Mercurial > repos > devteam > testing_cgatools
diff testing_cgatools-982e19c29ec0/cgatools/tools/cgatools_1.6/mkvcf.xml @ 0:ef23f9cd599b draft default tip
Uploaded
| author | devteam |
|---|---|
| date | Thu, 27 Sep 2012 13:37:59 -0400 |
| parents | |
| children |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/testing_cgatools-982e19c29ec0/cgatools/tools/cgatools_1.6/mkvcf.xml Thu Sep 27 13:37:59 2012 -0400 @@ -0,0 +1,1001 @@ +<tool id="cg_mkvcf" name="mkvcf(beta) 1.6" version="1.0.0"> +<!-- +This tool creates a GUI for the mkvcf function of cgatools from Complete Genomics, Inc. +written 7-31-2012 by bcrain@completegenomics.com +--> + + <description>converts to vcf</description> + + <command interpreter="perl"> + <!--run wrapper script--> + mkvcf_wrapper.pl + --reference $crr.fields.path + --output $output + --genomes $count.genomes + --source $count.sources.source + --datasource $count.sources.data_sources.data_source + #if $count.sources.data_sources.data_source=="in" + #for $m in $count.sources.data_sources.files + --input $m.input + #end for + #else + --input $count.sources.data_sources.input + #end if + #if $count.sources.source=="masterVar" or $count.sources.source=="masterVar,CNV" + $count.sources.nocalls + --calibration $count.sources.calibration + #else if $count.sources.source=="SV" + --jctscore $count.sources.jctscore + --jctside $count.sources.jctside + --jctdistance $count.sources.jctdistance + --jctlength $count.sources.jctlength + $count.sources.jctpriority + $count.sources.jcttumor + #else if $count.sources.source=="masterVar,CNV,SV" or $count.sources.source=="masterVar,CNV,SV,MEI" + $count.sources.nocalls + --calibration $count.sources.calibration + --jctscore $count.sources.jctscore + --jctside $count.sources.jctside + --jctdistance $count.sources.jctdistance + --jctlength $count.sources.jctlength + $count.sources.jctpriority + $count.sources.jcttumor + #end if + --fields $count.sources.fields + </command> + + <outputs> + <data format="vcf" name="output" label="${tool.name} output"/> + </outputs> + + <inputs> + <!--form field to select crr file--> + <param name="crr" type="select" label="Reference genome (.crr file)"> + <options from_data_table="cg_crr_files" /> + </param> + + <!--select number of genomes - determines which input sources to show--> + <conditional name="count"> + <param name="genomes" type="select" label="Select the number of genomes to add to the vcf file" help="Note: multi-genome vcfs (2 or more genomes) can only be generated for format version 2.0 and up"> + <option value="1" selected="true">1 - allowed data sources are masterVar, CNV, SV, MEI</option> + <option value="2">2 - allowed data sources are masterVar, CNV, SV (format v2.x)</option> + <option value="3">3 or more - allowed data sources are masterVar, CNV (format v2.x)</option> + </param> + + <when value="1"> + <!--form field to select input sources--> + <conditional name="sources"> + <param name="source" type="select" label="Data sources to be included for this genome"> + <option value="masterVar,CNV,SV,MEI" selected="true">masterVar + CNV + SV + MEI</option> + <option value="masterVar">masterVar</option> + <option value="CNV">CNV</option> + <option value="SV">SV</option> + <option value="MEI">MEI</option> + </param> + + <when value="masterVar,CNV,SV,MEI"> + <!--conditional to select inputs--> + <conditional name="data_sources"> + <param name="data_source" type="select" label="Where are the input files?"> + <option value="out" selected="true">located outside Galaxy (data on server or mounted drive)</option> + </param> + + <when value="out"> + <!--form field to enter input file--> + <param name="input" type="text" label="Genome root directory" size="200" help="Enter full path /path/dir (e.g. /harddrive/GS00000XXXX-DID/GS00000YYYY-ASM/GS00123-DNA_G01)."> + <validator type="empty_field" message="You must supply the genome root directory"/> + </param> + </when> + </conditional> + + <!--form field to select no-calls--> + <param name="nocalls" type="select" label="Include no-calls?"> + <option value="" selected="true">no</option> + <option value="--nocalls">yes</option> + </param> + + <!--form field to enter calibration directory--> + <param name="calibration" type="text" size="300" label="Directory calibration data (/path/calibration-root)" help="The directory containing calibration data. For example, there should exist a file calibration-root/0.0.0/metrics.tsv. Calibration data can be downloaded from ftp://ftp.completegenomics.com/ScoreCalibrationFiles/var-calibration-v2.tgz"/> + + <!--form fields junction threshold options--> + <param name="jctscore" type="integer" value="10" label="Junction score thresholds (discordant mate pair count) (default 10)"> + <validator type="empty_field" message="You must enter a value, for the default value enter 10" /> + </param> + <param name="jctside" type="integer" value="70" label="Junction side length threshold (default 70)"> + <validator type="empty_field" message="You must enter a value, for the default value enter 70" /> + </param> + <param name="jctdistance" type="integer" value="200" label="Distance tolerance for junction compatibility (default 200)"> + <validator type="empty_field" message="You must enter a value, for the default value enter 200" /> + </param> + <param name="jctlength" type="integer" value="500" label="Length threshold for compatible junctions (default 500)"> + <validator type="empty_field" message="You must enter a value, for the default value enter 500" /> + </param> + + <!--form field to select junction confidence in tumors--> + <param name="jctpriority" type="select" label="Use normal junction priority for vcf output?"> + <option value="" selected="true">no</option> + <option value="--jctpriority">yes</option> + </param> + + <!--form field to select junction confidence in tumors--> + <param name="jcttumor" type="select" label="Use high confidence junctions for tumors?"> + <option value="" selected="true">no</option> + <option value="--jcttumor">yes</option> + </param> + + <!--form field to select field names to include in vcf--> + <param name="fields" type="select" label="Field names to be included in vcf file" multiple="true" help="Select all field names (default) or a collection of individual field names."> + <option value="all" selected="true">-- all (default) --</option> + <option value="NS">NS - Number of samples</option> + <option value="AN">AN - Total number of alleles in called genotypes</option> + <option value="AC">AC - Allele count in genotypes</option> + <option value="CGA_XR">CGA_XR - External database reference</option> + <option value="CGA_FI">CGA_FI - Functional impact</option> + <option value="CGA_PFAM">CGA_PFAM - PFAM domain </option> + <option value="CGA_MIRB">CGA_MIRB - miRBaseId</option> + <option value="CGA_SDO">CGA_SDO - Depth of overlapping segmental duplications</option> + <option value="CGA_RPT">CGA_RPT - Overlapping repeatMasker annotations</option> + <option value="GT">GT - Genotype</option> + <option value="PS">PS - Phase set</option> + <option value="FT">FT - Sample genotype filters</option> + <option value="GL">GL - Genotype likelihoods</option> + <option value="CGA_CEHQ">CGA_CEHQ - Calibrated haplotype quality based on EAF assumption</option> + <option value="CGA_CEGL">CGA_CEGL - Genotype likelihoods based on CEHQ</option> + <option value="SS">SS - Somatic status</option> + <option value="HQ">HQ - Haplotype quality</option> + <option value="EHQ">EHQ - Haplotype quality based on EAF assumption</option> + <option value="GQ">GQ - Genotype quality</option> + <option value="DP">DP - Total read depth</option> + <option value="AD">AD - Allelic depths</option> + <option value="CGA_RDP">CGA_RDP - Read depth in reference</option> + <option value="CGA_ODP">CGA_ODP - Other total read depth: somatic comparison</option> + <option value="CGA_OAD">CGA_OAD - Other allelic depths: somatic comparison</option> + <option value="CGA_ORDP">CGA_ORDP - Other reference depth: somatic comparison </option> + <option value="CGA_SOMC">CGA_SOMC - Somatic Category</option> + <option value="CGA_SOMR">CGA_SOMR - Somatic Rank</option> + <option value="CGA_SOMS">CGA_SOMS - Somatic Score</option> + <option value="CGA_GP">CGA_GP - Normalized mean GC corrected coverage</option> + <option value="CGA_NP">CGA_NP - Normalized mean coverage for 2k window</option> + <option value="CGA_CP">CGA_CP - Diploid-model ploidy call for segment including this interval</option> + <option value="CGA_PS">CGA_PS - Diploid-model called ploidy score</option> + <option value="CGA_CT">CGA_CT - Diploid-model CNV type</option> + <option value="CGA_TS">CGA_TS - Diploid-model CNV type score</option> + <option value="CGA_CL">CGA_CL - Nondiploid-model called level</option> + <option value="CGA_LS">CGA_LS - Nondiploid-model called level score</option> + <option value="CGA_SCL">CGA_SCL - Nondiploid-model somatic called level</option> + <option value="CGA_SLS">CGA_SLS - Non-diploid-model somatic called level score</option> + <option value="CGA_LAF">CGA_LAF - Lesser Allele Fraction estimate, 100k window</option> + <option value="CGA_LLAF">CGA_LLAF - Lesser Allele Fraction lower bound, 100k window</option> + <option value="CGA_ULAF">CGA_ULAF - Lesser Allele Fraction upper bound, 100k window</option> + <option value="SVTYPE">SVTYPE - Type of structural variation</option> + <option value="CGA_BF">CGA_BF - Frequency in set of baseline genomes</option> + <option value="CGA_MEDEL">CGA_MEDEL - Mobile element deletion</option> + <option value="MATEID">MATEID - ID of mate breakend</option> + <option value="CGA_BNDG">CGA_BNDG - Transcript name and strand of genes containing breakend</option> + <option value="CGA_BNDGO">CGA_BNDGO - Transcript name and strand of genes containing mate breakend</option> + <option value="CGA_BNDP">CGA_BNDP - Precision of breakend</option> + <option value="CGA_BNDMPC">CGA_BNDMPC - Mate pair count supporting a breakend</option> + <option value="CGA_BNDPOS">CGA_BNDPOS - Position of breakend as detected in individual genome</option> + <option value="CGA_BNDDEF">CGA_BNDDEF - Breakend definition in individual genome</option> + <option value="CGA_IS">CGA_IS - Measure of confidence that there is a mobile element insertion</option> + <option value="CGA_IDC">CGA_IDC - Count of paired ends consistently indicating a mobile element insertion</option> + <option value="CGA_IDCL">CGA_IDCL - Count of paired ends indicating a mobile element insertion anchored 5'</option> + <option value="CGA_IDCR">CGA_IDCR - Count of paired ends indicating a mobile element insertion anchored 3'</option> + <option value="CGA_RDC">CGA_RDC - Count of paired ends supporting the presence of a reference allele</option> + <option value="CGA_NBET">CGA_NBET - Next-best estimate of type of MEI</option> + <option value="CGA_ETS">CGA_ETS - Measure of confidence that the ElementType (MEINFO:NAME) is correct</option> + <option value="CGA_KES">CGA_KES - Fraction of known MEI with at least as good an InsertionScore</option> + </param> + </when> + + <when value="masterVar"> + <!--conditional to select inputs--> + <conditional name="data_sources"> + <param name="data_source" type="select" label="Where is the input file?"> + <option value="in" selected="true">imported into Galaxy</option> + <option value="out">located outside Galaxy (data on server or mounted drive)</option> + </param> + + <when value="in"> + <!--form field to select mastervar files--> + <repeat name="files" title="MasterVar file" min="1" max="1"> + <param name="input" type="data" format="cg_mastervar" label="Dataset"> + <validator type="dataset_ok_validator" /> + <validator type="dataset_metadata_in_file" filename="cg_crr_files.loc" + metadata_name="dbkey" metadata_column="1" + message="cgatools is not currently available for this build."/> + </param> + </repeat> + </when> + + <when value="out"> + <!--form field to enter input file--> + <param name="input" type="text" label="Genome root directory or masterVar file" size="200" help="Enter full path /path/dir (e.g. /harddrive/GS00000XXXX-DID/GS00000YYYY-ASM/GS00123-DNA_G01), or /path/masterVarfile (e.g. /harddrive/GS00000XXXX-DID/GS00000YYYY-ASM/GS00123-DNA_G01/ASM/masterVarBeta-GS00000YYYY-ASM.tsv.bz2)."> + <validator type="empty_field" message="You must supply the genome root directory or masterVar file"/> + </param> + </when> + </conditional> + + <!--form field to select no-calls--> + <param name="nocalls" type="select" label="Include no-calls?"> + <option value="" selected="true">no</option> + <option value="--nocalls">yes</option> + </param> + + <!--form field to enter calibration directory--> + <param name="calibration" type="text" size="300" label="Directory calibration data (/path/calibration-root)" help="The directory containing calibration data. For example, there should exist a file calibration-root/0.0.0/metrics.tsv. Calibration data can be downloaded from ftp://ftp.completegenomics.com/ScoreCalibrationFiles/var-calibration-v2.tgz"/> + + <!--form field to select field names to include in vcf--> + <param name="fields" type="select" label="Field names to be included in vcf file" multiple="true" help="Select all field names (default) or a collection of individual field names."> + <option value="all" selected="true">-- all (default) --</option> + <option value="NS">NS - Number of samples</option> + <option value="AN">AN - Total number of alleles in called genotypes</option> + <option value="AC">AC - Allele count in genotypes</option> + <option value="CGA_XR">CGA_XR - External database reference</option> + <option value="CGA_FI">CGA_FI - Functional impact</option> + <option value="CGA_PFAM">CGA_PFAM - PFAM domain </option> + <option value="CGA_MIRB">CGA_MIRB - miRBaseId</option> + <option value="CGA_SDO">CGA_SDO - Depth of overlapping segmental duplications</option> + <option value="CGA_RPT">CGA_RPT - Overlapping repeatMasker annotations</option> + <option value="GT">GT - Genotype</option> + <option value="PS">PS - Phase set</option> + <option value="FT">FT - Sample genotype filters</option> + <option value="GL">GL - Genotype likelihoods</option> + <option value="CGA_CEHQ">CGA_CEHQ - Calibrated haplotype quality based on EAF assumption</option> + <option value="CGA_CEGL">CGA_CEGL - Genotype likelihoods based on CEHQ</option> + <option value="SS">SS - Somatic status</option> + <option value="HQ">HQ - Haplotype quality</option> + <option value="EHQ">EHQ - Haplotype quality based on EAF assumption</option> + <option value="GQ">GQ - Genotype quality</option> + <option value="DP">DP - Total read depth</option> + <option value="AD">AD - Allelic depths</option> + <option value="CGA_RDP">CGA_RDP - Read depth in reference</option> + <option value="CGA_ODP">CGA_ODP - Other total read depth: somatic comparison</option> + <option value="CGA_OAD">CGA_OAD - Other allelic depths: somatic comparison</option> + <option value="CGA_ORDP">CGA_ORDP - Other reference depth: somatic comparison </option> + <option value="CGA_SOMC">CGA_SOMC - Somatic Category</option> + <option value="CGA_SOMR">CGA_SOMR - Somatic Rank</option> + <option value="CGA_SOMS">CGA_SOMS - Somatic Score</option> + </param> + </when> + + <when value="CNV"> + <!--conditional to select inputs--> + <conditional name="data_sources"> + <param name="data_source" type="select" label="Where are the input files?"> + <option value="out" selected="true">located outside Galaxy (data on server or mounted drive)</option> + </param> + + <when value="out"> + <!--form field to enter input file--> + <param name="input" type="text" label="Genome root directory" size="200" help="Enter full path /path/dir (e.g. /harddrive/GS00000XXXX-DID/GS00000YYYY-ASM/GS00123-DNA_G01)."> + <validator type="empty_field" message="You must supply the genome root directory"/> + </param> + </when> + </conditional> + + <!--form field to select field names to include in vcf--> + <param name="fields" type="select" label="Field names to be included in vcf file" multiple="true" help="Select all field names (default) or a collection of individual field names."> + <option value="all" selected="true">-- all (default) --</option> + <option value="GT">GT - Genotype</option> + <option value="CGA_GP">CGA_GP - Normalized mean GC corrected coverage</option> + <option value="CGA_NP">CGA_NP - Normalized mean coverage for 2k window</option> + <option value="CGA_CP">CGA_CP - Diploid-model ploidy call for segment</option> + <option value="CGA_PS">CGA_PS - Diploid-model called ploidy score</option> + <option value="CGA_CT">CGA_CT - Diploid-model CNV type</option> + <option value="CGA_TS">CGA_TS - Diploid-model CNV type score</option> + <option value="CGA_CL">CGA_CL - Nondiploid-model called level</option> + <option value="CGA_LS">CGA_LS - Nondiploid-model called level score</option> + <option value="CGA_SCL">CGA_SCL - Nondiploid-model somatic called level</option> + <option value="CGA_SLS">CGA_SLS - Non-diploid-model somatic called level score</option> + <option value="CGA_LAF">CGA_LAF - Lesser Allele Fraction estimate, 100k window</option> + <option value="CGA_LLAF">CGA_LLAF - Lesser Allele Fraction lower bound, 100k window</option> + <option value="CGA_ULAF">CGA_ULAF - Lesser Allele Fraction upper bound, 100k window</option> + </param> + </when> + + <when value="SV"> + <!--conditional to select inputs--> + <conditional name="data_sources"> + <param name="data_source" type="select" label="Where are the input files?"> + <option value="in" selected="true">imported into Galaxy</option> + <option value="out">located outside Galaxy (data on server or mounted drive)</option> + </param> + + <when value="in"> + <!--form field to select SV file--> + <repeat name="files" title="SV file" min="1" max="1"> + <param name="input" type="data" format="tabular" label="Dataset"> + <validator type="dataset_ok_validator" /> + <validator type="dataset_metadata_in_file" filename="cg_crr_files.loc" + metadata_name="dbkey" metadata_column="1" + message="cgatools is not currently available for this build."/> + </param> + </repeat> + </when> + + <when value="out"> + <!--form field to enter input file--> + <param name="input" type="text" label="Genome root directory or SV file" size="200" help="Enter full path /path/dir (e.g. /harddrive/GS00000XXXX-DID/GS00000YYYY-ASM/GS00123-DNA_G01), or /path/SVfile (e.g. /harddrive/GS00000XXXX-DID/GS00000YYYY-ASM/GS00123-DNA_G01/ASM/SV/allJunctionsBeta-GS00000YYYY-ASM.tsv)."> + <validator type="empty_field" message="You must supply the genome root directory or SV file"/> + </param> + </when> + </conditional> + + <!--form fields junction threshold options--> + <param name="jctscore" type="integer" value="10" label="Junction score thresholds (discordant mate pair count) (default 10)"> + <validator type="empty_field" message="You must enter a value, for the default value enter 10" /> + </param> + <param name="jctside" type="integer" value="70" label="Junction side length threshold (default 70)"> + <validator type="empty_field" message="You must enter a value, for the default value enter 70" /> + </param> + <param name="jctdistance" type="integer" value="200" label="Distance tolerance for junction compatibility (default 200)"> + <validator type="empty_field" message="You must enter a value, for the default value enter 200" /> + </param> + <param name="jctlength" type="integer" value="500" label="Length threshold for compatible junctions (default 500)"> + <validator type="empty_field" message="You must enter a value, for the default value enter 500" /> + </param> + + <!--form field to select junction confidence in tumors--> + <param name="jctpriority" type="select" label="Use normal junction priority for vcf output?"> + <option value="" selected="true">no</option> + <option value="--jctpriority">yes</option> + </param> + + <!--form field to select junction confidence in tumors--> + <param name="jcttumor" type="select" label="Use high confidence junctions for tumors?"> + <option value="" selected="true">no</option> + <option value="--jcttumor">yes</option> + </param> + + <!--form field to select field names to include in vcf--> + <param name="fields" type="select" label="Field names to be included in vcf file" multiple="true" help="Select all field names (default) or a collection of individual field names."> + <option value="all" selected="true">-- all (default) --</option> + <option value="GT">GT - Genotype</option> + <option value="FT">FT - Sample genotype filters</option> + <option value="NS">NS - Number of samples</option> + <option value="CGA_XR">CGA_XR - External database reference</option> + <option value="SVTYPE">SVTYPE - Type of structural variation</option> + <option value="CGA_BF">CGA_BF - Frequency in set of baseline genomes</option> + <option value="CGA_MEDEL">CGA_MEDEL - Mobile element deletion</option> + <option value="MATEID">MATEID - ID of mate breakend</option> + <option value="CGA_BNDG">CGA_BNDG - Transcript name and strand of genes containing breakend</option> + <option value="CGA_BNDGO">CGA_BNDGO - Transcript name and strand of genes containing mate breakend</option> + <option value="CGA_BNDP">CGA_BNDP - Precision of breakend</option> + <option value="CGA_BNDMPC">CGA_BNDMPC - Mate pair count supporting a breakend</option> + <option value="CGA_BNDPOS">CGA_BNDPOS - Position of breakend as detected in individual genome</option> + <option value="CGA_BNDDEF">CGA_BNDDEF - Breakend definition in individual genome</option> + </param> + </when> + + <when value="MEI"> + <!--conditional to select inputs--> + <conditional name="data_sources"> + <param name="data_source" type="select" label="Where are the input files?"> + <option value="out" selected="true">located outside Galaxy</option> + </param> + + <when value="out"> + <!--form field to select outside list of genome directories or mastervar files--> + <param name="input" type="text" label="Genome root directory" size="200" help="Enter full path /path/dir (e.g. /harddrive/GS00000XXXX-DID/GS00000YYYY-ASM/GS00123-DNA_G01)."> + <validator type="empty_field" message="You must supply the genome root directory"/> + </param> + </when> + </conditional> + + <!--form field to select field names to include in vcf--> + <param name="fields" type="select" label="Field names to be included in vcf file" multiple="true" help="Select all field names (default) or a collection of individual field names."> + <option value="all" selected="true">-- all (default) --</option> + <option value="GT">GT - Genotype</option> + <option value="FT">FT - Sample genotype filters</option> + <option value="CGA_IS">CGA_IS - Measure of confidence that there is a mobile element insertion</option> + <option value="CGA_IDC">CGA_IDC - Count of paired ends consistently indicating a mobile element insertion</option> + <option value="CGA_IDCL">CGA_IDCL - Count of paired ends indicating a mobile element insertion, anchored 5'</option> + <option value="CGA_IDCR">CGA_IDCR - Count of paired ends indicating a mobile element insertion, anchored 3'</option> + <option value="CGA_RDC">CGA_RDC - Count of paired ends supporting the presence of a reference allele</option> + <option value="CGA_NBET">CGA_NBET - Next-best estimate of type of MEI</option> + <option value="CGA_ETS">CGA_ETS - Measure of confidence that the ElementType (MEINFO:NAME) is correct</option> + <option value="CGA_KES">CGA_KES - Fraction of known MEI with at least as good an InsertionScore</option> + </param> + </when> + + </conditional> + </when> + + <when value="2"> + <!--form field to select input sources--> + <conditional name="sources"> + <param name="source" type="select" label="Data sources to be included for each genome"> + <option value="masterVar,CNV,SV" selected="true">masterVar + CNV + SV</option> + <option value="masterVar">masterVar</option> + <option value="CNV">CNV</option> + <option value="SV">SV</option> + </param> + + <when value="masterVar,CNV,SV"> + <!--conditional to select inputs--> + <conditional name="data_sources"> + <param name="data_source" type="select" label="Where are the input files?"> + <option value="out" selected="true">located outside Galaxy (data on server or mounted drive)</option> + </param> + + <when value="out"> + <!--form field to enter input file--> + <param name="input" type="text" label="File with list of genome root directories" size="200" help="Enter file name with full path (/path/file). This file should contain a list of genome root directory names, one per line in the format /path/dir (e.g. /harddrive/GS00000XXXX-DID/GS00000YYYY-ASM/GS00123-DNA_G01). For normal/tumor comparisons list the baseline genome first."> + <validator type="empty_field" message="You must supply the list of genome root directories"/> + </param> + </when> + </conditional> + + <!--form field to select no-calls--> + <param name="nocalls" type="select" label="Include no-calls?"> + <option value="" selected="true">no</option> + <option value="--nocalls">yes</option> + </param> + + <!--form field to enter calibration directory--> + <param name="calibration" type="text" size="300" label="Directory calibration data (/path/calibration-root)" help="The directory containing calibration data. For example, there should exist a file calibration-root/0.0.0/metrics.tsv. Calibration data can be downloaded from ftp://ftp.completegenomics.com/ScoreCalibrationFiles/var-calibration-v2.tgz"/> + + <!--form fields junction threshold options--> + <param name="jctscore" type="integer" value="10" label="Junction score thresholds (discordant mate pair count) (default 10)"> + <validator type="empty_field" message="You must enter a value, for the default value enter 10" /> + </param> + <param name="jctside" type="integer" value="70" label="Junction side length threshold (default 70)"> + <validator type="empty_field" message="You must enter a value, for the default value enter 70" /> + </param> + <param name="jctdistance" type="integer" value="200" label="Distance tolerance for junction compatibility (default 200)"> + <validator type="empty_field" message="You must enter a value, for the default value enter 200" /> + </param> + <param name="jctlength" type="integer" value="500" label="Length threshold for compatible junctions (default 500)"> + <validator type="empty_field" message="You must enter a value, for the default value enter 500" /> + </param> + + <!--form field to select junction confidence in tumors--> + <param name="jctpriority" type="select" label="Use normal junction priority for vcf output?"> + <option value="" selected="true">no</option> + <option value="--jctpriority">yes</option> + </param> + + <!--form field to select junction confidence in tumors--> + <param name="jcttumor" type="select" label="Use high confidence junctions for tumors?"> + <option value="" selected="true">no</option> + <option value="--jcttumor">yes</option> + </param> + + <!--form field to select field names to include in vcf--> + <param name="fields" type="select" label="Field names to be included in vcf file" multiple="true" help="Select all field names (default) or a collection of individual field names."> + <option value="all" selected="true">-- all (default) --</option> + <option value="NS">NS - Number of samples</option> + <option value="AN">AN - Total number of alleles in called genotypes</option> + <option value="AC">AC - Allele count in genotypes</option> + <option value="CGA_XR">CGA_XR - External database reference</option> + <option value="CGA_FI">CGA_FI - Functional impact</option> + <option value="CGA_PFAM">CGA_PFAM - PFAM domain </option> + <option value="CGA_MIRB">CGA_MIRB - miRBaseId</option> + <option value="CGA_SDO">CGA_SDO - Depth of overlapping segmental duplications</option> + <option value="CGA_RPT">CGA_RPT - Overlapping repeatMasker annotations</option> + <option value="GT">GT - Genotype</option> + <option value="PS">PS - Phase set</option> + <option value="FT">FT - Sample genotype filters</option> + <option value="GL">GL - Genotype likelihoods</option> + <option value="CGA_CEHQ">CGA_CEHQ - Calibrated haplotype quality based on EAF assumption</option> + <option value="CGA_CEGL">CGA_CEGL - Genotype likelihoods based on CEHQ</option> + <option value="SS">SS - Somatic status</option> + <option value="HQ">HQ - Haplotype quality</option> + <option value="EHQ">EHQ - Haplotype quality based on EAF assumption</option> + <option value="GQ">GQ - Genotype quality</option> + <option value="DP">DP - Total read depth</option> + <option value="AD">AD - Allelic depths</option> + <option value="CGA_RDP">CGA_RDP - Read depth in reference</option> + <option value="CGA_ODP">CGA_ODP - Other total read depth: somatic comparison</option> + <option value="CGA_OAD">CGA_OAD - Other allelic depths: somatic comparison</option> + <option value="CGA_ORDP">CGA_ORDP - Other reference depth: somatic comparison </option> + <option value="CGA_SOMC">CGA_SOMC - Somatic Category</option> + <option value="CGA_SOMR">CGA_SOMR - Somatic Rank</option> + <option value="CGA_SOMS">CGA_SOMS - Somatic Score</option> + <option value="CGA_GP">CGA_GP - Normalized mean GC corrected coverage</option> + <option value="CGA_NP">CGA_NP - Normalized mean coverage for 2k window</option> + <option value="CGA_CP">CGA_CP - Diploid-model ploidy call for segment</option> + <option value="CGA_PS">CGA_PS - Diploid-model called ploidy score</option> + <option value="CGA_CT">CGA_CT - Diploid-model CNV type</option> + <option value="CGA_TS">CGA_TS - Diploid-model CNV type score</option> + <option value="CGA_CL">CGA_CL - Nondiploid-model called level</option> + <option value="CGA_LS">CGA_LS - Nondiploid-model called level score</option> + <option value="CGA_SCL">CGA_SCL - Nondiploid-model somatic called level</option> + <option value="CGA_SLS">CGA_SLS - Non-diploid-model somatic called level score</option> + <option value="CGA_LAF">CGA_LAF - Lesser Allele Fraction estimate, 100k window</option> + <option value="CGA_LLAF">CGA_LLAF - Lesser Allele Fraction lower bound, 100k window</option> + <option value="CGA_ULAF">CGA_ULAF - Lesser Allele Fraction upper bound, 100k window</option> + <option value="SVTYPE">SVTYPE - Type of structural variation</option> + <option value="CGA_BF">CGA_BF - Frequency in set of baseline genomes</option> + <option value="CGA_MEDEL">CGA_MEDEL - Mobile element deletion</option> + <option value="MATEID">MATEID - ID of mate breakend</option> + <option value="CGA_BNDG">CGA_BNDG - Transcript name and strand of genes containing breakend</option> + <option value="CGA_BNDGO">CGA_BNDGO - Transcript name and strand of genes containing mate breakend</option> + <option value="CGA_BNDP">CGA_BNDP - Precision of breakend</option> + <option value="CGA_BNDMPC">CGA_BNDMPC - Mate pair count supporting a breakend</option> + <option value="CGA_BNDPOS">CGA_BNDPOS - Position of breakend as detected in individual genome</option> + <option value="CGA_BNDDEF">CGA_BNDDEF - Breakend definition in individual genome</option> + </param> + </when> + + <when value="masterVar"> + <!--conditional to select inputs--> + <conditional name="data_sources"> + <param name="data_source" type="select" label="Where are the input files?"> + <option value="in" selected="true">imported into Galaxy</option> + <option value="out">located outside Galaxy (data on server or mounted drive)</option> + </param> + + <when value="in"> + <!--form field to select input files--> + <repeat name="files" title="MasterVar file" min="1" max="2"> + <param name="input" type="data" format="cg_mastervar" label="Dataset"> + <validator type="dataset_ok_validator"/> + <validator type="dataset_metadata_in_file" filename="cg_crr_files.loc" + metadata_name="dbkey" metadata_column="1" + message="cgatools is not currently available for this build."/> + </param> + </repeat> + </when> + + <when value="out"> + <!--form field to enter input file--> + <param name="input" type="text" label="File with list of genome root directories or masterVar files" size="200" help="Enter file name with full path (/path/file). This file should contain a list of genome root directory names, one per line in the format /path/dir (e.g. /harddrive/GS00000XXXX-DID/GS00000YYYY-ASM/GS00123-DNA_G01), or a list of masterVar files, one per line in the format /path/masterVarfile (e.g. /harddrive/GS00000XXXX-DID/GS00000YYYY-ASM/GS00123-DNA_G01/ASM/masterVarBeta-GS00000YYYY-ASM.tsv.bz2)."> + <validator type="empty_field" message="You must supply the list of genome root directories or masterVar files"/> + </param> + </when> + </conditional> + + <!--form field to select no-calls--> + <param name="nocalls" type="select" label="Include no-calls?"> + <option value="" selected="true">no</option> + <option value="--nocalls">yes</option> + </param> + + <!--form field to enter calibration directory--> + <param name="calibration" type="text" size="300" label="Directory calibration data (/path/calibration-root)" help="The directory containing calibration data. For example, there should exist a file calibration-root/0.0.0/metrics.tsv. Calibration data can be downloaded from ftp://ftp.completegenomics.com/ScoreCalibrationFiles/var-calibration-v2.tgz"/> + + <!--form field to select field names to include in vcf--> + <param name="fields" type="select" label="Field names to be included in vcf file" multiple="true" help="Select all field names (default) or a collection of individual field names."> + <option value="all" selected="true">-- all (default) --</option> + <option value="NS">NS - Number of samples</option> + <option value="AN">AN - Total number of alleles in called genotypes</option> + <option value="AC">AC - Allele count in genotypes</option> + <option value="CGA_XR">CGA_XR - External database reference</option> + <option value="CGA_FI">CGA_FI - Functional impact</option> + <option value="CGA_PFAM">CGA_PFAM - PFAM domain </option> + <option value="CGA_MIRB">CGA_MIRB - miRBaseId</option> + <option value="CGA_SDO">CGA_SDO - Depth of overlapping segmental duplications</option> + <option value="CGA_RPT">CGA_RPT - Overlapping repeatMasker annotations</option> + <option value="GT">GT - Genotype</option> + <option value="PS">PS - Phase set</option> + <option value="FT">FT - Sample genotype filters</option> + <option value="GL">GL - Genotype likelihoods</option> + <option value="CGA_CEHQ">CGA_CEHQ - Calibrated haplotype quality based on EAF assumption</option> + <option value="CGA_CEGL">CGA_CEGL - Genotype likelihoods based on CEHQ</option> + <option value="SS">SS - Somatic status</option> + <option value="HQ">HQ - Haplotype quality</option> + <option value="EHQ">EHQ - Haplotype quality based on EAF assumption</option> + <option value="GQ">GQ - Genotype quality</option> + <option value="DP">DP - Total read depth</option> + <option value="AD">AD - Allelic depths</option> + <option value="CGA_RDP">CGA_RDP - Read depth in reference</option> + <option value="CGA_ODP">CGA_ODP - Other total read depth: somatic comparison</option> + <option value="CGA_OAD">CGA_OAD - Other allelic depths: somatic comparison</option> + <option value="CGA_ORDP">CGA_ORDP - Other reference depth: somatic comparison </option> + <option value="CGA_SOMC">CGA_SOMC - Somatic Category</option> + <option value="CGA_SOMR">CGA_SOMR - Somatic Rank</option> + <option value="CGA_SOMS">CGA_SOMS - Somatic Score</option> + </param> + </when> + + <when value="CNV"> + <!--conditional to select inputs--> + <conditional name="data_sources"> + <param name="data_source" type="select" label="Where are the input files?"> + <option value="out" selected="true">located outside Galaxy (data on server or mounted drive)</option> + </param> + + <when value="out"> + <!--form field to enter input file--> + <param name="input" type="text" label="File with list of genome root directories" size="200" help="Enter file name with full path (/path/file). This file should contain a list of genome root directory names, one per line in the format /path/dir (e.g. /harddrive/GS00000XXXX-DID/GS00000YYYY-ASM/GS00123-DNA_G01)."> + <validator type="empty_field" message="You must supply the list of genome root directories"/> + </param> + </when> + </conditional> + + <!--form field to select field names to include in vcf--> + <param name="fields" type="select" label="Field names to be included in vcf file" multiple="true" help="Select all field names (default) or a collection of individual field names."> + <option value="all" selected="true">-- all (default) --</option> + <option value="GT">GT - Genotype</option> + <option value="CGA_GP">CGA_GP - Normalized mean GC corrected coverage</option> + <option value="CGA_NP">CGA_NP - Normalized mean coverage for 2k window</option> + <option value="CGA_CP">CGA_CP - Diploid-model ploidy call for segment</option> + <option value="CGA_PS">CGA_PS - Diploid-model called ploidy score</option> + <option value="CGA_CT">CGA_CT - Diploid-model CNV type</option> + <option value="CGA_TS">CGA_TS - Diploid-model CNV type score</option> + <option value="CGA_CL">CGA_CL - Nondiploid-model called level</option> + <option value="CGA_LS">CGA_LS - Nondiploid-model called level score</option> + <option value="CGA_SCL">CGA_SCL - Nondiploid-model somatic called level</option> + <option value="CGA_SLS">CGA_SLS - Non-diploid-model somatic called level score</option> + <option value="CGA_LAF">CGA_LAF - Lesser Allele Fraction estimate, 100k window</option> + <option value="CGA_LLAF">CGA_LLAF - Lesser Allele Fraction lower bound, 100k window</option> + <option value="CGA_ULAF">CGA_ULAF - Lesser Allele Fraction upper bound, 100k window</option> + </param> + </when> + + <when value="SV"> + <!--conditional to select inputs--> + <conditional name="data_sources"> + <param name="data_source" type="select" label="Where are the input files?"> + <option value="in" selected="true">imported into Galaxy</option> + <option value="out">located outside Galaxy (data on server or mounted drive)</option> + </param> + + <when value="in"> + <!--form field to select mastervar files--> + <repeat name="files" title="SV files" min="1" max="2"> + <param name="input" type="data" format="tabular" label="Dataset"> + <validator type="dataset_ok_validator" /> + <validator type="dataset_metadata_in_file" filename="cg_crr_files.loc" + metadata_name="dbkey" metadata_column="1" + message="cgatools is not currently available for this build."/> + </param> + </repeat> + </when> + + <when value="out"> + <!--form field to enter input file--> + <param name="input" type="text" label="File with list of genome root directories or SV files" size="200" help="Enter file name with full path (/path/file). This file should contain a list of genome root directory names, one per line in the format /path/dir (e.g. /harddrive/GS00000XXXX-DID/GS00000YYYY-ASM/GS00123-DNA_G01), or a list of SV files, one per line in the format /path/SVfile (e.g. /harddrive/GS00000XXXX-DID/GS00000YYYY-ASM/GS00123-DNA_G01/ASM/SV/allJunctionsBeta-GS00000YYYY-ASM.tsv)."> + <validator type="empty_field" message="You must supply the list of genome root directories or SV files"/> + </param> + </when> + </conditional> + + <!--form fields junction threshold options--> + <param name="jctscore" type="integer" value="10" label="Junction score thresholds (discordant mate pair count) (default 10)"> + <validator type="empty_field" message="You must enter a value, for the default value enter 10" /> + </param> + <param name="jctside" type="integer" value="70" label="Junction side length threshold (default 70)"> + <validator type="empty_field" message="You must enter a value, for the default value enter 70" /> + </param> + <param name="jctdistance" type="integer" value="200" label="Distance tolerance for junction compatibility (default 200)"> + <validator type="empty_field" message="You must enter a value, for the default value enter 200" /> + </param> + <param name="jctlength" type="integer" value="500" label="Length threshold for compatible junctions (default 500)"> + <validator type="empty_field" message="You must enter a value, for the default value enter 500" /> + </param> + + <!--form field to select junction confidence in tumors--> + <param name="jctpriority" type="select" label="Use normal junction priority for vcf output?"> + <option value="" selected="true">no</option> + <option value="--jctpriority">yes</option> + </param> + + <!--form field to select junction confidence in tumors--> + <param name="jcttumor" type="select" label="Use high confidence junctions for tumors?"> + <option value="" selected="true">no</option> + <option value="--jcttumor">yes</option> + </param> + + <!--form field to select field names to include in vcf--> + <param name="fields" type="select" label="Field names to be included in vcf file" multiple="true" help="Select all field names (default) or a collection of individual field names."> + <option value="all" selected="true">-- all (default) --</option> + <option value="GT">GT - Genotype</option> + <option value="FT">FT - Sample genotype filters</option> + <option value="SVTYPE">SVTYPE - Type of structural variation</option> + <option value="CGA_BF">CGA_BF - Frequency in set of baseline genomes</option> + <option value="CGA_MEDEL">CGA_MEDEL - Mobile element deletion</option> + <option value="MATEID">MATEID - ID of mate breakend</option> + <option value="CGA_BNDG">CGA_BNDG - Transcript name and strand of genes containing breakend</option> + <option value="CGA_BNDGO">CGA_BNDGO - Transcript name and strand of genes containing mate breakend</option> + <option value="CGA_BNDP">CGA_BNDP - Precision of breakend</option> + <option value="CGA_BNDMPC">CGA_BNDMPC - Mate pair count supporting a breakend</option> + <option value="CGA_BNDPOS">CGA_BNDPOS - Position of breakend as detected in individual genome</option> + <option value="CGA_BNDDEF">CGA_BNDDEF - Breakend definition in individual genome</option> + </param> + </when> + </conditional> + </when> + + <when value="3"> + <!--form field to select input sources--> + <conditional name="sources"> + <param name="source" type="select" label="Data sources to be included for each genome"> + <option value="masterVar,CNV" selected="true">masterVar + CNV</option> + <option value="masterVar">masterVar</option> + <option value="CNV">CNV</option> + </param> + + <when value="masterVar,CNV"> + <!--conditional to select inputs--> + <conditional name="data_sources"> + <param name="data_source" type="select" label="Where are the input files?"> + <option value="out" selected="true">located outside Galaxy (data on server or mounted drive)</option> + </param> + + <when value="out"> + <!--form field to select outside list of genome directories or mastervar files--> + <param name="input" type="text" label="File with list of genome root directories" size="200" help="Enter file name with full path (/path/file). This file should contain a list of genome root directory names, one per line in the format /path/dir (e.g. /harddrive/GS00000XXXX-DID/GS00000YYYY-ASM/GS00123-DNA_G01)."> + <validator type="empty_field" message="You must supply the list of genome root directories"/> + </param> + </when> + </conditional> + + <!--form field to select no-calls--> + <param name="nocalls" type="select" label="Include no-calls?"> + <option value="" selected="true">no</option> + <option value="--nocalls">yes</option> + </param> + + <!--form field to enter calibration directory--> + <param name="calibration" type="text" size="300" label="Directory calibration data (/path/calibration-root)" help="The directory containing calibration data. For example, there should exist a file calibration-root/0.0.0/metrics.tsv. Calibration data can be downloaded from ftp://ftp.completegenomics.com/ScoreCalibrationFiles/var-calibration-v2.tgz"/> + + <!--form field to select field names to include in vcf--> + <param name="fields" type="select" label="Field names to be included in vcf file" multiple="true" help="Select all field names (default) or a collection of individual field names."> + <option value="all" selected="true">-- all (default) --</option> + <option value="NS">NS - Number of samples</option> + <option value="AN">AN - Total number of alleles in called genotypes</option> + <option value="AC">AC - Allele count in genotypes</option> + <option value="CGA_XR">CGA_XR - External database reference</option> + <option value="CGA_FI">CGA_FI - Functional impact</option> + <option value="CGA_PFAM">CGA_PFAM - PFAM domain </option> + <option value="CGA_MIRB">CGA_MIRB - miRBaseId</option> + <option value="CGA_SDO">CGA_SDO - Depth of overlapping segmental duplications</option> + <option value="CGA_RPT">CGA_RPT - Overlapping repeatMasker annotations</option> + <option value="GT">GT - Genotype</option> + <option value="PS">PS - Phase set</option> + <option value="FT">FT - Sample genotype filters</option> + <option value="GL">GL - Genotype likelihoods</option> + <option value="CGA_CEHQ">CGA_CEHQ - Calibrated haplotype quality based on EAF assumption</option> + <option value="CGA_CEGL">CGA_CEGL - Genotype likelihoods based on CEHQ</option> + <option value="SS">SS - Somatic status</option> + <option value="HQ">HQ - Haplotype quality</option> + <option value="EHQ">EHQ - Haplotype quality based on EAF assumption</option> + <option value="GQ">GQ - Genotype quality</option> + <option value="DP">DP - Total read depth</option> + <option value="AD">AD - Allelic depths</option> + <option value="CGA_RDP">CGA_RDP - Read depth in reference</option> + <option value="CGA_ODP">CGA_ODP - Other total read depth: somatic comparison</option> + <option value="CGA_OAD">CGA_OAD - Other allelic depths: somatic comparison</option> + <option value="CGA_ORDP">CGA_ORDP - Other reference depth: somatic comparison </option> + <option value="CGA_SOMC">CGA_SOMC - Somatic Category</option> + <option value="CGA_SOMR">CGA_SOMR - Somatic Rank</option> + <option value="CGA_SOMS">CGA_SOMS - Somatic Score</option> + <option value="CGA_GP">CGA_GP - Normalized mean GC corrected coverage</option> + <option value="CGA_NP">CGA_NP - Normalized mean coverage for 2k window</option> + <option value="CGA_CP">CGA_CP - Diploid-model ploidy call for segment</option> + <option value="CGA_PS">CGA_PS - Diploid-model called ploidy score</option> + <option value="CGA_CT">CGA_CT - Diploid-model CNV type</option> + <option value="CGA_TS">CGA_TS - Diploid-model CNV type score</option> + <option value="CGA_CL">CGA_CL - Nondiploid-model called level</option> + <option value="CGA_LS">CGA_LS - Nondiploid-model called level score</option> + <option value="CGA_SCL">CGA_SCL - Nondiploid-model somatic called level</option> + <option value="CGA_SLS">CGA_SLS - Non-diploid-model somatic called level score</option> + <option value="CGA_LAF">CGA_LAF - Lesser Allele Fraction estimate, 100k window</option> + <option value="CGA_LLAF">CGA_LLAF - Lesser Allele Fraction lower bound, 100k window</option> + <option value="CGA_ULAF">CGA_ULAF - Lesser Allele Fraction upper bound, 100k window</option> + </param> + </when> + + <when value="masterVar"> + <!--conditional to select inputs--> + <conditional name="data_sources"> + <param name="data_source" type="select" label="Where are the input files?"> + <option value="in" selected="true">imported into Galaxy</option> + <option value="out">located outside Galaxy (data on server or mounted drive)</option> + </param> + + <when value="in"> + <!--form field to select mastervar files--> + <repeat name="files" title="MasterVar files" min="1"> + <param name="input" type="data" format="cg_mastervar" label="Dataset"> + <validator type="dataset_ok_validator" /> + <validator type="dataset_metadata_in_file" filename="cg_crr_files.loc" + metadata_name="dbkey" metadata_column="1" + message="cgatools is not currently available for this build."/> + </param> + </repeat> + </when> + + <when value="out"> + <!--form field to enter input file--> + <param name="input" type="text" label="File with list of genome root directories or masterVar files" size="200" help="Enter file name with full path (/path/file). This file should contain a list of genome root directory names, one per line in the format /path/dir (e.g. /harddrive/GS00000XXXX-DID/GS00000YYYY-ASM/GS00123-DNA_G01), or a list of masterVar files, one per line in the format /path/masterVarfile (e.g. /harddrive/GS00000XXXX-DID/GS00000YYYY-ASM/GS00123-DNA_G01/ASM/masterVarBeta-GS00000YYYY-ASM.tsv.bz2)."> + <validator type="empty_field" message="You must supply the list of genome root directories or masterVar files"/> + </param> + </when> + </conditional> + + <!--form field to select no-calls--> + <param name="nocalls" type="select" label="Include no-calls?"> + <option value="" selected="true">no</option> + <option value="--nocalls">yes</option> + </param> + + <!--form field to enter calibration directory--> + <param name="calibration" type="text" size="300" label="Directory calibration data (/path/calibration-root)" help="The directory containing calibration data. For example, there should exist a file calibration-root/0.0.0/metrics.tsv. Calibration data can be downloaded from ftp://ftp.completegenomics.com/ScoreCalibrationFiles/var-calibration-v2.tgz"/> + + <!--form field to select field names to include in vcf--> + <param name="fields" type="select" label="Field names to be included in vcf file" multiple="true" help="Select all field names (default) or a collection of individual field names."> + <option value="all" selected="true">-- all (default) --</option> + <option value="NS">NS - Number of samples</option> + <option value="AN">AN - Total number of alleles in called genotypes</option> + <option value="AC">AC - Allele count in genotypes</option> + <option value="CGA_XR">CGA_XR - External database reference</option> + <option value="CGA_FI">CGA_FI - Functional impact</option> + <option value="CGA_PFAM">CGA_PFAM - PFAM domain </option> + <option value="CGA_MIRB">CGA_MIRB - miRBaseId</option> + <option value="CGA_SDO">CGA_SDO - Depth of overlapping segmental duplications</option> + <option value="CGA_RPT">CGA_RPT - Overlapping repeatMasker annotations</option> + <option value="GT">GT - Genotype</option> + <option value="PS">PS - Phase set</option> + <option value="FT">FT - Sample genotype filters</option> + <option value="GL">GL - Genotype likelihoods</option> + <option value="CGA_CEHQ">CGA_CEHQ - Calibrated haplotype quality based on EAF assumption</option> + <option value="CGA_CEGL">CGA_CEGL - Genotype likelihoods based on CEHQ</option> + <option value="SS">SS - Somatic status</option> + <option value="HQ">HQ - Haplotype quality</option> + <option value="EHQ">EHQ - Haplotype quality based on EAF assumption</option> + <option value="GQ">GQ - Genotype quality</option> + <option value="DP">DP - Total read depth</option> + <option value="AD">AD - Allelic depths</option> + <option value="CGA_RDP">CGA_RDP - Read depth in reference</option> + <option value="CGA_ODP">CGA_ODP - Other total read depth: somatic comparison</option> + <option value="CGA_OAD">CGA_OAD - Other allelic depths: somatic comparison</option> + <option value="CGA_ORDP">CGA_ORDP - Other reference depth: somatic comparison </option> + <option value="CGA_SOMC">CGA_SOMC - Somatic Category</option> + <option value="CGA_SOMR">CGA_SOMR - Somatic Rank</option> + <option value="CGA_SOMS">CGA_SOMS - Somatic Score</option> + </param> + </when> + + <when value="CNV"> + <!--conditional to select inputs--> + <conditional name="data_sources"> + <param name="data_source" type="select" label="Where are the input files?"> + <option value="out" selected="true">located outside Galaxy (data on server or mounted drive)</option> + </param> + + <when value="out"> + <!--form field to enter input file--> + <param name="input" type="text" label="File with list of genome root directories" size="200" help="Enter file name with full path (/path/file). This file should contain a list of genome root directory names, one per line in the format /path/dir (e.g. /harddrive/GS00000XXXX-DID/GS00000YYYY-ASM/GS00123-DNA_G01)."> + <validator type="empty_field" message="You must supply the list of genome root directories"/> + </param> + </when> + </conditional> + + <!--form field to select field names to include in vcf--> + <param name="fields" type="select" label="Field names to be included in vcf file" multiple="true" help="Select all field names (default) or a collection of individual field names."> + <option value="all" selected="true">-- all (default) --</option> + <option value="GT">GT - Genotype</option> + <option value="CGA_GP">CGA_GP - Normalized mean GC corrected coverage</option> + <option value="CGA_NP">CGA_NP - Normalized mean coverage for 2k window</option> + <option value="CGA_CP">CGA_CP - Diploid-model ploidy call for segment</option> + <option value="CGA_PS">CGA_PS - Diploid-model called ploidy score</option> + <option value="CGA_CT">CGA_CT - Diploid-model CNV type</option> + <option value="CGA_TS">CGA_TS - Diploid-model CNV type score</option> + <option value="CGA_CL">CGA_CL - Nondiploid-model called level</option> + <option value="CGA_LS">CGA_LS - Nondiploid-model called level score</option> + <option value="CGA_SCL">CGA_SCL - Nondiploid-model somatic called level</option> + <option value="CGA_SLS">CGA_SLS - Non-diploid-model somatic called level score</option> + <option value="CGA_LAF">CGA_LAF - Lesser Allele Fraction estimate, 100k window</option> + <option value="CGA_LLAF">CGA_LLAF - Lesser Allele Fraction lower bound, 100k window</option> + <option value="CGA_ULAF">CGA_ULAF - Lesser Allele Fraction upper bound, 100k window</option> + </param> + </when> + </conditional> + </when> + </conditional> + </inputs> + + <help> + +**What it does** + +This tool uses cgatools mkvcf to convert Complete Genomics masterVar files, including CNV, SV and/or MEI data, to vcf format version. + +**cgatools 1.6.0 Documentation** + +Userguide: http://cgatools.sourceforge.net/docs/1.6.0/cgatools-user-guide.pdf + +Release notes: http://cgatools.sourceforge.net/docs/1.6.0/cgatools-release-notes.pdf + +**Command line reference**:: + + COMMAND NAME + mkvcf - Converts var file(s) or masterVar file(s) to VCF. + + DESCRIPTION + Converts var file(s) or masterVar file(s) to VCF. + + OPTIONS + -h [ --help ] + Print this help message. + + --beta + This is a beta command. To run this command, you must pass the --beta + flag. + + --reference arg + The reference crr file. + + --output arg (=STDOUT) + The output file (may be omitted for stdout). + + --field-names arg (=GT,PS,NS,AN,AC,SS,FT,CGA_XR,CGA_FI,GQ,HQ,EHQ,CGA_CEHQ,GL, + CGA_CEGL,DP,AD,CGA_RDP,CGA_ODP,CGA_OAD,CGA_ORDP,CGA_PFAM,CGA_MIRB,CGA_RPT, + CGA_SDO,CGA_SOMC,CGA_SOMR,CGA_SOMS,CGA_GP,CGA_NP,CGA_CP,CGA_PS,CGA_CT, + CGA_TS,CGA_CL,CGA_LS,CGA_SCL,CGA_SLS,CGA_LAF,CGA_LLAF,CGA_ULAF,CGA_IS, + CGA_IDC,CGA_IDCL,CGA_IDCR,CGA_RDC,CGA_NBET,CGA_ETS,CGA_KES,CGA_BF, + CGA_MEDEL,MATEID,SVTYPE,CGA_BNDG,CGA_BNDGO,CGA_BNDMPC,CGA_BNDPOS,CGA_BNDDEF, + CGA_BNDP) + Comma-separated list of field names. By default, all fields are + included, but you may override this option to ensure only a subset of + the fields is included in the VCF output. For a description of each + field, see the cgatools user guide. + + --source-names arg (=masterVar,CNV,SV,MEI) + Comma-separated list of source names. The following source names are + available: + masterVar - Includes records extracted from the masterVar file. + CNV - Includes CNV-related records. + SV - Includes records derived from junctions files. + MEI - Includes records describing mobile element insertions. + Some of these source types are only available for more recent pipeline + versions, and some of these source types do not support multi-genome + VCFs. For more information about which source types are available for + which versions of the Complete Genomics pipeline software, see the + cgatools user guide. + + --genome-root arg + For each genome to include in the VCF, the genome root directory, for + example /data/GS00118-DNA_A01; this directory is expected to contain + the ASM and LIB subdirectories, for example. You must supply this + option for each genome in the VCF, unless you are using + --source-names=masterVar and you have specified the --master-var option + for each genome in the VCF. + + --master-var arg + For each genome to include in the VCF, the masterVar file. If + genome-roots parameter is given, this parameter defaults to the + masterVar in the given genome-root. + + --include-no-calls + Small variants VCF records include loci that have no + reference-inconsistent calls. + + --calibration-root arg + The directory containing calibration data. For example, there should + exist a file calibration-root/version0.0.0/metrics.tsv. This option is only + required if CGA_CEHQ or CGA_CEGL are included in the --field-names + parameter. + + --junction-file arg + For each genome to include in the VCF, the junctions file. If + genome-roots parameter is given, this parameter defaults to the + respective junctions file in the export directory. + + --junction-score-threshold arg (=10) + Junction score thresholds (discordant mate pair count). + + --junction-side-length-threshold arg (=70) + Junction side length threshold. + + --junction-distance-tolerance arg (=200) + Distance tolerance for junction compatibility. + + --junction-length-threshold arg (=500) + Length threshold for compatible junctions. + + --junction-normal-priority + Normal junction priority for vcf output. + + --junction-tumor-hc + use high confidence junctions for tumors. + + + SUPPORTED FORMAT_VERSION + 0.3 or later + </help> +</tool>