[pull] master from emmanuelparadis:master

README.md

@@ -9,4 +9,4 @@ This repository contains:
 
 More information on pegas (including description of data structures):
 
-http://ape-package.ird.fr/pegas.html
+http://emmanuelparadis.github.io/pegas.html

pegas/DESCRIPTION

@@ -1,18 +1,18 @@
 Package: pegas
-Version: 0.14
-Date: 2020-09-16
+Version: 1.3-0.4
+Date: 2025-12-04
 Title: Population and Evolutionary Genetics Analysis System
 Authors@R: c(person("Emmanuel", "Paradis", role = c("aut", "cre", "cph"), email = "[email protected]", comment = c(ORCID = "0000-0003-3092-2199")),
   person("Thibaut", "Jombart", role = c("aut", "cph"), comment = c(ORCID = "0000-0003-2226-8692")),
   person("Zhian N.", "Kamvar", role = c("aut", "cph"), comment = c(ORCID = "0000-0003-1458-7108")),
   person("Brian", "Knaus", role = c("aut", "cph"), comment = c(ORCID = "0000-0003-1665-4343")),
-  person("Klaus", "Schliep", role = c("aut", "cph")),
+  person("Klaus", "Schliep", role = c("aut", "cph"), comment = c(ORCID = "0000-0003-2941-0161")),
   person("Alastair", "Potts", role = c("aut", "cph"), comment = c(ORCID = "0000-0003-0919-7279")),
   person("David", "Winter", role = c("aut", "cph"), comment = c(ORCID = "0000-0002-6165-0029")))
-Depends: R (>= 3.2.0), ape (>= 5.3-11), adegenet
+Depends: R (>= 3.2.0), ape (>= 5.3-11)
 Imports: graphics, utils, methods
-Suggests: rgl, snpStats
+Suggests: rgl, snpStats, adegenet
 ZipData: no
 Description: Functions for reading, writing, plotting, analysing, and manipulating allelic and haplotypic data, including from VCF files, and for the analysis of population nucleotide sequences and micro-satellites including coalescent analyses, linkage disequilibrium, population structure (Fst, Amova) and equilibrium (HWE), haplotype networks, minimum spanning tree and network, and median-joining networks.
 License: GPL (>= 2)
-URL: http://ape-package.ird.fr/pegas.html
+URL: https://emmanuelparadis.github.io/pegas.html

pegas/NAMESPACE

@@ -2,33 +2,35 @@ useDynLib(pegas, .registration = TRUE)
 
 export(alleles2loci, allelicrichness, amova, as.igraph.haploNet,
        as.loci, as.network.haploNet, diffHaplo, dist.hamming,
-       dist.haplotype.loci, dist.asd, dist.snp, expand.genotype, F2,
-       F3, F4, Fst, genind2loci, geod, geoTrans, geoTrans2, getAlleles,
-       getGenotypes, getINFO, getPloidy, getPhi, H, haploNet,
-       haploFreq, hap.div, haplotype, heterozygosity, hw.test,
-       is.phased, is.snp, LD, LD2, LDscan, LDmap, loci2alleles,
-       loci2genind, loci2SnpMatrix, mjn, msn, mst, MMD, nuc.div,
-       plotNetMDS, proba.genotype, R2.test, rangePOS, rarefactionplot,
-       read.gtx, read.loci, read.vcf, replot, rhost, rmst, rr.test,
-       Rst, selectQUAL, site.spectrum, stairway, sw, tajima.test,
+       dist.haplotype.loci, dist.asd, expand.genotype, F2, F3, F4,
+       Fst, genind2loci, geod, geoTrans, geoTrans2, getAlleles,
+       getGenotypes, getHaploNetOptions, getINFO, getPloidy, getPhi,
+       H, haploNet, haploFreq, hap.div, haplotype, heterozygosity,
+       hw.test, is.phased, is.snp, LD, LD2, LDscan, LDmap,
+       loci2alleles, loci2genind, loci2SnpMatrix, mjn, msn, mst, MMD,
+       mutations, nuc.div, nullAlleles2NA, plotNetMDS, proba.genotype,
+       R2.test, rangePOS, rarefactionplot, read.gtx, read.loci,
+       read.vcf, replot, rhost, rmst, rr.test, Rst, selectQUAL,
+       setHaploNetOptions, site.spectrum, stairway, sw, tajima.test,
        theta.h, theta.k, theta.msat, theta.s, unphase, theta.tree,
        theta.tree.hetero, VCFheader, VCFlabels, VCFloci, write.loci,
-       write.pegas.amova)
+       write.pegas.amova, write.vcf)
 
 importFrom(ape, as.evonet, as.phylo, BOTHlabels, branching.times,
-           base.freq, dist.dna, dist.nodes, floating.pie.asp,
+           base.freq, dist.dna, dist.nodes, fancyarrows, floating.pie.asp,
            GC.content, latag2n, perm.rowscols, polar2rect, rcoal,
            rect2polar, seg.sites)
-importFrom(adegenet, df2genind, genind2df)
+#importFrom(adegenet, df2genind, genind2df)
 importFrom(graphics, abline, axis, barplot, hist, lines, lines.default, locator,
-           matplot, mtext, par, polygon, plot, plot.default, rect, segments,
-           strheight, symbols, text, xinch)
+           matplot, mtext, par, points, polygon, plot, plot.default, rect,
+           segments, strheight, strwidth, symbols, text, xinch)
 importFrom(grDevices, colorRampPalette, dev.cur, devAskNewPage,
            deviceIsInteractive, rainbow, rgb)
 importFrom(stats, as.dist, cmdscale, cophenetic, density, dist, integrate,
-           na.omit, nlminb, pbeta, pchisq, pnorm, printCoefmat, rpois, sd,
-           uniroot, weighted.mean)
-importFrom(utils, as.roman, combn, edit, read.table, write.csv, write.table)
+           median, na.omit, nlminb, pbeta, pchisq, pnorm, printCoefmat, rpois,
+           sd, setNames, uniroot, weighted.mean)
+importFrom(utils, as.roman, combn, edit, packageVersion, read.table,
+           write.csv, write.table)
 importFrom(methods, new)
 
 S3method(print, amova)
@@ -37,6 +39,7 @@ S3method(as.loci, character)
 S3method(as.loci, data.frame)
 S3method(as.loci, factor)
 S3method(as.loci, genind)
+S3method(as.loci, matrix)
 
 S3method(H, default)
 S3method(H, loci)
@@ -75,6 +78,8 @@ S3method(theta.s, DNAbin)
 S3method(all.equal, haploNet)
 S3method(as.phylo, haploNet)
 S3method(as.evonet, haploNet)
+S3method(cophenetic, haploNet)
+S3method(labels, haploNet)
 S3method(plot, haploNet)
 S3method(print, haploNet)
 
@@ -96,6 +101,8 @@ S3method(print, loci)
 S3method(rbind, loci)
 S3method(summary, loci)
 
+S3method(plot, mjn)
+
 S3method(plot, spectrum)
 
 S3method(lines, stairway)

pegas/NEWS

@@ -1,3 +1,214 @@
+		CHANGES IN PEGAS VERSION 1.3-0.3
+
+
+NEW FEATURES
+
+    o rmst() has a new option: random = FALSE. The new default
+      algorithm of this function finds all MSTs for the data and
+      combines them to create the returned RMST. The results are
+      identical to those with the random algorithm with a sufficiently
+      large number of iterations (see PR #86 on GitHub).
+
+    o The colour of the alternative links of a haplotype network can
+      now be changed with the new option $link.color.alt through
+      setHaploNetOptions().
+
+    o haploNet() and mjn() now return a network with a single node and
+      zero link when given a single haplotype as input. They return
+      NULL when given an input with zero data.
+
+
+BUG FIXES
+
+    o rmst() failed when given a single distance (i.e., there's only 2
+      haplotypes): it now calls mst().
+
+    o rmst() created an object named "rnt" in the user's workspace.
+      This is fixed.
+
+    o print.haploNet() did not always display correctly link lengths.
+
+    o When plotting a haplotype network, modifying the aspect of the
+      alternative links did not work.
+
+    o A bug was fixed in dist.asd(, pairwise.deletion = TRUE) (see
+      issue #91 on GitHub).
+
+
+
+		CHANGES IN PEGAS VERSION 1.3
+
+
+NEW FEATURES
+
+    o plot.haploNet() has a new argument 'col.lab' to change the
+      colors of the haplotype labels. It can be changed through the
+      option "labels.color" (see ?setHaploNetOptions).
+
+    o The R code of mst() has been replaced by a C code which can be
+      1000 times faster with several 100s observations (this improves
+      also rmst() and all other functions calling mst()). The code now
+      scales very nearly as O(n^2) in practice.
+
+    o rmst() now returns a network with a "backbone-MST" so that
+      repeated analyses of the same data are likely to return
+      graphically similar networks (see issue #82 on GitHub).
+
+
+BUG FIXES
+
+    o tajima.test() may use different sets of sites when computing the
+      number of segregating sites and the mean pairwise distance. This
+      has been fixed by adding pairwise.deletion = TRUE to the call to
+      dist.dna (see issue #77 on GitHub).
+
+    o The placement of mutation ticks on alternative links of
+      haplotype networks has been fixed (see issue #77 on GitHub).
+
+
+
+		CHANGES IN PEGAS VERSION 1.2
+
+
+NEW FEATURES
+
+    o The new function nullAlleles2NA changes genotypes with at least
+      one `null allele' into NA.
+
+    o MMD() now returns invisibly a list with the plotted data (i.e.,
+      histogram, empirical density, and expected curve under stable
+      population).
+
+    o dist.asd() has now the option 'pairwise.deletion = FALSE'.
+
+
+BUG FIXES
+
+    o The estimator variance in theta.s() has been corrected (thanks
+      to Carsten Wiuf) and the help page has been updated.
+
+    o plot.haploNet() did not handle correctly the 'bg' argument when
+      it is a vector of colours. This also affected the plot of MJN
+      networks.
+
+    o VCF files with DOS-style end of lines (i.e., CRLF) are now
+      supported.
+
+    o Argument 'bg' was not always well interpreted in plot.haploNet()
+      and plot.mjn().
+
+
+OTHER CHANGES
+
+    o There is a new (non-interactive) example in ?replot.
+
+    o The help page of plot.mjn() has been clarified about the usage
+      of the arguments 'shape' and 'bg'.
+
+
+
+		CHANGES IN PEGAS VERSION 1.1
+
+
+BUG FIXES
+
+    o plot.haploNet() did not use 'bg' correctly when 'pie' was
+      used. The help page has been clarified that this argument could
+      also be a function.
+
+    o setHaploNetOptions(pie.colors.function = ) did not work
+      correcly; similarly for 'pie.inner.segments.color'.
+
+    o The argument 'scale.ratio' was not always passed correctly among
+      internal functions when plotting "haploNet" objects (see issue
+      #59 on GH).
+
+    o haplotype.character() failed to work correctly (see issue #61).
+
+
+OTHER CHANGES
+
+    o amova() now accepts distance objects which inherit the class
+      "dist" (instead of being strictly equal).
+
+    o adegenet has been moved from 'Imports' to 'Suggests'.
+
+
+
+      		CHANGES IN PEGAS VERSION 1.0
+
+
+NEW FEATURES
+
+    o The new function mutations() draws mutations on a network (with
+      many options; see ?mutations).
+
+    o The new function write.vcf writes an object of class "loci" into
+      a VCF file.
+
+    o There is a new cophenetic() method for objects of class
+      "haploNet", and a new labels() method.
+
+    o diffHaplo() has been simplified and gains the options 'strict'
+      and 'trailingGapsAsN' which are passed to ape::seg.sites().
+
+    o mjn() has a new option 'quiet = FALSE'; its code has been
+      improved and is now 10 times faster (25 times with 100 sequences
+      resulting in running times less than 15 sec). The returned
+      object have the class c("mjn", "haploNet") and there is a new
+      plot.mjn() method.
+
+    o replot() has been improved: the instructions are more detailed,
+      there is a new option 'col.identifier' to show the node to be
+      moved, and the bounding box of the plot is now calculated
+      correctly so the network does not "shrink" after each move.
+
+    o plot.haploNet() has two new options: 'shape' and 'xy' to change
+      the symbol shapes and their coordinates, respectively.
+
+    o There are two new functions, getHaploNetOptions and
+      setHaploNetOptions, to help users change the graphical
+      paramaters when plotting haplotype networks.
+
+    o There is a new as.loci() method for matrices.
+
+    o rmst() implements a new algorithm to stop iterations after no
+      new links are found: this is controlled by the new options
+      'stop.criterion' and 'iter.lim'. There is also a new option
+      'quiet = FALSE'.
+
+    o Fst() now runs in the case of a single population, returning the
+      Fis (and Fit which equates 1).
+
+    o There is a new vignette "PlotHaploNet" detailing some aspects of
+      plotting haplotype networks with pegas, including the new
+      features and options.
+
+
+BUG FIXES
+
+    o A bug was fixed in geoTrans2().
+
+    o as.loci.data.frame() now works with "tibble" objects (thanks to
+      Jean-Baka Domelevo Entfellner for the fix).
+
+    o allelicrichness(, method = "rarefaction") used to return the raw
+      allelic richness: this is fixed and this function gains the
+      option 'min.n' to work with this method (common sample size used
+      for all populations).
+
+    o haplotype() on an empty "DNAbin" object returns an empty
+      "haplotype" object similarly to pegas 0.12 (see issue #53 on GH).
+
+
+OTHER CHANGES
+
+    o adegenet has been moved from 'Depends' to 'Imports'.
+
+    o dist.snp() has been removed.
+
+
+
 		CHANGES IN PEGAS VERSION 0.14
 
 

pegas/R/Fst.R

@@ -1,8 +1,8 @@
-## Fst.R (2019-02-25)
+## Fst.R (2021-02-24)
 
 ##   F-Statistics
 
-## Copyright 2009-2019 Emmanuel Paradis
+## Copyright 2009-2021 Emmanuel Paradis
 
 ## This file is part of the R-package `pegas'.
 ## See the file ../DESCRIPTION for licensing issues.
@@ -43,7 +43,7 @@ Fst <- function(x, pop = NULL, quiet = TRUE, na.alleles = "")
         nBYpop <- tabulate(Z$pop)
         r <- length(nBYpop) # number of pops
         nbar <- N/r
-        nC <- (N - sum(nBYpop^2)/N)/(r - 1)
+        nC <- if (r == 1) 0 else (N - sum(nBYpop^2)/N)/(r - 1)
         ALLELES <- getAlleles(Z)[[1]]
         h <- p <- matrix(0, r, length(ALLELES))
         for (i in 1:r) {
@@ -61,14 +61,14 @@ Fst <- function(x, pop = NULL, quiet = TRUE, na.alleles = "")
         }
         ptild <- p/(2 * nBYpop)
         pbar <- colSums(p)/(2 * N) # for each allele in the locus
-        s2 <- colSums(nBYpop * (ptild - rep(pbar, each = r))^2)/((r - 1) * nbar)
+        s2 <- if (r == 1) rep(0, length(ALLELES)) else colSums(nBYpop * (ptild - rep(pbar, each = r))^2)/((r - 1) * nbar)
         hbar <- colSums(h)/N # id.
         A <- pbar * (1 - pbar) - (r - 1) * s2/r
         a <- nbar * (s2 - (A - hbar/4)/(nbar - 1))/nC
         b <- nbar * (A - (2*nbar - 1) * hbar/(4*nbar))/(nbar - 1)
         c <- hbar/2
-        res[j, 1] <- 1 - sum(c)/sum(a + b + c)
-        res[j, 2] <- sum(a)/sum(a + b + c)
+        res[j, 1] <- if (r == 1) NA else 1 - sum(c)/sum(a + b + c)
+        res[j, 2] <- if (r == 1) NA else sum(a)/sum(a + b + c)
         res[j, 3] <- 1 - sum(c)/sum(b + c)
     }
     if (!quiet) cat("... Done.\n")