| Previous changeset 4:d09254e37c68 (2020-06-08) Next changeset 6:cb5691381acb (2023-06-08) |
|
Commit message:
"planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/manta commit 86427647db100383faa432008b58e768b56ac416" |
|
modified:
manta.xml manta_macros.xml test-data/candidateSV.vcf.gz test-data/candidateSmallIndels.vcf.gz test-data/somaticSV.vcf.gz |
|
added:
customConfigManta.py |
|
removed:
customized.ini |
| b |
| diff -r d09254e37c68 -r f55d45b0c6d1 customConfigManta.py --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/customConfigManta.py Tue Jun 09 06:23:39 2020 -0400 |
| [ |
| @@ -0,0 +1,80 @@ +import argparse + + +def Parser(): + the_parser = argparse.ArgumentParser() + the_parser.add_argument( + '--minCandidateVariantSize', type=int, default=8, + help="Run Manta reporting for all SVs/indels at or above this size") + the_parser.add_argument( + '--rnaMinCandidateVariantSize', type=int, default=1000, + help="Separate option (to provide different default) used for \ + runs in RNA-mode") + the_parser.add_argument( + '--minEdgeObservations', type=int, default=3, + help="Remove all edges from the graph unless they're supported \ + by this many 'observations'") + the_parser.add_argument( + '--graphNodeMaxEdgeCount', type=int, default=10, + help="If both nodes of an edge have an edge count higher than this, \ + then skip evaluation of the edge") + the_parser.add_argument( + '--minCandidateSpanningCount', type=int, default=3, + help="Run discovery and candidate reporting for all SVs/indels with \ + at least this many spanning support observations") + the_parser.add_argument( + '--minScoredVariantSize', type=int, default=50, + help="After candidate identification, only score and report \ + SVs/indels at or above this size") + the_parser.add_argument( + '--minDiploidVariantScore', type=int, default=10, + help="minimum VCF QUAL score for a variant to be included in \ + the diploid vcf") + the_parser.add_argument( + '--minPassDiploidVariantScore', type=int, default=20, + help="VCF QUAL score below which a variant is marked as \ + filtered in the diploid vcf") + the_parser.add_argument( + '--minPassDiploidGTScore', type=int, default=15, + help="minimum genotype quality score below which single samples \ + are filtered for a variant in the diploid vcf") + the_parser.add_argument( + '--minSomaticScore', type=int, default=10, + help="minimum VCF QUAL score for a variant to be included in the \ + diploid vcf") + the_parser.add_argument( + '--minPassSomaticScore', type=int, default=30, + help="somatic quality scores below this level are filtered in the \ + somatic vcf") + the_parser.add_argument( + '--enableRemoteReadRetrievalForInsertionsInGermlineCallingModes', + type=int, default=1, + help="includes tumor-normal subtraction and tumor-only calling") + the_parser.add_argument( + '--enableRemoteReadRetrievalForInsertionsInCancerCallingModes', + type=int, default=0, + help="GermlineCallingModes includes all other calling modes") + the_parser.add_argument( + '--useOverlapPairEvidence', type=int, default=0, + help="Set 1 if an overlapping read pair will be considered as \ + evidence. Set to 0 to skip overlapping read pairs") + args = the_parser.parse_args() + return args + + +if __name__ == "__main__": + args = Parser() + # recover arguments as a dictionary with keys = argument name and values + # are argument values + argsDict = args.__dict__ + ini_lines = [] + # implement first, hard-coded ini lines + ini_lines.append('[manta]') + ini_lines.append('referenceFasta = /dummy/path/to/genome.fa') + # implement the rest of the ini lines for the argsDict + for argument in argsDict: + ini_lines.append("%s = %s" % (argument, str(argsDict[argument]))) + # print ini_lines in configManta.py.ini + handler = open('configManta.py.ini', 'w') + for line in ini_lines: + handler.write("%s\n" % line) |
| b |
| diff -r d09254e37c68 -r f55d45b0c6d1 customized.ini --- a/customized.ini Mon Jun 08 03:11:56 2020 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 |
| [ |
| @@ -1,58 +0,0 @@ - -# -# This section contains all configuration settings for the top-level manta workflow, -# -[manta] - -referenceFasta = /illumina/development/Isis/Genomes/Homo_sapiens/UCSC/hg19/Sequence/WholeGenomeFasta/genome.fa - -# Run discovery and candidate reporting for all SVs/indels at or above this size -# Separate option (to provide different default) used for runs in RNA-mode -minCandidateVariantSize = 8 -rnaMinCandidateVariantSize = 1000 - -# Remove all edges from the graph unless they're supported by this many 'observations'. -# Note that one supporting read pair or split read usually equals one observation, but evidence is sometimes downweighted. -minEdgeObservations = 3 - -# If both nodes of an edge have an edge count higher than this, then skip evaluation of the edge. -# Set to 0 to turn this filtration off -graphNodeMaxEdgeCount = 10 - -# Run discovery and candidate reporting for all SVs/indels with at least this -# many spanning support observations -minCandidateSpanningCount = 3 - -# After candidate identification, only score and report SVs/indels at or above this size: -minScoredVariantSize = 50 - -# minimum VCF "QUAL" score for a variant to be included in the diploid vcf: -minDiploidVariantScore = 10 - -# VCF "QUAL" score below which a variant is marked as filtered in the diploid vcf: -minPassDiploidVariantScore = 20 - -# minimum genotype quality score below which single samples are filtered for a variant in the diploid vcf: -minPassDiploidGTScore = 15 - -# somatic quality scores below this level are not included in the somatic vcf: -minSomaticScore = 10 - -# somatic quality scores below this level are filtered in the somatic vcf: -minPassSomaticScore = 30 - -# Remote read retrieval is used ot improve the assembly of putative insertions by retrieving any mate reads in remote -# locations with poor mapping quality, which pair to confidently mapping reads near the insertion locus. These reads -# can help to fully assemble longer insertions, under certain circumstances this feature can add a very large runtime -# burden. For instance, given the very high chimeric pair rates found in degraded FFPE samples, the runtime of the read -# retrieval process can be unpredicable. For this reason the feature is disabled by default for somatic variant calling. -# This feature can be enabled/disabled separately for germline and cancer calling below. -# -# Here "CancerCallingModes" includes tumor-normal subtraction and tumor-only calling. "GermlineCallingModes" includes -# all other calling modes. -enableRemoteReadRetrievalForInsertionsInGermlineCallingModes = 1 -enableRemoteReadRetrievalForInsertionsInCancerCallingModes = 0 - -# Set if an overlapping read pair will be considered as evidence -# Set to 0 to skip overlapping read pairs -useOverlapPairEvidence = 0 |
| b |
| diff -r d09254e37c68 -r f55d45b0c6d1 manta.xml --- a/manta.xml Mon Jun 08 03:11:56 2020 -0400 +++ b/manta.xml Tue Jun 09 06:23:39 2020 -0400 |
| [ |
| b'@@ -24,26 +24,27 @@\n ln -s \'$bam_input.tumor_bam_file.metadata.bam_index\' tumor.bai &&\n #end if\n \n- #if str( $set_configuration.set_configuration_switch ) == "Customized":\n- sed -i \'s/minCandidateVariantSize = 8/minCandidateVariantSize = $set_configuration.minCandidateVariantSize/\' ./configManta.py.ini &&\n- sed -i \'s/rnaMinCandidateVariantSize = 1000/rnaMinCandidateVariantSize = $set_configuration.rnaMinCandidateVariantSize/\' ./configManta.py.ini &&\n- sed -i \'s/minEdgeObservations = 3/minEdgeObservations = $set_configuration.minEdgeObservations/\' ./configManta.py.ini &&\n- sed -i \'s/graphNodeMaxEdgeCount = 10/graphNodeMaxEdgeCount = $set_configuration.graphNodeMaxEdgeCount/\' ./configManta.py.ini &&\n- sed -i \'s/minCandidateSpanningCount = 3/minCandidateSpanningCount = $set_configuration.minCandidateSpanningCount/\' ./configManta.py.ini &&\n- sed -i \'s/minScoredVariantSize = 50/minScoredVariantSize = $set_configuration.minScoredVariantSize/\' ./configManta.py.ini &&\n- sed -i \'s/minDiploidVariantScore = 10/minDiploidVariantScore = $set_configuration.minDiploidVariantScore/\' ./configManta.py.ini &&\n- sed -i \'s/minPassDiploidVariantScore = 20/minPassDiploidVariantScore = $set_configuration.minPassDiploidVariantScore/\' ./configManta.py.ini &&\n- sed -i \'s/minPassDiploidGTScore = 15/minPassDiploidGTScore = $set_configuration.minPassDiploidGTScore/\' ./configManta.py.ini &&\n- sed -i \'s/minSomaticScore = 10/minSomaticScore = $set_configuration.minSomaticScore/\' ./configManta.py.ini &&\n- sed -i \'s/minPassSomaticScore = 30/minPassSomaticScore = $set_configuration.minPassSomaticScore/\' ./configManta.py.ini &&\n- sed -i \'s/enableRemoteReadRetrievalForInsertionsInGermlineCallingModes = 1/enableRemoteReadRetrievalForInsertionsInGermlineCallingModes = $set_configuration.enableRemoteReadRetrievalForInsertionsInGermlineCallingModes/\' ./configManta.py.ini &&\n- sed -i \'s/enableRemoteReadRetrievalForInsertionsInCancerCallingModes = 0/enableRemoteReadRetrievalForInsertionsInCancerCallingModes = $set_configuration.enableRemoteReadRetrievalForInsertionsInCancerCallingModes/\' ./configManta.py.ini &&\n- sed -i \'s/useOverlapPairEvidence = 0/useOverlapPairEvidence = $set_configuration.useOverlapPairEvidence/\' ./configManta.py.ini &&\n- #end if\n-\n #if str( $set_configuration.set_configuration_switch ) == "Custom_config_file":\n cp \'$set_configuration.CustomConfigFile\' ./configManta.py.ini &&\n #end if\n+ #if str( $set_configuration.set_configuration_switch ) == "Customized":\n+ rm ./configManta.py.ini &&\n+ python $__tool_directory__/customConfigManta.py\n+ --minCandidateVariantSize \'$set_configuration.minCandidateVariantSize\'\n+ --rnaMinCandidateVariantSize \'$set_configuration.rnaMinCandidateVariantSize\'\n+ --minEdgeObservations \'$set_configuration.minEdgeObservations\'\n+ --graphNodeMaxEdgeCount \'$set_configuration.graphNodeMaxEdgeCount\'\n+ --minCandidateSpanningCount \'$set_configuration.minCandidateSpanningCount\'\n+ --minScoredVariantSize \'$set_configuration.minScoredVariantSize\'\n+ --minDiploidVariantScore \'$set_configuration.minDiploidVariantScore\'\n+ --minPassDiploidVariantScore \'$set_configuration.minPassDiploidVariantScore\'\n+ --minPassDiploidGTScore \'$set_configuration.minPassDiploidGTScore\'\n+ --minSomaticScore \'$set_configuration.minSomaticScore\'\n+ --minPassSomaticScore \'$set_configuration.minPassSomaticScore\'\n+ --enableRemoteReadRetrievalForInsertionsInGermlineCallingModes \'$set_configuration.enableRemoteReadRetrievalForInsertionsInGermlineCallingModes\'\n+ --enableRemoteReadRetrievalForInsertionsInCancerCallingModes \'$set_configuration.enableRemoteReadRetrievalForInsertionsInCancerCallingModes\'\n+ --useOverlapPairEvidence \'$set_configuration.useOverlapPairEvidence\' &&\n+ #end if\n \n configManta.py --referenceFasta=\'${refe'..b' <param name="candidateSmallIndels_check" value="True"/>\n- <param name="somaticSV_check" value="True"/>\n- <output name="candidateSmallIndels" file="candidateSmallIndels.vcf.gz" decompress="true" lines_diff="4"/>\n- <output name="somaticSV" file="somaticSV.vcf.gz" decompress="true" lines_diff="4"/>\n+ <output name="candidateSmallIndels" file="candidateSmallIndels.vcf.gz" decompress="true" lines_diff="6"/>\n+ <output name="somaticSV" file="somaticSV.vcf.gz" decompress="true" lines_diff="6"/>\n </test>\n- <test>\n+ <test>\n+ <param name="reference_source_selector" value="cached"/>\n+ <param name="index" value="hg19"/>\n+ <param name="bam_input_selector" value="tumor_bam" dbkey="hg19"/>\n+ <param name="normal_bam_file" ftype="bam" value="HCC1954_normal.bam"/>\n+ <param name="tumor_bam_file" ftype="bam" value="HCC1954_tumor.bam"/>\n+ <param name="set_configuration_switch" value="Customized"/>\n+ <param name="callMemMb" value="1000"/>\n+ <param name="candidateSmallIndels_check" value="True"/>\n+ <output name="candidateSmallIndels" file="candidateSmallIndels.vcf.gz" decompress="true" lines_diff="6"/>\n+ <output name="somaticSV" file="somaticSV.vcf.gz" decompress="true" lines_diff="6"/>\n+ </test>\n+ <test>\n <param name="reference_source_selector" value="cached"/>\n <param name="index" value="hg19"/>\n <param name="bam_input_selector" value="tumor_bam" dbkey="hg19"/>\n@@ -185,7 +175,8 @@\n <param name="set_configuration_switch" value="Default_config_file"/>\n <param name="callMemMb" value="1000"/>\n <param name="candidateSmallIndels_check" value="True"/>\n- <output name="candidateSmallIndels" file="candidateSmallIndels.vcf.gz" decompress="true" lines_diff="4"/>\n+ <output name="candidateSmallIndels" file="candidateSmallIndels.vcf.gz" decompress="true" lines_diff="6"/>\n+ <output name="somaticSV" file="somaticSV.vcf.gz" decompress="true" lines_diff="6"/>\n </test>\n <test>\n <param name="reference_source_selector" value="history"/>\n@@ -196,7 +187,8 @@\n <param name="set_configuration_switch" value="Default_config_file"/>\n <param name="callMemMb" value="1000"/>\n <param name="candidateSV_check" value="True"/>\n- <output name="candidateSV" file="candidateSV.vcf.gz" decompress="true" lines_diff="4"/>\n+ <output name="candidateSV" file="candidateSV.vcf.gz" decompress="true" lines_diff="6"/>\n+ <output name="somaticSV" file="somaticSV.vcf.gz" decompress="true" lines_diff="6"/>\n </test>\n <test>\n <param name="reference_source_selector" value="history"/>\n@@ -207,10 +199,10 @@\n <param name="set_configuration_switch" value="Default_config_file"/>\n <param name="callMemMb" value="1000"/>\n <param name="candidateSmallIndels_check" value="True"/>\n- <output name="candidateSmallIndels" file="candidateSmallIndels.vcf.gz" decompress="true" lines_diff="4"/>\n+ <output name="candidateSmallIndels" file="candidateSmallIndels.vcf.gz" decompress="true" lines_diff="6"/>\n+ <output name="somaticSV" file="somaticSV.vcf.gz" decompress="true" lines_diff="6"/>\n </test>\n- </tests>\n-\n+ </tests>\n <help><![CDATA[\n **Outputs**\n The primary Manta outputs are a set of VCF 4.1 files. Currently there are 3 VCF files\n@@ -333,10 +325,8 @@\n \n For further info see: https://github.com/Illumina/manta\n \n- ]]></help>\n-\n+ ]]></help>\n <citations>\n <citation type="doi">10.1093/bioinformatics/btv710</citation>\n </citations>\n-\n </tool>\n' |
| b |
| diff -r d09254e37c68 -r f55d45b0c6d1 manta_macros.xml --- a/manta_macros.xml Mon Jun 08 03:11:56 2020 -0400 +++ b/manta_macros.xml Tue Jun 09 06:23:39 2020 -0400 |
| [ |
| @@ -1,7 +1,7 @@ <macros> <token name="@VERSION@">1.6</token> - <token name="@WRAPPER_VERSION@">@VERSION@+galaxy6</token> + <token name="@WRAPPER_VERSION@">@VERSION@+galaxy7</token> <token name="@pipefail@"><![CDATA[set -o | grep -q pipefail && set -o pipefail;]]></token> <token name="@set_reference_fasta_filename@"><![CDATA[ |
| b |
| diff -r d09254e37c68 -r f55d45b0c6d1 test-data/candidateSV.vcf.gz |
| b |
| Binary file test-data/candidateSV.vcf.gz has changed |
| b |
| diff -r d09254e37c68 -r f55d45b0c6d1 test-data/candidateSmallIndels.vcf.gz |
| b |
| Binary file test-data/candidateSmallIndels.vcf.gz has changed |
| b |
| diff -r d09254e37c68 -r f55d45b0c6d1 test-data/somaticSV.vcf.gz |
| b |
| Binary file test-data/somaticSV.vcf.gz has changed |