Mercurial > repos > elixir-it > covacs_freebayes
changeset 0:03593410f057 draft
Uploaded
| author | elixir-it |
|---|---|
| date | Fri, 09 Nov 2018 05:25:43 -0500 |
| parents | |
| children | cbe203c9bc3a |
| files | bed_macros.xml covacs_freebayes.xml covacs_macros.xml filter.fb.pl tool-data/covacs_bed.loc.sample tool-data/covacs_gatk_indexes.loc.sample tool_data_table_conf.xml.sample |
| diffstat | 7 files changed, 221 insertions(+), 0 deletions(-) [+] |
line wrap: on
line diff
--- /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 @@ +<macros> + <macro name="bed_loc"> + <conditional name="bed_source"> + <param name="bed_source_selector" type="select" label="Will you select a bed file from your history or use a built-in bed?"> + <option value="cached">Use a built-in bed</option> + <option value="history">Use a bed from history as reference</option> + </param> + <when value="cached"> + <param name="bed_cached" type="select" label="Using reference bed" help="Select bed from the list"> + <options from_data_table="covacs_bed"> + <filter type="sort_by" column="2" /> + <validator type="no_options" message="No bed are available" /> + </options> + <validator type="no_options" message="A built-in bed file is not available"/> + </param> + </when> + <when value="history"> + <param name="bed_history" type="data" format="bed" label="Use the following dataset as reference bed " help="You can upload a bed file to the history and use it" optional="true" /> + </when> + </conditional> + </macro> +</macros>
--- /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 @@ + <tool id="covacs_frebayes" name="covacs_freebayes" version="1.2.0"> + <description>Bayesian genetic variant detection, freebayes V = 1.2.0 </description> + <macros> + <import>covacs_macros.xml</import> + <import>bed_macros.xml</import> + </macros> + <requirements> + <requirement type="package" version="1.2.0" >freebayes</requirement> + </requirements> + <command> + <![CDATA[ + + + + + freebayes + + ##call chose genome from mutect2_indexes.loc and from history + #if $reference_source.reference_source_selector == "cached" + -f $reference_source.ref_file.fields.path + #end if + #if $reference_source.reference_source_selector == "history" + -f $reference_source.ref_file_h + #end if + + #if $input2 + -C $input2 + #end if + + #if $bed_source.bed_source_selector == "history" and $bed_source.bed_history + -t $bed_source.bed_history + #end if + #if $bed_source.bed_source_selector == "cached" + -t $bed_source.bed_cached.fields.path + #end if + + $input1 + > $output + + + && perl $__tool_directory__/filter.fb.pl $output $output_filtered + + + ]]> + </command> + <inputs> + <expand macro="reference_loc"/> + <param format="bam" name="input1" label="bam file" type="data" optional="true" /> + <expand macro="bed_loc"/> + <param name="input2" label="-C min-alternate-count" type="integer" value="5" optional="true"/> + </inputs> + <outputs> + <data format="vcf" name="output" label="${tool.name} on ${on_string}:vcf"/> + <data format="vcf" name="output_filtered" label="freebayes filtered on ${on_string}" /> + </outputs> + <help> +**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. + + + </help> + <citations> + <citation type="doi">10.1186/s12864-018-4508-1</citation> + <citation type="bibtex"> + @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} + } + </citation> + </citations> +</tool> +
--- /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 @@ +<macros> + <macro name="reference_loc"> + <conditional name="reference_source"> + <param name="reference_source_selector" type="select" label="Will you select a reference genome from your history or use a built-in fasta?" > + <option value="cached">Use a built-in genome index</option> + <option value="history">Use a genome from history and build index</option> + </param> + <when value="cached"> + <param name="ref_file" type="select" label="Using reference genome" help="Select genome from the list"> + <options from_data_table="covacs_gatk_indexes"> + <filter type="sort_by" column="2" /> + <validator type="no_options" message="No genomes are available" /> + </options> + <validator type="no_options" message="A reference genome is not available for the build associated with the selected input file"/> + </param> + </when> + <when value="history"> + <param name="ref_file_h" type="data" format="fasta" label="Use the following dataset as the reference sequence" help="You can upload a FASTA sequence to the history and use it as reference" /> + </when> + </conditional> + </macro> +</macros>
--- /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,">$out"); +while(<IN>) +{ + if ($_=~/^#/) + { + 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);
--- /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): +# +#<unique_id> <dbkey> <display_name> <file_path> +# +# +#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
--- /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): +# +#<unique_build_id> <dbkey> <display_name> <file_path> +# +#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
--- /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 @@ +<tables> +<!-- Location of bed-file for covacs --> + <table name="covacs_bed" comment_char="#"> + <columns> value, dbkey, name, path</columns> + <file path="tool-data/covacs_bed.loc" /> + </table> +<!-- Location of index file for covacs gatk wrapper --> + <table name="covacs_gatk_indexes" comment_char="#"> + <columns> value, dbkey, name, path</columns> + <file path="tool-data/covacs_gatk_indexes.loc" /> + </table> +</tables>