settings.cfg

#**********************************************
#*    Configuration file for HybPhyloMaker    *
#* https://github.com/tomas-fer/HybPhyloMaker *
#*               Tomas Fer, 2024              *
#*          tomas.fer@natur.cuni.cz           *
#*                   v.1.8.0i                 *
#**********************************************

#--------------------------------------------------------------------------------------------------------------------
# **** GENERAL SETTINGS ****
#--------------------------------------------------------------------------------------------------------------------
# Metacentrum (1) or local (0) or Hydra (2)
location="1"

# If on MetaCentrum select server (brno2, praha1, plzen1, budejovice1, brno6, brno3-cerit, brno9-ceitec, ostrava1)
server=brno2

#Where is your data folder
data=testdata

#File for adapter removal (must be in HybSeqSource)
adapterfile=NEBNext-PE.fa

#--------------------------------------------------------------------------------------------------------------------
# **** GENE TREE SETTINGS ****
#--------------------------------------------------------------------------------------------------------------------
#Tree-building method (RAxML or FastTree)
tree=RAxML

#Bootstrap FastTree (yes/no). no=normal FastTree with local branch support, very fast; yes=FastTree is applied to each of 100 bootstrap replicates, slow
FastTreeBoot=no

#Standard or rapid bootstrapping in RAxML (standard or rapid)
raxmlboot=rapid

#Number of bootstrap replicates for RAxML gene trees
bsrep=100

#Use bootstopping strategy for RAxML gene trees, i.e., bootstrapping until convergence (yes/no)
bootstop=no

#Evolutionary model for RAxML (GTRGAMMA, GTRGAMMAI, GTRCAT, GTRCATI)
#NOTE: Do not use CAT model for datasets with less than 50 taxa! Do not combine GTRCAT and rapid bootstrapping!
model=GTRGAMMA

#Use 'no', 'by exon' or 'by codon and exon' partitioning when building gene trees with RAxML (no, exon, codon)
#Codon is only for the data with corrected reading frame!
genetreepart=exon

#Outgroup (as it appears in RAxML files)
OUTGROUP="Siphonochilus-aethiopicus_S130"

#--------------------------------------------------------------------------------------------------------------------
# **** SPECIES TREE SETTINGS ****
#--------------------------------------------------------------------------------------------------------------------

#Bootstrap ExaML (yes/no)
examlboot=no

#Multilocus bootstrap for Astral and Astrid trees (yes/no)
mlbs=no

#Combine support values from main, bootstrap and bootstrap consensus trees to one tree (for Astral and Astrid trees)
combine=no

#Collapse trees for ASTRAL (integer, 0-99), set to '0' if no collapsing is requested
collapse=0

#Calculate ASTRAL tree with local posterior probabilities of three alternative hypotheses using '-t 4' (yes/no)
astralt4=yes

#Work only with trees with requisite taxa present (yes/no)
requisite=no

#List of requisite taxa (write taxon names separated by "|", the whole expression must be within quotes!)
requisitetaxa="Siphonochilus"

#Number of MCMC steps for BUCKy
nrbucky=1000000

#Number of runs for BUCKy (parameter '-k')
nrruns=2

#Number of chains for BUCKy (parameter '-c')
nrchains=2

#Parameter 'alpha' for BUCKy (parameter '-a')
alpha=1

#Parameter '-s' for PhyParts (cut-off for bootstrap support in gene trees)
phypartsbs=0.5

#Colours for PhyParts pie charts (four named colours separated by spaces, the whole expression must be within quotes)
#see https://en.wikipedia.org/wiki/Web_colors for colour's names
#leave empty for original colours
ppcolors="blue green red silver"

#Get only first XXX gene trees for PhyParts (leave empty if all trees should be used)
nrpptrees=

#Species tree for Quartet Sampling (Astral, FastTree or ExaML)
qstree=FastTree

#Constraint tree for ExaML. The tree should be in HybSeqSource folder and needs to contain all taxa of the alignment!
constrtree=constrtree.tre

#SNP thinning for Dsuite (first, random or thinning)
SNPs=thinning

#hstart for SNaQ/PhyloNet. For SNaQ this should be set to '0' unless further implemented!
hstart=0

#hmax for SNaQ/PhyloNet. Maximum number of hybrid nodes.
hmax=5

#Number of runs of the PhyloNet search (parameter '-x')
numruns=10

#--------------------------------------------------------------------------------------------------------------------
# **** MISSING DATA SETTINGS ****
#--------------------------------------------------------------------------------------------------------------------
#Delete species with more than % of missing data
MISSINGPERCENT=70

#Only include loci with at least % of species
SPECIESPRESENCE=75

#Removing gap and 'n' only positions in exon alignments using trimAl (yes/no)
noallgaps=no

#Trimming exon alignments using trimAl gappyout (yes/no)
gappyout=no

#--------------------------------------------------------------------------------------------------------------------
# **** TYPE OF DATA ****
#--------------------------------------------------------------------------------------------------------------------
#Working with cpDNA (yes/no)
cp=no

#Working with updated list of genes (yes/no)
update=no

#Working with corrected reading frame for exons/genes (yes/no)
corrected=no

#Working with data trimmed by trimAl (yes/no)
trimmed=no

#Maximum number of stop codons allowed per alignment (i.e., considered as errors)
maxstop=5

#Name of the sample selection folder (to be created with script 12)
selection=

#--------------------------------------------------------------------------------------------------------------------
# **** REFERENCE FILES ****
#--------------------------------------------------------------------------------------------------------------------
#Number of Ns to separate exons in pseudoreference (400 is recommended for 2x150 bp reads and 800 for 2x250 bp reads)
nrns=400

#File name with exonic probe sequences (must be stored in HybSeqSource folder)
probes=curcuma_HybSeqProbes_test.fa

#Minimum sequence identity between probe and sample (default is 90) - used in BLAT
minident=90

#File name with cpDNA CDS sequences (must be stored in HybSeqSource folder)
cpDNACDS=Curcuma-roscoeana_plastomeCDS_test.fa

#File name with full plastome cpDNA reference (one IR should be removed)
cpDNA=

#File name with full plastome cpDNA (GenBank flat file) (must be stored in HybSeqSource folder)
cpGBfile=

#GenBank accession number of full plastome cpDNA record (e.g. KR967361)
cpGBnr=

#Minimum sequence length in plastome reference (to be generated by script 0f)
#mincplength=200

#--------------------------------------------------------------------------------------------------------------------
# **** PATH TO DATA ****
#--------------------------------------------------------------------------------------------------------------------
#path to other transcriptomes/genomes to combine (NO if no other data sources available)
othersource=NO

#path to other pslx files to combine
otherpslx=pslx_to_combine

#path to other cpDNA pslx files to combine
otherpslxcp=pslx_cpDNA_to_combine

#--------------------------------------------------------------------------------------------------------------------
# **** SOFTWARE BINARIES AND NUMBER OF CORES ****
#--------------------------------------------------------------------------------------------------------------------
#binary name for sequential version of RAxML (raxmlHPC, raxmlHPC-SSE3, or raxmlHPC-AVX)
raxmlseq=raxmlHPC-SSE3

#binary name for Pthreads version of RAxML (raxmlHPC-PTHREADS, raxmlHPC-PTHREADS-SSE3, or raxmlHPC-PTHREADS-AVX)
raxmlpthreads=raxmlHPC-PTHREADS-SSE3

#binary name for FastTree
fasttreebin=FastTree

#java file for ASTRAL (e.g., astral.5.7.7.jar - this file must be in HybSeqSource together with lib folder - see Astral homepage)
astraljar=astral.5.7.7.jar

#binary name for ASTRID (ASTRID, ASTRID-linux, or ASTRID-osx) - must be in HybSeqSource
astridbin=ASTRID

#binary name for ExaML (examl, examl-AVX, or examl-OMP-AVX)
examlbin=examl

#number of cores/threads available (not applicable for clusters where number of cores is set using PBS and passed through env variables)
numbcores=2

#--------------------------------------------------------------------------------------------------------------------
# **** PARALLELIZATION SETTINGS ****
#--------------------------------------------------------------------------------------------------------------------
#parallel MAFFT (yes or no)
parallelmafft=yes

#parallel RAxML (yes or no)
parallelraxml=no

#how many RAxML calculation will be calculated per single submitted job (number of jobs = number of genes / raxmlperjob)
raxmlperjob=10

#--------------------------------------------------------------------------------------------------------------------
# *** MAPPING AND CONSENSUS SETTINGS, HETEROZYGOSITY ****
#--------------------------------------------------------------------------------------------------------------------
#mapping method (bowtie2/bwa)
mappingmethod=bwa

#whether mapping using bowtie2 should be done (yes/no)
mapping=yes

#consensus calling software (kindel/ococo/consensusfixer); kindel/ococo for majority base, consensusfixer for ambiguities
conscall=kindel

#minimum site coverage for SNP calling (N will be in consensus for sites with lower coverage)
mincov=2

#majority threshold for consensus calling (0-1) - not working in OCOCO!
majthres=0.51

#minimal relative frequency of alternative base to call as ambiguity (only for ConsensusFixer)
plurality=0.3

#calculate number of heterozygous sites per exon
nohetcalculation=yes

#maximum number of heterozygous sites per exon to include it
maxhet=4

#--------------------------------------------------------------------------------------------------------------------
# *** DATA DOWNLOAD SETTINGS **** (currently not working due to change on Illumina BaseSpace web page!!!)
#--------------------------------------------------------------------------------------------------------------------
#Download samples from Illumina BaseSpace (yes/no)
download=no
#ID of the Illumina BaseSpace project from which the samples should be downloaded
projectID=
#ID of the Illumina BaseSpace run (only if a basic run statistics is required)
runID=
#Illumina BaseSpace API server (see https://developer.basespace.illumina.com/docs/content/documentation/cli/cli-overview#SpecifyAPIserverandAccessToken)
#bsserver=https://api.euc1.sh.basespace.illumina.com
bsserver=https://api.basespace.illumina.com

#--------------------------------------------------------------------------------------------------------------------
# **** OTHER SETTINGS ****
#--------------------------------------------------------------------------------------------------------------------
#using AMAS (fast/slow); try 'slow' only if you observe 'Argument list too long' error
AMAS=fast

#number of exons for generating test dataset (script 0d)
nrexons=958 #this is equivalent of 250 loci for Curcuma probes