSh;U zOncm_HX6uM3c$84xZO`mUu$~scgjQ4ZR2h$S52Q%^j+Cjdye$H;Pz5dw)PwieCs^j z;C*LC0l-4YH*2^`Hws`FDWz!m3!%RWJbp1<<@<>D%T`)HNY8*V7We zC+U0JvR_8+9xBC}PLH`D9nx@-9yfI9oqtMf&s8jVfE54DR?`tF8PC73PAd`i^*rff z*0t(q?hTZ#Yf46XRPfkI(j)ZCLn=4D;SKq|54m~-`Q&j;trV4>U>gg)kO29{eacf! zK9%Q?Ym5)&9`w^Q?LOrY`tPbH_tH7&t2Er72|e?G5}-4@k7?ss!DOk#YTr`fWcdQe zp@$Vripp=$2UoD=^}HXGD%+HAg3R}=G2y2E>shO=^&;~4fsvbL4jrhKPr z_JooE9M9mo920zXG9{je-68aL2JYXX;jKVF@$;l?%|4P+(0{3#p3)uO#QB+qmy!(p zsi$eTJ%&AaiFTUyr&-7mXp@~b*) za;la9-mt5MKF4@ci((ulBfj9oPtX_M65=HMoJ@yvOU<6Ox^`!V$ELtJ+OetN8ilLC8Lq5TJc zQ_0foI@JKXBc662CY<`_bKQ{OZ*uh&>h~1 z^!tD>{A~$wJ=!HgF7F}UL7Z{F>QEZEWd}Bd;LxKD4u$X9HfMf2fyuo_URA;LiS}{^#*necC4?o>zi; z#C$9CiN$eYSNxSeaYesa>J!8d7|#{@g!8iA^+_ynva|<*^PlWN3%l;WY7dIM(f?3; zP_A2$SQshS*5)hO9ri}8Up0H9VY>poA=gG8zV?vyiz!i&!fG__^saX7Jd%n(##`} z7X^Goelvl20Q3jqhO#5W1Kc#&Rp3n{p`G!A3o`c{IA#Wz^ZpI%o zbn4GDAIUr;{5|G1r6l0QHn+$d2!Dw@H0meDTiND$eh&R0`Z>G~`Dy0yb%!_d;i@b2 zH{#%`3-d3U+zC6{-duk(jw0m(KWtUTrI4?YtaH zd_uJb^u<%mj}OfAL~1EqS5njWY8h?9 z*uoCUqF!e_7V=#L$M->B(;f#8Mz)7NpQAT@V)i}UaniwaPa7=w+& zy9I^gNDolc-7eG^FsyrcbZDSB5*-@aE+Qx>G6+ZPyo`~?h!C{wy@JD|f(Z(>3M$OIIts1pJ+p$APWKh_kpok&7phMV@pwQt)zN=kFV`O2=p`$T6 zAUG(3ui@Yw9vT>#|F-;O@9437a;NYSBl?7g2l8tb>0%5M5ESVW9u~wi_FbYQf}%nK z_>o;h^3md#vF#ci%)6Ysj*SXxA08eW5)~CHpy(DfD!{lY~b*qinXu_@v| zIw***Vc*LbHaI+j-C*A*C^R%Aj3C?f2?>o1=Z%hi!b1lKg#`wQ10RMAA08B8dbBo( zO)DX7#AHSC7J>@WLvxZkja2C|j4eT4#h|4TjPrujipfa9^Mo-+ql;vC8gpEfcHZ0x z`CA6F7{g*z|8vFxomVDJ3C&0|Dzyz(Fx{a8#rka78?lX;S}&?e<0YY(6}b)1N|!QXTQ=I z-1j#Ii~bdOn|%)(Dmx#ariHuB3U@tTQbt9^;J^wHvGRx>1HcuY9KmE}9V<7u!bUI_ zuwsWRhy~+HFqSbGEImOCI(nG&K=or;0B=Sb5HY3j3g$3ZQc~zSSn|vnlVp+@@Fyk_ zt|WVc{vbmW5maW@nUSF7NDowZcr${GNU=hBCX)o7vS6TQL2j`EPeh7f=~5Yq^Hk=S zn3;j+Po_^A`hk(z1ZITv$sGA#X4HQ(-dr&Td^r9^L>1#&5-WqD?`gbH-f8^M_{53^ znfitE1B_6?(8hC=RBgTx`Y4urI>Vcp6;^V9vBAukYyg2cr?I0Tv&QRnhc}EjiSo>qyTFNfamAy=6*E}bsN~WZhdo2*i+Y;& z2QvpW{$F4|rM{n)2Jcm5vyvW>AUr=6|ndi!O*wtd? zJLX5x4{&nH_kFk-78yv@ExQJl2t+OcWjZnMH&kHX#Ng}W^ZcUu2*B5vx=Gfma7n77Kp<^y;-OwtRIauMOwVfrt4b!wR6 zcolA`Vg5?5|C6u&%8x4AZfHUO+u&Nt8R@4rnWlL@gYxFVFOb&;zSmDvCR+ute zvG&CV9E&19v3$w9=I_$%IM#0-{R@HYD%MR3yk!=_@dnb`9Xd(FjO3q#@TYgZT_npjX` zR!RFYJ3e%7dnLK%jmG6y?N!nbE?;-Y|C#h8|ESkjQ%DX`GQOH(mw$nfM(s9zvUFRg@i@q{ z6k7m?k8&-rKp>U4pR1ZAT*=(_c3-zaJ(TZf);CF@atSy+$GBKxD!4rHxs-6n|LLhK zWu*Jsap@eap|d9R$3K=b272Zre?*Bxf2Md9^rXT{+lF}s0xjjBzqEqS<@AQPgmJIL zBhg?dFfRG_B9rSYh6K1+L^>~gpOQ0ZG( zS$m+@nNNI3{(?UBH{6yxY z=z~<~r!yd9&gTkWO}{9=XyZtV)5e3ap3XrZC7Y(}r>FIUx7qiwqZK2<`_>}5Z!LoR z)*`lVEkgU&9a|b+5p__jx7NH|h#soN;l(0q zpt_lp4%JfloJxpRl!5nG8p#3ZMYYV|Xtn+;`jNae%}bRLr4ji=cnJzteoEQc=5l2o z#us=cf-i+FW8s322GX+X1h0-OqPRj0mAVAq@G&bt>I-kdQ%YqX7h8I%TuCifDgrO& zBd5b_1@AWSB zksm=4Igck;Zn66F%S0=^KdUQ5BC!DaIcr64h~|p zP^&OjL#jSmQ;gApO~rbzf@)8;8rdhb_ESmaH?L1kcA;3`4feRG*UR6P5$gf<(tDVF z`Fj&j8H2?4CLYul)c%aAaUJ#!^L^l;Zdb+zc>9)Id#Av=D5-RHeu z(fKd)eo7+ph{zb1|FhN%S6->rz|XOQEeW2FjGBbhS+tqB@=mqZ`cbw=f3U`lEqsI= z;E!5{atRV~UvrGTX?U~N8hlLhOjLYd@}*d_mUFn^_0YE>?}s(V;DgD2SXa9vpweK(=|!h|n8`w^+fM4mmCXycsD0_Ku${!b zz}Nv-)RHW<(2su z#+_O1f;J83dg94=Gx9bfOU&~u;r5&PI1=~K)}jskx~t#cFucX@voS6TpNn&@C@IKz zDsiX&VH}S7o_d4wD@qLlfApuYS(%MT+>rU6*DlTWhT*MRL635c3gh^+fq*Z6N15?_ z@w*AsR7ZoCf zjg!KaL>83;xjvPB!#=?}J64nwwdz@c>6v*&u|MfNt}~;p#7a0|c(JyR zun~ogo@}mjM2?^Mi1myZlk}4X$BK+Z^cV4E+=M;=;(UUGk*!Z3OK=ld36=38#_6eB zxSkrhPf^*5ZLYv$oJ9C)xQ_7;GO1aykaH7#4|0Lx^clC~93Uz~G7inTnYm%EJEgu6 zIAV_F9KrtMT$^Zab8&^2=vR&>`oI?JVfBW$@Ue2CH_7GX9LhPEHacuWQK5>JWsz$a z&jS~czx5#M5g;}s=3>Su_&naXSEqRZ>QgeE>EqKjB2yW^mBSd1uwCgRkONCw3NbU) z06E`gfiu^;Ggd)v3;K&34&C9+7)!jlJtDX{w8dfTi|d)sBKMGSed-0uJM|5i=3-?G z`<3%3+w6zeTh!AsW*ume^ZKFW6B@(4`XM?MrgmI4&5Iq}>t=+;u14udEPh->zFv|M$B$ zHE%XEZ+e(Fo0~UVm^WLRH(QxETbnmoMbZJU(ZukoUvQy|#HoN&2StLe0bK`{s$qDa zi}^TZaoGSxghQGlN7s!i5UzpvMGbDBys~QF8!RFilAH>V4iUf1!Za9%9EU1t)1+Q; z3StapB@fhV7uD#4iysOf6h$ z$Uo0h6|z6MWjdI0&c(p`4(r)a6?OOT)2VZz3e=j-%$pvscz_cwap^QRFd}?JaQL8* zfRHE_1S}B{5gia>3=8qeKNl1c6(WAW%XwJA4|a7l21JEN@Sybw!eBqnKfo9&uD0vw z>F@1HuTT?nqO(BX;`+jZ&moE3|2Vf)X2{m78pLfQDjh1py_4v zUo9g4^q2Yjt^9_pDYM|pSgd%k==H2r8?m^DkQ{t@#T^rx_T6*Kvdr!2= z{48bMoT{su83(t!I&PiS)vQ4q^6q|U6_!v}}_O>ViXZKWFT&&?fr`2K0nl^f;`boFqXGkIr+u7}n>kG!4Qw*ID> zQ#XA&=2BwYw(IQrHJZ1hs-aWGoH0A!TE5TVn0PmSqsOcRn*!TsR;YM-mERYm%Gao| z#G%cly=&)>|GNByXYcIFT@f?g+jqw8pR?7n({AirQ$DmoPIP+z;w^49u6O(M^~aoh zed%3Ey3qVog_;#zKG-v7#M=S0KWK0F_0{hm`dzoLF|x%}H+S3W(W|W&jP5tG$N4OW ze!nkF^FFZpA_WbnSBC;e=VIube!&{m`Z@?`2juTwCpT@q+t6+b8!E+|sSu_nq8D+Eu50<5jD? zyLDLIH|Tl;o14xy<=>VomKtK)A=|7dbf_|5|0ktVXGdR+197l{bxh!d$nCVchIaQl~?69aDQ+n?YEpS?uA!9x3kRVWv(~&d=z^t zq;va}em&fmST{=;-swMAe7#yuU46UJo{haH4*4{tL-8`!728FpP2024Ytv8l_pe{3 zF0AGHUfTGJZj&=wUYquNVm+&UJ+^l)IVgHjOw*AAYrV5>SMATsM$aE^_u~1IZh?W_ zckj(RcSzciqD~GEYrOQ*z3u-o3^?(y)~*!4yCt%hM5RyqIOUTj4V!o`doSqFumc@J zU3f?-px3>df=n!_eVJfbiDVhNBoy7ueM%xw#Pdo{cP+n*SUFP+0cd2&mW(D zo_Kn;)!0@2<5$nwy5zWXa+AQI_>MhWR2VXHXu!nxK3=!rT$M8$T(;-VDxWy)!i?)< zCVDxS%j>(L!K`N+Dvw=S`AOe}@}*J(+>N=b+kUiKu{z)H?(w@GUOqt^6AYna9iJ~A zacWchiZ0Oyhm}^Q?vC3Lur_qW`4dNH*G&I>UF5=LK1YuScl#_S_259)Vf(wk)xvi2wxtz3{M@oC|9E?N z!h){vBurUw)M-iSPklc9zIUIS9mX58Zhe_P&@S!nCN;wOw{=H83a&fsaVc-#3VnzE3?znGr=`<-$fM*R}|^SwRs34sfalwK=)J6Ao|YJBlI&j%(w32v6^|5n!#%Qi-N zlnd*!eo}0`_k2QQHZ7_fbNbO8=lR3?ELgkf+QZcw0~bi||NfxsALWfHJv$uQzP!p~ z8{b~L+I%=~fk)!T3oXaR*j*n~{j)!+R4QHGwc4<+0(@*;ha7c_KNB+L#Q2BleVcR& zZ?MVl$RnxQ#bYB6Z}B?S;Y_z5LUtXG^@#WC6mB)zqmH0&hi+CogcRf4taX_W~X0mCbrBQYM0tQwWd7c zR@)QfS|*?Rs?J*%@&@LeD;0dX`px74wI+0)Hhavm-^;A{bwj(lRxRB|Oi8VNt!7&6EiZ0<@#6lq4nry>UMl8X;y?wzk5AjpntN*N2ZNHnt7Mc0k8a#{MsGj4{h)fS zTmST|+Ay!0oud{mTu`@)Yw+Qdt6HWseE;~i0j(a@3Ylv^W3QWUpL*UO-pfAN!nxIt zdsl3}GT{08u(OR9t`5n2GPq2`^4=aFh8*i%uhg{Dw>ulxOkA?Y zg>hFsCYQK*^JrA{ZjM&te*O5}F+U}DX>fQ;Vr<0S#Xd1fE59!1>wd(^^{X~{RZgtw zQzq%;z5^RK7dcw2_JPWSs$Fk7X;lB;-7nVPdcEZoWzWsyxu;is)1>!TZBAZ^Y7-MQ z&+qcp$amB+%N=}LrqvIrJ#XT)`|mcnbo#sMVOOhGtFiRav1gfmrmmS~clL5$`{JIF z{w)^&zM^%}Z`YNMyVuk&1}PRLH3zSQer=P!?aJl1L0_?kW1#0^+J`|z$ulhZP9 z`))nAGO_0L1Cb5(*4^*)JmI3+IcCU~x3BnAs}r!btJ@*l%)Axv?;QEdy4<>cI}(z% z`Wt%PJ`wVtxyCOX+PM5OX3WTS(-xJv(z<`yHOnXLx9LCm>L;bHmmZyva(#@)?u_DN z=C88Nh|5d8-)BbL<2i=0EvEJz72R%}MXA_}1xgtGB23-q(9lkIy0= z^f>o)Y3ZC}ub-1k*lyPn3GJvR(bI=JD%mSf|7Fs^<4Wy#E%n~#QOW%qsXBq!wFf*O8R?rb^S z^KQ|fa-?aeTKqcHqf3!M?@CjS-VV6YY=UR-+CRP<^kdRTd%vA;)hhIxZgXwYvKrSM zbi(Gs`XUKq1J3R%spQOQ`fKri{$J z%+3$n$9t{vyy2f1JYm9i&o(jEYu9@&9umC!*0YQg3GZzFs$-o#CVTJy0N2!iKU=N< E03y@!?*IS* literal 8253 zcmV-DAj01tiwFP!000001MOXRTvSK9UV4$H66_5TI~HuwB?+WjLdih4}UmWj@(gpVy zH-dyX~n1#!yC?abP9JC*glSUqN;70kgI zc+!C%9eB}!4;>7ogF$pKln#c_!7w`TrUPF(2%v+JbPz-bpU^>I%|CAleC|QJl2fr` z+KVP*bO%C7^CNyai(3e{?pS{qk#L7gkJVieGPS3h9}$vIX-}LcXoN*G(|q5Cx zL#{DCgbe7XGU++tEc!1+l6&qZ^i>g_FNL0YMiO9Pcwdmlvw+D`NR@u2K$GPgoQED3 zFewVZLLb~iN%zz9m{h4w@-0wF@1y7S?`M;@f#H1@@``znI|2QD8v2xeKk4i9kaLoI zl2_9Iq#w4RoqKvX(({+0H?ClwxSeb=+5}g|A&HN7rF@Fuh%Z=MPJG3(!yWKCVKtkGKN#U!kO@3=VI?xlF=K$OrzU zr^#;1gFSeM>@?|5GzPAOH;i>rhV!sbxC+>pInul!JjHvczg_`vdT)s&_XdaeZRpW5 z2|wW_>}Mm4>t~qfawWMFV9ycW!c*vvD(C~?EtCOAj0>&;dW8D#siaQ?(j$<6?k@Vx zVC_Lk?nG1QfoG8O7r>G1haA`sSyF#+k09@CzJz^~kLS^U9ORfQ0^XP(1n6;r>~OMo zNZtz!Q-6~k!M8(MA5J)&Z4q)z&OF}|;~^jCEumN7tc&Kjua(rESVwA4v<0qY4`F^~ zb|CB^vP(o$sXc?k`y%;&(6i9fT#2MV#D=gVU_bN5wSz1|5%f=eX?%$Fr002iNq$9J zNlwLjz#Dco)8`mZqBX`*KH>{D^ajJin?sz0ekYSVvKyd>1=w#i&k-7&NcIWzPX(UG zJiwtpxJulY1wHaT^bGU|Z;bY+zl)@K)!^_Zd80Cu>@d`!H@I|3{$>B!40PvAQ2b<#_`dF_5PIK0VEd?Sr#ng?l|3#F*%LBBr7eaZ0CQze`P*vkUh zfABYja>=d}Ww1N4$nJx@!;d2Slk}TVEY%GSZ^Db@i{>+`)4ZsEp8go#WCvE(mRIus zMbp~Pakrp%?&-~|#ZjwjBkNk7kg)H8Il08S`gU;*WukX(bdd~^yM}7P$ zK45To=aAnAeBp0%i0hGE!sIdo@eaZn&+}H$&qmM}ui;<5hP`4g=@Z@@_725kQ1W)t zdEN}qS4rm$4sZB>B9d%mhlw`O3(y0iE%dMzVFE50Dcn0>|4cw;}*J5@d=12XwHj96gUtf;- zHx2DUuNWHMWQTC&z#aY`i)W;vB!3)v1(x?AJDc)sz>D<{=_R^Od5wJFPW?&xpU$Tm zrhUTVdG$z-)GnDm(L2xVihrh0?9ng!`ULRyuRAq;C%b=ik|bdUoBv zY7er!(f?6AB9p+ZA?6C*0o&{pxyL;y<`XOZG}zxfH+Yi1s?*{aq#-q>Fb{wR6l&_0=bHq^^Nd7C|+%V%O zysWmq_@N-A(bw5(D+;DIZCBM)-S_*W_}66V<6i-hlZ_#6u(fMDbRt({*|e`9b98(0#~H zQy$;o@J2pdw1@si99*=c{EH-a%#OCGt-mRb!c_r3lp@8Ykgws5QHMV&6j5GDYKJ${ z8z04nsZYq?5RktSaw%>ExdnepfSe1+a|wtOGQ5kS5A?2c`H%Do`N`mfcOjJ zUm>1IE(p;3^=0Np>RTp9PeLhBwQ%5I>OYaPo5+;ra#gKS*!jJjIvl z!d`4larD~pbG|uBBeakFjfgr=_Fz-Iw}FBBJJsNcxJ%<%Y%R&D*hVrOXkHVY!AEfc z9wwL&HS#d|l%WbW&X{>8YMB4|jL#QLEnDttaYMUdl*Cc(6hL0~pm9j>4& z7K5WTiYR3Wy>f`M1}*wArbD8`=qcMFGolm&)M}M7DoVwm7^;|7Q>WJslZVTv$yIMZ zd6;sBe5QOlwP)@t*GyJu2w7isczAT=bomte?mE62d2pC~vRuQOF!7gDN16JoSsz$v zkKbZr7BF3*pwF-vDG#5Z)=)QC1SwQ1WjKLs9;8%7s_8+iAhl|OB0N;VPK;JgnWE5W zo0bN#b|s_7O({$j2MN0ybegc#nGbX4%$Vek2mKJgRs#n)DmRUcL zl16)se1HE>bf*7Cc#}M_q$@4%px>Vek{3C_wAcnt8i&OO%z3y9e5pSW>=ekjCejD` zl|4`WO2**HKQUPJx4^sB?=T@{=j+?;?P2$~hwkqvBWpG|umXgwJR*+);4)8+z@*GN zR&LM=8^&0`iXB=(%otaUv5di>?+Ieik%vhhsNq-^z?&ish?tV_GUhO?q$HuI!BSnD zF-c4k8UENLLMzE$qCbeCi3loX)+r-FmLqwf28TCAkP#^sNS=vF0#BJSP|G2=Sb@hP zMX+>98L{i6%4=z z$%y2zf`p7lQAP|Xj1yY%PUD3lc`z0^;7-PlfXo`*Z*X|Sc;iT(Y2_|(BD`qDBS$M{ zu(DC8B4Zr(3^`wsr>^8vr>^MSwXSbzP#G7TBYBB`d~+T*uF#fonUSH+$_9VL+l+vtBfu3OEFiLff90p!Ax!mOeR>-R6zwk9Qii{O|EDtzgOb)< zG=hw~;1l&V%->*`{&zKu{xJO;d^%~Ey7&|-NyGdzz5Z8z`X9c^y8k4FN;P$wGLmv% z<^$x@-)6VWy@vH45kM2a)lfxPc+Hf@nl~R-GY`sX3byc9hfc3)j;aAll}e#ev#MI9 zp7OTkfGEuj2CH`3G-GBl+%Db*#Ar*5H+$q3$la?1td-UfY@R7C%V~xBfQC7poMcB(k9#+$g!Pt zUI1a5g^v(sCj14sb;2tUZcNZ`3a&lQF;r+R$hj2MBE4pyJF)J0fcH{Ev3y21@BtF z!weUVM|WdK-Pw^lJLBzPfF>q9X0S zy(fhfn?Xm%_T+@em_6e0T#m7HAz8N@Z?sS{;&H#w(aj7eNJ8{J-R{NpxVsWQLLTsV zFiG1HH#iC2Cfr@%QYvk4EE-`O;)l4NrhUAsm@AZ?=hC&eS7dP|%X<$wwEEhF3)pbbJxD~~G~?@@#Nc_AJB zS>UPbNrATamaWnWG*^lKl6IMHWN3JE823U_m3F{i67Gd*YLMP6oWm?EgEjLI*7qd| zCyw+_snkzgmR9ODKXGqrI-{nCxMWEm2)SDEez`@6({<^+2qH`a~%SEzAtcT?` z*alN<27Sf0E5&kzHqvu!8%#tG#k%lf5j7AUYBL>0N4%#Qq7@C`{W&2y0KF(S_!F(x zzePV18BX$2c|>Vg5))p6faRuK1= z8niONaPa=)sKZD$507N?@JKcfk7V=k$akX-mTa_;R-sr8tq&lo7RBg5;i64u8NZ(> zazuF{Yrl}z57gcin<$NJQ8_5*;K7mYAWlAfUd z1cv0Ba)z|&FHz`7?@&J`p`=-#@TPXrj-laAo1?JJVra7-qWBk)wTO9=^e=7BUJTr5 z2>_PJ{BAR5qA(&i#&WlWKQ@(M{Zjge)Q11{cr$%Vxoz6So~XHmBcrT?b09-5mU8K& zFNhLNlv0`(OMoxwAFLl`)+hZZ6r|^`8k%*fN7V&&pXpy((nI)=H$>Jt$tijHwD}3V zeYP1&M(zIMZS*MWGPkw+iu_=@q6oqXre=u@^GbZ%{7H4O35}Lu$`>iall(15~bGAN#h8D$zo|b zl$qO&Qp$sOS3ezX6kgtB?x#OJ@H>^d@cQRRxPhBii%(ORt=@5|Yu}HP9`--i^vSRJ ziWG0(;;3d{j~yHwdZ3xpiVrPrH!b82UhTlgKh0ZK-6}RJ_b12q+7Hf|zf-+^c$ELV zUPt>iYyI)cs!8WEuX$|Qy>h(0yTgikN4$odO?VxdR@krO-lYrnE{VC5)34ul^D%C# z4!4vIY+4y}$)*CGQ-Z_!5de%3MXP13& zv}$wGA|JoSX+Kqn4HrH#02#IJlZRN5>n-P9HOM_^oowF~6-T@;M!U<$jA@E|pF* zmv^r7Wu0%j&iVeV*$+iK#ZzvdS?;*%5I8io`tj0<-nnrN)AwD!m)fLGV@uxvZs}^9 zK2tZ&DH>Nk^ZQ31Z9CM{&${^p%fxF3Mg%O~T|M;BR--ePuD=c4Zmc-pOu3~FOwFvP<%u95K2`kBw2Wpj5&zl_f@&L1-0 z^qF7NPxhZk?dtWx;vK0GZjX}pd>pWpKXT*lm!EFF@}}dg#J=g4(S6HCXw++$U2dAY z_Ug23XHVt&aq4gPC#_%Ka%ajOzob!f({)0hnGRr1*^z4_gGI-gB z=3A>exjwsI^lRl;8S0idk2Kg9XaDf{r>T#Xg9a3g8Sc8lxO?`Lf&aMY=h!=FgiK>(4hLk z(QA{sO&#CngY8G#e%Ua3^%V0ruQv=04IOsuMD@+H+~ERoo;tkC#yc5@{vjK8`FWe8 z1^!R#RcweVp8HwB=UqE@^@;mPadz@)FO~hs^tft|tu1mhj=eYMTztdN<8l%k?MNJ3$7=N#chBy>xgx64FLGdf zOz8IGAx#78o}XYe(dKfRY@v~5&9YImn)WxJct*x3B#s5Sf@$8oOms`!4N z#tTNb#yq|F)ZNopu_s%mnql>NeZbthdQ-&$}5Tw;yOhviG32*R-U!~;mSI{+TOo7W8ZM& zXNTSG*1oWxzI0XK=B3Nrhr~1q{Ay9fZ%-O|P5U|Zr;OuS*`cxLof3E-+m<(b&#JrP z_4wSEVciP@-Ww7Tw+GRTE%HqKMjq`udR44@&Yt96Gn3381Ur9msYNrV#`diyuM6=twV#;i zkab--|MINo#iP0oRCn6zfBps6{q}{a=k|ME^}0TEr}F5Kjk zv$(Oy&Ngw4+%JFpY7Mqx^AgW)E7pJm$i04L1L>yMKG5 zUJeoS3!U%x>pRDob86h{_P#f7GVgm$Y?gDUj%~fuP5eK*X1;9Y)dQad=YHQz&P|x! zrQhN}e||u4hdzCNENeB{(`8W9nl-WQTiA!4yRx-cLFbPz9vs*EMH}Txi^V4#{DM08 zjLxVy)6=&1t`nR0-5d9MNBE5{YvPsFFDEqU+}Ou`wDLk=2gili(gw-5&DpTc{kzKr z1*gk5@2F?7;OC5wcUU_#ZQ$orW?$$MdpK|SvR55#&t+cSIPJrEi7CT|?(Q^uMf9qL zL2c_lvFWuYJ;i-qy+@A{qnw9Y8O{9Vvkzl_%pct8-2R+Y&C~V1Nx56TY2@d6-o}1i z-|7~Zw*@uGy>jyOo_%JCb=sb89^C3dx4F~C{^okS-t`~ z7u7dOvC98$O5_J(%qC0UUPT?1ZCA}%nE7GXJJ-H<4o_*>s`bVf7s^V57HnH)e&g;a zi@F|>0X^6Mwz-e>ciWxPGkW-Z6XDWuc17W$jh<%)eSP7x88(w=xeV`{K5odhY?nfmkgs`mbe zvvUsw$VR4JR{mq9{42}8c0b3&Ox?b4ZG(G##x~rxY4$0TvGYY zx-qM_nwF$j7iI=6PS0B*o6&Q@sAS z!Zn|*B}d$v|76psUqbokH_9WIoF7`*?$^N!0#6=t4{!dY`J9{gGZR|$nLS|1riQ!A z+wVJba$QmX5%Q%Yc2CJYv-{cp3p01h6Y{>UU+S_iQB__s>ev zcbH|*2)S{xzEHWM+b?y;1T1f6+9WKbQel0_E_BMDElE%RfJ=S@qV{6&w`>*L&t zS9MNu`fyaz)D5wo&ZdfFZd8-Z7|&go<~nC}y7kEg+n5%MUp{cnm@u_{>qF1HduRHt z{3@ZebKKp%t<-B1H%^~o_1O5>uYrorBUg3&%CcQ?;l@Ghf0=#hi=92IVvdX+kmb46 v<6%Hf*zDPdJo+XXC+zT8KQZjs Date: Thu, 9 Mar 2017 14:48:56 -0500 Subject: [PATCH 31/50] Revert "AAdata dataset was removed" This reverts commit c3491a7c297c990ae90b941e63f5bb74ffd22c20. --- R/data-AA.R | 141 +++++++++++++++++++++++++++++++++++++++++++ data/AAdata.RData | Bin 0 -> 7945 bytes data/datalist | 1 + man/AAdata.Rd | 149 ++++++++++++++++++++++++++++++++++++++++++++++ 4 files changed, 291 insertions(+) create mode 100644 R/data-AA.R create mode 100644 data/AAdata.RData create mode 100644 man/AAdata.Rd diff --git a/R/data-AA.R b/R/data-AA.R new file mode 100644 index 0000000..7394cfa --- /dev/null +++ b/R/data-AA.R @@ -0,0 +1,141 @@ +#' @name AAdata +#' @docType data +#' @title Properties, scales and indices for the 20 naturally occurring amino acids from various sources +#' @description A list with a collection of properties, scales and indices for the 20 naturally occurring amino acids from various sources. +#' @usage data(AAdata) +#' @format A list as follows: \itemize{ +#' \item{Hydrophobicity} The hydrophobicity is an important stabilization force in protein folding; this force changes depending on the solvent in which the protein is found. \itemize{ +#' \item{Aboderin:} Aboderin, A. A. (1971). An empirical hydrophobicity scale for alpha-amino-acids and some of its applications. International Journal of Biochemistry, 2(11), 537-544. +#' \item{AbrahamLeo:} Abraham D.J., Leo A.J. Hydrophobicity (delta G1/2 cal). Proteins: Structure, Function and Genetics 2:130-152(1987). +#' \item{Argos:} Argos, P., Rao, J. K., & Hargrave, P. A. (1982). Structural Prediction of Membrane-Bound Proteins. European Journal of Biochemistry, 128(2-3), 565-575. +#' \item{BlackMould:} Black S.D., Mould D.R. Hydrophobicity of physiological L-alpha amino acids. Anal. Biochem. 193:72-82(1991). +#' \item{BullBreese:} Bull H.B., Breese K. Hydrophobicity (free energy of transfer to surface in kcal/mole). Arch. Biochem. Biophys. 161:665-670(1974). +#' \item{Casari:} Casari, G., & Sippl, M. J. (1992). Structure-derived hydrophobic potential: hydrophobic potential derived from X-ray structures of globular proteins is able to identify native folds. Journal of molecular biology, 224(3), 725-732. +#' \item{Chothia:} Chothia, C. (1976). The nature of the accessible and buried surfaces in proteins. Journal of molecular biology, 105(1), 1-12. +#' \item{Cid:} Cid, H., Bunster, M., Canales, M., & Gazitua, F. (1992). Hydrophobicity and structural classes in proteins. Protein engineering, 5(5), 373-375. +#' \item{Cowan3.4:} Cowan R., Whittaker R.G. Hydrophobicity indices at pH 3.4 determined by HPLC. Peptide Research 3:75-80(1990). +#' \item{Cowan7.5:} Cowan R., Whittaker R.G. Hydrophobicity indices at pH 7.5 determined by HPLC. Peptide Research 3:75-80(1990). +#' \item{Eisenberg:} Eisenberg D., Schwarz E., Komarony M., Wall R. Normalized consensus hydrophobicity scale. J. Mol. Biol. 179:125-142(1984). +#' \item{Engelman:} Engelman, D. M., Steitz, T. A., & Goldman, A. (1986). Identifying nonpolar transbilayer helices in amino acid sequences of membrane proteins. Annual review of biophysics and biophysical chemistry, 15(1), 321-353. +#' \item{Fasman:} Fasman, G. D. (Ed.). (1989). Prediction of protein structure and the principles of protein conformation. Springer. +#' \item{Fauchere:} Fauchere J.-L., Pliska V.E. Hydrophobicity scale (pi-r). Eur. J. Med. Chem. 18:369-375(1983). +#' \item{Goldsack:} Goldsack, D. E., & Chalifoux, R. C. (1973). Contribution of the free energy of mixing of hydrophobic side chains to the stability of the tertiary structure of proteins. Journal of theoretical biology, 39(3), 645-651. +#' \item{Guy:} Guy H.R. Hydrophobicity scale based on free energy of transfer (kcal/mole). Biophys J. 47:61-70(1985). +#' \item{HoppWoods:} Hopp T.P., Woods K.R. Hydrophilicity. Proc. Natl. Acad. Sci. U.S.A. 78:3824-3828(1981). +#' \item{Janin:} Janin J. Free energy of transfer from inside to outside of a globular protein. Nature 277:491-492(1979). +#' \item{Jones:} Jones, D. D. (1975). Amino acid properties and side-chain orientation in proteins: a cross correlation approach. Journal of theoretical biology, 50(1), 167-183. +#' \item{Juretic:} Juretic, D., Lucic, B., Zucic, D., & Trinajstic, N. (1998). Protein transmembrane structure: recognition and prediction by using hydrophobicity scales through preference functions. Theoretical and computational chemistry, 5, 405-445. +#' \item{Kidera:} Kidera, A., Konishi, Y., Oka, M., Ooi, T., & Scheraga, H. A. (1985). Statistical analysis of the physical properties of the 20 naturally occurring amino acids. Journal of Protein Chemistry, 4(1), 23-55. +#' \item{Kuhn:} Kuhn, L. A., Swanson, C. A., Pique, M. E., Tainer, J. A., & Getzoff, E. D. (1995). Atomic and residue hydrophilicity in the context of folded protein structures. Proteins: Structure, Function, and Bioinformatics, 23(4), 536-547. +#' \item{KyteDoolittle:} Kyte J., Doolittle R.F. Hydropathicity. J. Mol. Biol. 157:105-132(1982). +#' \item{Levitt:} Levitt, M. (1976). A simplified representation of protein conformations for rapid simulation of protein folding. Journal of molecular biology, 104(1), 59-107. +#' \item{Manavalan:} Manavalan P., Ponnuswamy Average surrounding hydrophobicity. P.K. Nature 275:673-674(1978). +#' \item{Miyazawa:} Miyazawa S., Jernigen R.L. Hydrophobicity scale (contact energy derived from 3D data). Macromolecules 18:534-552(1985). +#' \item{Parker:} Parker J.M.R., Guo D., Hodges R.S. Hydrophilicity scale derived from HPLC peptide retention times. Biochemistry 25:5425-5431(1986). +#' \item{Ponnuswamy:} Ponnuswamy, P. K. (1993). Hydrophobic charactesristics of folded proteins. Progress in biophysics and molecular biology, 59(1), 57-103. +#' \item{Prabhakaran:} Prabhakaran, M. (1990). The distribution of physical, chemical and conformational properties in signal and nascent peptides. Biochem. J, 269, 691-696. +#' \item{Rao:} Rao M.J.K., Argos P. Membrane buried helix parameter. Biochim. Biophys. Acta 869:197-214(1986). +#' \item{Rose:} Rose G.D., Geselowitz A.R., Lesser G.J., Lee R.H., Zehfus M.H. Mean fractional area loss (f) [average area buried/standard state area]. Science 229:834-838(1985) +#' \item{Roseman:} Roseman M.A. Hydrophobicity scale (pi-r). J. Mol. Biol. 200:513-522(1988). +#' \item{Sweet:} Sweet R.M., Eisenberg D. Optimized matching hydrophobicity (OMH). J. Mol. Biol. 171:479-488(1983). +#' \item{Tanford:} Tanford C. Hydrophobicity scale (Contribution of hydrophobic interactions to the stability of the globular conformation of proteins). J. Am. Chem. Soc. 84:4240-4274(1962). +#' \item{Welling:} Welling G.W., Weijer W.J., Van der Zee R., Welling-Wester S. Antigenicity value X 10. FEBS Lett. 188:215-218(1985). +#' \item{Wilson:} Wilson K.J., Honegger A., Stotzel R.P., Hughes G.J. Hydrophobic constants derived from HPLC peptide retention times. Biochem. J. 199:31-41(1981). +#' \item{Wolfenden:} Wolfenden R.V., Andersson L., Cullis P.M., Southgate C.C.F. Hydration potential (kcal/mole) at 25C. Biochemistry 20:849-855(1981). +#' \item{Zimmerman:} Zimmerman, J. M., Eliezer, N., & Simha, R. (1968). The characterization of amino acid sequences in proteins by statistical methods. Journal of theoretical biology, 21(2), 170-201. +#' } +#' \item{crucianiProperties:} The three Cruciani et. al (2004) properties, are the scaled principal component scores that summarize a broad set of descriptors calculated based on the interaction of each amino acid residue with several chemical groups (or "probes"), such as charged ions, methyl, hydroxyl groups, and so forth. \itemize{ +#' \item{PP1:} Polarity, +#' \item{PP2:} Hydrophobicity, +#' \item{PP3:} H-bonding +#' } +#' \item{kideraFactors:} The Kidera Factors were originally derived by applying multivariate analysis to 188 physical properties of the 20 amino acids and using dimension reduction techniques. A 10-dimensional vector of orthogonal factors was then obtained for each amino acid.The first four factors are essentially pure physical properties; the remaining six factors are superpositions of several physical properties, and are labelled for convenience by the name of the most heavily weighted component \itemize{ +#' \item{helix.bend.pref:} Helix/bend preference +#' \item{side.chain.size:} Side-chain size +#' \item{extended.str.pref:} Extended structure preference +#' \item{hydrophobicity:} Hydrophobicity +#' \item{double.bend.pref:} Double-bend preference +#' \item{partial.spec.vol:} Partial specific volume +#' \item{flat.ext.pref:} Flat extended preference +#' \item{occurrence.alpha.reg:} Occurrence in alpha region +#' \item{pK.C:} pK-C +#' \item{surrounding.hydrop:} Surrounding hydrophobicity +#' } +#' \item{pK}\itemize{ +#' \item{Bjellqvist:} Bjellqvist, B., Hughes, G.J., Pasquali, Ch., Paquet, N., Ravier, F., Sanchez, J.Ch., Frutige,r S., Hochstrasser D. (1993) The focusing positions of polypeptides in immobilized pH gradients can be predicted from their amino acid sequences. Electrophoresis, 14:1023-1031. +#' \item{Dawson:} Dawson, R. M. C.; Elliot, D. C.; Elliot, W. H.; Jones, K. M. Data for biochemical research. Oxford University Press, 1989; p. 592. +#' \item{EMBOSS:} EMBOSS data are from http://emboss.sourceforge.net/apps/release/5.0/emboss/apps/iep.html. +#' \item{Lehninger:} Nelson, D. L.; Cox, M. M. Lehninger Principles of Biochemistry, Fourth Edition; W. H. Freeman, 2004; p. 1100. +#' \item{Murray:} Murray, R.K., Granner, D.K., Rodwell, V.W. (2006) Harper's illustrated Biochemistry. 27th edition. Published by The McGraw-Hill Companies. +#' \item{Rodwell:} Rodwell, J. Heterogeneity of component bands in isoelectric focusing patterns. Analytical Biochemistry, 1982, 119 (2), 440-449. +#' \item{Sillero:} Sillero, A., Maldonado, A. (2006) Isoelectric point determination of proteins and other macromolecules: oscillating method. Comput Biol Med., 36:157-166. +#' \item{Solomon:} Solomon, T.W.G. (1998) Fundamentals of Organic Chemistry, 5th edition. Published by Wiley. +#' \item{Stryer:} Stryer L. (1999) Biochemia. czwarta edycja. Wydawnictwo Naukowe PWN. +#' } +#' \item{zScales} The five Sandberg et al. (1998) Z-scales describe each amino acid with numerical values, descriptors, which represent the physicochemical properties of the amino acids including NMR data and thin-layer chromatography (TLC) data.\itemize{ +#' \item{Z1:} Lipophilicity +#' \item{Z2:} Steric properties (Steric bulk/Polarizability) +#' \item{Z3:} Electronic properties (Polarity / Charge) +#' \item{Z4:} Related to electronegativity, heat of formation, electrophilicity and hardness. +#' \item{Z5:} Related to electronegativity, heat of formation, electrophilicity and hardness. +#' } +#' \item{FASGAI} Factor Analysis Scale of Generalized Amino Acid Information (FASGAI) proposed by Liang and Li (2007), is a set of amino acid descriptors, that reflects hydrophobicity, alpha and turn propensities, bulky properties, compositional characteristics, local flexibility, and electronic properties, was derived from multi-dimensional properties of 20 naturally occurring amino acids. \itemize{ +#' \item{F1:} Hydrophobicity index +#' \item{F2:} Alpha and turn propensities +#' \item{F3:} Bulky properties +#' \item{F4:} Compositional characteristic index +#' \item{F5:} Local flexibility +#' \item{F6:} Electronic properties +#' } +#' \item{VHSE} The principal components score Vectors of Hydrophobic, Steric, and Electronic properties, is derived from principal components analysis (PCA) on independent families of 18 hydrophobic properties, 17 steric properties, and 15 electronic properties, respectively, which are included in total 50 physicochemical variables of 20 coded amino acids. \itemize{ +#' \item{VHSE1 and VHSE2:} Hydrophobic properties +#' \item{VHSE3 and VHSE4:} Steric properties +#' \item{VHSE5 to VHSE8:} Electronic properties +#' } +#' } +#' @source +#' \itemize{ +#' \item{Hydrophobicity}\itemize{ +#' \item ExPASy-Protscale (http://web.expasy.org/protscale/) +#' \item AAIndex Database (http://www.genome.jp/aaindex/) +#' } +#' \item{pK}\itemize{ +#' \item Kiraga, J. (2008) Analysis and computer simulations of variability of isoelectric point of proteins in the proteomes. PhD thesis, University of Wroclaw, Poland. +#' } +#' } +#' @references +#' \itemize{ +#' \item{Hydrophobicity}\itemize{ +#' \item Nakai, K., Kidera, A., and Kanehisa, M.; Cluster analysis of amino acid indices for prediction of protein structure and function. Protein Eng. 2, 93-100 (1988). +#' +#' \item Tomii, K. and Kanehisa, M.; Analysis of amino acid indices and mutation matrices for sequence comparison and structure prediction of proteins. Protein Eng. 9, 27-36 (1996). +#' +#' \item Kawashima, S., Ogata, H., and Kanehisa, M.; AAindex: amino acid index database. Nucleic Acids Res. 27, 368-369 (1999). +#' +#' \item Kawashima, S. and Kanehisa, M.; AAindex: amino acid index database. Nucleic Acids Res. 28, 374 (2000). +#' +#' \item Kawashima, S., Pokarowski, P., Pokarowska, M., Kolinski, A., Katayama, T., and Kanehisa, M.; AAindex: amino acid index database, progress report 2008. Nucleic Acids Res. 36, D202-D205 (2008). +#' } +#' \item{crucianiProperties:} \itemize{ +#' \item Cruciani, G., Baroni, M., Carosati, E., Clementi, M., Valigi, R., and Clementi, S. (2004) Peptide studies by means of principal properties of amino acids derived from MIF descriptors. J. Chemom. 18, 146-155. +#' } +#' \item{kideraFactors:} \itemize{ +#' \item Kidera, A., Konishi, Y., Oka, M., Ooi, T., & Scheraga, H. A. (1985). Statistical analysis of the physical properties of the 20 naturally occurring amino acids. Journal of Protein Chemistry, 4(1), 23-55. +#' } +#' \item{pK:} \itemize{ +#' \item Aronson, J. N. The Henderson-Hasselbalch equation revisited. Biochemical Education, 1983, 11 (2), 68. +#' \item Moore, D. S.. Amino acid and peptide net charges: A simple calculational procedure. Biochemical Education, 1986, 13 (1), 10-12. +#' \item Goloborodko, A.A.; Levitsky, L.I.; Ivanov, M.V.; and Gorshkov, M.V. (2013) "Pyteomics - a Python Framework for Exploratory Data Analysis and Rapid Software Prototyping in Proteomics", Journal of The American Society for Mass Spectrometry, 24(2), 301-304. +#' \item Kiraga, J. (2008) Analysis and computer simulations of variability of isoelectric point of proteins in the proteomes. PhD thesis, University of Wroclaw, Poland. +#' } +#' \item{zScales} \itemize{ +#' \item Sandberg M, Eriksson L, Jonsson J, Sjostrom M, Wold S: New chemical descriptors relevant for the design of biologically active peptides. A multivariate characterization of 87 amino acids. J Med Chem 1998, 41:2481-2491. +#' } +#' \item{FASGAI} \itemize{ +#' \item Liang, G., & Li, Z. (2007). Factor analysis scale of generalized amino acid information as the source of a new set of descriptors for elucidating the structure and activity relationships of cationic antimicrobial peptides. Molecular Informatics, 26(6), 754-763. +#' } +#' \item{VHSE} \itemize{ +#' \item Mei, H. U., Liao, Z. H., Zhou, Y., & Li, S. Z. (2005). A new set of amino acid descriptors and its application in peptide QSARs. Peptide Science, 80(6), 775-786. +#' } +#' } +NULL diff --git a/data/AAdata.RData b/data/AAdata.RData new file mode 100644 index 0000000000000000000000000000000000000000..cdd2bf47419544a24074f5b9fb6ade59b0a5f58a GIT binary patch literal 7945 zcmV+kANJrMiwFP!000001MOXRSX9TmUOFgECD=P+$AT@I0o zbM~EYzInegqxXPO-D{1iC6mbvWkyDZGDD-PLu13Le+*>CGK;Fx)Ws!G9xkuCp z2VQjGMh6~rFpv%g(ZNtU7(xfb=)j#0Jn6uP4o1>}A02!_2fkJRyd&_rN9~HvMvZAN z8jaB%2u00~du1(ZF5J0S>(kKKdt7Ri?t+l6J>BfMka$*m;v7LEES!q7l+ApH_>Koqwa{J+mxPak#qbD~rdv!3kWxshh$IR(m8gRU2>pv_$Z!hUEg1RB!t>o^OK5TU> zZ9Ml#QZn2tU9)qzSLm0Qq}=okZ^(B#+Or55)ZWis?aCgdB>32!9%6y8Fv zF+PMe=%*6tIpG5OFG-SnE*|=-0M8dg&%7WB&@;R*OXFF3K}5R44fssHFGN^EK~hleeDXeIN3Qd5=2{{e2Gllzur0Sxl6#U@ z(*L9%wxXQ}HE^WouR(8I$2@UcC)NYmdnGX+sCRg;lW-Q2XdHt-rILI+q0K73j2+-pK@o?fhB=33p zslSOw@a<66gAop6TZ9~wG0(Tac*w!K;{YbmuS)|T26t$-`>A)`98mw40a{ib(#lb!fZ8qYKj(l{52QO|*XeTn-LVW%fcI0@j(0`WiCn?k9? z>qHrNM+Wge$UE#P;-947ghHvVZ+H`4BwsY2QJv<+n&;_{;Y~cSyt=%S{Vy6oBOWGNLN7oMh*r?U7LZHu6sq%erTchmv}22Y0k7u4%ZX>RaYW;W{I@i} z+UhC)CVLw4#OyqjLN4?I+2#4L56^?o-Nt=2{923`Vt%aY*Jl22vg=DR|E8cl=oNj# zn|KIU3fy7uF@Hu1O0vfhS731;;@K2u1756uNH5WKifiNocj`~l|8zcCKluss=hY=W zQoUsQq{ey1EB;KM*q~o(>J#`6$e+vf3C+v;u1}JIQ%ybyoPWm$Yw)^%mk+YI(f?6C z$hX%87N+oRrTL0?1m9@$i^MlN_t)tSzAfVLZ7=Ec4&P2nq~P1ZuhPX&dag6@b_6f! zg!?<8UmZ_L`45f}5?^U6m;5&!(Ow6z!A!H-g3vS0aT`sqL6W!3d1-vn|< zNmCgAd;^?s4!rGgKb{v`NY_P5n!_#W&w=F+A#TQaH~Aln z^wgfGcqGLcVee5~lgkE9RHqVg17Jld?f{w6;PR{{J`isY9nLtMX1_6O+=oG1TM9q`3Q21=xZ>r~KlAdAl zG_pg@;rB2G4=E+RPX1WPw+YUlfxad_jyxFN41B&^-}Fhf-{FXh<}Uu~K!rvbf_g0% ze~mm?K6$7@jWZ@Lnjm!;UGA@v2TU5Kj!*@%GZ89Pe~m&Brob6fS9zFRqeRWjHCP=U ztdyf_gvYfuv)LkC-zGm(& zj|d1>Xy`M{J=Cheu&S@6H+w`(rOlHgCWGZ63<8tE>JSB8F&iAAQG_c4 z=#@j1RcO(VF&+{TOix)2nI5hfpjNAt;o&L<#Zbl6sye-Pm^?&2Rjzvf$-|V>qs*(ngYrlb$_D|?>$mB`?k zztCCqkHEXy?=T`|=jqw){bBd_ht3};qgrfmUi z5}}o3uhAcrp$QKvMb;@ILCldXP`$&OJjn1A3nb5!NdilmWuTTqZm|N7d5XYvNg1*0 zq|EP8WCoT$W%?ALAILMCNf9Ca%pCdu%&7liylKT4@S*X~JgOMi99tO-eNW_t;7PyG`~VWlGPKc-kT1;_OdloFk)GjAkrmp>0c3+BW4saMAD(R@+e9KctRNxM zD9R`U3gd)Uywi9gPaeo32i%G52#BoF{d$Kt$QwuUOe=SR6X8WG9ywYugO!a!1(9*^ z88W^|PZR&3$N`c6cbHE}-xIkfV~OqHp=Wp#xuzAOv@(hKAMM;gdgVT?Fa!RSK}jn) zXk{y9D9|{djAhC+%db(Ak&2bcWUT5N-fTS6ihr8#$Y`Y%HP9ErUEuQ;@{H>&a!dMx zl@yL3&-Y7$Tvm2nOuT@(9RE}@3C`{P!74wuCdbt z_>b_2R$fDoQ~wg5r~47PA&;&8;9c!^)WSuZV1-H<>Ey2n33Lk8C??S9FlC^^DIi#` z3~>rm&L9U}9Ytig)~^=m6c(=e@P6yy>46$`Xt3H}8K4X&&!26eI>KM2_+9I^p>j>Q zQm%3e3snR-O;xLK-fDtM9`022jt_6PQwIb@Xf%qD0ELrW6&fse(kRI7XB;}ji9oI! zR&|#;A|y~5667R(j_kdCZ2@_+;9JRbf4nVaG$Nu@9~oN6kmK8-q`D>SG(?Ar=z5#!8SEN9oH@J92R;19iNU( z-Potox^v1;Y=cj1U*pp$-q%v9|1GE^WtFAC;u9I_NO5h4lvanZnfMNPy)i5=O=|AApNyF5^r%*{6=Fjx{-}&i(_^Mj{Cn{8`DN~hU6#FtAAfNU= zx@GD%tp5lfn)oe-DuP3*raacX>9DGKP)<{@nYTJ{T2*sY^--!+3XPgo)hhMm_bvN` zYo;?;wbP~vqs1`0cuOQkn`6A$Ahtl}UO8YjC-*WX8X)n&1_=jsq>?w3=$B|piR^G= zfKF3_0wvstb+BL(8(WITf1w%jkBA{4q1uoV1Ek;0kvoEDGP$jjaUEu}XbUqL8x|3r zri2>W7?9lClsLj@GR$bv08@qy7Tg#ivBTsqG_(Ifc$2w63+Fh5O}KZEV{7TWfP`u0 zK7yN>@E2g#32%^aV}yPqGaMTiaY!s9w}+5NF*A%KxR+={DSgA6Vt;I51#l3tku7tZ zVgoYK9A+BADl|i}4Q-F6e+aj!;e_tkC76%=Uq?L8wT zSq?fewkIb%#q1G-=dui?3yHejcq4?O5l{OCj&7XPCy+wwPc5_(E)*a6c$BUGaN)-# z9kmiD+yhQ;F)lW0cX^)umdkwR^XA5b`dqqno{I+?x~)ZjW)4?0-lYopOF}C8GtX7m zlLBq;EnBG*Xs#UnCG9fZP~Y(8Fz$tf3hjWuDm)0*R3W`ZxQJO;1~&5;?E9*O6G!@| zSn4M(Lo4-~pSX8bol(_8T%x28glw&NzuqcD>$>SvElF;LOf8BnF0k$8beovFEEDp;W;`YQgv<8Y0Wg^K zif}=vrqtX_Y^%OhYLB=JO_yvu9u@<(Ti1vF-c= z;8FNM2dt3qtJ{a3BU~S9)rtKQ;Vkq)KJ?QqWPq-sWyO+y5q_4&5tk~B2gaV_p^tL4 z)AgI1`h$11-(gBD#+|VpcgA+y8QXDZY{$JPJL)BS&wI?-xIqw~u|>*Iq+l^w2?!$7 zHg_z;kb?9SbR&I}PZ^BWx83(M2Q6?x^Uld#ej%1ApSjI}*4YH)fQna6~r@V)@OQL0`lqpL|oD}4w zBtj(jh$ghXJ*;I))+BEP1y4!-X?!H3fAT093-70GPAT~d{i1hxLynj}pyY{#kY5V^ zQ}P?|q~%a7Sd3+oY`gnRN@fGT^gIRcsXxj4LrHR!Jok>0we$;b$~5OnfL991FO6s5 z0Plim052rz3EGC9{ zbBKD#;0-2kKIsce%A%weniq?JFXNfzm!x=_|VEK zTIoV^O3S@z`893RLG`ri{l#0>NRmSm9$U#p$^TpR4ex5d!yFe)dGffy_lK1}fADTI++aQMk1~wv252Gzl=2XzXVo=@CS1vuKw3@Gt$B2p z2ZXCNbkZ=CU^1KG6ChWyyG`9)d^}tTRb%bPy#E&Ve-K(adCNlr)svmV6pBFYJE~gL zR9#+Mb==!KXnXyr2RY3)ciP*(wMO6u)%NK1=%l|@*}Mz`|A#aCJuK`JbNX8E;&1Y1 zEN`)`yL>|bq!~L6l1lyeRX!hW5K`KB&X+$u@;aNm;MUj2xq+KkiO-XluG)3AYv0ck z9{0c4!tkbR#}4)nJlxcN`KM-go8)sxZgk*dp64vBY#9}v{gd5C?FVPg z+pXR?JluP3uM_>6w*GuY#l(y0H(j>wTQT0o*>?Hd<8DJP#J&wn$?w@g~7DwL8 z>ep|l=@_S#$6Ck+HYtxh{?X<$GK;L|8T*}=o;wgYpty09o7=osPi@q?^+xl)_fE&I zn)zL$StXyGsMwOQ(8Fs{%1>otg9VSzY;UCMR31?{wocEdT{@(EyX&&m$h96#xx^kf z8ap(x{^Hc~(2oO_eKElFyQCjqdOtF2J*DS-TSwzo5iy2Q)5c60ey7xY%x`N7JkG^j zf7pDFL%IEoWu0q(Tl>4Nvv*uD`LSTPc-HAF^IbP=eTODjK3x*zo*msF_28`s$&G6_ zGWYc1maMYuGiB54f^nrYc0BoP`_Z0WwVF*ZkGpwzgwK+Fl|zqiGdOSV_}kE(hKfr~ zl^g3Nr;Pl5-qvFqhA3UQV`&F@Z^K<#n@qc12$-0WG~a!z_^tD2OV6F%a42NMqi!#b zE*Tk9aqDJCPQMO|&swL3O!+A2>V$5xj(hrwc75;U<$ZTz>$^AgUM+DjA2K-c<*cPQ zA6&nF^umEdpB1-~J&f_bo9H;+_;q@wZK1({QF8}#C)y3@vTd8kP`8*-ibtJ{o>&<* z`j~HG7i8=f;nin%x#K5p&BvYn+Ae=tL?Wl0RkrC!e~X2_0WPl54TZzFLV+#&OfUwAe7;?U{ju5Of$m>zisG(YIuT zM!jz7wI7>`vP66+W?V7ncijtfTLQUvf@5bi}VsdPz`6 z*M6}p{FiQQwymO*k_(68Q ztz>w{+O0`_qHhoXWQwhst)9Z)=}Z5aY*n3SAuaEV!*aW5eSWwSTpG zcxC#*;f61cIa{xLWixHbO5ZI@mO2lKZ0x&wVcBob8oEvWIr*owQyH0oQJ3svc@L`= z@x5o(S^jo>_Uqv8`92>F360(#?%XhB@UA(@9X|6^B^+4SKH=u8XI85w`$fgBd-yVD ze_#~%`EM_VTx}%J8{u~0=;r1*MqVRN^c}r2$~kL)Vy_tqrjPtveRH*WQ~O3XEhnuH z@HDmwinGnQrJQ$d=F7rST?eW=9q_*NitB#&@|25*TyMDD8oFC~;!3h}hU-AJLF9`G z;p112v*;{tDzLVSTO;?%9Y0In!^`N&ncgeMmVMq?)uZ;%Wee}dCbZj}V1E3o-oeT@ z&z}tZ#b|b~%891=!}1;Y(5L;b&FGbTV|}}i5-Z17#@hwoZ}lX1T$@>g7A%Xr{9FAk zzwGPZ-k_Il=)C+^5Bv3UHC<=}&HZ+C^`QF&9iooq3}5=Dqt(Uq8=IznIyWw9*wB5Q zW-X6cxxlY&y=Rua)}$sm&#n99NnCiVp%w-+e);Ot$i2CPJ6$}Km8^Nb!80Ly>vs*k z94}egtnXXd{MvTE`q|gdoZElUB(8SbbItr)KI%4S>e$~L?{+-=sMkE<)RQX}H@AJ? z)pvd0>kq>FCMZ^V-%kqrM2y^Q?%AuLqq6PF*$dJ??RxL#j#eQ_En2qT^y+d+vETgd zOHFUzA7xg@CCsPihTpdIsrAE7`_!}^9^ZvJG?-PEzi^Z5`9W(he>L55(oBcpeN)G6 zUUu=stGNZmDPD);w`MskJQvpKbo;ZGZ!_ig zcUH9bK9-q%*he-p<(l$eE99%q`&$1T898O=f_3#D^cmY=`{r3^jmFMR`r7W1{j|)y zN0H7ai|RzK+GbpoTA82jw1#+dig4+g-Ku9izQ-JX04g?lJF5@*2y{Cqtbt9gQp7 z|FP#1C*h{YwxZ)s&3>|M*e|y9>)WMai!Ti=Z};oq`Mzh4I)^lS)@*kC!}QqZeP#_< zyt%=?()I_>pIKkfe}sI=h<%f@&+mJ2=<Ivn`yZusUjL)*B#*Kpm$`!SaS_f|5tFEvy-8wJwRL<1IN#FE1 zw;|f8aAoHN`%gzDOxYOa+R9jw$c<{89_hO0>YP>?o$h>b*($R6qSucc(ka z_ulEAD^|xAcaFY)prv|U+@@)hEuI>l{MA>{dF0BDtIgXL=5HFb;g?xgzuDchBJ%j? z0U55_Tps&m1<#sw)TM8NVeBrK4MD*tpOzF|%lzcvdiQpITE6!m`A0`QReJycJy9QP literal 0 HcmV?d00001 diff --git a/data/datalist b/data/datalist index 2444b89..0fb67fe 100755 --- a/data/datalist +++ b/data/datalist @@ -1 +1,2 @@ +AAdata pepdata \ No newline at end of file diff --git a/man/AAdata.Rd b/man/AAdata.Rd new file mode 100644 index 0000000..1fac3ce --- /dev/null +++ b/man/AAdata.Rd @@ -0,0 +1,149 @@ +% Generated by roxygen2: do not edit by hand +% Please edit documentation in R/data-AA.R +\docType{data} +\name{AAdata} +\alias{AAdata} +\title{Properties, scales and indices for the 20 naturally occurring amino acids from various sources} +\format{A list as follows: \itemize{ +\item{Hydrophobicity} The hydrophobicity is an important stabilization force in protein folding; this force changes depending on the solvent in which the protein is found. \itemize{ +\item{Aboderin:} Aboderin, A. A. (1971). An empirical hydrophobicity scale for alpha-amino-acids and some of its applications. International Journal of Biochemistry, 2(11), 537-544. +\item{AbrahamLeo:} Abraham D.J., Leo A.J. Hydrophobicity (delta G1/2 cal). Proteins: Structure, Function and Genetics 2:130-152(1987). +\item{Argos:} Argos, P., Rao, J. K., & Hargrave, P. A. (1982). Structural Prediction of Membrane-Bound Proteins. European Journal of Biochemistry, 128(2-3), 565-575. +\item{BlackMould:} Black S.D., Mould D.R. Hydrophobicity of physiological L-alpha amino acids. Anal. Biochem. 193:72-82(1991). +\item{BullBreese:} Bull H.B., Breese K. Hydrophobicity (free energy of transfer to surface in kcal/mole). Arch. Biochem. Biophys. 161:665-670(1974). +\item{Casari:} Casari, G., & Sippl, M. J. (1992). Structure-derived hydrophobic potential: hydrophobic potential derived from X-ray structures of globular proteins is able to identify native folds. Journal of molecular biology, 224(3), 725-732. +\item{Chothia:} Chothia, C. (1976). The nature of the accessible and buried surfaces in proteins. Journal of molecular biology, 105(1), 1-12. +\item{Cid:} Cid, H., Bunster, M., Canales, M., & Gazitua, F. (1992). Hydrophobicity and structural classes in proteins. Protein engineering, 5(5), 373-375. +\item{Cowan3.4:} Cowan R., Whittaker R.G. Hydrophobicity indices at pH 3.4 determined by HPLC. Peptide Research 3:75-80(1990). +\item{Cowan7.5:} Cowan R., Whittaker R.G. Hydrophobicity indices at pH 7.5 determined by HPLC. Peptide Research 3:75-80(1990). +\item{Eisenberg:} Eisenberg D., Schwarz E., Komarony M., Wall R. Normalized consensus hydrophobicity scale. J. Mol. Biol. 179:125-142(1984). +\item{Engelman:} Engelman, D. M., Steitz, T. A., & Goldman, A. (1986). Identifying nonpolar transbilayer helices in amino acid sequences of membrane proteins. Annual review of biophysics and biophysical chemistry, 15(1), 321-353. +\item{Fasman:} Fasman, G. D. (Ed.). (1989). Prediction of protein structure and the principles of protein conformation. Springer. +\item{Fauchere:} Fauchere J.-L., Pliska V.E. Hydrophobicity scale (pi-r). Eur. J. Med. Chem. 18:369-375(1983). +\item{Goldsack:} Goldsack, D. E., & Chalifoux, R. C. (1973). Contribution of the free energy of mixing of hydrophobic side chains to the stability of the tertiary structure of proteins. Journal of theoretical biology, 39(3), 645-651. +\item{Guy:} Guy H.R. Hydrophobicity scale based on free energy of transfer (kcal/mole). Biophys J. 47:61-70(1985). +\item{HoppWoods:} Hopp T.P., Woods K.R. Hydrophilicity. Proc. Natl. Acad. Sci. U.S.A. 78:3824-3828(1981). +\item{Janin:} Janin J. Free energy of transfer from inside to outside of a globular protein. Nature 277:491-492(1979). +\item{Jones:} Jones, D. D. (1975). Amino acid properties and side-chain orientation in proteins: a cross correlation approach. Journal of theoretical biology, 50(1), 167-183. +\item{Juretic:} Juretic, D., Lucic, B., Zucic, D., & Trinajstic, N. (1998). Protein transmembrane structure: recognition and prediction by using hydrophobicity scales through preference functions. Theoretical and computational chemistry, 5, 405-445. +\item{Kidera:} Kidera, A., Konishi, Y., Oka, M., Ooi, T., & Scheraga, H. A. (1985). Statistical analysis of the physical properties of the 20 naturally occurring amino acids. Journal of Protein Chemistry, 4(1), 23-55. +\item{Kuhn:} Kuhn, L. A., Swanson, C. A., Pique, M. E., Tainer, J. A., & Getzoff, E. D. (1995). Atomic and residue hydrophilicity in the context of folded protein structures. Proteins: Structure, Function, and Bioinformatics, 23(4), 536-547. +\item{KyteDoolittle:} Kyte J., Doolittle R.F. Hydropathicity. J. Mol. Biol. 157:105-132(1982). +\item{Levitt:} Levitt, M. (1976). A simplified representation of protein conformations for rapid simulation of protein folding. Journal of molecular biology, 104(1), 59-107. +\item{Manavalan:} Manavalan P., Ponnuswamy Average surrounding hydrophobicity. P.K. Nature 275:673-674(1978). +\item{Miyazawa:} Miyazawa S., Jernigen R.L. Hydrophobicity scale (contact energy derived from 3D data). Macromolecules 18:534-552(1985). +\item{Parker:} Parker J.M.R., Guo D., Hodges R.S. Hydrophilicity scale derived from HPLC peptide retention times. Biochemistry 25:5425-5431(1986). +\item{Ponnuswamy:} Ponnuswamy, P. K. (1993). Hydrophobic charactesristics of folded proteins. Progress in biophysics and molecular biology, 59(1), 57-103. +\item{Prabhakaran:} Prabhakaran, M. (1990). The distribution of physical, chemical and conformational properties in signal and nascent peptides. Biochem. J, 269, 691-696. +\item{Rao:} Rao M.J.K., Argos P. Membrane buried helix parameter. Biochim. Biophys. Acta 869:197-214(1986). +\item{Rose:} Rose G.D., Geselowitz A.R., Lesser G.J., Lee R.H., Zehfus M.H. Mean fractional area loss (f) [average area buried/standard state area]. Science 229:834-838(1985) +\item{Roseman:} Roseman M.A. Hydrophobicity scale (pi-r). J. Mol. Biol. 200:513-522(1988). +\item{Sweet:} Sweet R.M., Eisenberg D. Optimized matching hydrophobicity (OMH). J. Mol. Biol. 171:479-488(1983). +\item{Tanford:} Tanford C. Hydrophobicity scale (Contribution of hydrophobic interactions to the stability of the globular conformation of proteins). J. Am. Chem. Soc. 84:4240-4274(1962). +\item{Welling:} Welling G.W., Weijer W.J., Van der Zee R., Welling-Wester S. Antigenicity value X 10. FEBS Lett. 188:215-218(1985). +\item{Wilson:} Wilson K.J., Honegger A., Stotzel R.P., Hughes G.J. Hydrophobic constants derived from HPLC peptide retention times. Biochem. J. 199:31-41(1981). +\item{Wolfenden:} Wolfenden R.V., Andersson L., Cullis P.M., Southgate C.C.F. Hydration potential (kcal/mole) at 25C. Biochemistry 20:849-855(1981). +\item{Zimmerman:} Zimmerman, J. M., Eliezer, N., & Simha, R. (1968). The characterization of amino acid sequences in proteins by statistical methods. Journal of theoretical biology, 21(2), 170-201. +} +\item{crucianiProperties:} The three Cruciani et. al (2004) properties, are the scaled principal component scores that summarize a broad set of descriptors calculated based on the interaction of each amino acid residue with several chemical groups (or "probes"), such as charged ions, methyl, hydroxyl groups, and so forth. \itemize{ +\item{PP1:} Polarity, +\item{PP2:} Hydrophobicity, +\item{PP3:} H-bonding +} +\item{kideraFactors:} The Kidera Factors were originally derived by applying multivariate analysis to 188 physical properties of the 20 amino acids and using dimension reduction techniques. A 10-dimensional vector of orthogonal factors was then obtained for each amino acid.The first four factors are essentially pure physical properties; the remaining six factors are superpositions of several physical properties, and are labelled for convenience by the name of the most heavily weighted component \itemize{ +\item{helix.bend.pref:} Helix/bend preference +\item{side.chain.size:} Side-chain size +\item{extended.str.pref:} Extended structure preference +\item{hydrophobicity:} Hydrophobicity +\item{double.bend.pref:} Double-bend preference +\item{partial.spec.vol:} Partial specific volume +\item{flat.ext.pref:} Flat extended preference +\item{occurrence.alpha.reg:} Occurrence in alpha region +\item{pK.C:} pK-C +\item{surrounding.hydrop:} Surrounding hydrophobicity +} +\item{pK}\itemize{ +\item{Bjellqvist:} Bjellqvist, B., Hughes, G.J., Pasquali, Ch., Paquet, N., Ravier, F., Sanchez, J.Ch., Frutige,r S., Hochstrasser D. (1993) The focusing positions of polypeptides in immobilized pH gradients can be predicted from their amino acid sequences. Electrophoresis, 14:1023-1031. +\item{Dawson:} Dawson, R. M. C.; Elliot, D. C.; Elliot, W. H.; Jones, K. M. Data for biochemical research. Oxford University Press, 1989; p. 592. +\item{EMBOSS:} EMBOSS data are from http://emboss.sourceforge.net/apps/release/5.0/emboss/apps/iep.html. +\item{Lehninger:} Nelson, D. L.; Cox, M. M. Lehninger Principles of Biochemistry, Fourth Edition; W. H. Freeman, 2004; p. 1100. +\item{Murray:} Murray, R.K., Granner, D.K., Rodwell, V.W. (2006) Harper's illustrated Biochemistry. 27th edition. Published by The McGraw-Hill Companies. +\item{Rodwell:} Rodwell, J. Heterogeneity of component bands in isoelectric focusing patterns. Analytical Biochemistry, 1982, 119 (2), 440-449. +\item{Sillero:} Sillero, A., Maldonado, A. (2006) Isoelectric point determination of proteins and other macromolecules: oscillating method. Comput Biol Med., 36:157-166. +\item{Solomon:} Solomon, T.W.G. (1998) Fundamentals of Organic Chemistry, 5th edition. Published by Wiley. +\item{Stryer:} Stryer L. (1999) Biochemia. czwarta edycja. Wydawnictwo Naukowe PWN. +} +\item{zScales} The five Sandberg et al. (1998) Z-scales describe each amino acid with numerical values, descriptors, which represent the physicochemical properties of the amino acids including NMR data and thin-layer chromatography (TLC) data.\itemize{ +\item{Z1:} Lipophilicity +\item{Z2:} Steric properties (Steric bulk/Polarizability) +\item{Z3:} Electronic properties (Polarity / Charge) +\item{Z4:} Related to electronegativity, heat of formation, electrophilicity and hardness. +\item{Z5:} Related to electronegativity, heat of formation, electrophilicity and hardness. +} +\item{FASGAI} Factor Analysis Scale of Generalized Amino Acid Information (FASGAI) proposed by Liang and Li (2007), is a set of amino acid descriptors, that reflects hydrophobicity, alpha and turn propensities, bulky properties, compositional characteristics, local flexibility, and electronic properties, was derived from multi-dimensional properties of 20 naturally occurring amino acids. \itemize{ +\item{F1:} Hydrophobicity index +\item{F2:} Alpha and turn propensities +\item{F3:} Bulky properties +\item{F4:} Compositional characteristic index +\item{F5:} Local flexibility +\item{F6:} Electronic properties +} +\item{VHSE} The principal components score Vectors of Hydrophobic, Steric, and Electronic properties, is derived from principal components analysis (PCA) on independent families of 18 hydrophobic properties, 17 steric properties, and 15 electronic properties, respectively, which are included in total 50 physicochemical variables of 20 coded amino acids. \itemize{ +\item{VHSE1 and VHSE2:} Hydrophobic properties +\item{VHSE3 and VHSE4:} Steric properties +\item{VHSE5 to VHSE8:} Electronic properties +} +}} +\source{ +\itemize{ +\item{Hydrophobicity}\itemize{ +\item ExPASy-Protscale (http://web.expasy.org/protscale/) +\item AAIndex Database (http://www.genome.jp/aaindex/) +} +\item{pK}\itemize{ +\item Kiraga, J. (2008) Analysis and computer simulations of variability of isoelectric point of proteins in the proteomes. PhD thesis, University of Wroclaw, Poland. +} +} +} +\usage{ +data(AAdata) +} +\description{ +A list with a collection of properties, scales and indices for the 20 naturally occurring amino acids from various sources. +} +\references{ +\itemize{ +\item{Hydrophobicity}\itemize{ +\item Nakai, K., Kidera, A., and Kanehisa, M.; Cluster analysis of amino acid indices for prediction of protein structure and function. Protein Eng. 2, 93-100 (1988). + +\item Tomii, K. and Kanehisa, M.; Analysis of amino acid indices and mutation matrices for sequence comparison and structure prediction of proteins. Protein Eng. 9, 27-36 (1996). + +\item Kawashima, S., Ogata, H., and Kanehisa, M.; AAindex: amino acid index database. Nucleic Acids Res. 27, 368-369 (1999). + +\item Kawashima, S. and Kanehisa, M.; AAindex: amino acid index database. Nucleic Acids Res. 28, 374 (2000). + +\item Kawashima, S., Pokarowski, P., Pokarowska, M., Kolinski, A., Katayama, T., and Kanehisa, M.; AAindex: amino acid index database, progress report 2008. Nucleic Acids Res. 36, D202-D205 (2008). +} +\item{crucianiProperties:} \itemize{ +\item Cruciani, G., Baroni, M., Carosati, E., Clementi, M., Valigi, R., and Clementi, S. (2004) Peptide studies by means of principal properties of amino acids derived from MIF descriptors. J. Chemom. 18, 146-155. +} +\item{kideraFactors:} \itemize{ +\item Kidera, A., Konishi, Y., Oka, M., Ooi, T., & Scheraga, H. A. (1985). Statistical analysis of the physical properties of the 20 naturally occurring amino acids. Journal of Protein Chemistry, 4(1), 23-55. +} +\item{pK:} \itemize{ +\item Aronson, J. N. The Henderson-Hasselbalch equation revisited. Biochemical Education, 1983, 11 (2), 68. +\item Moore, D. S.. Amino acid and peptide net charges: A simple calculational procedure. Biochemical Education, 1986, 13 (1), 10-12. +\item Goloborodko, A.A.; Levitsky, L.I.; Ivanov, M.V.; and Gorshkov, M.V. (2013) "Pyteomics - a Python Framework for Exploratory Data Analysis and Rapid Software Prototyping in Proteomics", Journal of The American Society for Mass Spectrometry, 24(2), 301-304. +\item Kiraga, J. (2008) Analysis and computer simulations of variability of isoelectric point of proteins in the proteomes. PhD thesis, University of Wroclaw, Poland. +} +\item{zScales} \itemize{ +\item Sandberg M, Eriksson L, Jonsson J, Sjostrom M, Wold S: New chemical descriptors relevant for the design of biologically active peptides. A multivariate characterization of 87 amino acids. J Med Chem 1998, 41:2481-2491. +} +\item{FASGAI} \itemize{ +\item Liang, G., & Li, Z. (2007). Factor analysis scale of generalized amino acid information as the source of a new set of descriptors for elucidating the structure and activity relationships of cationic antimicrobial peptides. Molecular Informatics, 26(6), 754-763. +} +\item{VHSE} \itemize{ +\item Mei, H. U., Liao, Z. H., Zhou, Y., & Li, S. Z. (2005). A new set of amino acid descriptors and its application in peptide QSARs. Peptide Science, 80(6), 775-786. +} +} +} From d2b5d84c8e35bc5123d2a68680da4295fcb5cf79 Mon Sep 17 00:00:00 2001 From: Daniel Osorio Date: Thu, 9 Mar 2017 15:01:53 -0500 Subject: [PATCH 32/50] Update Peptides --- DESCRIPTION | 2 +- NEWS.md | 13 ++++++++++--- 2 files changed, 11 insertions(+), 4 deletions(-) diff --git a/DESCRIPTION b/DESCRIPTION index 2527623..6e07e00 100644 --- a/DESCRIPTION +++ b/DESCRIPTION @@ -1,5 +1,5 @@ Package: Peptides -Version: 1.21.0 +Version: 2.0.0 Date: 2017-03-10 Title: Calculate Indices and Theoretical Physicochemical Properties of Protein Sequences Authors@R: c(person("Daniel","Osorio",email="dcosorioh@unal.edu.co",role=c("aut","cre")),person("Paola","Rondon-Villarreal",role=c("aut","ths")),person("Rodrigo","Torres",role=c("aut","ths")),person("J. Sebastian","Paez",email="jpaezpae@purdue.edu",role=c("ctb"))) diff --git a/NEWS.md b/NEWS.md index 768b31a..5e42429 100644 --- a/NEWS.md +++ b/NEWS.md @@ -1,15 +1,22 @@ NEWS ==== -**Peptides v.1.20.X** +**Peptides v.2.0.0** * All datasets were unified into AAdata -* zScales function was added - * All test were migrated to testthat +* readXVG and plotXVG functions were improved by J. Sebastian Paez + +* kideraFactors output vector was renamed as KF# + * fasgaiVectors function was added +* zScales function was added + +* vhseScales function was added + +* tScales function was added **Peptides v.1.2.2** * crucianiProperties function was added. From 0ab2945219a9453edfd95d9fc611714aa44a281c Mon Sep 17 00:00:00 2001 From: Daniel Osorio Date: Thu, 9 Mar 2017 16:13:56 -0500 Subject: [PATCH 33/50] The protFP function was added --- NAMESPACE | 1 + NEWS.md | 5 +---- R/protFP.R | 28 ++++++++++++++++++++++++++++ README.md | 1 + man/protFP.Rd | 26 ++++++++++++++++++++++++++ 5 files changed, 57 insertions(+), 4 deletions(-) create mode 100644 R/protFP.R create mode 100644 man/protFP.Rd diff --git a/NAMESPACE b/NAMESPACE index acfe8d0..81403cd 100755 --- a/NAMESPACE +++ b/NAMESPACE @@ -18,6 +18,7 @@ export(membpos) export(mw) export(pI) export(plotXVG) +export(protFP) export(readXVG) export(tScales) export(vhseScales) diff --git a/NEWS.md b/NEWS.md index 5e42429..6206bec 100644 --- a/NEWS.md +++ b/NEWS.md @@ -12,11 +12,8 @@ NEWS * fasgaiVectors function was added -* zScales function was added +* zScales, vhseScales, protFP and tScales functions were added -* vhseScales function was added - -* tScales function was added **Peptides v.1.2.2** * crucianiProperties function was added. diff --git a/R/protFP.R b/R/protFP.R new file mode 100644 index 0000000..f950503 --- /dev/null +++ b/R/protFP.R @@ -0,0 +1,28 @@ +#' @export protFP +#' @title Compute the protFP descriptors of a protein sequence +#' @description The ProtFP descriptor set was constructed from a large initial selection of indices obtained from the AAindex database for all 20 naturally occurring amino acids. +#' @references van Westen, G. J., Swier, R. F., Wegner, J. K., IJzerman, A. P., van Vlijmen, H. W., & Bender, A. (2013). Benchmarking of protein descriptor sets in proteochemometric modeling (part 1): comparative study of 13 amino acid descriptor sets. Journal of cheminformatics, 5(1), 41. +#' @param seq An amino-acids sequence +#' @return The computed average of protFP descriptors of all the amino acids in the corresponding peptide sequence. +#' @examples protFP(seq = "QWGRRCCGWGPGRRYCVRWC") +#' # [[1]] +#' # ProtFP1 ProtFP2 ProtFP3 ProtFP4 ProtFP5 ProtFP6 ProtFP7 ProtFP8 +#' # 0.2065 -0.0565 1.9930 -0.2845 0.7315 0.7000 0.1715 0.1135 + +protFP <- function(seq){ + # Remove spaces and line breaks + seq <- gsub("[[:space:]]+","",as.vector(seq)) + + # Split the sequence by amino-acids + seq <- strsplit(seq, "") + + # Load the ProtFP descriptors + descriptors <- AAdata$ProtFP + + # Computes the ProtFP descriptors for given sequences + lapply(seq, function(seq) { + sapply(names(descriptors), function(scale) { + (sum(descriptors[[scale]][seq], na.rm = TRUE) / length(seq)) + }) + }) +} \ No newline at end of file diff --git a/README.md b/README.md index f9935bb..6b6b046 100755 --- a/README.md +++ b/README.md @@ -40,6 +40,7 @@ Available functions |mw | Compute the molecular weight of a protein sequence | |pI | Compute the isoelectic point (pI) of a protein sequence | |plotXVG | Plot time series from GROMACS XVG files | +|protFP|Compute the protFP descriptors of a protein sequence| |readXVG | Read XVG files from GROMACS molecular dynamics package | |tScales| Compute the T-scales of a protein sequence| |vhseScales|Compute the VHSE-scales of a protein sequence| diff --git a/man/protFP.Rd b/man/protFP.Rd new file mode 100644 index 0000000..4b9a0d7 --- /dev/null +++ b/man/protFP.Rd @@ -0,0 +1,26 @@ +% Generated by roxygen2: do not edit by hand +% Please edit documentation in R/protFP.R +\name{protFP} +\alias{protFP} +\title{Compute the protFP descriptors of a protein sequence} +\usage{ +protFP(seq) +} +\arguments{ +\item{seq}{An amino-acids sequence} +} +\value{ +The computed average of protFP descriptors of all the amino acids in the corresponding peptide sequence. +} +\description{ +The ProtFP descriptor set was constructed from a large initial selection of indices obtained from the AAindex database for all 20 naturally occurring amino acids. +} +\examples{ +protFP(seq = "QWGRRCCGWGPGRRYCVRWC") +# [[1]] +# ProtFP1 ProtFP2 ProtFP3 ProtFP4 ProtFP5 ProtFP6 ProtFP7 ProtFP8 +# 0.2065 -0.0565 1.9930 -0.2845 0.7315 0.7000 0.1715 0.1135 +} +\references{ +van Westen, G. J., Swier, R. F., Wegner, J. K., IJzerman, A. P., van Vlijmen, H. W., & Bender, A. (2013). Benchmarking of protein descriptor sets in proteochemometric modeling (part 1): comparative study of 13 amino acid descriptor sets. Journal of cheminformatics, 5(1), 41. +} From d4dde321c6764d90e457aaed6312677a1cfddb53 Mon Sep 17 00:00:00 2001 From: Daniel Osorio Date: Thu, 9 Mar 2017 18:25:40 -0500 Subject: [PATCH 34/50] aaDescriptors function was added --- NAMESPACE | 1 + R/aaDescriptors.R | 38 ++++++++++++++++++++++++++++++++++++++ 2 files changed, 39 insertions(+) create mode 100644 R/aaDescriptors.R diff --git a/NAMESPACE b/NAMESPACE index 81403cd..f4b6b8d 100755 --- a/NAMESPACE +++ b/NAMESPACE @@ -1,5 +1,6 @@ # Generated by roxygen2: do not edit by hand +export(aaDescriptors) export(aacomp) export(aindex) export(autoCorrelation) diff --git a/R/aaDescriptors.R b/R/aaDescriptors.R new file mode 100644 index 0000000..54a471b --- /dev/null +++ b/R/aaDescriptors.R @@ -0,0 +1,38 @@ +#' @export aaDescriptors +aaDescriptors <- function(seq){ + # Remove spaces and line breaks + seq <- gsub("[[:space:]]+","",as.vector(seq)) + sequences <- length(seq) + # Length validation + if(all(nchar(seq)==nchar(seq[1]))){ + # Split by amino acids + seq <- strsplit(seq,"") + # Extract descriptors + desc <- lapply(seq,function(seq){ + sapply(seq,function(aa){ + c(data.frame(AAdata$Hydrophobicity)[aa,], + data.frame(AAdata$crucianiProperties)[aa,], + data.frame(AAdata$kideraFactors)[aa,], + data.frame(AAdata$zScales)[aa,], + data.frame(AAdata$FASGAI)[aa,], + data.frame(AAdata$tScales)[aa,], + data.frame(AAdata$VHSE)[aa,], + data.frame(AAdata$ProtFP)[aa,], + data.frame(AAdata$stScales)[aa,], + data.frame(AAdata$BLOSUM)[aa,], + data.frame(AAdata$MSWHIM)[aa,] + ) + }) + }) + # Format output + col_names <- as.vector((outer(rownames(desc[[1]]),seq_len(dim(desc[[1]])[2]),paste,sep="."))) + descriptors <- matrix(data = NA,nrow = sequences,ncol = length(col_names),dimnames = list(list(),col_names)) + for(sequence in seq_along(desc)){ + descriptors[sequence,] <- as.numeric(desc[[sequence]]) + } + # Return + return(descriptors) + } else { + stop("All sequences must have the same length.") + } +} From c0aafef02cceb225dde6c2410d2cb6ea52fa7177 Mon Sep 17 00:00:00 2001 From: Daniel Osorio Date: Fri, 10 Mar 2017 16:49:32 -0500 Subject: [PATCH 35/50] aaDescriptors function updated --- R/aaDescriptors.R | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/R/aaDescriptors.R b/R/aaDescriptors.R index 54a471b..6fed805 100644 --- a/R/aaDescriptors.R +++ b/R/aaDescriptors.R @@ -10,8 +10,7 @@ aaDescriptors <- function(seq){ # Extract descriptors desc <- lapply(seq,function(seq){ sapply(seq,function(aa){ - c(data.frame(AAdata$Hydrophobicity)[aa,], - data.frame(AAdata$crucianiProperties)[aa,], + c(data.frame(AAdata$crucianiProperties)[aa,], data.frame(AAdata$kideraFactors)[aa,], data.frame(AAdata$zScales)[aa,], data.frame(AAdata$FASGAI)[aa,], From effcf956cbaba745ab0217c049ae08f110271fbb Mon Sep 17 00:00:00 2001 From: Daniel Osorio Date: Fri, 10 Mar 2017 16:54:33 -0500 Subject: [PATCH 36/50] Update AAdata dataset --- data/AAdata.RData | Bin 7945 -> 9063 bytes 1 file changed, 0 insertions(+), 0 deletions(-) diff --git a/data/AAdata.RData b/data/AAdata.RData index cdd2bf47419544a24074f5b9fb6ade59b0a5f58a..ab9bdb2c4ab3892c75a47baabb65a1f8c1473472 100644 GIT binary patch literal 9063 zcmV-tBbeMDiwFP!000001MPixe2wSd|H+U+7E*hQ*fUmXd*2ZeTZV?VijzS?BxG2% zN3Eh&RjZ^_QL9zHRB<0W)E0XsF(M*l6AAg{eH0Bx$3v-RRMN!kzyyzb@jitu6=xF8c9;A)d7Tr+3s83Q+v&QiWQjtahcp~>KVXJ#?L zg2=b3xJoyRVHhQ4sQ3$_zXd#g(ck6sh|kMr>O4r#fLkUOL#B$WtWoDxD#Uv>Vm@$` zOX2)WjGx2zni}5!@%;XTZo0tpbQ@_x+E*dc%FQ+{T~o$M_kiPBr+{APGk%hOw5;@X z^xk1og8uT@i_#Gl7wK_R2mhi=;&{GV@c>ftciZ)6q;!mbUpKv6__y<=OL^DpoV_<# zx}h=|=~3~plch(Pmxp9-riM4@`#$LE5$KcWRkl)EdV*sD_(BTk8_y|ERr*w(gRZeY zlzZS$&(!CXBbdKyD&0%x!LPFLd@lIR15$vA;eA|P&k8n6B|-g_3OCD_I1fIoU{h3n z13$QmBk$+)*i_jkeJecjeSF^dezAF*7~WSvuh{pb{ovn+z)$)6$*+%r&Pn&ASMq=I zhgBHosu7NS{v`OuDeM#HipjdGc&|$4T}=+}#VXFqHLhdG59#VrVxRP#smc>d3UEA& z`wH~%HOQ5C9dd`@+c|iCmx{Ln{>1l5`Ko**Wnlg?RX$~McoXMmDqc!D@F$<9-1Zpq z;AP5b>YvUWxDsy&>pBh2Lq3u6Az!Ad`+{;8@8Nts1>Ssbj!O3?hxaA$(Pt`t$`i=X zW?0t`u+OEbbf-X`Bi_ng@Q)YZ2f$l-1{|?2qDv1`XBf#__UOx@(*1l$PtjAWphI#i;@NYQ(j#kx^n9CvZG4BI(wB)b>)CJ z0{)Ya=dlk+m=CD{ z_a%dm`~W@!{vn%VJkEEPy04lX-lR7k?^6y#AACbfQt4mw7k{!f_>l$nS@Lfh4PhUV z1)som$m`@wvX$YynH=8K6JM(9nfoBuxsr?iWAN99xbGtL^aK?r1@f{&`49T0lBddb zIt}EGWXgS@cj!@+Kgr*eY_)G{coQ$u7xy#vxi1=@=bylva$tcWy;A?zSsFekT>#&? zYP7GK8_K7qhPU|Lq(|aM{Ty0;^GURf~*Wej;lO`K4S9bjYA7 ztbe%@&esIq6>vYE*VR(5>lieJ>pF}p&hvd$FrG86<9(DDX}>i!yoH`ayEOd>jEe$3 z!oQh9KLF+fc0<_~a!4WUjg)6-e}R8T_&;GkQFcJCEPx)AgLMP{hpFMMs{(rKrc>#y zb!8Q24_T$xTDaa4bnWg6eFoc59AW=pE_6~bu}@+))=pz zY04+`D~LD**!`rvpf}j*#QC$pEd%-^w>Os_Vcpv=J^y8Zx-tdR(9KpX~ z2iG~!|Dw{JkfW^)`8Vw-(hJ~+qmFhd_-kZy^r4R`S@bKZm%DV`3dz61^yc) zjdml@E#jvX(76IXmjXMXz&jiK!05V^4tjlwefT!)DXQ*~#`WXWKgc(5p7y1(kQb}aj&5i_muui? zhVkLQ(V;I>9;}AZt8m0)m7A8b2}k9j>@&;~o$Z6dV~Ej(%zPfJkkK zc0|wM2%IV99yv53ikCZuX#Ltt z1Nq7xp+#u%$5{4=3E@-rJ;p@`caDe%3yqEr6HxRF9$nPuYkO(KwWGCRC7;|Ybewj) zb_~a}^43NU4~`_V-Vx#9F;Qc*Blz8Ayd$*%A==^ENHK(kua*;K=^G*Dz*^rf!KReo znBZW3hILhQ5PJ?y7;IOdJaDr^rFElJFf)CpEiwGMM93B)bPJA3XVnlGHerRoXxO#Ae0dEf^J~hlWAw6jG(f5Vl0{Di$q;U|bhLt=Nndj3Kh5mVjjq(F`fv% zzy3EW)Bhs8Nl(J*%H$6I{x}4AQ3+nMc$Z0ItyF2qr!2$lPFtjfhx4 z#tt)xMZ}eeSjJ*7)&#NWs9{nAH66(Uc+=7Viz$g$L=H2Pl0?tNQfL@4$w(3n{=_E2 zOtL4K4@PLhf=bUiJra~0sezgt-n1aYQml}k8A$?7Swx`bfo_q3CoDyfbjggwbu#nI z^vpo>XQWRS=7E;k6ncbAGjimABcuMC@n*&t@ZtIw7FDckNn{3t-&1%Yy;Jz1@QI8D znf!(O1B6f!p^b5rOm)8y{3wAf6T_RH6;^V9utCq5YytX*Wt+k_g-8h*BorET8b&~2 zoiO8_>xGs)2#XSMr?8{Iv&Q>P4sQr=66u+lyTFNfG2>BU#tbqWl@}DoAJu~B<`yG{5X4HURD3^fGbI>!c3(qb21?iQZd1kglt`?c^ z*dN6_K*?n!x2fSxTqLn?g1+hT7IX>ugOwl1?@_r(DF9uj8C80K{G;4p<~8^@=a=$4 z?}z7x7F*N7+u(PU#zl)BU0RkjTa`53N}8=pnr%v&ZA+T%N}BCUn(v}%S@en)ni5sl z7E^C4*U=RJ$xaL|gmb4Nf~63wCO5#5eLJX3aQ+zmG}}MH-}z7Qcl{H_zQ(Xw2KE(3 zP0Mh7yM$_OPTU^*~T8^jAxRzyJPE7aRshrax2$jl19zjXBJ}V41!thcRBJ|AJ2^hbfCs z;gKBXulV{u`RT8HRq0N{g2Tc_jSh{X8_KG)c1($*$;z`=r#^n%gKc{ThlGcQ4;8~( z^@@p%)Y1=T?Hds^rf4{J{X)aSf+HhDHzF)zM9Ij0(UIc>tom)Ul#o!N0m*iVQMSQ) zbA*|nnpXi}wV|b#K7YgjIKuZ|Rz1q*swAYdVoW(K3Xp6WE5O(nU0LKVqQ<1o@^91# z{uSnY#5SALN3Z^FiIxFMth68};5sx|of9-x)DEI#%h(py=%b~XF&si-g+{A0!E4d6TYOom5U2bZ4Glp2y(1gWT@Kx4`g#|%53wozpc9$WY3w}>a7(Gph zF_kq~M+{S-1r#+v6vQ?wi|N5K6}%08M=4x1|G1@SwGu5i(P}MPZ8RmjuT_bCXi{;B zStV;@esb8n&Puw=&E{2B?^m)9uUL1-@0s+Z=&Z*#QyCnhCwmf61VlGtSo&A-2=)syKZ|1wvm+E*gazLT&lTx;bL)N+!!UN z&+U#uA6GXWdj%uyiVF#sldh=vD35{1jbZwUI47y_R+X**mt3{du+9t>fp6k^qWnbWSv(e>%ldG&ssMm?{j7ES8txE;dY|10JxHF~f9%~GO?+T%da zQbI8t-pci$VuDnXey*jba3y!gyZxO4dMiK9YOJR~3{vQaOrUSOaP1CZz8_RGcL8pImjGq+~tSNB%6mESij>8Imrl{6I<5 zllPNV%JSlAdRNh5og}G!>0&Xtk5G_NrrcWpL=Ux;uC6bW!&@cezRFL)Be9rWL@8%g zx>Zv2DAqb6D!mog6L+7ZWI&qnR`FAgSI{qj?&K@VkzzI#Ax%Jq^V#Znvcu70K&9^? zW$goBr$6x_;}=Ymf77lmmja#Lfpk)U{Vo9&;I9IY?5oAVDw+PpCE+FFdR@;>D$G(2 zf*)jpKb=J|<^pE;s{BRyMO{ZylDZy*^mHElC|$o@KRshQcpLl6=EAgZ-leUkMDDQ>>jwUGAuTdkkbYZg3GnB#;+zQfqraT~FY=pA1``@q$Ygwj z$S_0vny47a%Jw27!BplE>xLDtpHd6L?h z3NlJr`A@_L=3)Fa6P0^dxriB{3|eJ8CH;+z=R=&0t`sZHLtAFtB&`wjW0L;4J`ylL z8H|g<`&n_6aafoalfxTyB=`a27-oQe>4#?=8t`OhlJMIiV^LI|Phngc@a6OLqjNrK z{b9TsIGZUH>GuXdpIA5}zQM?-B;Y3mur+wf+!7wDMubm{PW>9J+i zJnrGbvq;^Fo<~+afet2@F^YX=E(&!zJgi1(3(B;ng}2Bd$p#&l1K#G?b2BL0 zfZj#!1gmnW^CYS<(MCa?Hyzg#m^%U7satb?kmII9uD}~txqr*>W(>Jp8hBw3*O70q zDi0GzkwYSK2N8QNa$6`{@_#R}1+Gkhrj3G$r_{N&(pCq&-!zu|EyG*ZHg;kqV)sQD%j$K!<9kI`NxUL3zvYW;H+&OV0ub zq;upJGD3&)oUr|1KE(fWm!RUQAYz2{E~=`;v-%$S3-(*u_8GBr;SD24-Wt4Ls{>ej zM@B?<5y|D~wleIx8FpJ6cH0w;2PS`<2o*ny)2O`hJ9>aV+ z?oFH*kv~np8f9Gi1(Hm257*#Nkc#FCg_@7LLUzc`eR_LUR$$Urn^+lZv7Tw`^tm^=Onuv~uU7MA;g4J5gk70-eqr~gKb(F?*c5ac(D@D{oEd#fS&4RTqkL+U z!<$jG$%gWXu+!5o23w4{pSmsmkd*Ps7fA2qH#b-e41OQZEB8_MIS+5@7kJC?Hs067 z{z?8#`XwJWrc>e$TMqFTMZ&;;#QoeKxzDmL5BbVfoIh)#{F`w!b@KK>8#9 zq5qcnF+ZCA8`ut5Pe<&pe2)7t-v@lf{Jd%XqPGq2i{KBmEs!tMHj@q9xewCzMLH(G zAm5=)0X9p)FDPHquf=siKRV@>1mJFR^!?g=b?Z(&`}lp>tEFMLm0{P-u-n?O+s3fl z*09^ou-o3S%ba!_d`1h+>*`5TMdDV#t%D>%)qtu46K7alouxXsWif<^B*G<4lB4QI z7MR5U1X?8sVFrKl+8pAym_)E7xfL++3%^&COyQE_Qe_AQ-7wsOn7Bl|I4(m8c%CU7 zT!J)hP*i(jC`ydCzlJ1 zj0p_YhKG6=T?>wk4i(je?S~ha5ALE3jE;!pN%N6}!Fs%3pf*h0ZPmry&&!=)S?Yrc zcttfMvZu08_SDZV`D%?BuGls6)rJQ}jA#}W92}(onxc0{7G3_jsNK$Y=$eWPuRgA^ zqRCI4>P9M3w=!OBZ|n`Q&!3uX7I1w+$Lrb6WA~qIm-|J=__?)Kx6%&jbZz`Pvuk+) zn+orKY!;qZb@C@a-|#t@F#YUjyQQux7U=FK%wDkmj}{$1jKA6GXtg`Pr3YW@;+-8` z{p*3<1A?|!uQ2z0>r2%#r5&dm$+34I&n~RJFgopL=XV-*Po26UVqNcO-zjbPbgW+Y z!+9@;9ld|XebuIUgB{(R=1$q|+2hFC=TV879UE_%HEql1V=t$6?6}TqK(qO~YH7Mw zD;T@`ofQW(wyAfMH@nR~v?Zu>Zq;gMR{MT6x=P);OKmz_-oJLigm0@%eD>a+7c1ju zc=^ms{5fA&Y5L6rYpR4bDTv7)ShmgW=8Y1+Tz}lY@7G?{rHidkS9Pi8@X@}xBi{|2 z^HFE3Z?FCM(D#OQ-BE3(Ik{TaiHS8|IA*}8-WT$02K>G#%j;0=sp~a2x)f9xKc{J# zFUx$}V$u&sO8uC%L3gm(r#9r`w$pWIJz$~NoVe@b_0PlL|QSFiT!=^5KU_(l_pTlN-J-j%C454H4+ z@oB%I!1X=Pnu890=A1bv=AsljF@M>PPPQ}r1KmBAS5|J8e&BU^_T)`5PhwNe(|b&{ zeBe{WT6n%UbA7_dX16YG{?Kohy!+ghFF#p%>Sf~zaUGIuVmdtQ6B)61_Q`5# zi%*YEspAp4WKhI++v1ljskPzSW}oO`9h$ozne4FqLi91WYuk48t9Sp|(8eAe*Uk%= zy|l*a7foCroXz^J;H!HPwa)LZxOKVX&3&IF+z##5Ib%R?*QMsIQbu(B&s86fw$ox0 zo9)}|KWXUa8J=Y;npf)-lQn(cW{)jDH9ok0xo%NC#}Be5TymO{)AsuG-%}fz9q7HY zTls*P#qlji4X*dzx;^#3tQ50ggw@OEOM3JSB7p%M0oRMm+$TTk7m%x zhxPVk_}(p-zce~~@~0V}wP@PHYxxJkM}{Br40G(8w7k%Lbg$&ULQBGjO~Iit{mBRer|Mu zPgK{~u|ezh1y=Jfdu)i=P`i_fHeWRKnHje(=F7CHX$y{we?RA3?BGW;?vJ(&>~il} z@8qvnU2DJmT<`Zr`C3?CX>jZ2@?nc&oM zR2@2MSm2}&K3%u)e9g0)9Cp5#T_tt+#hEw8PV%s?T-bk8liANU)fl&|#*_Yw!pXQf zF4t7WQ~AW$MB>yQLLA_x}7x|9-bTCus9- zf1N$pD(mhRU8MbQ>yCXA(s1}=XD^?s{j`g|snxSW{R)q>V*5!=Mt;8VPDp)i@{*hL z%KT=3{lvJfz0Du&a&uVx$Z^c9`Ti?s&35ZCwyOVEGxC4GQ`vL$F9|>2+n1aYwD4Gk zwX&Cet@G_Bl%4y0aN3iQR+)b9^ccB(bF^FK@b2p;Cp7xNJ1l<7;)d~O9^J8DFrweW zwTrJmjNKfxQ2Oxq2R;6%qRr^zd1U8`nvX4f`tIrQ@%)8ushcmh9UpIXBcRR~f7GmA zp^9Ve;ok&$TRIMnb4orNI`!m)huQsGbd6}T#rN1Fsnw<9qmFL#IPH11=Z4TdClcI} zJ-SAijeRgAdhl0+Y@6zqWjWZ#Ez3b z-e&iw?LtDI-o4fJSBpt)3x`={_R4gTN8avua(vtL)890B=VIaD!t>4{SL)nKA5?E* zx9M}n9{;`K%3n8iYG~HhY2?(*I@ddPm}D+hsM7Y*)|W5uU-ukZJ@s-K`*Me>`hI%G zYWBR-+dm3O`=Pp48ZxGN$C>`Va_4|X?c4wKtoCpZmu}IE7AV?j;p1I%2r(YwlkMHFlZe!nW?KKxwsMX{lUPli-%TE)xlx9?A8WE{#{xxSqBv|sLhxW2SgwTeC!o;hZ^EZp_D_w1*Q?T_9+ zy=?URQ{t}m>ba@O#JMr^r}wL0{*GPSMM>A(rj)yND=xZDPg}F`zkd4u*q_q7H#xd3 zH6ilu67Tr5Ro_!rrq zZ?v7N?7Ma1#hKOLwebI@!>Oy$9pZ!M`(C*g^`36*3LEdXS&c*M&!05?{`)O1pZTFq z__bQK>n?kA{8?_lX=`R%ox9TCx~zMYUz;VruWVoX`*jtP?zQ&%cBD(CiTRl`mU$fR z_Vw{k$Jq^^;L^K8(x4S{j_!FhB`Y`4XZ!h8sV*}PMK#&q@SxrEluNp9@k6)0d)2#k zgTU=QoQ_!L7Owno_o!diy=dsWDs!Qq#&V@Iusip?x9-#Y z5A1XcuW_fwr1RJBudUgBV&~6SRN9o+aO>d%-(+>_qn*`f(}=Xgn;vXCK7NCC?c=Y@ z=elf-3(L#z|KLeM=)Hw?eQVy?cC^pk(mxeQ(@(egb(mZCQbAtTr^Y1)-fT6|J!I`4 zKLl({`(*$33(VSueb;lIMOI#Omw=NN7uT0c85el&KzXHLZp&ZG4)B{(-Lh&(U_o%{ zoen{3eu{YEXtiqU*nN*jUmX5L>qASHH_M*iG`_<7{o_Y1UFcEAGWep@zv}(59vlCd zTqn87g^!NgkF7cL$qmGCUEYDX-NTQ+8d?QQeDzxf9@ z?K{8mS2hi@GnaK+^6SJuzSz*_#n{~+cTV0o zbM~EYzInegqxXPO-D{1iC6mbvWkyDZGDD-PLu13Le+*>CGK;Fx)Ws!G9xkuCp z2VQjGMh6~rFpv%g(ZNtU7(xfb=)j#0Jn6uP4o1>}A02!_2fkJRyd&_rN9~HvMvZAN z8jaB%2u00~du1(ZF5J0S>(kKKdt7Ri?t+l6J>BfMka$*m;v7LEES!q7l+ApH_>Koqwa{J+mxPak#qbD~rdv!3kWxshh$IR(m8gRU2>pv_$Z!hUEg1RB!t>o^OK5TU> zZ9Ml#QZn2tU9)qzSLm0Qq}=okZ^(B#+Or55)ZWis?aCgdB>32!9%6y8Fv zF+PMe=%*6tIpG5OFG-SnE*|=-0M8dg&%7WB&@;R*OXFF3K}5R44fssHFGN^EK~hleeDXeIN3Qd5=2{{e2Gllzur0Sxl6#U@ z(*L9%wxXQ}HE^WouR(8I$2@UcC)NYmdnGX+sCRg;lW-Q2XdHt-rILI+q0K73j2+-pK@o?fhB=33p zslSOw@a<66gAop6TZ9~wG0(Tac*w!K;{YbmuS)|T26t$-`>A)`98mw40a{ib(#lb!fZ8qYKj(l{52QO|*XeTn-LVW%fcI0@j(0`WiCn?k9? z>qHrNM+Wge$UE#P;-947ghHvVZ+H`4BwsY2QJv<+n&;_{;Y~cSyt=%S{Vy6oBOWGNLN7oMh*r?U7LZHu6sq%erTchmv}22Y0k7u4%ZX>RaYW;W{I@i} z+UhC)CVLw4#OyqjLN4?I+2#4L56^?o-Nt=2{923`Vt%aY*Jl22vg=DR|E8cl=oNj# zn|KIU3fy7uF@Hu1O0vfhS731;;@K2u1756uNH5WKifiNocj`~l|8zcCKluss=hY=W zQoUsQq{ey1EB;KM*q~o(>J#`6$e+vf3C+v;u1}JIQ%ybyoPWm$Yw)^%mk+YI(f?6C z$hX%87N+oRrTL0?1m9@$i^MlN_t)tSzAfVLZ7=Ec4&P2nq~P1ZuhPX&dag6@b_6f! zg!?<8UmZ_L`45f}5?^U6m;5&!(Ow6z!A!H-g3vS0aT`sqL6W!3d1-vn|< zNmCgAd;^?s4!rGgKb{v`NY_P5n!_#W&w=F+A#TQaH~Aln z^wgfGcqGLcVee5~lgkE9RHqVg17Jld?f{w6;PR{{J`isY9nLtMX1_6O+=oG1TM9q`3Q21=xZ>r~KlAdAl zG_pg@;rB2G4=E+RPX1WPw+YUlfxad_jyxFN41B&^-}Fhf-{FXh<}Uu~K!rvbf_g0% ze~mm?K6$7@jWZ@Lnjm!;UGA@v2TU5Kj!*@%GZ89Pe~m&Brob6fS9zFRqeRWjHCP=U ztdyf_gvYfuv)LkC-zGm(& zj|d1>Xy`M{J=Cheu&S@6H+w`(rOlHgCWGZ63<8tE>JSB8F&iAAQG_c4 z=#@j1RcO(VF&+{TOix)2nI5hfpjNAt;o&L<#Zbl6sye-Pm^?&2Rjzvf$-|V>qs*(ngYrlb$_D|?>$mB`?k zztCCqkHEXy?=T`|=jqw){bBd_ht3};qgrfmUi z5}}o3uhAcrp$QKvMb;@ILCldXP`$&OJjn1A3nb5!NdilmWuTTqZm|N7d5XYvNg1*0 zq|EP8WCoT$W%?ALAILMCNf9Ca%pCdu%&7liylKT4@S*X~JgOMi99tO-eNW_t;7PyG`~VWlGPKc-kT1;_OdloFk)GjAkrmp>0c3+BW4saMAD(R@+e9KctRNxM zD9R`U3gd)Uywi9gPaeo32i%G52#BoF{d$Kt$QwuUOe=SR6X8WG9ywYugO!a!1(9*^ z88W^|PZR&3$N`c6cbHE}-xIkfV~OqHp=Wp#xuzAOv@(hKAMM;gdgVT?Fa!RSK}jn) zXk{y9D9|{djAhC+%db(Ak&2bcWUT5N-fTS6ihr8#$Y`Y%HP9ErUEuQ;@{H>&a!dMx zl@yL3&-Y7$Tvm2nOuT@(9RE}@3C`{P!74wuCdbt z_>b_2R$fDoQ~wg5r~47PA&;&8;9c!^)WSuZV1-H<>Ey2n33Lk8C??S9FlC^^DIi#` z3~>rm&L9U}9Ytig)~^=m6c(=e@P6yy>46$`Xt3H}8K4X&&!26eI>KM2_+9I^p>j>Q zQm%3e3snR-O;xLK-fDtM9`022jt_6PQwIb@Xf%qD0ELrW6&fse(kRI7XB;}ji9oI! zR&|#;A|y~5667R(j_kdCZ2@_+;9JRbf4nVaG$Nu@9~oN6kmK8-q`D>SG(?Ar=z5#!8SEN9oH@J92R;19iNU( z-Potox^v1;Y=cj1U*pp$-q%v9|1GE^WtFAC;u9I_NO5h4lvanZnfMNPy)i5=O=|AApNyF5^r%*{6=Fjx{-}&i(_^Mj{Cn{8`DN~hU6#FtAAfNU= zx@GD%tp5lfn)oe-DuP3*raacX>9DGKP)<{@nYTJ{T2*sY^--!+3XPgo)hhMm_bvN` zYo;?;wbP~vqs1`0cuOQkn`6A$Ahtl}UO8YjC-*WX8X)n&1_=jsq>?w3=$B|piR^G= zfKF3_0wvstb+BL(8(WITf1w%jkBA{4q1uoV1Ek;0kvoEDGP$jjaUEu}XbUqL8x|3r zri2>W7?9lClsLj@GR$bv08@qy7Tg#ivBTsqG_(Ifc$2w63+Fh5O}KZEV{7TWfP`u0 zK7yN>@E2g#32%^aV}yPqGaMTiaY!s9w}+5NF*A%KxR+={DSgA6Vt;I51#l3tku7tZ zVgoYK9A+BADl|i}4Q-F6e+aj!;e_tkC76%=Uq?L8wT zSq?fewkIb%#q1G-=dui?3yHejcq4?O5l{OCj&7XPCy+wwPc5_(E)*a6c$BUGaN)-# z9kmiD+yhQ;F)lW0cX^)umdkwR^XA5b`dqqno{I+?x~)ZjW)4?0-lYopOF}C8GtX7m zlLBq;EnBG*Xs#UnCG9fZP~Y(8Fz$tf3hjWuDm)0*R3W`ZxQJO;1~&5;?E9*O6G!@| zSn4M(Lo4-~pSX8bol(_8T%x28glw&NzuqcD>$>SvElF;LOf8BnF0k$8beovFEEDp;W;`YQgv<8Y0Wg^K zif}=vrqtX_Y^%OhYLB=JO_yvu9u@<(Ti1vF-c= z;8FNM2dt3qtJ{a3BU~S9)rtKQ;Vkq)KJ?QqWPq-sWyO+y5q_4&5tk~B2gaV_p^tL4 z)AgI1`h$11-(gBD#+|VpcgA+y8QXDZY{$JPJL)BS&wI?-xIqw~u|>*Iq+l^w2?!$7 zHg_z;kb?9SbR&I}PZ^BWx83(M2Q6?x^Uld#ej%1ApSjI}*4YH)fQna6~r@V)@OQL0`lqpL|oD}4w zBtj(jh$ghXJ*;I))+BEP1y4!-X?!H3fAT093-70GPAT~d{i1hxLynj}pyY{#kY5V^ zQ}P?|q~%a7Sd3+oY`gnRN@fGT^gIRcsXxj4LrHR!Jok>0we$;b$~5OnfL991FO6s5 z0Plim052rz3EGC9{ zbBKD#;0-2kKIsce%A%weniq?JFXNfzm!x=_|VEK zTIoV^O3S@z`893RLG`ri{l#0>NRmSm9$U#p$^TpR4ex5d!yFe)dGffy_lK1}fADTI++aQMk1~wv252Gzl=2XzXVo=@CS1vuKw3@Gt$B2p z2ZXCNbkZ=CU^1KG6ChWyyG`9)d^}tTRb%bPy#E&Ve-K(adCNlr)svmV6pBFYJE~gL zR9#+Mb==!KXnXyr2RY3)ciP*(wMO6u)%NK1=%l|@*}Mz`|A#aCJuK`JbNX8E;&1Y1 zEN`)`yL>|bq!~L6l1lyeRX!hW5K`KB&X+$u@;aNm;MUj2xq+KkiO-XluG)3AYv0ck z9{0c4!tkbR#}4)nJlxcN`KM-go8)sxZgk*dp64vBY#9}v{gd5C?FVPg z+pXR?JluP3uM_>6w*GuY#l(y0H(j>wTQT0o*>?Hd<8DJP#J&wn$?w@g~7DwL8 z>ep|l=@_S#$6Ck+HYtxh{?X<$GK;L|8T*}=o;wgYpty09o7=osPi@q?^+xl)_fE&I zn)zL$StXyGsMwOQ(8Fs{%1>otg9VSzY;UCMR31?{wocEdT{@(EyX&&m$h96#xx^kf z8ap(x{^Hc~(2oO_eKElFyQCjqdOtF2J*DS-TSwzo5iy2Q)5c60ey7xY%x`N7JkG^j zf7pDFL%IEoWu0q(Tl>4Nvv*uD`LSTPc-HAF^IbP=eTODjK3x*zo*msF_28`s$&G6_ zGWYc1maMYuGiB54f^nrYc0BoP`_Z0WwVF*ZkGpwzgwK+Fl|zqiGdOSV_}kE(hKfr~ zl^g3Nr;Pl5-qvFqhA3UQV`&F@Z^K<#n@qc12$-0WG~a!z_^tD2OV6F%a42NMqi!#b zE*Tk9aqDJCPQMO|&swL3O!+A2>V$5xj(hrwc75;U<$ZTz>$^AgUM+DjA2K-c<*cPQ zA6&nF^umEdpB1-~J&f_bo9H;+_;q@wZK1({QF8}#C)y3@vTd8kP`8*-ibtJ{o>&<* z`j~HG7i8=f;nin%x#K5p&BvYn+Ae=tL?Wl0RkrC!e~X2_0WPl54TZzFLV+#&OfUwAe7;?U{ju5Of$m>zisG(YIuT zM!jz7wI7>`vP66+W?V7ncijtfTLQUvf@5bi}VsdPz`6 z*M6}p{FiQQwymO*k_(68Q ztz>w{+O0`_qHhoXWQwhst)9Z)=}Z5aY*n3SAuaEV!*aW5eSWwSTpG zcxC#*;f61cIa{xLWixHbO5ZI@mO2lKZ0x&wVcBob8oEvWIr*owQyH0oQJ3svc@L`= z@x5o(S^jo>_Uqv8`92>F360(#?%XhB@UA(@9X|6^B^+4SKH=u8XI85w`$fgBd-yVD ze_#~%`EM_VTx}%J8{u~0=;r1*MqVRN^c}r2$~kL)Vy_tqrjPtveRH*WQ~O3XEhnuH z@HDmwinGnQrJQ$d=F7rST?eW=9q_*NitB#&@|25*TyMDD8oFC~;!3h}hU-AJLF9`G z;p112v*;{tDzLVSTO;?%9Y0In!^`N&ncgeMmVMq?)uZ;%Wee}dCbZj}V1E3o-oeT@ z&z}tZ#b|b~%891=!}1;Y(5L;b&FGbTV|}}i5-Z17#@hwoZ}lX1T$@>g7A%Xr{9FAk zzwGPZ-k_Il=)C+^5Bv3UHC<=}&HZ+C^`QF&9iooq3}5=Dqt(Uq8=IznIyWw9*wB5Q zW-X6cxxlY&y=Rua)}$sm&#n99NnCiVp%w-+e);Ot$i2CPJ6$}Km8^Nb!80Ly>vs*k z94}egtnXXd{MvTE`q|gdoZElUB(8SbbItr)KI%4S>e$~L?{+-=sMkE<)RQX}H@AJ? z)pvd0>kq>FCMZ^V-%kqrM2y^Q?%AuLqq6PF*$dJ??RxL#j#eQ_En2qT^y+d+vETgd zOHFUzA7xg@CCsPihTpdIsrAE7`_!}^9^ZvJG?-PEzi^Z5`9W(he>L55(oBcpeN)G6 zUUu=stGNZmDPD);w`MskJQvpKbo;ZGZ!_ig zcUH9bK9-q%*he-p<(l$eE99%q`&$1T898O=f_3#D^cmY=`{r3^jmFMR`r7W1{j|)y zN0H7ai|RzK+GbpoTA82jw1#+dig4+g-Ku9izQ-JX04g?lJF5@*2y{Cqtbt9gQp7 z|FP#1C*h{YwxZ)s&3>|M*e|y9>)WMai!Ti=Z};oq`Mzh4I)^lS)@*kC!}QqZeP#_< zyt%=?()I_>pIKkfe}sI=h<%f@&+mJ2=<Ivn`yZusUjL)*B#*Kpm$`!SaS_f|5tFEvy-8wJwRL<1IN#FE1 zw;|f8aAoHN`%gzDOxYOa+R9jw$c<{89_hO0>YP>?o$h>b*($R6qSucc(ka z_ulEAD^|xAcaFY)prv|U+@@)hEuI>l{MA>{dF0BDtIgXL=5HFb;g?xgzuDchBJ%j? z0U55_Tps&m1<#sw)TM8NVeBrK4MD*tpOzF|%lzcvdiQpITE6!m`A0`QReJycJy9QP From 77ae03aa4bdd2b5941a2cca7615d6a3ecb7968c5 Mon Sep 17 00:00:00 2001 From: Daniel Osorio Date: Fri, 10 Mar 2017 17:06:27 -0500 Subject: [PATCH 37/50] stScales function was added --- NAMESPACE | 1 + R/stScales.R | 28 ++++++++++++++++++++++++++++ man/stScales.Rd | 26 ++++++++++++++++++++++++++ 3 files changed, 55 insertions(+) create mode 100644 R/stScales.R create mode 100644 man/stScales.Rd diff --git a/NAMESPACE b/NAMESPACE index f4b6b8d..bcca096 100755 --- a/NAMESPACE +++ b/NAMESPACE @@ -21,6 +21,7 @@ export(pI) export(plotXVG) export(protFP) export(readXVG) +export(stScales) export(tScales) export(vhseScales) export(zScales) diff --git a/R/stScales.R b/R/stScales.R new file mode 100644 index 0000000..ab6c213 --- /dev/null +++ b/R/stScales.R @@ -0,0 +1,28 @@ +#' @export stScales +#' @title Compute the ST-scales of a protein sequence +#' @description ST-scales were proposed by Yang et al, taking 827 properties into account which are mainly constitutional, topological, geometrical, hydrophobic, elec- tronic, and steric properties of a total set of 167 AAs. +#' @references Yang, L., Shu, M., Ma, K., Mei, H., Jiang, Y., & Li, Z. (2010). ST-scale as a novel amino acid descriptor and its application in QSAM of peptides and analogues. Amino acids, 38(3), 805-816. +#' @param seq An amino-acids sequence +#' @return The computed average of ST-scales of all the amino acids in the corresponding peptide sequence. +#' @examples stScales(seq = "QWGRRCCGWGPGRRYCVRWC") +#' # [[1]] +#' # ST1 ST2 ST3 ST4 ST5 ST6 ST7 ST8 +#' # -0.6360 0.0795 0.0520 0.0700 -0.2790 -0.8105 0.5820 0.5430 + +stScales <- function(seq){ + # Remove spaces and line breaks + seq <- gsub("[[:space:]]+","",as.vector(seq)) + + # Split the sequence by amino-acids + seq <- strsplit(seq, "") + + # Load the ST-scales + scales <- AAdata$stScales + + # Computes the ST-scales for given sequences + lapply(seq, function(seq) { + sapply(names(scales), function(scale) { + (sum(scales[[scale]][seq], na.rm = TRUE) / length(seq)) + }) + }) +} \ No newline at end of file diff --git a/man/stScales.Rd b/man/stScales.Rd new file mode 100644 index 0000000..512d92b --- /dev/null +++ b/man/stScales.Rd @@ -0,0 +1,26 @@ +% Generated by roxygen2: do not edit by hand +% Please edit documentation in R/stScales.R +\name{stScales} +\alias{stScales} +\title{Compute the ST-scales of a protein sequence} +\usage{ +stScales(seq) +} +\arguments{ +\item{seq}{An amino-acids sequence} +} +\value{ +The computed average of ST-scales of all the amino acids in the corresponding peptide sequence. +} +\description{ +ST-scales were proposed by Yang et al, taking 827 properties into account which are mainly constitutional, topological, geometrical, hydrophobic, elec- tronic, and steric properties of a total set of 167 AAs. +} +\examples{ +stScales(seq = "QWGRRCCGWGPGRRYCVRWC") +# [[1]] +# ST1 ST2 ST3 ST4 ST5 ST6 ST7 ST8 +# -0.6360 0.0795 0.0520 0.0700 -0.2790 -0.8105 0.5820 0.5430 +} +\references{ +Yang, L., Shu, M., Ma, K., Mei, H., Jiang, Y., & Li, Z. (2010). ST-scale as a novel amino acid descriptor and its application in QSAM of peptides and analogues. Amino acids, 38(3), 805-816. +} From 7fe6cccf5fa2dbc2aeebff6c71f90743890650a7 Mon Sep 17 00:00:00 2001 From: Daniel Osorio Date: Fri, 10 Mar 2017 17:07:55 -0500 Subject: [PATCH 38/50] stScales function was added --- README.md | 1 + 1 file changed, 1 insertion(+) diff --git a/README.md b/README.md index 6b6b046..92dbbe2 100755 --- a/README.md +++ b/README.md @@ -42,6 +42,7 @@ Available functions |plotXVG | Plot time series from GROMACS XVG files | |protFP|Compute the protFP descriptors of a protein sequence| |readXVG | Read XVG files from GROMACS molecular dynamics package | +|stScales| Compute the ST-scales of a protein sequence| |tScales| Compute the T-scales of a protein sequence| |vhseScales|Compute the VHSE-scales of a protein sequence| |zScales| Compute the Z-scales of a protein sequence | From a2f2b7b298715ef1066e0d9ba8c284924148fd68 Mon Sep 17 00:00:00 2001 From: Daniel Osorio Date: Fri, 10 Mar 2017 17:43:14 -0500 Subject: [PATCH 39/50] aaDescriptors function was fully documented --- R/aaDescriptors.R | 16 ++++++++++++++++ man/aaDescriptors.Rd | 31 +++++++++++++++++++++++++++++++ 2 files changed, 47 insertions(+) create mode 100644 man/aaDescriptors.Rd diff --git a/R/aaDescriptors.R b/R/aaDescriptors.R index 6fed805..997a68b 100644 --- a/R/aaDescriptors.R +++ b/R/aaDescriptors.R @@ -1,4 +1,20 @@ #' @export aaDescriptors +#' @title Compute 66 descriptors (crucianiProperties, kideraFactors, zScales, FASGAI, tScales, VHSE, protFP, stScales, BLOSUM and MSWHIM) by amino acid of a protein sequence +#' @description The function return 66 amino acid descriptors for the 20 natural amino acids. Available descriptors are: \itemize{ +#' \item{crucianiProperties:} Cruciani, G., Baroni, M., Carosati, E., Clementi, M., Valigi, R., and Clementi, S. (2004) Peptide studies by means of principal properties of amino acids derived from MIF descriptors. J. Chemom. 18, 146-155., +#' \item{kideraFactors:} Kidera, A., Konishi, Y., Oka, M., Ooi, T., & Scheraga, H. A. (1985). Statistical analysis of the physical properties of the 20 naturally occurring amino acids. Journal of Protein Chemistry, 4(1), 23-55., +#' \item{zScales:} Sandberg M, Eriksson L, Jonsson J, Sjostrom M, Wold S: New chemical descriptors relevant for the design of biologically active peptides. A multivariate characterization of 87 amino acids. J Med Chem 1998, 41:2481-2491., +#' \item{FASGAI:} Liang, G., & Li, Z. (2007). Factor analysis scale of generalized amino acid information as the source of a new set of descriptors for elucidating the structure and activity relationships of cationic antimicrobial peptides. Molecular Informatics, 26(6), 754-763., +#' \item{tScales:} Tian F, Zhou P, Li Z: T-scale as a novel vector of topological descriptors for amino acids and its application in QSARs of peptides. J Mol Struct. 2007, 830: 106-115. 10.1016/j.molstruc.2006.07.004., +#' \item{VHSE:} VHSE-scales (principal components score Vectors of Hydrophobic, Steric, and Electronic properties), is derived from principal components analysis (PCA) on independent families of 18 hydrophobic properties, 17 steric properties, and 15 electronic properties, respectively, which are included in total 50 physicochemical variables of 20 coded amino acids., +#' \item{protFP:} van Westen, G. J., Swier, R. F., Wegner, J. K., IJzerman, A. P., van Vlijmen, H. W., & Bender, A. (2013). Benchmarking of protein descriptor sets in proteochemometric modeling (part 1): comparative study of 13 amino acid descriptor sets. Journal of cheminformatics, 5(1), 41., +#' \item{stScales:} Yang, L., Shu, M., Ma, K., Mei, H., Jiang, Y., & Li, Z. (2010). ST-scale as a novel amino acid descriptor and its application in QSAM of peptides and analogues. Amino acids, 38(3), 805-816., +#' \item{BLOSUM:} Georgiev, A. G. (2009). Interpretable numerical descriptors of amino acid space. Journal of Computational Biology, 16(5), 703-723., +#' \item{MSWHIM:} Zaliani, A., & Gancia, E. (1999). MS-WHIM scores for amino acids: a new 3D-description for peptide QSAR and QSPR studies. Journal of chemical information and computer sciences, 39(3), 525-533. +#' } +#' @param seq An amino-acids sequence. If multiple sequences are given all of them must have the same length (gap symbols are allowed.) +#' @return a matrix with 66 amino acid descriptors for each aminoacid in a protein sequence. +#' @examples aaDescriptors(seq = "KLKLLLLLKLK") aaDescriptors <- function(seq){ # Remove spaces and line breaks seq <- gsub("[[:space:]]+","",as.vector(seq)) diff --git a/man/aaDescriptors.Rd b/man/aaDescriptors.Rd new file mode 100644 index 0000000..698d13a --- /dev/null +++ b/man/aaDescriptors.Rd @@ -0,0 +1,31 @@ +% Generated by roxygen2: do not edit by hand +% Please edit documentation in R/aaDescriptors.R +\name{aaDescriptors} +\alias{aaDescriptors} +\title{Compute 66 descriptors (crucianiProperties, kideraFactors, zScales, FASGAI, tScales, VHSE, protFP, stScales, BLOSUM and MSWHIM) by amino acid of a protein sequence} +\usage{ +aaDescriptors(seq) +} +\arguments{ +\item{seq}{An amino-acids sequence. If multiple sequences are given all of them must have the same length (gap symbols are allowed.)} +} +\value{ +a matrix with 66 amino acid descriptors for each aminoacid in a protein sequence. +} +\description{ +The function return 66 amino acid descriptors for the 20 natural amino acids. Available descriptors are: \itemize{ +\item{crucianiProperties:} Cruciani, G., Baroni, M., Carosati, E., Clementi, M., Valigi, R., and Clementi, S. (2004) Peptide studies by means of principal properties of amino acids derived from MIF descriptors. J. Chemom. 18, 146-155., +\item{kideraFactors:} Kidera, A., Konishi, Y., Oka, M., Ooi, T., & Scheraga, H. A. (1985). Statistical analysis of the physical properties of the 20 naturally occurring amino acids. Journal of Protein Chemistry, 4(1), 23-55., +\item{zScales:} Sandberg M, Eriksson L, Jonsson J, Sjostrom M, Wold S: New chemical descriptors relevant for the design of biologically active peptides. A multivariate characterization of 87 amino acids. J Med Chem 1998, 41:2481-2491., +\item{FASGAI:} Liang, G., & Li, Z. (2007). Factor analysis scale of generalized amino acid information as the source of a new set of descriptors for elucidating the structure and activity relationships of cationic antimicrobial peptides. Molecular Informatics, 26(6), 754-763., +\item{tScales:} Tian F, Zhou P, Li Z: T-scale as a novel vector of topological descriptors for amino acids and its application in QSARs of peptides. J Mol Struct. 2007, 830: 106-115. 10.1016/j.molstruc.2006.07.004., +\item{VHSE:} VHSE-scales (principal components score Vectors of Hydrophobic, Steric, and Electronic properties), is derived from principal components analysis (PCA) on independent families of 18 hydrophobic properties, 17 steric properties, and 15 electronic properties, respectively, which are included in total 50 physicochemical variables of 20 coded amino acids., +\item{protFP:} van Westen, G. J., Swier, R. F., Wegner, J. K., IJzerman, A. P., van Vlijmen, H. W., & Bender, A. (2013). Benchmarking of protein descriptor sets in proteochemometric modeling (part 1): comparative study of 13 amino acid descriptor sets. Journal of cheminformatics, 5(1), 41., +\item{stScales:} Yang, L., Shu, M., Ma, K., Mei, H., Jiang, Y., & Li, Z. (2010). ST-scale as a novel amino acid descriptor and its application in QSAM of peptides and analogues. Amino acids, 38(3), 805-816., +\item{BLOSUM:} Georgiev, A. G. (2009). Interpretable numerical descriptors of amino acid space. Journal of Computational Biology, 16(5), 703-723., +\item{MSWHIM:} Zaliani, A., & Gancia, E. (1999). MS-WHIM scores for amino acids: a new 3D-description for peptide QSAR and QSPR studies. Journal of chemical information and computer sciences, 39(3), 525-533. +} +} +\examples{ +aaDescriptors(seq = "KLKLLLLLKLK") +} From 314bed47d6793381b6dae73ce01ed002d1830f2d Mon Sep 17 00:00:00 2001 From: Daniel Osorio Date: Fri, 10 Mar 2017 17:47:11 -0500 Subject: [PATCH 40/50] kideraFactors documentation was fixed --- R/kideraFactors.R | 6 ++++-- man/kideraFactors.Rd | 6 ++++-- 2 files changed, 8 insertions(+), 4 deletions(-) diff --git a/R/kideraFactors.R b/R/kideraFactors.R index bde2eac..b871d31 100644 --- a/R/kideraFactors.R +++ b/R/kideraFactors.R @@ -20,8 +20,10 @@ #' @examples #' kideraFactors(seq = "KLKLLLLLKLK") #' # [[1]] -#' KF1 KF2 KF3 KF4 KF5 KF6 KF7 KF8 KF9 KF10 -#' -0.78545455 0.29818182 -0.23636364 -0.08181818 0.21000000 -1.89363636 1.02909091 -0.51272727 0.11181818 0.81000000 +#' # KF1 KF2 KF3 KF4 KF5 +#' # -0.78545455 0.29818182 -0.23636364 -0.08181818 0.21000000 +#' # KF6 KF7 KF8 KF9 KF10 +#' # -1.89363636 1.02909091 -0.51272727 0.11181818 0.81000000 kideraFactors <- function (seq) { # Remove the break lines from the sequence diff --git a/man/kideraFactors.Rd b/man/kideraFactors.Rd index ada9fed..717e164 100644 --- a/man/kideraFactors.Rd +++ b/man/kideraFactors.Rd @@ -30,8 +30,10 @@ The Kidera Factors were originally derived by applying multivariate analysis to \examples{ kideraFactors(seq = "KLKLLLLLKLK") # [[1]] - KF1 KF2 KF3 KF4 KF5 KF6 KF7 KF8 KF9 KF10 --0.78545455 0.29818182 -0.23636364 -0.08181818 0.21000000 -1.89363636 1.02909091 -0.51272727 0.11181818 0.81000000 +# KF1 KF2 KF3 KF4 KF5 +# -0.78545455 0.29818182 -0.23636364 -0.08181818 0.21000000 +# KF6 KF7 KF8 KF9 KF10 +# -1.89363636 1.02909091 -0.51272727 0.11181818 0.81000000 } \references{ Kidera, A., Konishi, Y., Oka, M., Ooi, T., & Scheraga, H. A. (1985). Statistical analysis of the physical properties of the 20 naturally occurring amino acids. Journal of Protein Chemistry, 4(1), 23-55. From 480647c8a28997e5a32372b41ba6435151f45072 Mon Sep 17 00:00:00 2001 From: Daniel Osorio Date: Fri, 10 Mar 2017 17:58:08 -0500 Subject: [PATCH 41/50] aaDescriptors function was added --- NEWS.md | 2 +- README.md | 1 + 2 files changed, 2 insertions(+), 1 deletion(-) diff --git a/NEWS.md b/NEWS.md index 6206bec..dcb91e1 100644 --- a/NEWS.md +++ b/NEWS.md @@ -12,7 +12,7 @@ NEWS * fasgaiVectors function was added -* zScales, vhseScales, protFP and tScales functions were added +* aaDescriptos, zScales, vhseScales, protFP, tScales and stScales functions were added **Peptides v.1.2.2** diff --git a/README.md b/README.md index 92dbbe2..ce09d54 100755 --- a/README.md +++ b/README.md @@ -23,6 +23,7 @@ Available functions | Code | Function | | :------------- |:-------------| |aacomp | Compute the amino-acid composition of a protein sequence| +|aaDescriptors|Compute 66 descriptors (crucianiProperties, kideraFactors, zScales, FASGAI, tScales, VHSE, protFP, stScales, BLOSUM and MSWHIM) by amino acid of a protein sequence| |aindex | Compute the aliphatic index of a protein sequence | |autoCorrelation|Compute the auto-correlation index of a protein sequence| |autoCovariance|Compute the auto-covariance index of a protein sequence| From 6f72519d273d4d168ed64d3555ff4d598b6c6b4b Mon Sep 17 00:00:00 2001 From: Daniel Osorio Date: Fri, 10 Mar 2017 17:59:43 -0500 Subject: [PATCH 42/50] aaDescriptors function title was fixed --- R/aaDescriptors.R | 2 +- README.md | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/R/aaDescriptors.R b/R/aaDescriptors.R index 997a68b..a059f56 100644 --- a/R/aaDescriptors.R +++ b/R/aaDescriptors.R @@ -1,5 +1,5 @@ #' @export aaDescriptors -#' @title Compute 66 descriptors (crucianiProperties, kideraFactors, zScales, FASGAI, tScales, VHSE, protFP, stScales, BLOSUM and MSWHIM) by amino acid of a protein sequence +#' @title Compute 66 descriptors for each amino acid of a protein sequence. #' @description The function return 66 amino acid descriptors for the 20 natural amino acids. Available descriptors are: \itemize{ #' \item{crucianiProperties:} Cruciani, G., Baroni, M., Carosati, E., Clementi, M., Valigi, R., and Clementi, S. (2004) Peptide studies by means of principal properties of amino acids derived from MIF descriptors. J. Chemom. 18, 146-155., #' \item{kideraFactors:} Kidera, A., Konishi, Y., Oka, M., Ooi, T., & Scheraga, H. A. (1985). Statistical analysis of the physical properties of the 20 naturally occurring amino acids. Journal of Protein Chemistry, 4(1), 23-55., diff --git a/README.md b/README.md index ce09d54..7f41bb3 100755 --- a/README.md +++ b/README.md @@ -23,7 +23,7 @@ Available functions | Code | Function | | :------------- |:-------------| |aacomp | Compute the amino-acid composition of a protein sequence| -|aaDescriptors|Compute 66 descriptors (crucianiProperties, kideraFactors, zScales, FASGAI, tScales, VHSE, protFP, stScales, BLOSUM and MSWHIM) by amino acid of a protein sequence| +|aaDescriptors|Compute 66 descriptors for each amino acid of a protein sequence| |aindex | Compute the aliphatic index of a protein sequence | |autoCorrelation|Compute the auto-correlation index of a protein sequence| |autoCovariance|Compute the auto-covariance index of a protein sequence| From 316edb96db6f4b8585b168c82cde955188cdd356 Mon Sep 17 00:00:00 2001 From: Daniel Osorio Date: Fri, 10 Mar 2017 18:01:35 -0500 Subject: [PATCH 43/50] aaDescriptors function title was fixed --- man/aaDescriptors.Rd | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/man/aaDescriptors.Rd b/man/aaDescriptors.Rd index 698d13a..5321c36 100644 --- a/man/aaDescriptors.Rd +++ b/man/aaDescriptors.Rd @@ -2,7 +2,7 @@ % Please edit documentation in R/aaDescriptors.R \name{aaDescriptors} \alias{aaDescriptors} -\title{Compute 66 descriptors (crucianiProperties, kideraFactors, zScales, FASGAI, tScales, VHSE, protFP, stScales, BLOSUM and MSWHIM) by amino acid of a protein sequence} +\title{Compute 66 descriptors for each amino acid of a protein sequence.} \usage{ aaDescriptors(seq) } From d11ea1d69640e1e3d14e31b4b31b1be2b16aeea4 Mon Sep 17 00:00:00 2001 From: Daniel Osorio Date: Fri, 10 Mar 2017 18:01:43 -0500 Subject: [PATCH 44/50] README fixed --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index 7f41bb3..1f42b9f 100755 --- a/README.md +++ b/README.md @@ -33,7 +33,7 @@ Available functions |crucianiProperties | Compute the Cruciani properties of a protein sequence | |fasgaiVectors| Compute the FASGAI vectors of a protein sequence | |hmoment | Compute the hydrophobic moment of a protein sequence | -|hydrophobicity | Compute the hydrophobicity index | +|hydrophobicity | Compute the hydrophobicity index of a protein sequence | |instaindex | Compute the instability index of a protein sequence | |kideraFactors | Compute the Kidera factors of a protein sequence | |lengthpep| Compute the aminoacid length of a protein sequence | From ecc443a724abe3e2d7b00c4d9b39241c3e719da0 Mon Sep 17 00:00:00 2001 From: Daniel Osorio Date: Fri, 10 Mar 2017 19:05:30 -0500 Subject: [PATCH 45/50] blosumIndices function was added --- DESCRIPTION | 2 +- R/blosumIndices.R | 31 +++++++++++++++++++++++++++++++ README.md | 1 + man/blosumIndices.Rd | 30 ++++++++++++++++++++++++++++++ 4 files changed, 63 insertions(+), 1 deletion(-) create mode 100644 R/blosumIndices.R create mode 100644 man/blosumIndices.Rd diff --git a/DESCRIPTION b/DESCRIPTION index 6e07e00..f82a250 100644 --- a/DESCRIPTION +++ b/DESCRIPTION @@ -1,6 +1,6 @@ Package: Peptides Version: 2.0.0 -Date: 2017-03-10 +Date: 2017-03-12 Title: Calculate Indices and Theoretical Physicochemical Properties of Protein Sequences Authors@R: c(person("Daniel","Osorio",email="dcosorioh@unal.edu.co",role=c("aut","cre")),person("Paola","Rondon-Villarreal",role=c("aut","ths")),person("Rodrigo","Torres",role=c("aut","ths")),person("J. Sebastian","Paez",email="jpaezpae@purdue.edu",role=c("ctb"))) Maintainer: Daniel Osorio diff --git a/R/blosumIndices.R b/R/blosumIndices.R new file mode 100644 index 0000000..a96a8b5 --- /dev/null +++ b/R/blosumIndices.R @@ -0,0 +1,31 @@ +#' @title blosumIndices +#' @title Compute the BLOSUM62 derived indices of a protein sequence +#' @description BLOSUM indices were derived of physicochemical properties that have been subjected to a VARIMAX analyses and an alignment matrix of the 20 natural AAs using the BLOSUM62 matrix. +#' @references Georgiev, A. G. (2009). Interpretable numerical descriptors of amino acid space. Journal of Computational Biology, 16(5), 703-723. +#' @param seq An amino-acids sequence +#' @return The computed average of BLOSUM indices of all the amino acids in the corresponding peptide sequence. +#' @examples blosumIndices(seq = "KLKLLLLLKLK") +#' # [[1]] +#' # BLOSUM1 BLOSUM2 BLOSUM3 BLOSUM4 BLOSUM5 +#' # -0.4827273 -0.5618182 -0.8509091 -0.4172727 0.3172727 +#' +#' # BLOSUM6 BLOSUM7 BLOSUM8 BLOSUM9 BLOSUM10 +#' # 0.2527273 0.1463636 0.1427273 -0.2145455 -0.3218182 +#' +blosumIndices <- function(seq) { + # Remove spaces and line breaks + seq <- gsub("[[:space:]]+","",as.vector(seq)) + + # Split the sequence by amino-acids + seq <- strsplit(seq, "") + + # Load the BLOSUM indices + scales <- AAdata$BLOSUM + + # Computes the BLOSUM indices for given sequences + lapply(seq, function(seq) { + sapply(names(scales), function(scale) { + (sum(scales[[scale]][seq], na.rm = TRUE) / length(seq)) + }) + }) +} \ No newline at end of file diff --git a/README.md b/README.md index 1f42b9f..70701b5 100755 --- a/README.md +++ b/README.md @@ -27,6 +27,7 @@ Available functions |aindex | Compute the aliphatic index of a protein sequence | |autoCorrelation|Compute the auto-correlation index of a protein sequence| |autoCovariance|Compute the auto-covariance index of a protein sequence| +|blosumIndices|Compute the BLOSUM62 derived indices of a protein sequence| |boman | Compute the Boman (Potential Protein Interaction) index | |charge | Compute the theoretical net charge of a protein sequence | |crossCovariance|Compute the cross-covariance index of a protein sequence| diff --git a/man/blosumIndices.Rd b/man/blosumIndices.Rd new file mode 100644 index 0000000..17cb34a --- /dev/null +++ b/man/blosumIndices.Rd @@ -0,0 +1,30 @@ +% Generated by roxygen2: do not edit by hand +% Please edit documentation in R/blosumIndices.R +\name{blosumIndices} +\alias{blosumIndices} +\title{blosumIndices} +\usage{ +blosumIndices(seq) +} +\arguments{ +\item{seq}{An amino-acids sequence} +} +\value{ +The computed average of BLOSUM indices of all the amino acids in the corresponding peptide sequence. +} +\description{ +BLOSUM indices were derived of physicochemical properties that have been subjected to a VARIMAX analyses and an alignment matrix of the 20 natural AAs using the BLOSUM62 matrix. +} +\examples{ +blosumIndices(seq = "KLKLLLLLKLK") +# [[1]] +# BLOSUM1 BLOSUM2 BLOSUM3 BLOSUM4 BLOSUM5 +# -0.4827273 -0.5618182 -0.8509091 -0.4172727 0.3172727 + +# BLOSUM6 BLOSUM7 BLOSUM8 BLOSUM9 BLOSUM10 +# 0.2527273 0.1463636 0.1427273 -0.2145455 -0.3218182 + +} +\references{ +Georgiev, A. G. (2009). Interpretable numerical descriptors of amino acid space. Journal of Computational Biology, 16(5), 703-723. +} From 7241e4b075eec3186b29c46c37fee5519a66af6a Mon Sep 17 00:00:00 2001 From: Daniel Osorio Date: Fri, 10 Mar 2017 19:07:01 -0500 Subject: [PATCH 46/50] blosumIndices function was added --- NAMESPACE | 1 + R/blosumIndices.R | 1 + 2 files changed, 2 insertions(+) diff --git a/NAMESPACE b/NAMESPACE index bcca096..3f88332 100755 --- a/NAMESPACE +++ b/NAMESPACE @@ -5,6 +5,7 @@ export(aacomp) export(aindex) export(autoCorrelation) export(autoCovariance) +export(blosumIndices) export(boman) export(charge) export(crossCovariance) diff --git a/R/blosumIndices.R b/R/blosumIndices.R index a96a8b5..5ab7f3b 100644 --- a/R/blosumIndices.R +++ b/R/blosumIndices.R @@ -1,3 +1,4 @@ +#' @export blosumIndices #' @title blosumIndices #' @title Compute the BLOSUM62 derived indices of a protein sequence #' @description BLOSUM indices were derived of physicochemical properties that have been subjected to a VARIMAX analyses and an alignment matrix of the 20 natural AAs using the BLOSUM62 matrix. From 4633d68aeb41b0bbe9483db715d7f438e46172e0 Mon Sep 17 00:00:00 2001 From: Daniel Osorio Date: Sat, 11 Mar 2017 19:07:22 -0500 Subject: [PATCH 47/50] blosumIndices documentation was fixed --- R/blosumIndices.R | 1 - man/blosumIndices.Rd | 2 +- 2 files changed, 1 insertion(+), 2 deletions(-) diff --git a/R/blosumIndices.R b/R/blosumIndices.R index 5ab7f3b..6b9f7fe 100644 --- a/R/blosumIndices.R +++ b/R/blosumIndices.R @@ -1,5 +1,4 @@ #' @export blosumIndices -#' @title blosumIndices #' @title Compute the BLOSUM62 derived indices of a protein sequence #' @description BLOSUM indices were derived of physicochemical properties that have been subjected to a VARIMAX analyses and an alignment matrix of the 20 natural AAs using the BLOSUM62 matrix. #' @references Georgiev, A. G. (2009). Interpretable numerical descriptors of amino acid space. Journal of Computational Biology, 16(5), 703-723. diff --git a/man/blosumIndices.Rd b/man/blosumIndices.Rd index 17cb34a..9466f8a 100644 --- a/man/blosumIndices.Rd +++ b/man/blosumIndices.Rd @@ -2,7 +2,7 @@ % Please edit documentation in R/blosumIndices.R \name{blosumIndices} \alias{blosumIndices} -\title{blosumIndices} +\title{Compute the BLOSUM62 derived indices of a protein sequence} \usage{ blosumIndices(seq) } From cdd9b23935db8379e2bc89ad053b8d5badfabe87 Mon Sep 17 00:00:00 2001 From: Daniel Osorio Date: Sat, 11 Mar 2017 19:20:17 -0500 Subject: [PATCH 48/50] mswhimScores function was added --- NAMESPACE | 1 + R/mswhimScores.R | 28 ++++++++++++++++++++++++++++ README.md | 1 + man/mswhimScores.Rd | 26 ++++++++++++++++++++++++++ 4 files changed, 56 insertions(+) create mode 100644 R/mswhimScores.R create mode 100644 man/mswhimScores.Rd diff --git a/NAMESPACE b/NAMESPACE index 3f88332..2da6839 100755 --- a/NAMESPACE +++ b/NAMESPACE @@ -17,6 +17,7 @@ export(instaindex) export(kideraFactors) export(lengthpep) export(membpos) +export(mswhimScores) export(mw) export(pI) export(plotXVG) diff --git a/R/mswhimScores.R b/R/mswhimScores.R new file mode 100644 index 0000000..3be937c --- /dev/null +++ b/R/mswhimScores.R @@ -0,0 +1,28 @@ +#' @export mswhimScores +#' @title Compute the MS-WHIM scores of a protein sequence +#' @description MS-WHIM scores were derived from 36 electrostatic potential properties derived from the three-dimensional structure of the 20 natural amino acids +#' @references Zaliani, A., & Gancia, E. (1999). MS-WHIM scores for amino acids: a new 3D-description for peptide QSAR and QSPR studies. Journal of chemical information and computer sciences, 39(3), 525-533. +#' @param seq An amino-acids sequence +#' @return The computed average of MS-WHIM scores of all the amino acids in the corresponding peptide sequence. +#' @examples mswhimScores(seq = "KLKLLLLLKLK") +#' # [[1]] +#' # MSWHIM1 MSWHIM2 MSWHIM3 +#' # -0.6563636 0.4872727 0.1163636 + +mswhimScores <- function(seq){ + # Remove spaces and line breaks + seq <- gsub("[[:space:]]+","",as.vector(seq)) + + # Split the sequence by amino-acids + seq <- strsplit(seq, "") + + # Load the MSWHIM scores + scales <- AAdata$MSWHIM + + # Computes the MSWHIM scores for given sequences + lapply(seq, function(seq) { + sapply(names(scales), function(scale) { + (sum(scales[[scale]][seq], na.rm = TRUE) / length(seq)) + }) + }) +} \ No newline at end of file diff --git a/README.md b/README.md index 70701b5..e0857b1 100755 --- a/README.md +++ b/README.md @@ -39,6 +39,7 @@ Available functions |kideraFactors | Compute the Kidera factors of a protein sequence | |lengthpep| Compute the aminoacid length of a protein sequence | |membpos | Compute theoretically the class of a protein sequence | +|mswhimScores|Compute the MS-WHIM scores of a protein sequence| |mw | Compute the molecular weight of a protein sequence | |pI | Compute the isoelectic point (pI) of a protein sequence | |plotXVG | Plot time series from GROMACS XVG files | diff --git a/man/mswhimScores.Rd b/man/mswhimScores.Rd new file mode 100644 index 0000000..ec206c5 --- /dev/null +++ b/man/mswhimScores.Rd @@ -0,0 +1,26 @@ +% Generated by roxygen2: do not edit by hand +% Please edit documentation in R/mswhimScores.R +\name{mswhimScores} +\alias{mswhimScores} +\title{Compute the MS-WHIM scores of a protein sequence} +\usage{ +mswhimScores(seq) +} +\arguments{ +\item{seq}{An amino-acids sequence} +} +\value{ +The computed average of MS-WHIM scores of all the amino acids in the corresponding peptide sequence. +} +\description{ +MS-WHIM scores were derived from 36 electrostatic potential properties derived from the three-dimensional structure of the 20 natural amino acids +} +\examples{ +mswhimScores(seq = "KLKLLLLLKLK") +# [[1]] +# MSWHIM1 MSWHIM2 MSWHIM3 +# -0.6563636 0.4872727 0.1163636 +} +\references{ +Zaliani, A., & Gancia, E. (1999). MS-WHIM scores for amino acids: a new 3D-description for peptide QSAR and QSPR studies. Journal of chemical information and computer sciences, 39(3), 525-533. +} From fc2540f9a0f13f9c9679ecbf81f93240088302a4 Mon Sep 17 00:00:00 2001 From: Daniel Osorio Date: Sat, 11 Mar 2017 20:55:31 -0500 Subject: [PATCH 49/50] aaCheck function added and applied --- NAMESPACE | 6 +++--- R/aaCheck.R | 12 ++++++++++++ R/aaDescriptors.R | 6 ++---- R/aacomp.R | 14 +++++++------- R/aindex.R | 13 +++++-------- R/autocorrelation.R | 7 ++++--- R/autocovariance.R | 7 ++++--- R/blosumIndices.R | 7 +++---- R/boman.R | 8 +++----- R/charge.R | 9 +++------ R/crosscovariance.R | 7 ++++--- R/crucianiProperties.R | 6 +++--- R/fasgaiVectors.R | 5 ++--- R/hmoment.R | 3 +-- R/hydrophobicity.R | 5 +++-- R/instaindex.R | 29 ++++++++++++----------------- R/kideraFactors.R | 12 +++++++----- R/lengthpep.R | 4 ++-- R/membpos.R | 16 ++++++++++++---- R/mswhimScores.R | 4 +--- R/mw.R | 7 ++++--- R/pI.R | 1 - R/protFP.R | 7 ++----- R/stScales.R | 7 ++----- R/tScales.R | 7 ++----- R/vhseScales.R | 7 ++----- R/zScales.R | 5 +---- README.md | 6 +++--- man/aacomp.Rd | 10 +++++----- man/aindex.Rd | 8 ++++---- man/instaindex.Rd | 8 ++++---- tests/testthat/test.aacomp.R | 6 +++--- tests/testthat/test.aindex.R | 4 ++-- tests/testthat/test.instaindex.R | 4 ++-- 34 files changed, 129 insertions(+), 138 deletions(-) create mode 100644 R/aaCheck.R diff --git a/NAMESPACE b/NAMESPACE index 2da6839..b6f9a44 100755 --- a/NAMESPACE +++ b/NAMESPACE @@ -1,8 +1,8 @@ # Generated by roxygen2: do not edit by hand +export(aIndex) +export(aaComp) export(aaDescriptors) -export(aacomp) -export(aindex) export(autoCorrelation) export(autoCovariance) export(blosumIndices) @@ -13,7 +13,7 @@ export(crucianiProperties) export(fasgaiVectors) export(hmoment) export(hydrophobicity) -export(instaindex) +export(instaIndex) export(kideraFactors) export(lengthpep) export(membpos) diff --git a/R/aaCheck.R b/R/aaCheck.R new file mode 100644 index 0000000..20a6d5a --- /dev/null +++ b/R/aaCheck.R @@ -0,0 +1,12 @@ +aaCheck <- function(seq){ + seq <- toupper(seq) + seq <- gsub(pattern = "[[:space:]]+",replacement = "",x = seq) + seq <- strsplit(x = seq,split = "") + check <- unlist(lapply(seq,function(sequence){ + !all(seq[[1]]%in%c("A" ,"C" ,"D" ,"E" ,"F" ,"G" ,"H" ,"I" ,"K" ,"L" ,"M" ,"N" ,"P" ,"Q" ,"R" ,"S" ,"T" ,"V" ,"W" ,"Y", "-")) + })) + if(sum(check) > 0){ + sapply(which(check == TRUE),function(sequence){warning(paste0("Sequence ",sequence," has unrecognized amino acid types. Output value might be wrong calculated"),call. = FALSE)}) + } + return(seq) +} diff --git a/R/aaDescriptors.R b/R/aaDescriptors.R index a059f56..0e29770 100644 --- a/R/aaDescriptors.R +++ b/R/aaDescriptors.R @@ -17,12 +17,10 @@ #' @examples aaDescriptors(seq = "KLKLLLLLKLK") aaDescriptors <- function(seq){ # Remove spaces and line breaks - seq <- gsub("[[:space:]]+","",as.vector(seq)) + seq <- aaCheck(seq) sequences <- length(seq) # Length validation - if(all(nchar(seq)==nchar(seq[1]))){ - # Split by amino acids - seq <- strsplit(seq,"") + if(all(lengths(seq)==length(seq[[1]]))){ # Extract descriptors desc <- lapply(seq,function(seq){ sapply(seq,function(aa){ diff --git a/R/aacomp.R b/R/aacomp.R index 82ad43c..b807fc9 100755 --- a/R/aacomp.R +++ b/R/aacomp.R @@ -1,10 +1,10 @@ -#' @export aacomp +#' @export aaComp #' @title Compute the amino acid composition of a protein sequence #' @description This function calculates the amount of amino acids of a particular class and classified as: Tiny, Small, Aliphatic, Aromatic, Non-polar, Polar, Charged, Basic and Acidic based on their size and R-groups using same function implemented in EMBOSS 'pepstat'. #' The output is a matrix with the number and percentage of amino acids of a particular class #' @details Amino acids are zwitterionic molecules with an amine and a carboxyl group present in their structure. #' Some amino acids possess side chains with specific properties that allow grouping them in different ways. -#' The \code{aacomp} function classifies amino acids based on their size, side chains, hydrophobicity, charge and their response to pH 7. +#' The \code{aaComp} function classifies amino acids based on their size, side chains, hydrophobicity, charge and their response to pH 7. #' @param seq An amino-acid sequence #' @return The output is a matrix with the number and percentage of amino acids of a particular class #' \itemize{ @@ -35,7 +35,7 @@ #' # Acidic (B+D+E+Z) 0 00.000 #' #' ## AA composition of PDB: 1D9J Cecropin Peptide -#' aacomp(seq= "KWKLFKKIGIGKFLHSAKKFX") +#' aaComp(seq= "KWKLFKKIGIGKFLHSAKKFX") #' #' ## Output #' # Number Mole % @@ -49,11 +49,11 @@ #' # Basic 8 38.095 #' # Acidic 0 0.000 -aacomp<-function(seq){ +aaComp<-function(seq){ # Remove space characters: tab, newline, vertical tab, form feed, carriage return, space and possibly other locale-dependent characters. - seq <- gsub("[[:space:]]+","",as.vector(seq)) - # Divide the amino acid sequence and makes a frequencies table - seq <- lapply(seq, function(seq){table(unlist(strsplit(seq,"")))}) + seq <- aaCheck(seq) + # Make a frequencies table + seq <- lapply(seq, function(seq){table(unlist(seq))}) # Applying composition function aacomp <- lapply(seq, function(seq){ # Create data matrix output diff --git a/R/aindex.R b/R/aindex.R index cec30fd..05a7522 100755 --- a/R/aindex.R +++ b/R/aindex.R @@ -1,4 +1,4 @@ -#' @export aindex +#' @export aIndex #' @title Compute the aliphatic index of a protein sequence #' @description This function calculates the Ikai (1980) aliphatic index of a protein. The \code{aindex} is defined as the relative volume occupied by aliphatic side chains (Alanine, Valine, Isoleucine, and Leucine). It may be regarded as a positive factor for the increase of thermostability of globular proteins. #' @@ -12,16 +12,13 @@ #' # SEQUENCE: SDKEVDEVDAALSDLEITLE #' # Aliphatic index: 117.00 #' -#' aindex(seq = "SDKEVDEVDAALSDLEITLE") +#' aIndex(seq = "SDKEVDEVDAALSDLEITLE") #' # [1] 117 -aindex <- function(seq) { - seq <- gsub("[[:space:]]+","",as.vector(seq)) +aIndex <- function(seq) { + seq <- aaCheck(seq) # Divide the amino acid sequence and extracts the relative frequency of Alanine, Valine, Leucine and Isoleucine - seq <- - lapply(seq, function(seq) { - table(unlist(strsplit(seq, ""))) / nchar(seq) - }) + seq <- lapply(seq, function(seq) { table(unlist(seq)) / length(seq) }) # Aliphatic index = X(Ala) + a * X(Val) + b * ( X(Ile) + X(Leu) ) # where X(Ala), X(Val), X(Ile), and X(Leu) are mole percent (100 X mole fraction) # of alanine, valine, isoleucine, and leucine. diff --git a/R/autocorrelation.R b/R/autocorrelation.R index 087cd9d..32f15ef 100644 --- a/R/autocorrelation.R +++ b/R/autocorrelation.R @@ -35,9 +35,10 @@ autoCorrelation <- if (center == TRUE) { property <- scale(property)[,] } - sequence <- gsub("[[:space:]]+", "", as.vector(sequence)) - if (lag < (min(nchar(sequence)) - 1)) { - sequence <- strsplit(sequence, "") + # Split sequence by amino acids + sequence <- aaCheck(sequence) + if (lag < (min(lengths(sequence)) - 1)) { + # Apply the Cruciani formula unlist(lapply(sequence, function(sequence) { sum(sapply(seq_len(length(sequence) - lag), function(position) { property[sequence[[position]]] * property[sequence[[position + lag]]] diff --git a/R/autocovariance.R b/R/autocovariance.R index 47a9418..8a18629 100644 --- a/R/autocovariance.R +++ b/R/autocovariance.R @@ -34,9 +34,10 @@ autoCovariance <- function(sequence, lag, property, center = TRUE) { if (center == TRUE) { property <- scale(property)[,] } - sequence <- gsub("[[:space:]]+", "", as.vector(sequence)) - if (lag < (min(nchar(sequence)) - 1)) { - sequence <- strsplit(sequence, "") + # Split sequence by amino acids + sequence <- aaCheck(sequence) + if (lag < (min(lengths(sequence)) - 1)) { + # Apply the Cruciani formula unlist(lapply(sequence, function(sequence) { sum(sapply(seq_len(length(sequence) - lag), function(position) { property[sequence[[position]]] * property[sequence[[position + lag]]] diff --git a/R/blosumIndices.R b/R/blosumIndices.R index 6b9f7fe..6f9d979 100644 --- a/R/blosumIndices.R +++ b/R/blosumIndices.R @@ -13,11 +13,10 @@ #' # 0.2527273 0.1463636 0.1427273 -0.2145455 -0.3218182 #' blosumIndices <- function(seq) { - # Remove spaces and line breaks - seq <- gsub("[[:space:]]+","",as.vector(seq)) - + # Split the sequence by amino-acids - seq <- strsplit(seq, "") + # Remove spaces and line breaks + seq <- aaCheck(seq) # Load the BLOSUM indices scales <- AAdata$BLOSUM diff --git a/R/boman.R b/R/boman.R index a28cd20..273be28 100755 --- a/R/boman.R +++ b/R/boman.R @@ -19,7 +19,6 @@ #' # [1] -1.235833 #' boman <- function(seq) { - seq <- gsub("[[:space:]]+", "", as.vector(seq)) # Create the Boman scale vector boman <- c( @@ -43,13 +42,12 @@ boman <- function(seq) { D = -8.72, R = -14.92 ) + # Split sequence by amino acid + seq <- aaCheck(seq) # Asign a value to each amino acids in the sequence, sum the values and divide on amino acid sequence length - # Report the index rounded to 2 decimals - seq <- lapply(seq, function(seq) { - unlist(strsplit(seq, "")) - }) bindex <- lapply(seq, function(seq) { return(-1 * sum(boman[seq], na.rm = TRUE) / length(seq)) }) + # Return the Boman index return(unlist(bindex)) } diff --git a/R/charge.R b/R/charge.R index 28b2fad..85c5017 100755 --- a/R/charge.R +++ b/R/charge.R @@ -70,12 +70,9 @@ charge <- function(seq, pH = 7, pKscale = "Lehninger") { # Divide the amino acid sequence and makes an absolute frequencies table - seq <- gsub("[[:space:]]+", "", as.vector(seq)) - aa <- - lapply(seq, function(seq) { - table(factor(unlist(strsplit( - toupper(seq), "" - )), levels = LETTERS)) + seq <- aaCheck(seq) + aa <-lapply(seq, function(seq) { + table(factor(unlist(seq), levels = LETTERS)) }) # Set pKscale pK <- AAdata$pK diff --git a/R/crosscovariance.R b/R/crosscovariance.R index 154c226..910ae35 100644 --- a/R/crosscovariance.R +++ b/R/crosscovariance.R @@ -43,9 +43,10 @@ crossCovariance <- property1 <- scale(property1)[,] property2 <- scale(property2)[,] } - sequence <- gsub("[[:space:]]+", "", as.vector(sequence)) - if (lag < (min(nchar(sequence)) - 1)) { - sequence <- strsplit(sequence, "") + # Split sequence by amino acids + sequence <- aaCheck(sequence) + if (lag < (min(lengths(sequence)) - 1)) { + # Apply Cruciani formula unlist(lapply(sequence, function(sequence) { sum(sapply(seq_len(length(sequence) - lag), function(position) { property1[sequence[[position]]] * property2[sequence[[position + lag]]] diff --git a/R/crucianiProperties.R b/R/crucianiProperties.R index 74dbb74..5773ba9 100644 --- a/R/crucianiProperties.R +++ b/R/crucianiProperties.R @@ -9,11 +9,11 @@ #' # -0.1130 -0.0220 0.2735 crucianiProperties <- function(seq) { # Remove spaces and line breaks - seq <- gsub("[[:space:]]+", "", as.vector(seq)) + seq <- aaCheck(seq) + # Load Cruciani Properties properties <- AAdata$crucianiProperties - # Split sequence - seq <- strsplit(toupper(seq), split = "") + # Calculate averages lapply(seq, function(seq) { sapply(names(properties), function(property) { diff --git a/R/fasgaiVectors.R b/R/fasgaiVectors.R index c9ce363..9e35fd3 100644 --- a/R/fasgaiVectors.R +++ b/R/fasgaiVectors.R @@ -10,11 +10,10 @@ #' # F1 F2 F3 F4 F5 F6 #' # -0.13675 -0.45485 -0.11695 -0.45800 -0.38015 0.52740 fasgaiVectors <- function(seq) { - # Remove spaces and line breaks - seq <- gsub("[[:space:]]+","",as.vector(seq)) + # Remove spaces and line breaks # Split the sequence by amino-acids - seq <- strsplit(seq, "") + seq <- aaCheck(seq) # Load the FASGAI vectors vectors <- AAdata$FASGAI diff --git a/R/hmoment.R b/R/hmoment.R index ae8d03f..77bdb3e 100755 --- a/R/hmoment.R +++ b/R/hmoment.R @@ -26,10 +26,9 @@ hmoment <- function(seq, angle = 100, window = 11) { # Loading hydrophobicity scale - seq <- gsub("[[:space:]]+", "", as.vector(seq)) h <- AAdata$Hydrophobicity$Eisenberg # Splitting the sequence in amino acids - aa <- strsplit(seq,"") + aa <- aaCheck(seq) # Setting the sequence length pep <- lapply(aa, function(aa) { stats::embed(aa, min(c(length(aa), window))) diff --git a/R/hydrophobicity.R b/R/hydrophobicity.R index 80e473e..3725f01 100755 --- a/R/hydrophobicity.R +++ b/R/hydrophobicity.R @@ -173,16 +173,17 @@ #' hydrophobicity(seq = "QWGRRCCGWGPGRRYCVRWC",scale = "Zimmerman") #' #[1] 0.943 hydrophobicity <- function(seq, scale = "KyteDoolittle") { - seq <- gsub("[[:space:]]+", "", as.vector(seq)) # Loading hydrophobicity scales Hydrophobicity <- AAdata$Hydrophobicity # Setting the hydrophobicity scale scale <- match.arg(scale, names(Hydrophobicity)) + # Split sequence by aminoacids + seq <- aaCheck(seq) # Sum the hydrophobicity of each amino acid and divide them between the sequence length # Return the GRAVY value h <- lapply(seq, function(seq) { - (sum(Hydrophobicity[[scale]][unlist(strsplit(seq, ""))], na.rm = TRUE) / nchar(seq)) + (sum(Hydrophobicity[[scale]][seq], na.rm = TRUE) / length(seq)) }) return(unlist(h)) } diff --git a/R/instaindex.R b/R/instaindex.R index 4d276b2..5b0feba 100755 --- a/R/instaindex.R +++ b/R/instaindex.R @@ -1,19 +1,19 @@ -#' @export instaindex +#' @export instaIndex #' @title Compute the instability index of a protein sequence #' @description This function calculates the instability index proposed by Guruprasad (1990). This index predicts the stability of a protein based on its amino acid composition, a protein whose instability index is smaller than 40 is predicted as stable, a value above 40 predicts that the protein may be unstable. #' @param seq An amino-acids sequence #' @return The computed instability index for a given amino-acids sequence #' @references Guruprasad K, Reddy BV, Pandit MW (1990). "Correlation between stability of a protein and its dipeptide composition: a novel approach for predicting in vivo stability of a protein from its primary sequence". Protein Eng. 4 (2): 155 - 61. doi:10.1093/protein/4.2.155 -#' @examples +#' @examples #' # COMPARED TO ExPASy INSTAINDEX #' # http://web.expasy.org/protparam/ #' # SEQUENCE: QWGRRCCGWGPGRRYCVRWC #' # The instability index (II) is computed to be 83.68 -#' -#' instaindex(seq = "QWGRRCCGWGPGRRYCVRWC") +#' +#' instaIndex(seq = "QWGRRCCGWGPGRRYCVRWC") #' # [1] 83.68 -#' -instaindex <- function(seq) { +#' +instaIndex <- function(seq) { # Setting the Guruprasad scale guruprasad <- c( @@ -419,20 +419,15 @@ instaindex <- function(seq) { 'NA' = 1 ) # Divide the amino acid sequence in dipeptides - seq <- gsub("[[:space:]]+", "", as.vector(seq)) - aa <- lapply(seq, function(seq) { - unlist(strsplit(seq, "")) + aa <- aaCheck(seq) + dp <- lapply(aa, function(aa) { + apply(embed(aa, 2)[, 2:1], 1, paste0, collapse = "") }) - dp <- - lapply(aa, function(aa) { - apply(embed(aa, 2)[, 2:1], 1, paste0, collapse = "") - }) # Apply the formula: # (10/L)*sum(DIWV(XiYi+1) for each dipeptide) # Return the index value rounded to 2 decimals - gp <- - lapply(dp, function(dp) { - (10 / (length(dp) + 1)) * sum(guruprasad[dp], na.rm = TRUE) - }) + gp <- lapply(dp, function(dp) { + (10 / (length(dp) + 1)) * sum(guruprasad[dp], na.rm = TRUE) + }) return(unlist(gp)) } diff --git a/R/kideraFactors.R b/R/kideraFactors.R index b871d31..f20e755 100644 --- a/R/kideraFactors.R +++ b/R/kideraFactors.R @@ -26,18 +26,20 @@ #' # -1.89363636 1.02909091 -0.51272727 0.11181818 0.81000000 kideraFactors <- function (seq) { - # Remove the break lines from the sequence - seq <- gsub("[[:space:]]+", "", as.vector(seq)) + + # Remove the break lines from the sequence and Split by amino acids + seq <- aaCheck(seq) + # Load the KFactors data factors <- AAdata$kideraFactors + # Compute the selected Kidera factor. - seq <- lapply(seq, function(seq) { - unlist(strsplit(seq, "")) - }) kFactors <- lapply(seq, function(seq) { sapply(names(factors), function(factor) { (sum(factors[[factor]][seq], na.rm = TRUE) / length(seq)) }) }) + + # Return return(kFactors) } diff --git a/R/lengthpep.R b/R/lengthpep.R index 86581c9..4f8830c 100755 --- a/R/lengthpep.R +++ b/R/lengthpep.R @@ -11,7 +11,7 @@ #' lengthpep(seq = "QWGRRCCGWGPGRRYCVRWC") #' # [1] 20 lengthpep <- function(seq) { - seq <- gsub("[[:space:]]+", "", as.vector(seq)) + seq <- aaCheck(seq) # Count the amino acids - nchar(seq) + lengths(seq) } diff --git a/R/membpos.R b/R/membpos.R index 222e346..fb2b169 100755 --- a/R/membpos.R +++ b/R/membpos.R @@ -32,13 +32,20 @@ #' # 8 INFCLILIFLLL 0.944 0.257 Surface #' # 9 NFCLILIFLLLI 0.944 0.229 Surface membpos <- function(seq, angle = 100) { - # Setting input length - seq <- gsub("[[:space:]]+", "", as.vector(seq)) + # Check amino acids + seq <- aaCheck(seq) + + # Set window length window <- min(nchar(seq), 11) + + # Paste sequences + seq <- unlist(lapply(seq,function(seq){paste0(seq,collapse = "")})) + + # K-mers lapply(seq, function(seq){ pep <- - substring(toupper(seq), (window):nchar(seq), first = 1:((nchar(seq) - window) + - 1)) + substring(toupper(seq), (window):nchar(seq), first = 1:((nchar(seq) - window) +1)) + # Compute the hmoment and hydrophobicity for each amino acid window data <- as.data.frame(matrix(nrow = length(pep), ncol = 5)) data[, 1] <- pep @@ -50,6 +57,7 @@ membpos <- function(seq, angle = 100) { hmoment(x, angle, window))), 3) data[, 4] <- (data[, 2] * -0.421) + 0.579 colnames(data) <- c("Pep", "H", "uH", "m", "MembPos") + # Assigns a class depending on the hydrophobicity and hmoment data[which(data$uH <= data$m & data$H >= 0.5), 5] <- "Transmembrane" data[which(data$uH <= data$m & data$H <= 0.5), 5] <- "Globular" diff --git a/R/mswhimScores.R b/R/mswhimScores.R index 3be937c..5ff3430 100644 --- a/R/mswhimScores.R +++ b/R/mswhimScores.R @@ -11,10 +11,8 @@ mswhimScores <- function(seq){ # Remove spaces and line breaks - seq <- gsub("[[:space:]]+","",as.vector(seq)) - # Split the sequence by amino-acids - seq <- strsplit(seq, "") + seq <- aaCheck(seq) # Load the MSWHIM scores scales <- AAdata$MSWHIM diff --git a/R/mw.R b/R/mw.R index 93ce23a..a5a5226 100755 --- a/R/mw.R +++ b/R/mw.R @@ -17,7 +17,9 @@ #' mw(seq = "QWGRRCCGWGPGRRYCVRWC",monoisotopic = TRUE) #' # [1] 2484.12 mw <- function(seq, monoisotopic = FALSE) { - seq <- gsub("[[:space:]]", "", as.vector(seq)) + # Split sequence by amino acids + seq <- aaCheck(seq) + # Create the weight scale if (monoisotopic == TRUE) { weight <- @@ -77,7 +79,6 @@ mw <- function(seq, monoisotopic = FALSE) { # Sum the weight of each amino acid and add H2O weight unlist(lapply(seq, function(seq) { - sum(weight[c(strsplit(toupper(seq), split = "")[[1]], "H2O")], na.rm = - TRUE) + sum(weight[c(seq, "H2O")], na.rm = TRUE) })) } diff --git a/R/pI.R b/R/pI.R index ba9f950..04a1df0 100755 --- a/R/pI.R +++ b/R/pI.R @@ -37,7 +37,6 @@ #' pI(seq= "QWGRRCCGWGPGRRYCVRWC",pKscale= "Rodwell") #' # [1] 9.718 pI <- function (seq, pKscale = "EMBOSS") { - seq <- gsub("[[:space:]]+", "", as.vector(seq)) # Define pH values pHs <- seq(0 , 14 , 0.0001) # Evaluate the net charge for defined pHs diff --git a/R/protFP.R b/R/protFP.R index f950503..e5270af 100644 --- a/R/protFP.R +++ b/R/protFP.R @@ -10,11 +10,8 @@ #' # 0.2065 -0.0565 1.9930 -0.2845 0.7315 0.7000 0.1715 0.1135 protFP <- function(seq){ - # Remove spaces and line breaks - seq <- gsub("[[:space:]]+","",as.vector(seq)) - - # Split the sequence by amino-acids - seq <- strsplit(seq, "") + # Split sequences by amino acids - Remove spaces and line breaks + seq <- aaCheck(seq) # Load the ProtFP descriptors descriptors <- AAdata$ProtFP diff --git a/R/stScales.R b/R/stScales.R index ab6c213..1cb3038 100644 --- a/R/stScales.R +++ b/R/stScales.R @@ -10,11 +10,8 @@ #' # -0.6360 0.0795 0.0520 0.0700 -0.2790 -0.8105 0.5820 0.5430 stScales <- function(seq){ - # Remove spaces and line breaks - seq <- gsub("[[:space:]]+","",as.vector(seq)) - - # Split the sequence by amino-acids - seq <- strsplit(seq, "") + # Split the sequence by amino-acids - Remove spaces and line breaks + seq <- aaCheck(seq) # Load the ST-scales scales <- AAdata$stScales diff --git a/R/tScales.R b/R/tScales.R index 3ec51b6..6c7f30f 100644 --- a/R/tScales.R +++ b/R/tScales.R @@ -10,11 +10,8 @@ #' # -3.2700 -0.0035 -0.3855 -0.1475 0.7585 tScales <- function(seq){ - # Remove spaces and line breaks - seq <- gsub("[[:space:]]+","",as.vector(seq)) - - # Split the sequence by amino-acids - seq <- strsplit(seq, "") + # Split the sequence by amino-acids - Remove spaces and line breaks + seq <- aaCheck(seq) # Load the T-scales scales <- AAdata$tScales diff --git a/R/vhseScales.R b/R/vhseScales.R index 0243f13..8184920 100644 --- a/R/vhseScales.R +++ b/R/vhseScales.R @@ -14,11 +14,8 @@ #' #-0.1150 0.0630 -0.0055 0.7955 0.4355 0.2485 0.1740 -0.0960 #' vhseScales <- function(seq){ - # Remove spaces and line breaks - seq <- gsub("[[:space:]]+","",as.vector(seq)) - - # Split the sequence by amino-acids - seq <- strsplit(seq, "") + # Split the sequence by amino-acids - Remove spaces and line breaks + seq <- aaCheck(seq) # Load the VHSE-scales scales <- AAdata$VHSE diff --git a/R/zScales.R b/R/zScales.R index dee1975..db69028 100644 --- a/R/zScales.R +++ b/R/zScales.R @@ -17,11 +17,8 @@ #' # Z1 Z2 Z3 Z4 Z5 #' # 0.6200 0.0865 0.0665 0.7280 -0.8740 zScales <- function(seq) { - # Remove spaces and line breaks - seq <- gsub("[[:space:]]+","",as.vector(seq)) - # Split the sequence by amino-acids - seq <- strsplit(seq, "") + seq <- aaCheck(seq) # Load the Z-scales scales <- AAdata$zScales diff --git a/README.md b/README.md index e0857b1..0ef9d4c 100755 --- a/README.md +++ b/README.md @@ -22,9 +22,9 @@ Available functions ------------------- | Code | Function | | :------------- |:-------------| -|aacomp | Compute the amino-acid composition of a protein sequence| +|aaComp | Compute the amino-acid composition of a protein sequence| |aaDescriptors|Compute 66 descriptors for each amino acid of a protein sequence| -|aindex | Compute the aliphatic index of a protein sequence | +|aIndex | Compute the aliphatic index of a protein sequence | |autoCorrelation|Compute the auto-correlation index of a protein sequence| |autoCovariance|Compute the auto-covariance index of a protein sequence| |blosumIndices|Compute the BLOSUM62 derived indices of a protein sequence| @@ -35,7 +35,7 @@ Available functions |fasgaiVectors| Compute the FASGAI vectors of a protein sequence | |hmoment | Compute the hydrophobic moment of a protein sequence | |hydrophobicity | Compute the hydrophobicity index of a protein sequence | -|instaindex | Compute the instability index of a protein sequence | +|instaIndex | Compute the instability index of a protein sequence | |kideraFactors | Compute the Kidera factors of a protein sequence | |lengthpep| Compute the aminoacid length of a protein sequence | |membpos | Compute theoretically the class of a protein sequence | diff --git a/man/aacomp.Rd b/man/aacomp.Rd index 8d2e2ed..0b076bf 100644 --- a/man/aacomp.Rd +++ b/man/aacomp.Rd @@ -1,10 +1,10 @@ % Generated by roxygen2: do not edit by hand % Please edit documentation in R/aacomp.R -\name{aacomp} -\alias{aacomp} +\name{aaComp} +\alias{aaComp} \title{Compute the amino acid composition of a protein sequence} \usage{ -aacomp(seq) +aaComp(seq) } \arguments{ \item{seq}{An amino-acid sequence} @@ -30,7 +30,7 @@ The output is a matrix with the number and percentage of amino acids of a partic \details{ Amino acids are zwitterionic molecules with an amine and a carboxyl group present in their structure. Some amino acids possess side chains with specific properties that allow grouping them in different ways. -The \code{aacomp} function classifies amino acids based on their size, side chains, hydrophobicity, charge and their response to pH 7. +The \code{aaComp} function classifies amino acids based on their size, side chains, hydrophobicity, charge and their response to pH 7. } \note{ This function was originally written by Alan Bleasby (ajb@ebi.ac.uk) for the EMBOSS package. @@ -51,7 +51,7 @@ Further information: http://emboss.sourceforge.net/apps/cvs/emboss/apps/pepstats # Acidic (B+D+E+Z) 0 00.000 ## AA composition of PDB: 1D9J Cecropin Peptide -aacomp(seq= "KWKLFKKIGIGKFLHSAKKFX") +aaComp(seq= "KWKLFKKIGIGKFLHSAKKFX") ## Output # Number Mole \% diff --git a/man/aindex.Rd b/man/aindex.Rd index 5221110..8c99755 100644 --- a/man/aindex.Rd +++ b/man/aindex.Rd @@ -1,10 +1,10 @@ % Generated by roxygen2: do not edit by hand % Please edit documentation in R/aindex.R -\name{aindex} -\alias{aindex} +\name{aIndex} +\alias{aIndex} \title{Compute the aliphatic index of a protein sequence} \usage{ -aindex(seq) +aIndex(seq) } \arguments{ \item{seq}{An amino-acids sequence} @@ -24,7 +24,7 @@ Aliphatic amino acids (A, I, L and V) are responsible for the thermal stability # SEQUENCE: SDKEVDEVDAALSDLEITLE # Aliphatic index: 117.00 -aindex(seq = "SDKEVDEVDAALSDLEITLE") +aIndex(seq = "SDKEVDEVDAALSDLEITLE") # [1] 117 } \references{ diff --git a/man/instaindex.Rd b/man/instaindex.Rd index dbf8a39..3806670 100644 --- a/man/instaindex.Rd +++ b/man/instaindex.Rd @@ -1,10 +1,10 @@ % Generated by roxygen2: do not edit by hand % Please edit documentation in R/instaindex.R -\name{instaindex} -\alias{instaindex} +\name{instaIndex} +\alias{instaIndex} \title{Compute the instability index of a protein sequence} \usage{ -instaindex(seq) +instaIndex(seq) } \arguments{ \item{seq}{An amino-acids sequence} @@ -21,7 +21,7 @@ This function calculates the instability index proposed by Guruprasad (1990). Th # SEQUENCE: QWGRRCCGWGPGRRYCVRWC # The instability index (II) is computed to be 83.68 -instaindex(seq = "QWGRRCCGWGPGRRYCVRWC") +instaIndex(seq = "QWGRRCCGWGPGRRYCVRWC") # [1] 83.68 } diff --git a/tests/testthat/test.aacomp.R b/tests/testthat/test.aacomp.R index d8b94e5..48bb5f2 100644 --- a/tests/testthat/test.aacomp.R +++ b/tests/testthat/test.aacomp.R @@ -1,6 +1,6 @@ # CHECK OUTPUT CLASS test_that("aacomp function: output value should be a matrix",{ - expect_true(is.matrix(aacomp("QWGRRCCGWGPGRRYCVRWC")[[1]])) + expect_true(is.matrix(aaComp("QWGRRCCGWGPGRRYCVRWC")[[1]])) }) @@ -19,11 +19,11 @@ test_that("aacomp function: output value should be a matrix",{ # CHECK VALUES test_that("aacomp function: absolute frequencies are wrong",{ - expect_equal(aacomp("QWGRRCCGWGPGRRYCVRWC")[[1]][1:9],c(8,10,1,4,14,6,5,5,0)) + expect_equal(aaComp("QWGRRCCGWGPGRRYCVRWC")[[1]][1:9],c(8,10,1,4,14,6,5,5,0)) }) #CHECK PERCENTAGES test_that("aacomp function: relative frequencies are wrong",{ - expect_equal(aacomp("QWGRRCCGWGPGRRYCVRWC")[[1]][10:18],c(40,50,5,20,70,30,25,25,0)) + expect_equal(aaComp("QWGRRCCGWGPGRRYCVRWC")[[1]][10:18],c(40,50,5,20,70,30,25,25,0)) }) diff --git a/tests/testthat/test.aindex.R b/tests/testthat/test.aindex.R index 3cbd662..8f0b6e3 100644 --- a/tests/testthat/test.aindex.R +++ b/tests/testthat/test.aindex.R @@ -6,10 +6,10 @@ # CHECK VALUES test_that("aindex function: output value is wrong",{ - expect_equal(aindex(seq = "DAYAQWLKDGGPSSGRPPPS"),29.50) + expect_equal(aIndex(seq = "DAYAQWLKDGGPSSGRPPPS"),29.50) }) # # CHECK OUTPUT CLASS test_that("aindex function: output class is wrong",{ - expect_true(is.numeric(aindex(seq = "DAYAQWLKDGGPSSGRPPPS"))) + expect_true(is.numeric(aIndex(seq = "DAYAQWLKDGGPSSGRPPPS"))) }) diff --git a/tests/testthat/test.instaindex.R b/tests/testthat/test.instaindex.R index 145cc6d..7c91e27 100644 --- a/tests/testthat/test.instaindex.R +++ b/tests/testthat/test.instaindex.R @@ -6,10 +6,10 @@ # CHECK INSTAINDEX VALUE test_that("instaindex function: the computed value is wrong",{ - expect_equal(instaindex(seq = "QWGRRCCGWGPGRRYCVRWC"), 83.68) + expect_equal(instaIndex(seq = "QWGRRCCGWGPGRRYCVRWC"), 83.68) }) # CHECK OUTPUT CLASS test_that("instaindex function: the output class is wrong",{ - expect_true(is.numeric(instaindex(seq = "QWGRRCCGWGPGRRYCVRWC"))) + expect_true(is.numeric(instaIndex(seq = "QWGRRCCGWGPGRRYCVRWC"))) }) \ No newline at end of file From ceb646c1aa63a84238b4998d36edf53de3b938d4 Mon Sep 17 00:00:00 2001 From: Daniel Osorio Date: Sat, 11 Mar 2017 21:13:40 -0500 Subject: [PATCH 50/50] NEWS Update --- NEWS.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/NEWS.md b/NEWS.md index dcb91e1..f976682 100644 --- a/NEWS.md +++ b/NEWS.md @@ -10,9 +10,9 @@ NEWS * kideraFactors output vector was renamed as KF# -* fasgaiVectors function was added +* Now all sequences are checked before to property calculation -* aaDescriptos, zScales, vhseScales, protFP, tScales and stScales functions were added +* aaDescriptos, fasgaiVectors, blosumIndices, mswhimScores, zScales, vhseScales, protFP, tScales and stScales functions were added **Peptides v.1.2.2**