Mercurial > repos > jjohnson > snpeff

comparison snpEff.xml @ 0:e1d9f6a0ad53

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded
author jjohnson
date Thu, 04 Jul 2013 10:43:55 -0400
parents
children 6ad9205c1307
comparison
equal deleted inserted replaced
-1:000000000000 0:e1d9f6a0ad53
1 <tool id="snpEff" name="SnpEff" version="3.2">
2 <description>Variant effect and annotation</description>
3 <!--
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)
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
62 -->
63 <requirements>
64 <requirement type="package" version="3.2">snpEff</requirement>
65 </requirements>
66 <command>
67 SNPEFF_DATA_DIR=`grep '^data_dir' \$JAVA_JAR_PATH/snpEff.config | sed 's/.*data_dir.*[=:]//'`;
68 eval "if [ ! -e \$SNPEFF_DATA_DIR/$genomeVersion ] ;
69 then java -Xmx6G -jar \$JAVA_JAR_PATH/snpEff.jar download -c \$JAVA_JAR_PATH/snpEff.config $genomeVersion ;
70 fi";
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>
106 <inputs>
107 <param format="vcf,tabular,pileup,bed" name="input" type="data" label="Sequence changes (SNPs, MNPs, InDels)"/>
108
109 <param name="inputFormat" type="select" label="Input format">
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>
118 <option value="txt">Tabular</option>
119 <option value="bed">BED</option>
120 <option value="bedAnn">BED Annotations</option>
121 </param>
122
123 <param name="genomeVersion" type="select" label="Genome">
124 <!--GENOME DESCRIPTION-->
125 <options from_data_table="snpeff_genomedb"/>
126 </param>
127
128 <param name="udLength" type="select" label="Upstream / Downstream length">
129 <option value="0">No upstream / downstream intervals (0 bases)</option>
130 <option value="200">200 bases</option>
131 <option value="500">500 bases</option>
132 <option value="1000">1000 bases</option>
133 <option value="2000">2000 bases</option>
134 <option value="5000" selected="true">5000 bases</option>
135 <option value="10000">10000 bases</option>
136 <option value="20000">20000 bases</option>
137 </param>
138
139 <param name="spliceSiteSize" type="select" optional="true" label="Set size for splice sites (donor and acceptor) in bases. Default: 2">
140 <option value="1">1 base</option>
141 <option value="2">2 bases</option>
142 <option value="3">3 bases</option>
143 <option value="4">4 bases</option>
144 <option value="5">5 bases</option>
145 <option value="6">6 bases</option>
146 <option value="7">7 bases</option>
147 <option value="8">8 bases</option>
148 <option value="9">9 bases</option>
149 </param>
150
151 <param name="filterHomHet" type="select" display="radio" label="Filter homozygous / heterozygous changes">
152 <option value="no_filter" selected="true">No filter (analyze everything)</option>
153 <option value="hom">Analyze homozygous sequence changes only </option>
154 <option value="het">Analyze heterozygous sequence changes only </option>
155 </param>
156
157 <!-- The tool testing code can not handle select,radio,check boxes values that start with '-', so the '-' is added in the command generation -->
158 <param name="filterIn" type="select" display="radio" label="Filter sequence changes">
159 <option value="no_filter" selected="true">No filter (analyze everything)</option>
160 <option value="del">Analyze deletions only </option>
161 <option value="ins">Analyze insertions only </option>
162 <option value="mnp">Only MNPs (multiple nucleotide polymorphisms) </option>
163 <option value="snp">Only SNPs (single nucleotide polymorphisms) </option>
164 </param>
165
166 <param name="annotations" type="select" display="checkboxes" multiple="true" label="Annotation options">
167 <option value="cancer">Perform 'cancer' comparissons (Somatic vs Germline). Default: false</option>
168 <option value="canon">Only use canonical transcripts.</option>
169 <option value="geneId">Use gene ID instead of gene name (VCF output). Default: false</option>
170 <option value="hgvs">Use HGVS annotations for amino acid sub-field. Default: false</option>
171 <option value="lof">Add loss of function (LOF) and Nonsense mediated decay (NMD) tags.</option>
172 <option value="oicr">Add OICR tag in VCF file. Default: false</option>
173 <option value="onlyReg">Only use regulation tracks.</option>
174 <option value="sequenceOntolgy">Use Sequence Ontolgy terms. Default: false</option>
175 </param>
176
177 <param name="regulation" type="select" display="checkboxes" multiple="true" label="Non-coding and regulatory Annotation">
178 <help>These are available for only a few genomes</help>
179 <!--GENOME REG_NAME -->
180 <options from_data_table="snpeffect_regulationdb">
181 <filter type="param_value" ref="genomeVersion" key="name" column="1" />
182 </options>
183 </param>
184
185 <param name="intervals" format="bed" type="data" optional="true" label="Use custom interval file for annotation"/>
186 <param name="transcripts" format="tabular" type="data" optional="true" label="Only use the transcripts in this file. Format: One transcript ID per line."/>
187
188 <param name="filterOut" type="select" display="checkboxes" multiple="true" label="Filter output">
189 <option value="no-downstream">Do not show DOWNSTREAM changes </option>
190 <option value="no-intergenic">Do not show INTERGENIC changes </option>
191 <option value="no-intron">Do not show INTRON changes </option>
192 <option value="no-upstream">Do not show UPSTREAM changes </option>
193 <option value="no-utr">Do not show 5_PRIME_UTR or 3_PRIME_UTR changes </option>
194 </param>
195
196 <param name="offset" type="select" display="radio" optional="true" label="Chromosomal position">
197 <option value="" selected="true">Use default (based on input type)</option>
198 <option value="0">Force zero-based positions (both input and output)</option>
199 <option value="1">Force one-based positions (both input and output)</option>
200 </param>
201 <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.">
202 <validator type="regex" message="No whitespace allows">^\S*$</validator>
203
204 </param>
205 <param name="generate_stats" type="boolean" truevalue="" falsevalue="-noStats" checked="true" label="Produce Summary Stats"/>
206 <param name="noLog" type="boolean" truevalue="-noLog" falsevalue="" checked="true" label="Do not report usage statistics to server"/>
207 </inputs>
208 <outputs>
209 <data format="vcf" name="snpeff_output" >
210 <change_format>
211 <when input="outputFormat" value="vcf" format="vcf" />
212 <when input="outputFormat" value="txt" format="tabular" />
213 <when input="outputFormat" value="bed" format="bed" />
214 <when input="outputFormat" value="bedAnn" format="bed" />
215 </change_format>
216 </data>
217
218 <data format="html" name="statsFile">
219 <filter>generate_stats == True</filter>
220 </data>
221 </outputs>
222 <stdio>
223 <exit_code range="1:" level="fatal" description="Error" />
224 <exit_code range="-1" level="fatal" description="Error: Cannot open file" />
225 </stdio>
226 <tests>
227 <test>
228 <param name="input" ftype="vcf" value="vcf_homhet.vcf"/>
229 <param name="inputFormat" value="vcf"/>
230 <param name="outputFormat" value="vcf"/>
231 <param name="genomeVersion" value="testCase"/>
232 <param name="udLength" value="0"/>
233 <param name="filterHomHet" value="no_filter"/>
234 <param name="filterIn" value="no_filter"/>
235 <param name="generate_stats" value="False"/>
236 <!--
237 <param name="filterOut" value="no-upstream"/>
238 -->
239 <output name="snpeff_output">
240 <assert_contents>
241 <!-- Check that an effect was added -->
242 <has_text text="EFF=" />
243 </assert_contents>
244 </output>
245 <!-- Check for a HTML header indicating that this was successful -->
246 <!--
247 <output name="statsFile">
248 <assert_contents>
249 <has_text text="SnpEff: Variant analysis" />
250 </assert_contents>
251 </output>
252 -->
253 </test>
254
255 <test>
256 <param name="input" ftype="vcf" value="vcf_homhet.vcf"/>
257 <param name="inputFormat" value="vcf"/>
258 <param name="outputFormat" value="vcf"/>
259 <param name="genomeVersion" value="testCase"/>
260 <param name="udLength" value="0"/>
261 <param name="filterHomHet" value="het"/>
262 <param name="filterIn" value="no_filter"/>
263 <!--
264 <param name="filterOut" value=""/>
265 -->
266 <param name="generate_stats" value="False"/>
267 <output name="snpeff_output">
268 <assert_contents>
269 <!-- Check that NO effects were added since -het is set -->
270 <not_has_text text="EFF=NON_SYNONYMOUS_CODING" />
271 </assert_contents>
272 </output>
273 </test>
274 <test>
275 <param name="input" ftype="vcf" value="vcf_homhet.vcf"/>
276 <param name="inputFormat" value="vcf"/>
277 <param name="outputFormat" value="vcf"/>
278 <param name="genomeVersion" value="testCase"/>
279 <param name="udLength" value="0"/>
280 <param name="filterHomHet" value="no_filter"/>
281 <param name="filterIn" value="del"/>
282 <!--
283 <param name="filterOut" value=""/>
284 -->
285 <param name="generate_stats" value="False"/>
286 <output name="snpeff_output">
287 <assert_contents>
288 <!-- Check that deleletions were evaluated -->
289 <has_text_matching expression="Y\t59030478\t.*EFF=INTERGENIC" />
290 <!-- Check that insertion on last line was NOT evaluated -->
291 <has_text_matching expression="Y\t59032947\t.*SF=5\tGT" />
292 </assert_contents>
293 </output>
294 </test>
295 <test>
296 <param name="input" ftype="vcf" value="vcf_homhet.vcf"/>
297 <param name="inputFormat" value="vcf"/>
298 <param name="outputFormat" value="vcf"/>
299 <param name="genomeVersion" value="testCase"/>
300 <param name="udLength" value="0"/>
301 <param name="filterHomHet" value="no_filter"/>
302 <param name="filterIn" value="no_filter"/>
303 <param name="filterOut" value="no-upstream"/>
304 <param name="generate_stats" value="False"/>
305 <output name="snpeff_output">
306 <assert_contents>
307 <!-- Check that NO UPSTREAM effect was added -->
308 <not_has_text text="UPSTREAM" />
309 </assert_contents>
310 </output>
311 </test>
312
313 </tests>
314 <help>
315
316 This tool calculate the effect of variants (SNPs/MNPs/Insertions) and deletions.
317
318 For details about this tool, please go to http://snpEff.sourceforge.net
319
320 </help>
321 </tool>
322