Mercurial > repos > jjohnson > snpeff_with_dep

comparison snpEff.xml @ 24:f22f28cd881e

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Update for snpEff v3.2
author Jim Johnson <jj@umn.edu>
date Tue, 07 May 2013 14:58:15 -0500
parents 50c1a8ff6c82
children
comparison
equal deleted inserted replaced
23:50c1a8ff6c82 24:f22f28cd881e
1 <tool id="snpEff" name="SnpEff" version="3.1"> 1 <tool id="snpEff" name="SnpEff" version="3.2">
2 <description>Variant effect and annotation</description> 2 <description>Variant effect and annotation</description>
3 <!-- 3 <!--
4 You will need to change the path to wherever your installation is. 4 You will need to change the path to wherever your installation is.
5 You can change the amount of memory used by snpEff, just change the -Xmx parameter (e.g. use -Xmx2G for 2Gb of memory) 5 You can change the amount of memory used by snpEff, just change the -Xmx parameter (e.g. use -Xmx2G for 2Gb of memory)
6 <command>java -Xmx6G -jar /path/to/your/snpEff/snpEff.jar eff -c /path/to/your/snpEff/snpEff/snpEff.config $inputFormat $offset -upDownStreamLen $udLength $filterIn $filterHomHet -no $filterOut -stats $statsFile $genomeVersion $input > $output </command> 6 <command>java -Xmx6G -jar /path/to/your/snpEff/snpEff.jar eff -c /path/to/your/snpEff/snpEff/snpEff.config $inputFormat $offset -upDownStreamLen $udLength $filterIn $filterHomHet -no $filterOut -stats $statsFile $genomeVersion $input > $output </command>
7 Options:
8 -a , -around : Show N codons and amino acids around change (only in coding regions). Default is 0 codons.
9 -i <format> : Input format [ vcf, txt, pileup, bed ]. Default: VCF.
10 -o <format> : Ouput format [ txt, vcf, gatk, bed, bedAnn ]. Default: VCF.
11 -interval : Use a custom interval file (you may use this option many times)
12 -chr <string> : Prepend 'string' to chromosome name (e.g. 'chr1' instead of '1'). Only on TXT output.
13 -s, -stats : Name of stats file (summary). Default is 'snpEff_summary.html'
14 -t : Use multiple threads (implies '-noStats'). Default 'off'
15
16 Sequence change filter options:
17 -del : Analyze deletions only
18 -ins : Analyze insertions only
19 -hom : Analyze homozygous variants only
20 -het : Analyze heterozygous variants only
21 -minQ X, -minQuality X : Filter out variants with quality lower than X
22 -maxQ X, -maxQuality X : Filter out variants with quality higher than X
23 -minC X, -minCoverage X : Filter out variants with coverage lower than X
24 -maxC X, -maxCoverage X : Filter out variants with coverage higher than X
25 -nmp : Only MNPs (multiple nucleotide polymorphisms)
26 -snp : Only SNPs (single nucleotide polymorphisms)
27
28 Results filter options:
29 -fi <bedFile> : Only analyze changes that intersect with the intervals specified in this file (you may use this option many times)
30 -no-downstream : Do not show DOWNSTREAM changes
31 -no-intergenic : Do not show INTERGENIC changes
32 -no-intron : Do not show INTRON changes
33 -no-upstream : Do not show UPSTREAM changes
34 -no-utr : Do not show 5_PRIME_UTR or 3_PRIME_UTR changes
35
36 Annotations options:
37 -cancer : Perform 'cancer' comparissons (Somatic vs Germline). Default: false
38 -canon : Only use canonical transcripts.
39 -geneId : Use gene ID instead of gene name (VCF output). Default: false
40 -hgvs : Use HGVS annotations for amino acid sub-field. Default: false
41 -lof : Add loss of function (LOF) and Nonsense mediated decay (NMD) tags.
42 -reg <name> : Regulation track to use (this option can be used add several times).
43 -oicr : Add OICR tag in VCF file. Default: false
44 -onlyReg : Only use regulation tracks.
45 -onlyTr <file.txt> : Only use the transcripts in this file. Format: One transcript ID per line.
46 -sequenceOntolgy : Use Sequence Ontolgy terms. Default: false
47 -ss, -spliceSiteSize <int> : Set size for splice sites (donor and acceptor) in bases. Default: 2
48 -ud, -upDownStreamLen <int> : Set upstream downstream interval length (in bases)
49
50 Generic options:
51 -0 : File positions are zero-based (same as '-inOffset 0 -outOffset 0')
52 -1 : File positions are one-based (same as '-inOffset 1 -outOffset 1')
53 -c , -config : Specify config file
54 -h , -help : Show this help and exit
55 -if, -inOffset : Offset input by a number of bases. E.g. '-inOffset 1' for one-based input files
56 -of, -outOffset : Offset output by a number of bases. E.g. '-outOffset 1' for one-based output files
57 -noLog : Do not report usage statistics to server
58 -noStats : Do not create stats (summary) file
59 -q , -quiet : Quiet mode (do not show any messages or errors)
60 -v , -verbose : Verbose mode
61
7 --> 62 -->
8 <requirements> 63 <requirements>
9 <requirement type="package" version="3.1">snpEff</requirement> 64 <requirement type="package" version="3.2">snpEff</requirement>
10 </requirements> 65 </requirements>
11 <command> 66 <command>
12 export SNPEFF_DATA_DIR=`grep '^data_dir' \$JAVA_JAR_PATH/snpEff.config | sed 's/.*data_dir.*[=:]//'`; 67 SNPEFF_DATA_DIR=`grep '^data_dir' \$JAVA_JAR_PATH/snpEff.config | sed 's/.*data_dir.*[=:]//'`;
13 if [ ! -e \$SNPEFF_DATA_DIR/$genomeVersion ] ; 68 eval "if [ ! -e \$SNPEFF_DATA_DIR/$genomeVersion ] ;
14 then java -Xmx6G -jar \$JAVA_JAR_PATH/snpEff.jar download -c \$JAVA_JAR_PATH/snpEff.config $genomeVersion ; 69 then java -Xmx6G -jar \$JAVA_JAR_PATH/snpEff.jar download -c \$JAVA_JAR_PATH/snpEff.config $genomeVersion ;
15 fi; 70 fi";
16 java -Xmx6G -jar \$JAVA_JAR_PATH/snpEff.jar eff -c \$JAVA_JAR_PATH/snpEff.config -i $inputFormat -o $outputFormat -upDownStreamLen $udLength $filterIn $filterHomHet -no $filterOut -stats $statsFile $genomeVersion $input > $output </command> 71 java -Xmx6G -jar \$JAVA_JAR_PATH/snpEff.jar eff -c \$JAVA_JAR_PATH/snpEff.config -i $inputFormat -o $outputFormat -upDownStreamLen $udLength
72 #if $spliceSiteSize and $spliceSiteSize.__str__ != '':
73 -spliceSiteSize $spliceSiteSize
74 #end if
75 #if $filterIn and $filterIn.__str__ != 'no_filter':
76 -$filterIn
77 #end if
78 #if $filterHomHet and $filterHomHet.__str__ != 'no_filter':
79 -$filterHomHet
80 #end if
81 #if $annotations and $annotations.__str__ != '':
82 -#slurp
83 #echo ' -'.join($annotations.__str__.split(','))
84 #end if
85 #if $filterOut and $filterOut.__str__ != '':
86 -#slurp
87 #echo ' -'.join($filterOut.__str__.split(','))
88 #end if
89 #if str( $transcripts ) != 'None':
90 -onlyTr $transcripts
91 #end if
92 #if str( $intervals ) != 'None': ### fix this for multiple dataset input
93 -interval $intervals
94 #end if
95 #if $statsFile:
96 -stats $statsFile
97 #end if
98 #if $offset.__str__ != '':
99 -${offset}
100 #end if
101 #if $chr.__str__.strip() != '':
102 -chr "$chr"
103 #end if
104 $noLog $genomeVersion $input > $snpeff_output
105 </command>
17 <inputs> 106 <inputs>
18 <param format="vcf,tabular,pileup,bed" name="input" type="data" label="Sequence changes (SNPs, MNPs, InDels)"/> 107 <param format="vcf,tabular,pileup,bed" name="input" type="data" label="Sequence changes (SNPs, MNPs, InDels)"/>
19 108
20 <param name="inputFormat" type="select" label="Input format"> 109 <param name="inputFormat" type="select" label="Input format">
21 <option value="vcf">VCF</option> 110 <option value="vcf" selected="true">VCF</option>
111 <option value="txt">Tabular (Deprecated)</option>
112 <option value="pileup">Pileup (Deprecated)</option>
113 <option value="bed">BED (Deprecated)</option>
114 </param>
115
116 <param name="outputFormat" type="select" label="Output format">
117 <option value="vcf" selected="true">VCF (only if input is VCF)</option>
22 <option value="txt">Tabular</option> 118 <option value="txt">Tabular</option>
23 <option value="pileup">Pileup</option>
24 <option value="bed">BED</option>
25 </param>
26
27 <param name="outputFormat" type="select" label="Output format">
28 <option value="txt">Tabular</option>
29 <option value="vcf">VCF (only if input is VCF)</option>
30 <option value="bed">BED</option> 119 <option value="bed">BED</option>
31 <option value="bedAnn">BED Annotations</option> 120 <option value="bedAnn">BED Annotations</option>
32 </param> 121 </param>
33 122
34 <param name="genomeVersion" type="select" label="Genome"> 123 <param name="genomeVersion" type="select" label="Genome">
124 <!--GENOME DESCRIPTION-->
35 <options from_file="snpeffect_genomedb.loc"> 125 <options from_file="snpeffect_genomedb.loc">
36 <column name="name" index="1"/> 126 <column name="name" index="1"/>
37 <column name="value" index="0"/> 127 <column name="value" index="0"/>
38 </options> 128 </options>
39 </param> 129 </param>
47 <option value="5000" selected="true">5000 bases</option> 137 <option value="5000" selected="true">5000 bases</option>
48 <option value="10000">10000 bases</option> 138 <option value="10000">10000 bases</option>
49 <option value="20000">20000 bases</option> 139 <option value="20000">20000 bases</option>
50 </param> 140 </param>
51 141
52 <param name="filterHomHet" type="select" display="radio" label="Filter homozygous / heterozygous changes"> 142 <param name="spliceSiteSize" type="select" optional="true" label="Set size for splice sites (donor and acceptor) in bases. Default: 2">
53 <option value="">No filter (analyze everything)</option> 143 <option value="1">1 base</option>
54 <option value="-hom">Analyze homozygous sequence changes only </option> 144 <option value="2">2 bases</option>
55 <option value="-het">Analyze heterozygous sequence changes only </option> 145 <option value="3">3 bases</option>
56 </param> 146 <option value="4">4 bases</option>
57 147 <option value="5">5 bases</option>
58 <param name="filterIn" type="select" display="radio" label="Filter sequence changes"> 148 <option value="6">6 bases</option>
59 <option value="">No filter (analyze everything)</option> 149 <option value="7">7 bases</option>
60 <option value="-del">Analyze deletions only </option> 150 <option value="8">8 bases</option>
61 <option value="-ins">Analyze insertions only </option> 151 <option value="9">9 bases</option>
62 <option value="-nmp">Only MNPs (multiple nucleotide polymorphisms) </option> 152 </param>
63 <option value="-snp">Only SNPs (single nucleotide polymorphisms) </option> 153
64 </param> 154 <param name="filterHomHet" type="select" display="radio" label="Filter homozygous / heterozygous changes">
65 155 <option value="no_filter" selected="true">No filter (analyze everything)</option>
66 <param name="filterOut" type="select" display="checkboxes" multiple="true" optional="false" value="None" label="Filter output"> 156 <option value="hom">Analyze homozygous sequence changes only </option>
67 <option value="None" selected="true">None</option> 157 <option value="het">Analyze heterozygous sequence changes only </option>
68 <option value="downstream">Do not show DOWNSTREAM changes </option> 158 </param>
69 <option value="intergenic">Do not show INTERGENIC changes </option> 159
70 <option value="intron">Do not show INTRON changes </option> 160 <!-- The tool testing code can not handle select,radio,checkbox values that start with '-', so the '-' is added in the command generation -->
71 <option value="upstream">Do not show UPSTREAM changes </option> 161 <param name="filterIn" type="select" display="radio" label="Filter sequence changes">
72 <option value="utr">Do not show 5_PRIME_UTR or 3_PRIME_UTR changes </option> 162 <option value="no_filter" selected="true">No filter (analyze everything)</option>
73 </param> 163 <option value="del">Analyze deletions only </option>
74 164 <option value="ins">Analyze insertions only </option>
75 <param name="offset" type="select" display="radio" optional="true" label="Chromosomal position"> 165 <option value="mnp">Only MNPs (multiple nucleotide polymorphisms) </option>
76 <option value="">Use default (based on input type)</option> 166 <option value="snp">Only SNPs (single nucleotide polymorphisms) </option>
77 <option value="-0">Force zero-based positions (both input and output)</option> 167 </param>
78 <option value="-1">Force one-based positions (both input and output)</option> 168
79 </param> 169 <param name="annotations" type="select" display="checkboxes" multiple="true" optional="true" label="Annotation options">
170 <option value="cancer">Perform 'cancer' comparissons (Somatic vs Germline). Default: false</option>
171 <option value="canon">Only use canonical transcripts.</option>
172 <option value="geneId">Use gene ID instead of gene name (VCF output). Default: false</option>
173 <option value="hgvs">Use HGVS annotations for amino acid sub-field. Default: false</option>
174 <option value="lof">Add loss of function (LOF) and Nonsense mediated decay (NMD) tags.</option>
175 <option value="oicr">Add OICR tag in VCF file. Default: false</option>
176 <option value="onlyReg">Only use regulation tracks.</option>
177 <option value="sequenceOntolgy">Use Sequence Ontolgy terms. Default: false</option>
178 </param>
179
180 <param name="regulation" type="select" display="checkboxes" multiple="true" optional="true" label="Non-coding and regulatory Annotation">
181 <help>These are available for only a few genomes</help>
182 <!--GENOME REG_NAME -->
183 <options from_file="snpeffect_regulationdb.loc">
184 <column name="name" index="1"/>
185 <column name="value" index="0"/>
186 <filter type="param_value" ref="genomeVersion" key="name" column="1" />
187 </options>
188 </param>
189
190 <param name="intervals" format="bed" type="data" optional="true" label="Use custom interval file for annotation"/>
191 <param name="transcripts" format="tabular" type="data" optional="true" label="Only use the transcripts in this file. Format: One transcript ID per line."/>
192
193 <param name="filterOut" type="select" display="checkboxes" multiple="true" optional="true" label="Filter output">
194 <option value="no-downstream">Do not show DOWNSTREAM changes </option>
195 <option value="no-intergenic">Do not show INTERGENIC changes </option>
196 <option value="no-intron">Do not show INTRON changes </option>
197 <option value="no-upstream">Do not show UPSTREAM changes </option>
198 <option value="no-utr">Do not show 5_PRIME_UTR or 3_PRIME_UTR changes </option>
199 </param>
200
201 <param name="offset" type="select" display="radio" optional="true" label="Chromosomal position">
202 <option value="" selected="true">Use default (based on input type)</option>
203 <option value="0">Force zero-based positions (both input and output)</option>
204 <option value="1">Force one-based positions (both input and output)</option>
205 </param>
206 <param name="chr" type="text" optionl="true" label="Text to prepend to chromosome name" help="By default SnpEff simplifies all chromosome names. For instance 'chr1' is just '1'. You can prepend any string you want to the chromosome name.">
207 <validator type="regex" message="No whitespace allows">^\S*$</validator>
208
209 </param>
210 <param name="generate_stats" type="boolean" truevalue="" falsevalue="-noStats" checked="true" label="Produce Summary Stats"/>
211 <param name="noLog" type="boolean" truevalue="-noLog" falsevalue="" checked="true" label="Do not report usage statistics to server"/>
80 </inputs> 212 </inputs>
81 <outputs> 213 <outputs>
82 <data format="tabular" name="output" > 214 <data format="vcf" name="snpeff_output" >
83 <change_format> 215 <change_format>
216 <when input="outputFormat" value="vcf" format="vcf" />
84 <when input="outputFormat" value="txt" format="tabular" /> 217 <when input="outputFormat" value="txt" format="tabular" />
85 <when input="outputFormat" value="vcf" format="vcf" />
86 <when input="outputFormat" value="bed" format="bed" /> 218 <when input="outputFormat" value="bed" format="bed" />
87 <when input="outputFormat" value="bedAnn" format="bed" /> 219 <when input="outputFormat" value="bedAnn" format="bed" />
88 </change_format> 220 </change_format>
89 </data> 221 </data>
90 <data format="html" name="statsFile" /> 222
223 <data format="html" name="statsFile">
224 <filter>generate_stats == True</filter>
225 </data>
91 </outputs> 226 </outputs>
92 <stdio> 227 <stdio>
93 <exit_code range=":-1" level="fatal" description="Error: Cannot open file" />
94 <exit_code range="1:" level="fatal" description="Error" /> 228 <exit_code range="1:" level="fatal" description="Error" />
229 <exit_code range="-1" level="fatal" description="Error: Cannot open file" />
95 </stdio> 230 </stdio>
231 <tests>
232 <test>
233 <param name="input" ftype="vcf" value="vcf_homhet.vcf"/>
234 <param name="inputFormat" value="vcf"/>
235 <param name="outputFormat" value="vcf"/>
236 <param name="genomeVersion" value="testCase"/>
237 <param name="udLength" value="0"/>
238 <param name="filterHomHet" value="no_filter"/>
239 <param name="filterIn" value="no_filter"/>
240 <param name="generate_stats" value="False"/>
241 <!--
242 <param name="filterOut" value="no-upstream"/>
243 -->
244 <output name="snpeff_output">
245 <assert_contents>
246 <!-- Check that an effect was added -->
247 <has_text text="EFF=" />
248 </assert_contents>
249 </output>
250 <!-- Check for a HTML header indicating that this was successful -->
251 <!--
252 <output name="statsFile">
253 <assert_contents>
254 <has_text text="SnpEff: Variant analysis" />
255 </assert_contents>
256 </output>
257 -->
258 </test>
259
260 <test>
261 <param name="input" ftype="vcf" value="vcf_homhet.vcf"/>
262 <param name="inputFormat" value="vcf"/>
263 <param name="outputFormat" value="vcf"/>
264 <param name="genomeVersion" value="testCase"/>
265 <param name="udLength" value="0"/>
266 <param name="filterHomHet" value="het"/>
267 <param name="filterIn" value="no_filter"/>
268 <!--
269 <param name="filterOut" value=""/>
270 -->
271 <param name="generate_stats" value="False"/>
272 <output name="snpeff_output">
273 <assert_contents>
274 <!-- Check that NO effects were added since -het is set -->
275 <not_has_text text="EFF=NON_SYNONYMOUS_CODING" />
276 </assert_contents>
277 </output>
278 </test>
279 <test>
280 <param name="input" ftype="vcf" value="vcf_homhet.vcf"/>
281 <param name="inputFormat" value="vcf"/>
282 <param name="outputFormat" value="vcf"/>
283 <param name="genomeVersion" value="testCase"/>
284 <param name="udLength" value="0"/>
285 <param name="filterHomHet" value="no_filter"/>
286 <param name="filterIn" value="del"/>
287 <!--
288 <param name="filterOut" value=""/>
289 -->
290 <param name="generate_stats" value="False"/>
291 <output name="snpeff_output">
292 <assert_contents>
293 <!-- Check that deleletions were evaluated -->
294 <has_text_matching expression="Y\t59030478\t.*EFF=INTERGENIC" />
295 <!-- Check that insertion on last line was NOT evaluated -->
296 <has_text_matching expression="Y\t59032947\t.*SF=5\tGT" />
297 </assert_contents>
298 </output>
299 </test>
300 <test>
301 <param name="input" ftype="vcf" value="vcf_homhet.vcf"/>
302 <param name="inputFormat" value="vcf"/>
303 <param name="outputFormat" value="vcf"/>
304 <param name="genomeVersion" value="testCase"/>
305 <param name="udLength" value="0"/>
306 <param name="filterHomHet" value="no_filter"/>
307 <param name="filterIn" value="no_filter"/>
308 <param name="filterOut" value="no-upstream"/>
309 <param name="generate_stats" value="False"/>
310 <output name="snpeff_output">
311 <assert_contents>
312 <!-- Check that NO UPSTREAM effect was added -->
313 <not_has_text text="UPSTREAM" />
314 </assert_contents>
315 </output>
316 </test>
317
318 </tests>
96 <help> 319 <help>
97 320
98 This tool calculate the effect of variants (SNPs/MNPs/Insertions) and deletions. 321 This tool calculate the effect of variants (SNPs/MNPs/Insertions) and deletions.
99 322
100 For details about this tool, please go to http://snpEff.sourceforge.net 323 For details about this tool, please go to http://snpEff.sourceforge.net