Mercurial > repos > elixir-it > mutect2

comparison mutect2.xml @ 0:0cc081cd3992 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded
author elixir-it
date Thu, 28 Jun 2018 05:58:45 -0400
parents
children 2ebf2cd4f18f
comparison
equal deleted inserted replaced
-1:000000000000 0:0cc081cd3992
1 <tool id="mutect2" name="MuTect2" version="3.8">
2 <description>somatic SNP and indel caller</description>
3 <macros>
4 <import>mutect2_macros_add_loc.xml</import>
5 </macros>
6 <requirements>
7 <requirement type="package" version="3.8" >gatk</requirement>
8 <requirement type="package" version="2.7.1" >picard</requirement>
9 <requirement type="package" version="1.7" >samtools</requirement>
10 </requirements>
11 <command>
12 <![CDATA[
13 ##creation of .bai the -@ option is used to allocate additional threads
14 samtools index -@ \${GALAXY_SLOTS:-4} $input1 &&
15 samtools index -@ \${GALAXY_SLOTS:-4} $input2 &&
16
17 ## TODO creation of symlinks because mutect2 want the extensions of the file
18 ln -s $input1 tumor.bam &&
19 ln -s $input2 normal.bam &&
20 ln -s $input1".bai" tumor.bam.bai &&
21 ln -s $input2".bai" normal.bam.bai &&
22 #if $reference_source == "history"
23 ln -s $reference genome.fa &&
24 ln -s $reference".fai" genome.fa.fai
25 #end if
26 #if $list
27 ln -s $list position.bed &&
28 #end if
29 #if $dbSNP
30 ln -s $dbSNP dbSNP.vcf &&
31 #end if
32 #if $cosmic
33 ln -s $cosmic cosmic.vcf &&
34 #end if
35 #if $alleles
36 ln -s $alleles alleles.vcf
37 #end if
38
39 ##TODO creation of .dict file of the genome required by mutect2 to run
40 #if $reference_source == "history"
41 java -jar \$CONDA_DEFAULT_ENV/share/picard-2.7.1-2/picard.jar CreateSequenceDictionary R= genome.fa O= genome.dict 2>$log
42 #end if
43
44 ##TODO gatk-register take the GenomeAnalysisTK-3.8-0-ge9d806836.tar.bz2 unzip it
45 ##and move the .jar file to \$CONDA_DEFAULT_ENV/opt/gatk-3.8/ then the mutect2 command is runned
46 gatk3-register \$_CONDA_DIR/../GenomeAnalysisTK-3.8-0-ge9d806836.tar.bz2 2>$log ;
47 java -jar \$CONDA_DEFAULT_ENV/opt/gatk-3.8/GenomeAnalysisTK.jar -nct \${GALAXY_SLOTS:-4} -T MuTect2 -I:tumor tumor.bam -I:normal normal.bam -o $output
48 #if $reference_source == "history"
49 -R genome.fa
50 #else
51 -R $reference_source.ref_file.fields.path
52 #end if
53 ## TODO advanced inputs section if the optional inputs are present their options are added to the command
54 #if $dbSNP
55 --dbsnp dbSNP.vcf
56 #end if
57 #if $cosmic
58 --cosmic cosmic.vcf
59 #end if
60 #if $list
61 -L position.bed
62 #end if
63 #if $alleles
64 --alleles alleles.vcf
65 #end if
66
67 ##TODO advanced options section if the options inputs are different from the default value the option is added to the command
68
69 #if str($advanced.advanced_parameters) =="show":
70 #if $advanced.heterozygosity != "0.001"
71 --heterozygosity $advanced.heterozygosity
72 #end if
73 #if $advanced.heterozygosity_stdev != "0.01"
74 --heterozygosity_stdev $advanced.heterozygosity_stdev
75 #end if
76 #if $advanced.indel_heterozygosity != "1.25E-4"
77 --indel_heterozygosity $advanced.indel_heterozygosity
78 #end if
79 #if $advanced.initial_normal_lod != "0.5"
80 --initial_normal_lod $advanced.initial_normal_lod
81 #end if
82 #if $advanced.initial_tumor_lod != "4.0"
83 --initial_tumor_lod $advanced.initial_tumor_lod
84 #end if
85 #if $advanced.max_alt_allele_in_normal_fraction != "0.03"
86 --max_alt_allele_in_normal_fraction $advanced.max_alt_allele_in_normal_fraction
87 #end if
88 #if $advanced.max_alt_alleles_in_normal_count != "1"
89 --max_alt_alleles_in_normal_count $advanced.max_alt_alleles_in_normal_count
90 #end if
91 #if $advanced.max_alt_alleles_in_normal_qscore_sum != "20"
92 --max_alt_alleles_in_normal_qscore_sum $advanced.max_alt_alleles_in_normal_qscore_sum
93 #end if
94 #if $advanced.maxReadsInRegionPerSample != "1000"
95 --maxReadsInRegionPerSample $advanced.maxReadsInRegionPerSample
96 #end if
97 #if $advanced.min_base_quality_score != "10"
98 --min_base_quality_score $advanced.min_base_quality_score
99 #end if
100 #if $advanced.minReadsPerAlignmentStart != "5"
101 --minReadsPerAlignmentStart $advanced.minReadsPerAlignmentStart
102 #end if
103 #if $advanced.normal_lod != "2.2"
104 --normal_lod $advanced.normal_lod
105 #end if
106 #if $advanced.pir_mad_threshold != "3.0"
107 --pir_mad_threshold $advanced.pir_mad_threshold
108 #end if
109 #if $advanced.pir_median_threshold != "10.0"
110 --pir_median_threshold $advanced.pir_median_threshold
111 #end if
112 #if $advanced.power_constant_qscore != "30"
113 --power_constant_qscore $advanced.power_constant_qscore
114 #end if
115 #if $advanced.sample_ploidy != "2"
116 --sample_ploidy $advanced.sample_ploidy
117 #end if
118 #if $advanced.standard_min_confidence_threshold_for_calling != "10.0"
119 --standard_min_confidence_threshold_for_calling $advanced.standard_min_confidence_threshold_for_calling
120 #end if
121 #if $advanced.tumor_lod != "6.3"
122 --tumor_lod $advanced.tumor_lod
123 #end if
124 #if $advanced.contamination_fraction_to_filter != "0.0"
125 --contamination_fraction_to_filter $contamination_fraction_to_filter
126 #end if
127 #if $advanced.dbsnp_normal_lod != "5.5"
128 --dbsnp_normal_lod $dbsnp_normal_lod
129 #end if
130 #if $advanced.debug_read_name != ""
131 --debug_read_name $debug_read_name
132 #end if
133 #if $advanced.genotyping_mode != "DISCOVERY"
134 --genotyping_mode $genotyping_mode
135 #end if
136 #if $advanced.group
137 --group $advanced.group
138 #end if
139 #end if
140
141 ##TODO output section --> if the option string == "yes" the optional output is added
142 #if str($optional_out1.outFile1) =="yes"
143 --activeRegionOut $activeRegionOut_output
144 #end if
145 #if str($optional_out2.outFile2) =="yes"
146 --activityProfileOut $activityProfileOut_output
147 #end if
148 #if str($optional_out3.outFile3) =="yes"
149 --graphOutput $graphOutput_output
150 #end if
151 #if str($optional_out4.outFile4) =="yes"
152 --bamOutput $bamOutput_output
153 #end if
154 ##TODO the standard error is redirected to the log file
155 2> $log
156 ]]></command>
157 <inputs>
158 <expand macro="reference_loc"/>
159 <param format="bam" name="input1" type="data" label="tumor bam" help="bamfile"/>
160 <param format="bam" name="input2" type="data" label="normal bam" help="bamfile"/>
161 <param format="vcf" name="dbSNP" type="data" optional="true" label="dbsnp file.vcf" help="vcf file"/>
162 <param format="vcf" name="cosmic" type="data" optional="true" label="cosmic file.vcf" help="vcf file"/>
163 <param format="bed" name="list" type="data" optional="true" label="position list" help="bed file"/>
164 <param format="vcf" name="alleles" type="data" optional="true" label="set of alleles use in genotyping" help="vcf file"/>
165 <conditional name="advanced">
166 <param name="advanced_parameters" type="select" label="advanced_parameters">
167 <option value="hide" selected="true">Hide</option>
168 <option value="show">Show</option>
169 </param>
170 <when value="hide"/>
171 <when value="show">
172 <param name="heterozygosity" type="float" optional="true" value="0.001" help="Heterozygosity value used to compute prior likelihoods for any locus" />
173 <param name="heterozygosity_stdev" type="float" optional="true" value="0.01" help="Standard deviation of eterozygosity for SNP and indel calling"/>
174 <param name="indel_heterozygosity" type="text" value="1.25E-4" optional="true" help="Heterozygosity for indel calling" />
175 <param name="initial_normal_lod" type="float" optional="true" value="0.5" help="Initial LOD threshold for calling normal variant" />
176 <param name="initial_tumor_lod" type="float" optional="true" value="4.0" help="Initial LOD threshold for calling tumor variant" />
177 <param name="max_alt_allele_in_normal_fraction" type="float" optional="true" value="0.03" help="Threshold for maximum alternate allele fraction in normal" />
178 <param name="max_alt_alleles_in_normal_count" type="text" optional="true" value="1" help="Threshold for maximum alternate allele counts in normal" />
179 <param name="max_alt_alleles_in_normal_qscore_sum" type="text" optional="true" value="20" help="Threshold for maximum alternate allele quality score sum in normal" />
180 <param name="maxReadsInRegionPerSample" type="text" optional="true" value="1000" help="Maximum reads in an active region" />
181 <param name="min_base_quality_score" type="text" size="2" optional="true" value="10" help="Minimum base quality required to consider a base for calling" />
182 <param name="minReadsPerAlignmentStart" type="text" optional="true" value="5" help="Minimum number of reads sharing the same alignment start for each genomic location in an active region" />
183 <param name="normal_lod" type="float" optional="true" value="2.2" help="LOD threshold for calling normal non-germline" />
184 <param name="pir_mad_threshold" type="float" optional="true" value="3.0" help="threshold for clustered read position artifact MAD" />
185 <param name="pir_median_threshold" type="float" optional="true" value="10.0" help="threshold for clustered read position artifact median" />
186 <param name="power_constant_qscore" type="text" optional="true" value="30" help="Phred scale quality score constant to use in power calculations" />
187 <param name="sample_ploidy" type="text" optional="true" value="2" help="ploidy per sample" />
188 <param name="standard_min_confidence_threshold_for_calling" type="float" optional="true" value="10.0" help="The minimum phred-scaled confidence threshold at which variants should be called" />
189 <param name="tumor_lod" type="float" optional="true" value="6.3" help="LOD threshold for calling tumor variant" />
190 <param name="contamination_fraction_to_filter" type="float" optional="true" value="0.0" help="Fraction of contamination to aggressively remove" />
191 <param name="dbsnp_normal_lod" type="float" optional="true" value="5.5" help="LOD threshold for calling normal non-variant at dbsnp sites" />
192 <param name="debug_read_name" type="text" optional="true" value="" help="trace this read name through the calling process" />
193 <param name="genotyping_mode" type="select" optional="true" help="Specifies how to determine the alternate alleles to use for genotyping" >
194 <option value="DISCOVERY" selected="true">DISCOVERY</option>
195 <option value="GENOTYPE_GIVEN_ALLELES">GENOTYPE_GIVEN_ALLELES</option>
196 </param>
197 <param name="group" type="text" optional="true" help="one or more classes, groups of annotation to apply to variant call" />
198 </when>
199 </conditional>
200 <conditional name="optional_out1">
201 <param name="outFile1" type="select" label="activeRegionOut">
202 <option value="no" selected="true">no</option>
203 <option value="yes">yes</option>
204 </param>
205 <when value="no"/>
206 <when value="yes"/>
207 </conditional>
208 <conditional name="optional_out2">
209 <param name="outFile2" type="select" label="activityprofileOut">
210 <option value="no" selected="true">no</option>
211 <option value="yes">yes</option>
212 </param>
213 <when value="no"/>
214 <when value="yes"/>
215 </conditional>
216 <conditional name="optional_out3">
217 <param name="outFile3" type="select" label="graphOutput">
218 <option value="no" selected="true">no</option>
219 <option value="yes">yes</option>
220 </param>
221 <when value="no"/>
222 <when value="yes"/>
223 </conditional>
224 <conditional name="optional_out4">
225 <param name="outFile4" type="select" label="Bamoutput">
226 <option value="no" selected="true">no</option>
227 <option value="yes">yes</option>
228 </param>
229 <when value="no"/>
230 <when value="yes"/>
231 </conditional>
232 </inputs>
233 <outputs>
234 <data format="vcf" name="output" label="${tool.name} on ${on_string}"/>
235 <data format="txt" name="log" label="${tool.name} on ${on_string} :log"/>
236 <data format="txt" name="activeRegionOut_output" optional="true" label="${tool.name} on ${on_string} :activeRegionOut">
237 <filter>optional_out1['outFile1'] == 'yes'</filter>
238 </data>
239 <data format="txt" name="activityProfileOut_output" label="${tool.name} on ${on_string} :activityProfileOut">
240 <filter>optional_out2['outFile2'] == 'yes'</filter>
241 </data>
242 <data format="txt" name="graphOutput_output" label="${tool.name} on ${on_string} :graphOutput">
243 <filter>optional_out3['outFile3'] == 'yes'</filter>
244 </data>
245 <data format="txt" name="bamOutput_output" label="${tool.name} on ${on_string} :bamOutput">
246 <filter>optional_out4['outFile4'] == 'yes'</filter>
247 </data>
248 </outputs>
249 <tests>
250 <test>
251 <conditional name="reference_source">
252 <param name="reference_source_selector" value="history"/>
253 <param name="ref_file" value="test_fasta.fa"/>
254 </conditional>
255 <param name="input1" value="mutect2_test_tumoral2.bam" />
256 <param name="input2" value="mutect2_test_normal2.bam" />
257 </test>
258 </tests>
259 <help>
260 **IMPORTANT** to get the wrapper ready to start the admin user have to download gatk GATK 3.8-0-ge9d806836 from the broadinstitute site https://software.broadinstitute.org/gatk/download/archive and then move it in the conda_prefix folder
261 the path of the conda_prefix is written in the galaxy.ini(or .yml) file
262
263 MuTect2 is a somatic SNP and indel caller that combines the DREAM challenge-winning somatic genotyping engine of the original MuTect (Cibulskis et al., 2013) with the assembly-based machinery of HaplotypeCaller.
264 Galaxy wrapper for MuTect2 implements most but not all options available through the command line. Supported options are described below.
265
266 **Optional Inputs**
267
268 + --alleles none Set of alleles to use in genotyping
269 + --cosmic [] VCF file of COSMIC sites
270 + --dbsnp none dbSNP file
271 + --activityProfileOut NA Output the raw activity profile results in IGV format
272 + --graphOutput NA Write debug assembly graph information to this file
273
274 **Optional Parameters**
275
276 + --contamination_fraction_to_filter 0.0 Fraction of contamination to aggressively remove
277 + --dbsnp_normal_lod 5.5 LOD threshold for calling normal non-variant at dbsnp sites
278 + --debug_read_name NA trace this read name through the calling process
279 + --genotyping_mode DISCOVERY Specifies how to determine the alternate alleles to use for genotyping
280 + --group [] One or more classes/groups of annotations to apply to variant calls
281 + --heterozygosity 0.001 Heterozygosity value used to compute prior likelihoods for any locus
282 + --heterozygosity_stdev 0.01 Standard deviation of eterozygosity for SNP and indel calling
283 + --indel_heterozygosity 1.25E-4 Heterozygosity for indel calling
284 + --initial_normal_lod 0.5 Initial LOD threshold for calling normal variant
285 + --initial_tumor_lod 4.0 Initial LOD threshold for calling tumor variant
286 + --max_alt_allele_in_normal_fraction 0.03 Threshold for maximum alternate allele fraction in normal
287 + --max_alt_alleles_in_normal_count 1 Threshold for maximum alternate allele counts in normal
288 + --max_alt_alleles_in_normal_qscore_sum 20 Threshold for maximum alternate allele quality score sum in normal
289 + --maxReadsInRegionPerSample 1000 Maximum reads in an active region
290 + --min_base_quality_score 10 Minimum base quality required to consider a base for calling
291 + --minReadsPerAlignmentStart 5 Minimum number of reads sharing the same alignment start for each genomic location in an active region
292 + --normal_lod 2.2 LOD threshold for calling normal non-germline
293 + --pir_mad_threshold 3.0 threshold for clustered read position artifact MAD
294 + --pir_median_threshold 10.0 threshold for clustered read position artifact median
295 + --power_constant_qscore 30 Phred scale quality score constant to use in power calculations
296 + --sample_ploidy 2 Ploidy per sample. For pooled data, set to (Number of samples in each pool * Sample Ploidy).
297 + --standard_min_confidence_threshold_for_calling 10.0 The minimum phred-scaled confidence threshold at which variants should be called
298 + --tumor_lod 6.3 LOD threshold for calling tumor variant
299
300 **Advanced Outputs**
301
302 + --bamOutput
303 + --activeRegionOut
304 + --activityProfileOut
305 + --graphOutput
306
307 more information at https://software.broadinstitute.org/gatk/documentation/tooldocs/3.8-0/org_broadinstitute_gatk_tools_walkers_cancer_m2_MuTect2.php
308 </help>
309 <citations>
310 <citation type="doi">10.1038/nbt.2514</citation>
311 </citations>
312 </tool>