# HG changeset patch # User elixir-it # Date 1541759143 18000 # Node ID 03593410f057f91ad32d024f33e4e2c03569ca13 Uploaded diff -r 000000000000 -r 03593410f057 bed_macros.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/bed_macros.xml Fri Nov 09 05:25:43 2018 -0500 @@ -0,0 +1,22 @@ + + + + + + + + + + + + + + + + + + + + + + diff -r 000000000000 -r 03593410f057 covacs_freebayes.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/covacs_freebayes.xml Fri Nov 09 05:25:43 2018 -0500 @@ -0,0 +1,91 @@ + + Bayesian genetic variant detection, freebayes V = 1.2.0 + + covacs_macros.xml + bed_macros.xml + + + freebayes + + + $output + + + && perl $__tool_directory__/filter.fb.pl $output $output_filtered + + + ]]> + + + + + + + + + + + + +**Currently available options** + +-f --fasta-reference FILE + Use FILE as the reference sequence for analysis. + An index file (FILE.fai) will be created if none exists. + If neither --targets nor --region are specified, FreeBayes + will analyze every position in this reference. + +-C --min-alternate-count N + Require at least this count of observations supporting + an alternate allele within a single individual in order + to evaluate the position. +-t --targets FILE + Limit analysis to targets listed in the BED-format FILE. + +**Two output file are generated** + +The first output consists in a vcf file containing all the variants detected by Freebayes, the second file contains a subset of the variants filtered according to their QUAL score (QUAL >=20), see the CoVaCS paper for more details. + + + + + 10.1186/s12864-018-4508-1 + + @misc{1207.3907, + Author = {Erik Garrison}, + Title = {Haplotype-based variant detection from short-read sequencing}, + Year = {2012}, + Eprint = {arXiv:1207.3907}, + url = {http://arxiv.org/abs/1207.3907} + } + + + + diff -r 000000000000 -r 03593410f057 covacs_macros.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/covacs_macros.xml Fri Nov 09 05:25:43 2018 -0500 @@ -0,0 +1,22 @@ + + + + + + + + + + + + + + + + + + + + + + diff -r 000000000000 -r 03593410f057 filter.fb.pl --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/filter.fb.pl Fri Nov 09 05:25:43 2018 -0500 @@ -0,0 +1,21 @@ +#!/usr/bin/perl -w +# +$f=shift; +$out=shift; +open(IN,$f); +open(OUT,">$out"); +while() +{ + if ($_=~/^#/) + { + print OUT; + next; + }else{ + $vl=(split())[5]; + $gt=(split())[-1]; + $gt=(split(/\:/,$gt))[0]; + next if $gt eq "0/0"; + print OUT if $vl>20; + } +} +close(OUT); diff -r 000000000000 -r 03593410f057 tool-data/covacs_bed.loc.sample --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/tool-data/covacs_bed.loc.sample Fri Nov 09 05:25:43 2018 -0500 @@ -0,0 +1,17 @@ +#This is a sample file distributed with Galaxy that enables tools +#to use a directory bed file for covacs sequences data files. You will need +#to create these data files and then create a bed_loc.loc file +#similar to this one (store it in this directory) that points to +#the directories in which those files are stored. The bed_loc.loc +#file has this format (longer white space characters are TAB characters): +# +# +# +# +#Note that for backwards compatibility with workflows, the unique ID of +#an entry must be the path that was in the original loc file, because that +#is the value stored in the workflow for that parameter. That is why the +#hg19 entry above looks odd. New genomes can be better-looking. +# +hg19 hg19 hg19-padded /export/BED/S07084713_Padded.bed +hgbed hg19 hg19-bed-test /export/BED/chr22.bed diff -r 000000000000 -r 03593410f057 tool-data/covacs_gatk_indexes.loc.sample --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/tool-data/covacs_gatk_indexes.loc.sample Fri Nov 09 05:25:43 2018 -0500 @@ -0,0 +1,36 @@ +#This is a sample file distributed with Galaxy that enables tools +#to use a directory of all covacs wrapper that need a gatk reference. You will need +#to create these data files and then create a covacs_gatk_indexes.loc file +#similar to this one (store it in this directory) that points to +#the directories in which those files are stored. The covacs_gatk_indexes.loc +#file has this format (longer white space characters are TAB characters): +# +# +# +#So, for example, if you had phiX indexed stored in +#/depot/data2/galaxy/phiX/base/, +#then the bwa_index.loc entry would look like this: +# +#phiX174 phiX phiX Pretty /depot/data2/galaxy/phiX/base/phiX.fa +# +#and your /depot/data2/galaxy/phiX/base/ directory +#would contain phiX.dict, phiX.fa.fai files. +# +# +#Your covacs_gatk_indexes.loc file should include an entry per line for each +#index set you have stored. The "file" in the path does not actually +#exist, but it is the prefix for the actual index files. For example: +# +#phiX174 phiX phiX174 /depot/data2/galaxy/phiX/base/phiX.fa +#hg18canon hg18 hg18 Canonical /depot/data2/galaxy/hg18/base/hg18canon.fa +#hg18full hg18 hg18 Full /depot/data2/galaxy/hg18/base/hg18full.fa +#/orig/path/hg19.fa hg19 hg19 /depot/data2/galaxy/hg19/base/hg19.fa +#...etc... +# +#Note that for backwards compatibility with workflows, the unique ID of +#an entry must be the path that was in the original loc file, because that +#is the value stored in the workflow for that parameter. That is why the +#hg19 entry above looks odd. New genomes can be better-looking. +# +hg38 hg38 hg38_GDC /export/gatkhg38pl/GRCh38.d1.vd1.fa +hg19 hg19 hg19 /export/gatk_hg19_index_bundle/ucsc.hg19.fasta diff -r 000000000000 -r 03593410f057 tool_data_table_conf.xml.sample --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/tool_data_table_conf.xml.sample Fri Nov 09 05:25:43 2018 -0500 @@ -0,0 +1,12 @@ + + + + value, dbkey, name, path + +
+ + + value, dbkey, name, path + +
+