Mercurial > repos > artbio > manta
changeset 4:d09254e37c68 draft
"planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/manta commit 61062db986142ec4ba86757a724bcb9b94d9f838"
| author | artbio |
|---|---|
| date | Mon, 08 Jun 2020 03:11:56 -0400 |
| parents | d648e40c6da9 |
| children | f55d45b0c6d1 |
| files | candidateSV.vcf.gz candidateSmallIndels.vcf.gz manta.xml manta_macros.xml somaticSV.vcf.gz test-data/candidateSV.vcf.gz test-data/candidateSmallIndels.vcf.gz test-data/somaticSV.vcf.gz |
| diffstat | 8 files changed, 119 insertions(+), 85 deletions(-) [+] |
line wrap: on
line diff
--- a/manta.xml Sun Jun 07 16:43:54 2020 -0400 +++ b/manta.xml Mon Jun 08 03:11:56 2020 -0400 @@ -59,10 +59,7 @@ ln -s -f '${run_dir}/runWorkflow.py' '${run_manta_workflow}' && ln -s -f './configManta.py.ini' '${set_conf_file}' && - python2 '${run_dir}/runWorkflow.py' -m local -j \${GALAXY_SLOTS:-4} && - cp '${run_dir}/results/variants/candidateSV.vcf.gz' '${out_vcf1}' && - cp '${run_dir}/results/variants/diploidSV.vcf.gz' '${out_vcf2}' && - cp '${run_dir}/results/variants/candidateSmallIndels.vcf.gz' '${out_vcf3}' + python2 '${run_dir}/runWorkflow.py' -m local -j \${GALAXY_SLOTS:-4} ]]></command> @@ -85,7 +82,7 @@ </when> </conditional> - <param name="additional_param" type="select" multiple="true" display="checkboxes" label="Additional outputs" help="Additional parameters."> + <param name="additional_param" type="select" multiple="true" display="checkboxes" label="Additional parameters" > <option value="exome">Set options for WES input: turn off depth filters</option> <option value="rna">Set options for RNA-Seq input. Must specify exactly one bam input file</option> <option value="unstrandedRNA">Set if RNA-Seq input is unstranded: Allows splice-junctions on either strand</option> @@ -95,8 +92,7 @@ <param name="callMemMb" type="integer" value="8000" label="Set default task memory requirements" help="The maximum memory size to assign to tasks" /> <param name="scanSizeMb" type="integer" value="12" label="Set maximum sequence region size" help="The maximum sequence region size (in megabases) scanned by each task during SV Locus graph generation. (default: 12)" /> - <param name="retainTempFiles" type="boolean" checked="False" truevalue="-s" falsevalue="" label="Keep all temporary files" help="Click yes so all temporary files (for workflow debugging) will be kept."/> - <param name="generateEvidenceBam" type="boolean" checked="False" truevalue="-s" falsevalue="" label="Generate a bam of supporting reads for all SVs" help="Click yes for generating a BAM of supporting reads for all SVs."/> + <!-- <param name="generateEvidenceBam" type="boolean" checked="False" truevalue="-s" falsevalue="" label="Generate a bam of supporting reads for all SVs" help="Click yes for generating a BAM of supporting reads for all SVs."/> --> </section> @@ -104,9 +100,9 @@ <conditional name="set_configuration"> <param name="set_configuration_switch" type="select" label="Do you want to change default configuration settings?"> - <option value="Default_config_file">Default</option> - <option value="Custom_config_file">Upload a different config file</option> - <option value="Customized">Customize the options</option> + <option value="Default_config_file">Default Manta Configuration File</option> + <option value="Custom_config_file">Upload your Own Configuration File</option> + <option value="Customized">Customize a Configuration File using this Galaxy Form</option> </param> <when value="Default_config_file"> </when> @@ -133,14 +129,18 @@ <param name="runworkflow_file_check" type="boolean" label="output manta run_workflow file" checked="False" help="Show run_workflow file on history"/> <param name="config_file_check" type="boolean" label="output conf file" checked="False" help="Show configuration file on history"/> - <param name="O1_check" type="boolean" label="snvs filtred" checked="False" help="Show filtred snvs"/> - <param name="O2_check" type="boolean" label="indels filtred" checked="False" help="Show filtred indels"/> - <param name="O3_check" type="boolean" label="all snvs" checked="False" help="Show snvs"/> - + <param name="candidateSV_check" type="boolean" label="Unscored candidate SV and indels" checked="False" + help="Show unfiltered structural variants"/> + <param name="candidateSmallIndels_check" type="boolean" label="all snvs" checked="False" + help="Subset of the Unscored candidate SV and indels, containing only simple insertion and deletion variants"/> + <param name="diploidSV_check" type="boolean" label="filtered variants in diploid model" checked="False" + help="Show filtered variants in a diploid (only normal) model. In the case of a tumor/normal subtraction, the scores in this file *do not* + reflect any information from the tumor sample" /> + <param name="somaticSV_check" type="boolean" label="SVs and indels scored under a somatic variant model" checked="False" + help="This file will only be produced if a tumor sample alignment file is supplied during configuration"/> </inputs> <outputs> - <data format="txt" name="run_manta_workflow" label="Parameters for running Manta"> <filter>runworkflow_file_check == True</filter> </data> @@ -148,84 +148,117 @@ <data format="tabular" name="set_conf_file" label="conf_file.ini"> <filter>config_file_check == True</filter> </data> - <data format="vcf_bgzip" name="out_vcf1" label="${tool.name} on ${on_string} (Generating the candidateSV.vcf file)" from_work_dir="MantaWorkflow/results/variants/candidateSV.vcf.gz"> - <filter>O1_check == True</filter> + <data format="vcf_bgzip" name="candidateSV" label="Manta unfiltered SVs" from_work_dir="MantaWorkflow/results/variants/candidateSV.vcf.gz"> + <filter>candidateSV_check == True</filter> + </data> + <data format="vcf_bgzip" name="candidateSmallIndels" label="Manta unfiltered Small Indels" from_work_dir="MantaWorkflow/results/variants/candidateSmallIndels.vcf.gz"> + <filter>candidateSmallIndels_check == True</filter> </data> - <data format="vcf_bgzip" name="out_vcf2" label="${tool.name} on ${on_string} (Generating the diploidSV.vcf file)" from_work_dir="MantaWorkflow/results/variants/diploidSV.vcf.gz"> - <filter>O2_check == True</filter> + <data format="vcf_bgzip" name="diploidSV" label="Manta SVs (diploid model)" from_work_dir="MantaWorkflow/results/variants/diploidSV.vcf.gz"> + <filter>diploidSV_check == True</filter> </data> - <data format="vcf_bgzip" name="out_vcf3" label="${tool.name} on ${on_string} (Generating the candidateSmallIndels.vcf file)" from_work_dir="MantaWorkflow/results/variants/candidateSmallIndels.vcf.gz"> - <filter>O3_check == True</filter> + <data format="vcf_bgzip" name="somaticSV" label="Manta SVs (somatic model)" from_work_dir="MantaWorkflow/results/variants/somaticSV.vcf.gz"> + <filter>somaticSV_check == True</filter> </data> </outputs> <tests> - <test> - <conditional name="reference_source"> - <param name="reference_source_selector" value="cached"/> - <param name="index" value="hg19"/> - </conditional> - - <conditional name="bam_input"> - <param name="bam_input_selector" value="tumor_bam" dbkey="hg19"/> - <param name="normal_bam_file" ftype="bam" value="HCC1954_normal.bam"/> - <param name="tumor_bam_file" ftype="bam" value="HCC1954_tumor.bam"/> - </conditional> - - <conditional name="set_configuration"> - <param name="set_configuration_switch" value="Default_config_file"/> - </conditional> - <param name="callMemMb" value="1000"/> - <param name="O3_check" value="True"/> - <output name="out_vcf3" file="candidateSmallIndels.vcf.gz" decompress="true" lines_diff="4"/> - </test> - <test> - <conditional name="reference_source"> - <param name="reference_source_selector" value="history"/> - <param name="ref_file" ftype="fasta" value="hg19_region.fa"/> - </conditional> - - <conditional name="bam_input"> - <param name="bam_input_selector" value="tumor_bam"/> - <param name="normal_bam_file" ftype="bam" value="HCC1954_normal.bam"/> - <param name="tumor_bam_file" ftype="bam" value="HCC1954_tumor.bam"/> - </conditional> + <test> + <param name="reference_source_selector" value="cached"/> + <param name="index" value="hg19"/> + <param name="bam_input_selector" value="tumor_bam" dbkey="hg19"/> + <param name="normal_bam_file" ftype="bam" value="HCC1954_normal.bam"/> + <param name="tumor_bam_file" ftype="bam" value="HCC1954_tumor.bam"/> + <param name="set_configuration_switch" value="Default_config_file"/> + <param name="callMemMb" value="1000"/> + <param name="candidateSmallIndels_check" value="True"/> + <param name="somaticSV_check" value="True"/> + <output name="candidateSmallIndels" file="candidateSmallIndels.vcf.gz" decompress="true" lines_diff="4"/> + <output name="somaticSV" file="somaticSV.vcf.gz" decompress="true" lines_diff="4"/> + </test> + <test> + <param name="reference_source_selector" value="cached"/> + <param name="index" value="hg19"/> + <param name="bam_input_selector" value="tumor_bam" dbkey="hg19"/> + <param name="normal_bam_file" ftype="bam" value="HCC1954_normal.bam"/> + <param name="tumor_bam_file" ftype="bam" value="HCC1954_tumor.bam"/> + <param name="set_configuration_switch" value="Default_config_file"/> + <param name="callMemMb" value="1000"/> + <param name="candidateSmallIndels_check" value="True"/> + <output name="candidateSmallIndels" file="candidateSmallIndels.vcf.gz" decompress="true" lines_diff="4"/> + </test> + <test> + <param name="reference_source_selector" value="history"/> + <param name="ref_file" ftype="fasta" value="hg19_region.fa"/> + <param name="bam_input_selector" value="tumor_bam"/> + <param name="normal_bam_file" ftype="bam" value="HCC1954_normal.bam"/> + <param name="tumor_bam_file" ftype="bam" value="HCC1954_tumor.bam"/> + <param name="set_configuration_switch" value="Default_config_file"/> + <param name="callMemMb" value="1000"/> + <param name="candidateSV_check" value="True"/> + <output name="candidateSV" file="candidateSV.vcf.gz" decompress="true" lines_diff="4"/> + </test> + <test> + <param name="reference_source_selector" value="history"/> + <param name="ref_file" ftype="fasta" value="hg19_region.fa"/> + <param name="bam_input_selector" value="tumor_bam"/> + <param name="normal_bam_file" ftype="bam" value="HCC1954_normal.bam"/> + <param name="tumor_bam_file" ftype="bam" value="HCC1954_tumor.bam"/> + <param name="set_configuration_switch" value="Default_config_file"/> + <param name="callMemMb" value="1000"/> + <param name="candidateSmallIndels_check" value="True"/> + <output name="candidateSmallIndels" file="candidateSmallIndels.vcf.gz" decompress="true" lines_diff="4"/> + </test> + </tests> - <conditional name="set_configuration"> - <param name="set_configuration_switch" value="Default_config_file"/> - </conditional> - <param name="callMemMb" value="1000"/> - <param name="O1_check" value="True"/> - <output name="out_vcf1" file="candidateSV.vcf.gz" decompress="true" lines_diff="4"/> - </test> - <test> - <conditional name="reference_source"> - <param name="reference_source_selector" value="history"/> - <param name="ref_file" ftype="fasta" value="hg19_region.fa"/> - </conditional> + <help><![CDATA[ +**Outputs** + The primary Manta outputs are a set of VCF 4.1 files. Currently there are 3 VCF files + created for a germline analysis, and an additional somatic VCF is produced for a + tumor/normal subtraction. These files are: + + - diploidSV.vcf.gz + SVs and indels scored and genotyped under a diploid model for the set of samples in a + joint diploid sample analysis or for the normal sample in a tumor/normal subtraction + analysis. **In the case of a tumor/normal subtraction, the scores in this file do not + reflect any information from the tumor sample.** + + - somaticSV.vcf.gz + SVs and indels scored under a somatic variant model. This file will only be produced + if a tumor sample alignment file is supplied during configuration + + - candidateSV.vcf.gz + Unscored SV and indel candidates. Only a minimal amount of supporting evidence is + required for an SV to be entered as a candidate in this file. An SV or indel must be a + candidate to be considered for scoring, therefore an SV cannot appear in the other VCF + outputs if it is not present in this file. Note that by default this file includes + indels of size 8 and larger. The smallest indels in this set are intended to be passed + on to a small variant caller without scoring by manta itself (by default manta scoring + starts at size 50). + + - candidateSmallIndels.vcf.gz + Subset of the candidateSV.vcf.gz file containing only simple insertion and deletion + variants less than the minimum scored variant size (50 by default). Passing this file + to a small variant caller will provide continuous coverage over all indel sizes when + the small variant caller and manta outputs are evaluated together. Alternate small + indel candidate sets can be parsed out of the candidateSV.vcf.gz file if this + candidate set is not appropriate. + + For tumor-only analysis, Manta will produce an additional VCF: - <conditional name="bam_input"> - <param name="bam_input_selector" value="tumor_bam"/> - <param name="normal_bam_file" ftype="bam" value="HCC1954_normal.bam"/> - <param name="tumor_bam_file" ftype="bam" value="HCC1954_tumor.bam"/> - </conditional> + - tumorSV.vcf.gz + Subset of the candidateSV.vcf.gz file after removing redundant candidates and small + indels less than the minimum scored variant size (50 by default). The SVs are not + scored, but include additional details: (1) paired and split read supporting evidence + counts for each allele (2) a subset of the filters from the scored tumor-normal model + are applied to the single tumor case to improve precision. - <conditional name="set_configuration"> - <param name="set_configuration_switch" value="Default_config_file"/> - </conditional> - <param name="callMemMb" value="1000"/> - <param name="O3_check" value="True"/> - <output name="out_vcf3" file="candidateSmallIndels.vcf.gz" decompress="true" lines_diff="4"/> - </test> - </tests> - - <help><![CDATA[ -**Manta** -This script configures the Manta SV analysis pipeline. -You must specify a BAM or CRAM file for at least one sample. -Configuration will produce a workflow run script which -can execute the workflow on a single node or through -sge and resume any interrupted execution. +**Manta helps** + This script configures the Manta SV analysis pipeline. + You must specify a BAM or CRAM file for at least one sample. + Configuration will produce a workflow run script which + can execute the workflow on a single node or through + sge and resume any interrupted execution. **Options** --version show program's version number and exit @@ -266,6 +299,7 @@ configuration or only of interest for workflow development/debugging. They will not be printed here if a default exists unless --allHelp is specified + --existingAlignStatsFile=FILE Pre-calculated alignment statistics file. Skips alignment stats calculation.
--- a/manta_macros.xml Sun Jun 07 16:43:54 2020 -0400 +++ b/manta_macros.xml Mon Jun 08 03:11:56 2020 -0400 @@ -1,7 +1,7 @@ <macros> <token name="@VERSION@">1.6</token> - <token name="@WRAPPER_VERSION@">@VERSION@+galaxy5</token> + <token name="@WRAPPER_VERSION@">@VERSION@+galaxy6</token> <token name="@pipefail@"><![CDATA[set -o | grep -q pipefail && set -o pipefail;]]></token> <token name="@set_reference_fasta_filename@"><![CDATA[