Mercurial > repos > morinlab > vardictjava
changeset 0:fba18d3160d1 draft default tip
planemo upload for repository https://github.com/morinlab/tools-morinlab/tree/master/tools/vardictjava commit 4ef2d91b7c1686a2696b92fe538d4aec51d05e40-dirty
author | morinlab |
---|---|
date | Tue, 11 Oct 2016 14:37:45 -0400 |
parents | |
children | |
files | citations.xml tool-data/all_fasta.loc.sample tool_data_table_conf.xml.sample tool_dependencies.xml vardictjava.xml |
diffstat | 4 files changed, 300 insertions(+), 0 deletions(-) [+] |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/citations.xml Tue Oct 11 14:37:45 2016 -0400 @@ -0,0 +1,153 @@ +<macros> + <xml name="morinlab_citation"> + <citation type="bibtex"> + @unpublished{ + albuquerque2016galaxy, + author = "Marco Albuquerque and Bruno Grande and Elie Ritch and Martin Krzywinski and Prasath Pararajalingam and Selin Jessa and Paul Boutros and Sohrab Shah and Ryan Morin", + title = "A Suite of Galaxy Tools for Cancer Mutational Analysis", + note = "Unpublished Manuscript", + year = "2016" + } + </citation> + </xml> + <xml name="vardict_citation"> + <citation type="bibtex"> + @article{ + Lai20062016, + title = {VarDict: a novel and versatile variant caller for next-generation sequencing in cancer research}, + author = {Lai, Zhongwu and Markovets, Aleksandra and Ahdesmaki, Miika and Chapman, Brad and Hofmann, Oliver and McEwen, Robert and Johnson, Justin and Dougherty, Brian and Barrett, J. Carl and Dry, Jonathan R.}, + journal = {Nucleic Acids Research} + volume = {44}, + number = {11}, + pages = {e108}, + year = {2016}, + doi = {10.1093/nar/gkw227} + } + </citation> + </xml> + <xml name="somatic_sniper_citation"> + <citation> + @article{ + Larson01022012, + author = {Larson, David E. and Harris, Christopher C. and Chen, Ken and Koboldt, Daniel C. and Abbott, Travis E. and Dooling, David J. and Ley, Timothy J. and Mardis, Elaine R. and Wilson, Richard K. and Ding, Li}, + title = {SomaticSniper: identification of somatic point mutations in whole genome sequencing data}, + volume = {28}, + number = {3}, + pages = {311-317}, + year = {2012}, + doi = {10.1093/bioinformatics/btr665}, + journal = {Bioinformatics} + } + </citation> + </xml> + <xml name="galaxy_citation"> + <citation> + @ARTICLE{Goecks2010-ra, + title = "Galaxy: a comprehensive approach for supporting accessible, + reproducible, and transparent computational research in the life + sciences", + author = "Goecks, Jeremy and Nekrutenko, Anton and Taylor, James and + {Galaxy Team}", + journal = "Genome Biol.", + volume = 11, + number = 8, + pages = "R86", + month = "25~", + year = 2010 + } + </citation> + </xml> + + <xml name="delly_citation"> + <citation> + @ARTICLE{Rausch2012-yi, + title = "{DELLY}: structural variant discovery by integrated paired-end + and split-read analysis", + author = "Rausch, Tobias and Zichner, Thomas and Schlattl, Andreas and + St{\"{u}}tz, Adrian M and Benes, Vladimir and Korbel, Jan O", + journal = "Bioinformatics", + volume = 28, + number = 18, + pages = "i333--i339", + month = "15~", + year = 2012 +} + </citation> + </xml> + <xml name="mutationseq_citation"> + <citation type="bibtex"> +@ARTICLE{Ding2012-jq, + title = "Feature-based classifiers for somatic mutation detection in + tumour-normal paired sequencing data", + author = "Ding, Jiarui and Bashashati, Ali and Roth, Andrew and Oloumi, + Arusha and Tse, Kane and Zeng, Thomas and Haffari, Gholamreza and + Hirst, Martin and Marra, Marco A and Condon, Anne and Aparicio, + Samuel and Shah, Sohrab P", + journal = "Bioinformatics", + volume = 28, + number = 2, + pages = "167--175", + month = "15~" # jan, + year = 2012 +} + </citation> + </xml> + + <xml name="strelka_citation"> + <citation type="bibtex"> + @ARTICLE{Saunders2012-nh, + title = "Strelka: accurate somatic small-variant calling from sequenced + tumor-normal sample pairs", + author = "Saunders, Christopher T and Wong, Wendy S W and Swamy, Sajani and + Becq, Jennifer and Murray, Lisa J and Cheetham, R Keira", + journal = "Bioinformatics", + volume = 28, + number = 14, + pages = "1811--1817", + month = "15~" # jul, + year = 2012 + } + </citation> + </xml> + <xml name="radia_citation"> + <citation type="bibtex"> + @article{ + Radenbaugh2014-tj, + title={RADIA: RNA and DNA integrated analysis for somatic + mutation detection}, + author={Radenbaugh, Amie J and Ma, Singer and Ewing, Adam and Stuart, + Joshua M and Collisson, Eric A and Zhu, Jingchun and Haussler, + David}, + journal={PLoS One}, + volume={9}, + number={11}, + pages={e111516}, + year={2014}, + publisher={PLoS} + } + </citation> + </xml> + <xml name="titan_citation"> + <citation type="bibtex"> + @ARTICLE{Ha2014-pu, + title = "{TITAN}: inference of copy number architectures in clonal cell + populations from tumor whole-genome sequence data", + author = "Ha, Gavin and Roth, Andrew and Khattra, Jaswinder and Ho, + Julie and Yap, Damian and Prentice, Leah M and Melnyk, + Nataliya and McPherson, Andrew and Bashashati, Ali and Laks, + Emma and Biele, Justina and Ding, Jiarui and Le, Alan and + Rosner, Jamie and Shumansky, Karey and Marra, Marco A and + Gilks, C Blake and Huntsman, David G and McAlpine, Jessica N + and Aparicio, Samuel and Shah, Sohrab P", + journal = "Genome Res.", + publisher = "Cold Spring Harbor Lab", + volume = 24, + number = 11, + pages = "1881--1893", + month = "1~" # nov, + year = 2014, + keywords = "computational method" +} + </citation> + </xml> +</macros>
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/tool_data_table_conf.xml.sample Tue Oct 11 14:37:45 2016 -0400 @@ -0,0 +1,6 @@ +<tables> + <table name="fasta_indexes" comment_char="#"> + <columns>value, dbkey, name, path</columns> + <file path="tool-data/all_fasta.loc"/> + </table> +</tables>
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/tool_dependencies.xml Tue Oct 11 14:37:45 2016 -0400 @@ -0,0 +1,12 @@ +<?xml version="1.0"?> +<tool_dependency> + <package name="R" version="3.2.1"> + <repository changeset_revision="77d439695328" name="package_r_3_2_1" owner="iuc" toolshed="https://testtoolshed.g2.bx.psu.edu" /> + </package> + <package name="perl" version="5.18.1"> + <repository changeset_revision="95dad0955d7e" name="package_perl_5_18" owner="iuc" toolshed="https://testtoolshed.g2.bx.psu.edu" /> + </package> + <package name="vardictjava" version="1.4.6"> + <repository changeset_revision="53f0323d032c" name="package_vardictjava_1_4_6" owner="morinlab" toolshed="https://testtoolshed.g2.bx.psu.edu" /> + </package> +</tool_dependency>
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/vardictjava.xml Tue Oct 11 14:37:45 2016 -0400 @@ -0,0 +1,129 @@ +<tool id="vardictjava" name="VarDictJava" version="1.4.6"> + <description> + calls SNVs and indels for tumour-normal pairs. + </description> + + <requirements> + <requirement type="package" version="5.18.1">perl</requirement> + <requirement type="package" version="3.2.1">R</requirement> + <requirement type="package" version="1.4.6">vardictjava</requirement> + <requirement type="set_environment">VARDICTJAVA_ROOT_DIR</requirement> + </requirements> + + <command detect_errors="aggressive"><![CDATA[ + ## LINK BAM INDEX + ln -s $normal ./normal.bam; + ln -s $normal.metadata.bam_index ./normal.bam.bai; + ln -s $tumour tumor.bam; + ln -s $tumour.metadata.bam_index ./tumor.bam.bai; + + ## INDEX REFERENCE FASTA FILE IF FROM HISTORY + #if $reference_source.reference_source_selector == "history": + ln -s $reference_source.ref_file ref.fa; + samtools faidx ref.fa; + #else if $reference_source.reference_source_selector == "cached" + ln -s $reference_source.ref_file.fields.path ref.fa; + ln -s ${reference_source.ref_file.fields.path}.fai ref.fa.fai; + #end if + + ## BUILD BED FILE FROM CHROMOSOME LIST + #if $interval_file: + grep -w -f $interval_file ref.fa.fai > chromosomes.fa.fai; + #else + ln -s ref.fa.fai chromosomes.fa.fai; + #end if + awk 'BEGIN {FS=OFS="\t"} {print $1, "1", $2}' chromosomes.fa.fai > regions.bed; + + ## BUILD VARDICT COMMAND + \$VARDICTJAVA_ROOT_DIR/build/install/VarDict/bin/VarDict + -b "./tumor.bam|./normal.bam" + -G ref.fa + -z + -th \${GALAXY_SLOTS:-1} + + ## ADVANCED OPTIONS + -f $advancedsettings.f + -k $advancedsettings.k + -r $advancedsettings.r + -B $advancedsettings.B + -Q $advancedsettings.Q + -q $advancedsettings.q + -m $advancedsettings.m + -T $advancedsettings.T + -X $advancedsettings.X + -P $advancedsettings.P + -o $advancedsettings.o + -O $advancedsettings.O + -V $advancedsettings.V + + ## CONSTRUCT VCF TABLE + -c 1 -S 2 -E 3 -g 4 + + ## REGION SPECIFICATION (ENTIRE CHROMOSOMES) + regions.bed + + ## POSTPROCESSING + | \$VARDICTJAVA_ROOT_DIR/VarDict/testsomatic.R + | \$VARDICTJAVA_ROOT_DIR/VarDict/var2vcf_somatic.pl + -f $advancedsettings.f + + > $all_variants; + + ## Filter for PASS variants + awk 'BEGIN {FS=OFS="\t"} substr(\$0, 1, 1) == "#" {print \$0; next} \$7 == "PASS" {print \$0}' $all_variants > $passed_variants + ]]></command> + + <inputs> + <conditional name="reference_source"> + <param name="reference_source_selector" type="select" label="Choose the source for the reference genome file"> + <option value="cached" selected="True">Use a built-in genome</option> + <option value="history">Use a genome from the history</option> + </param> + <when value="cached"> + <param name="ref_file" type="select" label="Reference Genome File"> + <options from_data_table="fasta_indexes"/> + </param> + </when> + <when value="history"> + <param name="ref_file" format="fasta" type="data" label="Reference Genome File" /> + </when> + </conditional> + + <param name="normal" type="data" format="bam" label="Normal Alignment File" /> + <param name="tumour" type="data" format="bam" label="Tumour Alignment File" /> + <param name="interval_file" type="data" format="txt" optional="true" label="Chromosomes" help="Restrict SNV calls to the following list of chromosomes (one per line)" /> + + <section name="advancedsettings" title="Advanced Settings" expanded="False"> + <param name="f" type="float" value="0.01" label="Minimum variant allele fraction" /> + <param name="k" type="integer" value="1" label="Set to 0 to disable local realignment" /> + <param name="r" type="integer" value="2" label="Minimum number of reads supporting the variant" /> + <param name="B" type="integer" value="2" label="Minimum number of reads for determining strand bias" /> + <param name="Q" type="integer" value="1" label="Minimum mapping quality for reads to be considered" /> + <param name="m" type="integer" value="8" label="Maximum number of mismatches before a read is no longer considered (gaps are not counted as mismatches)" /> + <param name="T" type="integer" value="0" label="Maximum number of bases considered from 5' end (default: 0, no trimming)" /> + <param name="X" type="integer" value="3" label="Maximum number of extended based after indel to look for mismatches" /> + <param name="P" type="integer" value="5" label="Maximum average read position for a variant to be considered." /> + <param name="q" type="integer" value="25" label="Minimum phred score for a base to be considered a good call" /> + <param name="o" type="float" value="1.5" label="Minimum quality ratio [(good_quality_reads)/(bad_quality_reads+0.5)] (based on definition of a good call; see previous option)" /> + <param name="O" type="float" value="0" label="Minimum average mapping quality" /> + <param name="V" type="float" value="0.05" label="Maximum allowed variant allele fraction in the normal sample" /> + </section> + </inputs> + + <outputs> + <data name="all_variants" format="vcf" label="VarDict SNVs and Indels (All)" /> + <data name="passed_variants" format="vcf" label="VarDict SNVs and Indels (Passed)" /> + </outputs> + + <help> + <![CDATA[ + https://github.com/AstraZeneca-NGS/VarDictJava + ]]> + </help> + + <citations> + <expand macro="morinlab_citation" /> + <expand macro="galaxy_citation" /> + <expand macro="vardict_citation" /> + </citations> +</tool>