Mercurial > repos > iuc > vcf2maf

comparison vcf2maf.xml @ 1:e8510e04a86a draft default tip

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/vcf2maf commit f2287e6aab30c72ef1334688127711fc9624352e
author iuc
date Tue, 11 Oct 2022 20:30:54 +0000
parents 2973994fecd6
children
comparison
equal deleted inserted replaced
0:2973994fecd6 1:e8510e04a86a
1 <tool id="vcf2maf" name="Convert VCF to MAF" version="@TOOL_VERSION@"> 1 <tool id="vcf2maf" name="Convert VCF to MAF" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@">
2 <description>with vcf2maf</description> 2 <description>with vcf2maf</description>
3 <macros> 3 <macros>
4 <token name="@TOOL_VERSION@">1.6.21</token> 4 <token name="@TOOL_VERSION@">1.6.21</token>
5 <token name="@VERSION_SUFFIX@">1</token>
5 <token name="@DB_VERSION@">106</token> 6 <token name="@DB_VERSION@">106</token>
6 </macros> 7 </macros>
7 <requirements> 8 <requirements>
8 <requirement type="package" version="@TOOL_VERSION@">vcf2maf</requirement> 9 <requirement type="package" version="@TOOL_VERSION@">vcf2maf</requirement>
9 <requirement type="package" version="@DB_VERSION@.1">ensembl-vep</requirement> 10 <requirement type="package" version="@DB_VERSION@.1">ensembl-vep</requirement>
10 </requirements> 11 </requirements>
11 <command detect_errors="exit_code"><![CDATA[ 12 <command detect_errors="exit_code"><![CDATA[
13 ## cBioPortal only supports human and mouse but requires their assembly name in NCBI format so we have to translate the dbkey for those
14 #set $ncbi_names = {"hg19": "GRCh37", "hg38": "GRCh38", "mm10": "GRCm38", "mm39": "GRCm39"}
15
12 ln -s '${input1}' MainInput.vcf && 16 ln -s '${input1}' MainInput.vcf &&
13 #if $ref_seq.ref_source == "cached": 17 #if $ref_seq.ref_source == "cached":
14 ln -s '${ref_seq.ref.fields.path}' reference.fa && 18 ln -s '${ref_seq.ref.fields.path}' reference.fa &&
15 #elif $ref_seq.ref_source == "history": 19 #elif $ref_seq.ref_source == "history":
16 ln -s '${ref_seq.ref}' reference.fa && 20 ln -s '${ref_seq.ref}' reference.fa &&
17 #end if 21 #end if
18 vcf2maf.pl --input-vcf MainInput.vcf --output-maf MainOutput.maf --ref-fasta reference.fa 22 vcf2maf.pl --input-vcf MainInput.vcf --output-maf #if $include_header then 'MainOutput.maf' else 'temp.maf'# --ref-fasta reference.fa
19 #if $annotation_cache.source == "no_vep": 23 #if $annotation_cache.source == "no_vep":
20 --inhibit-vep 24 --inhibit-vep
25 #if $input1.metadata.dbkey in $ncbi_names:
26 --ncbi-build '${ncbi_names[$input1.metadata.dbkey]}'
27 #else:
28 --ncbi-build '${input1.metadata.dbkey}'
29 #end if
21 #else: 30 #else:
22 --vep-path \$(dirname \$(which vep)) 31 --vep-path \$(dirname \$(which vep))
23 --vep-data '${annotation_cache.cache_file.fields.path}' 32 --vep-data '${annotation_cache.cache_file.fields.path}'
24 --species '${annotation_cache.cache_file.fields.species}' 33 --species '${annotation_cache.cache_file.fields.species}'
25 --ncbi-build '${annotation_cache.cache_file.fields.value.split($annotation_cache.cache_file.fields.version + "_")[-1]}' 34 --ncbi-build '${annotation_cache.cache_file.fields.value.split($annotation_cache.cache_file.fields.version + "_")[-1]}'
54 #if $adv_opt.retain_fmt: 63 #if $adv_opt.retain_fmt:
55 --retain-fmt '${adv_opt.retain_fmt}' 64 --retain-fmt '${adv_opt.retain_fmt}'
56 #end if 65 #end if
57 #if $adv_opt.retain_ann: 66 #if $adv_opt.retain_ann:
58 --retain-ann '${adv_opt.retain_ann}' 67 --retain-ann '${adv_opt.retain_ann}'
68 #end if
69 #if not $include_header:
70 && tail -n+2 temp.maf > MainOutput.maf
59 #end if 71 #end if
60 ]]></command> 72 ]]></command>
61 <inputs> 73 <inputs>
62 <param type="data" name="input1" label="VCF input file" format="vcf"> 74 <param type="data" name="input1" label="VCF input file" format="vcf">
63 <validator type="unspecified_build" /> 75 <validator type="unspecified_build" />
106 118
107 <param argument="--tumor-id" type="text" optional="true" label="Enter tumor sample ID (optional)" help="Used to fill the Tumor_Sample_Barcode column of the output MAF with the tumor sample ID."/> 119 <param argument="--tumor-id" type="text" optional="true" label="Enter tumor sample ID (optional)" help="Used to fill the Tumor_Sample_Barcode column of the output MAF with the tumor sample ID."/>
108 <param argument="--normal-id" type="text" optional="true" label="Enter normal sample ID (optional)" help="Used to fill the Matched_Norm_Sample_Barcode column of the output MAF with the normal sample ID."/> 120 <param argument="--normal-id" type="text" optional="true" label="Enter normal sample ID (optional)" help="Used to fill the Matched_Norm_Sample_Barcode column of the output MAF with the normal sample ID."/>
109 <param argument="--vcf-tumor-id" type="text" optional="true" label="Enter name of tumor genotype column (optional)" help="VCFs from variant callers like VarScan use hardcoded sample IDs TUMOR/NORMAL to name genotype columns. Use this parameter to have vcf2maf correctly locate these columns to parse genotypes, while still printing proper sample IDs in the output MAF."/> 121 <param argument="--vcf-tumor-id" type="text" optional="true" label="Enter name of tumor genotype column (optional)" help="VCFs from variant callers like VarScan use hardcoded sample IDs TUMOR/NORMAL to name genotype columns. Use this parameter to have vcf2maf correctly locate these columns to parse genotypes, while still printing proper sample IDs in the output MAF."/>
110 <param argument="--vcf-normal-id" type="text" optional="true" label="Enter name of normal genotype column (optional)" help="VCFs from variant callers like VarScan use hardcoded sample IDs TUMOR/NORMAL to name genotype columns. Use this parameter to have vcf2maf correctly locate these columns to parse genotypes, while still printing proper sample IDs in the output MAF."/> 122 <param argument="--vcf-normal-id" type="text" optional="true" label="Enter name of normal genotype column (optional)" help="VCFs from variant callers like VarScan use hardcoded sample IDs TUMOR/NORMAL to name genotype columns. Use this parameter to have vcf2maf correctly locate these columns to parse genotypes, while still printing proper sample IDs in the output MAF."/>
123 <param name="include_header" type="boolean" checked="true" label="Include MAF version header in output file" help="The MAF version header is a comment that indicates the MAF version and is written into the first row of the ouput file. This is required by some downstream tools. The row containing column headers follows next."/>
111 124
112 <section name="adv_opt" title="Advanced options"> 125 <section name="adv_opt" title="Advanced options">
113 <param argument="--any-allele" type="boolean" optional="true" checked="false" label="Allow also mismatched variant alleles when reporting co-located variants"/> 126 <param argument="--any-allele" type="boolean" optional="true" checked="false" label="Allow also mismatched variant alleles when reporting co-located variants"/>
114 <param argument="--min-hom-vaf" type="float" optional="true" min="0" max="1" label="Enter minimum allele fraction to call a variant homozygous if GT is undefined in VCF" help="Default value is 0.7"/> 127 <param argument="--min-hom-vaf" type="float" optional="true" min="0" max="1" label="Enter minimum allele fraction to call a variant homozygous if GT is undefined in VCF" help="Default value is 0.7"/>
115 <param argument="--maf-center" type="text" optional="true" label="Enter variant calling center to report in MAF"/> 128 <param argument="--maf-center" type="text" optional="true" label="Enter variant calling center to report in MAF"/>
125 <test expect_num_outputs="1"> 138 <test expect_num_outputs="1">
126 <param name="input1" dbkey="hg19" value="input_test1.vcf" ftype="vcf" /> 139 <param name="input1" dbkey="hg19" value="input_test1.vcf" ftype="vcf" />
127 <param name="ref_source" value="history" /> 140 <param name="ref_source" value="history" />
128 <param name="ref" dbkey="hg19" value="test1.fa" ftype="fasta" /> 141 <param name="ref" dbkey="hg19" value="test1.fa" ftype="fasta" />
129 <param name="annotation_cache.source" value="no_vep" /> 142 <param name="annotation_cache.source" value="no_vep" />
143 <assert_command>
144 <has_text text="--ncbi-build 'GRCh37'"/>
145 </assert_command>
130 <output name="output1" file="output_test1.tabular" ftype="tabular" /> 146 <output name="output1" file="output_test1.tabular" ftype="tabular" />
131 </test> 147 </test>
132 <test expect_num_outputs="1"> 148 <test expect_num_outputs="1">
133 <param name="input1" dbkey="hg19" value="input_test1.vcf" ftype="vcf" /> 149 <param name="input1" dbkey="hg19" value="input_test1.vcf" ftype="vcf" />
134 <param name="ref_source" value="cached" /> 150 <param name="ref_source" value="cached" />
135 <param name="ref" value="hg19test" /> 151 <param name="ref" value="hg19test" />
136 <param name="annotation_cache.source" value="no_vep" /> 152 <param name="annotation_cache.source" value="no_vep" />
153 <assert_command>
154 <has_text text="--ncbi-build 'GRCh37'"/>
155 </assert_command>
137 <output name="output1" file="output_test1.tabular" ftype="tabular" /> 156 <output name="output1" file="output_test1.tabular" ftype="tabular" />
157 </test>
158 <test expect_num_outputs="1">
159 <param name="input1" dbkey="hg19" value="input_test1.vcf" ftype="vcf" />
160 <param name="ref_source" value="cached" />
161 <param name="ref" value="hg19test" />
162 <param name="annotation_cache.source" value="no_vep" />
163 <param name="include_header" value="False" />
164 <output name="output1" ftype="tabular" >
165 <assert_contents>
166 <has_n_lines n="2" />
167 <not_has_text text="#version 2.4" />
168 </assert_contents>
169 </output>
138 </test> 170 </test>
139 <test expect_num_outputs="1"> 171 <test expect_num_outputs="1">
140 <param name="input1" dbkey="dm6" value="input_test2.vcf" ftype="vcf" /> 172 <param name="input1" dbkey="dm6" value="input_test2.vcf" ftype="vcf" />
141 <param name="ref_source" value="history" /> 173 <param name="ref_source" value="history" />
142 <param name="ref" dbkey="dm6" value="test2.fa" ftype="fasta" /> 174 <param name="ref" dbkey="dm6" value="test2.fa" ftype="fasta" />
143 <param name="source" value="restricted" /> 175 <param name="source" value="restricted" />
144 <param name="cache_file" value="drosophila_melanogaster_vep_106_BDGP6.32" /> 176 <param name="cache_file" value="drosophila_melanogaster_vep_106_BDGP6.32" />
177 <assert_command>
178 <has_text text="--ncbi-build 'BDGP6.32'"/>
179 </assert_command>
145 <output name="output1" file="output_test2.tabular" ftype="tabular" /> 180 <output name="output1" file="output_test2.tabular" ftype="tabular" />
146 </test> 181 </test>
147 </tests> 182 </tests>
148 <help><![CDATA[ 183 <help><![CDATA[
149 The tool vcf2maf can parse a wide range of VCF-like formats and convert these into the `Mutation Annotation Format (MAF) <https://docs.gdc.cancer.gov/Data/File_Formats/MAF_Format/>`__. A central part of the conversion process is the selection of a single effect per variant. While this is often a subjective decision, vcf2maf offers a standardized way to achieve this by optionally utilizing Ensembl's `Variant Effect Predictor (VEP) <https://www.ensembl.org/info/docs/tools/vep/index.html>`__. ]]></help> 184 The tool vcf2maf can parse a wide range of VCF-like formats and convert these into the `Mutation Annotation Format (MAF) <https://docs.gdc.cancer.gov/Data/File_Formats/MAF_Format/>`__. A central part of the conversion process is the selection of a single effect per variant. While this is often a subjective decision, vcf2maf offers a standardized way to achieve this by optionally utilizing Ensembl's `Variant Effect Predictor (VEP) <https://www.ensembl.org/info/docs/tools/vep/index.html>`__. ]]></help>