Mercurial > repos > iuc > snpeff

comparison snpEff.xml @ 0:e8adfc4c0a6b draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded
author iuc
date Wed, 11 Dec 2013 08:53:32 -0500
parents
children 500832f27cbc
comparison
equal deleted inserted replaced
-1:000000000000 0:e8adfc4c0a6b
1 <tool id="snpEff" name="SnpEff" version="3.4">
2 <description>Variant effect and annotation</description>
3 <expand macro="requirements" />
4 <macros>
5 <import>snpEff_macros.xml</import>
6 </macros>
7 <command>
8 java -Xmx6G -jar \$SNPEFF_JAR_PATH/snpEff.jar eff
9 -c \$SNPEFF_JAR_PATH/snpEff.config
10 -i $inputFormat -o $outputFormat -upDownStreamLen $udLength
11 #if $spliceSiteSize and $spliceSiteSize.__str__ != '':
12 -spliceSiteSize $spliceSiteSize
13 #end if
14 #if $filterIn and $filterIn.__str__ != 'no_filter':
15 $filterIn
16 #end if
17 #if $filterHomHet and $filterHomHet.__str__ != 'no_filter':
18 $filterHomHet
19 #end if
20 #if $annotations and $annotations.__str__ != '':
21 #echo " "
22 #echo ' '.join($annotations.__str__.split(','))
23 #end if
24 #if $filterOut and $filterOut.__str__ != '':
25 #echo " "
26 #echo ' '.join($filterOut.__str__.split(','))
27 #end if
28 #if str( $transcripts ) != 'None':
29 -onlyTr $transcripts
30 #end if
31 #if str( $intervals ) != 'None': ### fix this for multiple dataset input
32 -interval $intervals
33 #end if
34 #if $statsFile:
35 -stats $statsFile
36 #end if
37 #if $offset.__str__ != '':
38 ${offset}
39 #end if
40 #if $chr.__str__.strip() != '':
41 -chr "$chr"
42 #end if
43 $noLog
44 #if $snpDb.genomeSrc == 'cached':
45 -dataDir ${snpDb.genomeVersion.fields.path}
46 #if $snpDb.extra_annotations and $snpDb.extra_annotations.__str__ != '':
47 #echo " "
48 #echo ' '.join($snpDb.extra_annotations.__str__.split(','))
49 #end if
50 #if $snpDb.regulation and $snpDb.regulation.__str__ != '':
51 -reg #echo ' -reg '.join($snpDb.regulation.__str__.split(','))#
52 #end if
53 $snpDb.genomeVersion
54 #elif $snpDb.genomeSrc == 'history':
55 -dataDir ${snpDb.snpeff_db.extra_files_path}
56 #if $snpDb.extra_annotations and $snpDb.extra_annotations.__str__ != '':
57 #set xannotations = [' '] + $snpDb.extra_annotations.__str__.split(',')
58 #echo " "
59 #echo ' -'.join($xannotations)
60 #end if
61 #if $snpDb.regulation and $snpDb.regulation.__str__ != '':
62 -reg #echo ' -reg '.join($snpDb.regulation.__str__.split(','))#
63 #end if
64 ${snpDb.snpeff_db.metadata.genome_version}
65 #else
66 -download
67 $snpDb.genome_version
68 #end if
69 $input > $snpeff_output
70 </command>
71 <inputs>
72 <param format="vcf,tabular,pileup,bed" name="input" type="data" label="Sequence changes (SNPs, MNPs, InDels)"/>
73
74 <param name="inputFormat" type="select" label="Input format">
75 <option value="vcf" selected="true">VCF</option>
76 <option value="txt">Tabular (Deprecated)</option>
77 <option value="pileup">Pileup (Deprecated)</option>
78 <option value="bed">BED (Deprecated)</option>
79 </param>
80
81 <param name="outputFormat" type="select" label="Output format">
82 <option value="vcf" selected="true">VCF (only if input is VCF)</option>
83 <option value="txt">Tabular</option>
84 <option value="bed">BED</option>
85 <option value="bedAnn">BED Annotations</option>
86 </param>
87
88 <conditional name="snpDb">
89 <param name="genomeSrc" type="select" label="Genome source">
90 <option value="cached">Locally installed reference genome</option>
91 <option value="history">Reference genome from your history</option>
92 <option value="named">Named on demand</option>
93 </param>
94 <when value="cached">
95 <param name="genomeVersion" type="select" label="Genome">
96 <!--GENOME DESCRIPTION-->
97 <options from_data_table="snpeff_genomedb">
98 <filter type="unique_value" column="0" />
99 </options>
100 </param>
101 <param name="extra_annotations" type="select" display="checkboxes" multiple="true" label="Additional Annotations">
102 <help>These are available for only a few genomes</help>
103 <options from_data_table="snpeff_annotations">
104 <filter type="param_value" ref="genomeVersion" key="genome" column="0" />
105 <filter type="unique_value" column="1" />
106 </options>
107 </param>
108 <param name="regulation" type="select" display="checkboxes" multiple="true" label="Non-coding and regulatory Annotation">
109 <help>These are available for only a few genomes</help>
110 <options from_data_table="snpeff_regulationdb">
111 <filter type="param_value" ref="genomeVersion" key="genome" column="0" />
112 <filter type="unique_value" column="1" />
113 </options>
114 </param>
115 </when>
116 <when value="history">
117 <param format="snpeffdb" name="snpeff_db" type="data" label="SnpEff Genome Version Data"/>
118 <!-- From metadata -->
119 <param name="extra_annotations" type="select" display="checkboxes" multiple="true" label="Additional Annotations">
120 <help>These are available for only a few genomes</help>
121 <options>
122 <filter type="data_meta" ref="snpeff_db" key="annotation" />
123 </options>
124 </param>
125 <param name="regulation" type="select" display="checkboxes" multiple="true" label="Non-coding and regulatory Annotation">
126 <help>These are available for only a few genomes</help>
127 <options>
128 <filter type="data_meta" ref="snpeff_db" key="regulation" />
129 </options>
130 </param>
131 </when>
132 <when value="named">
133 <param name="genome_version" type="text" value="GRCh37.68" label="Snpff Version Name"/>
134 </when>
135 </conditional>
136
137 <param name="udLength" type="select" label="Upstream / Downstream length">
138 <option value="0">No upstream / downstream intervals (0 bases)</option>
139 <option value="200">200 bases</option>
140 <option value="500">500 bases</option>
141 <option value="1000">1000 bases</option>
142 <option value="2000">2000 bases</option>
143 <option value="5000" selected="true">5000 bases</option>
144 <option value="10000">10000 bases</option>
145 <option value="20000">20000 bases</option>
146 </param>
147
148 <param name="spliceSiteSize" type="select" optional="true" label="Set size for splice sites (donor and acceptor) in bases" help="Default: 2">
149 <option value="1">1 base</option>
150 <option value="2">2 bases</option>
151 <option value="3">3 bases</option>
152 <option value="4">4 bases</option>
153 <option value="5">5 bases</option>
154 <option value="6">6 bases</option>
155 <option value="7">7 bases</option>
156 <option value="8">8 bases</option>
157 <option value="9">9 bases</option>
158 </param>
159
160 <param name="filterHomHet" type="select" display="radio" label="Filter homozygous / heterozygous changes">
161 <option value="no_filter" selected="true">No filter (analyze everything)</option>
162 <option value="-hom">Analyze homozygous sequence changes only </option>
163 <option value="-het">Analyze heterozygous sequence changes only </option>
164 </param>
165
166 <!-- The tool testing code can not handle select,radio,check boxes values that start with '-', so the '-' is added in the command generation -->
167 <param name="filterIn" type="select" display="radio" label="Filter sequence changes">
168 <option value="no_filter" selected="true">No filter (analyze everything)</option>
169 <option value="-del">Analyze deletions only </option>
170 <option value="-ins">Analyze insertions only </option>
171 <option value="-mnp">Only MNPs (multiple nucleotide polymorphisms) </option>
172 <option value="-snp">Only SNPs (single nucleotide polymorphisms) </option>
173 </param>
174
175 <param name="annotations" type="select" display="checkboxes" multiple="true" label="Annotation options">
176 <option value="-cancer">Perform 'cancer' comparissons (Somatic vs Germline)</option>
177 <option value="-canon">Only use canonical transcripts</option>
178 <option value="-geneId">Use gene ID instead of gene name (VCF output)</option>
179 <option value="-hgvs">Use HGVS annotations for amino acid sub-field</option>
180 <option value="-lof">Add loss of function (LOF) and Nonsense mediated decay (NMD) tags</option>
181 <option value="-oicr">Add OICR tag in VCF file</option>
182 <option value="-onlyReg">Only use regulation tracks</option>
183 <option value="-sequenceOntolgy">Use Sequence Ontolgy terms.</option>
184 </param>
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." help="Format is one transcript ID per line."/>
187 <param name="filterOut" type="select" display="checkboxes" multiple="true" label="Filter output">
188 <option value="-no-downstream">Do not show DOWNSTREAM changes</option>
189 <option value="-no-intergenic">Do not show INTERGENIC changes</option>
190 <option value="-no-intron">Do not show INTRON changes</option>
191 <option value="-no-upstream">Do not show UPSTREAM changes</option>
192 <option value="-no-utr">Do not show 5_PRIME_UTR or 3_PRIME_UTR changes</option>
193 </param>
194
195 <param name="offset" type="select" display="radio" optional="true" label="Chromosomal position">
196 <option value="" selected="true">Use default (based on input type)</option>
197 <option value="-0">Force zero-based positions (both input and output)</option>
198 <option value="-1">Force one-based positions (both input and output)</option>
199 </param>
200 <param name="chr" type="text" optionl="true" label="Text to prepend to chromosome name">
201 <help>
202 By default SnpEff simplifies all chromosome names. For instance 'chr1' is just '1'.
203 You can prepend any string you want to the chromosome name.
204 </help>
205 <validator type="regex" message="No whitespace allowed">^\S*$</validator>
206 </param>
207 <param name="generate_stats" type="boolean" truevalue="" falsevalue="-noStats" checked="true" label="Produce Summary Stats"/>
208 <param name="noLog" type="boolean" truevalue="-noLog" falsevalue="" checked="true" label="Do not report usage statistics to server"/>
209 </inputs>
210 <outputs>
211 <data format="vcf" name="snpeff_output" >
212 <change_format>
213 <when input="outputFormat" value="vcf" format="vcf" />
214 <when input="outputFormat" value="txt" format="tabular" />
215 <when input="outputFormat" value="bed" format="bed" />
216 <when input="outputFormat" value="bedAnn" format="bed" />
217 </change_format>
218 </data>
219 <data format="html" name="statsFile">
220 <filter>generate_stats == True</filter>
221 </data>
222 </outputs>
223 <expand macro="stdio" />
224 <tests>
225 <!-- Check that an effect was added in out VCF -->
226 <!-- Check for a HTML header indicating that this was successful -->
227 <!--
228 <output name="statsFile">
229 <assert_contents>
230 <has_text text="SnpEff: Variant analysis" />
231 </assert_contents>
232 </output>
233 -->
234 <!-- Setting filterOut throws exception in twilltestcase.py
235 <test>
236 <param name="input" ftype="vcf" value="vcf_homhet.vcf"/>
237 <param name="inputFormat" value="vcf"/>
238 <param name="outputFormat" value="vcf"/>
239 <param name="genomeSrc" value="named"/>
240 <param name="genome_version" value="testCase"/>
241 <param name="udLength" value="0"/>
242 <param name="filterHomHet" value="no_filter"/>
243 <param name="filterIn" value="no_filter"/>
244 <param name="generate_stats" value="False"/>
245 <param name="filterOut" value="+-no-upstream"/>
246 <output name="snpeff_output">
247 <assert_contents>
248 <has_text text="EFF=" />
249 </assert_contents>
250 </output>
251 </test>
252 -->
253
254 <test>
255 <param name="input" ftype="vcf" value="vcf_homhet.vcf"/>
256 <param name="inputFormat" value="vcf"/>
257 <param name="outputFormat" value="vcf"/>
258 <param name="genomeSrc" value="named"/>
259 <param name="genome_version" 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
275 <test>
276 <param name="input" ftype="vcf" value="vcf_homhet.vcf"/>
277 <param name="inputFormat" value="vcf"/>
278 <param name="outputFormat" value="vcf"/>
279 <param name="genomeSrc" value="named"/>
280 <param name="genome_version" value="testCase"/>
281 <param name="udLength" value="0"/>
282 <param name="filterHomHet" value="no_filter"/>
283 <param name="filterIn" value="del"/>
284 <!--
285 <param name="filterOut" value=""/>
286 -->
287 <param name="generate_stats" value="False"/>
288 <output name="snpeff_output">
289 <assert_contents>
290 <!-- Check that deleletions were evaluated -->
291 <has_text_matching expression="Y\t59030478\t.*EFF=INTERGENIC" />
292 <!-- Check that insertion on last line was NOT evaluated -->
293 <has_text_matching expression="Y\t59032947\t.*SF=5\tGT" />
294 </assert_contents>
295 </output>
296 </test>
297
298 <!-- Check that NO UPSTREAM effect was added -->
299 <!-- Setting filterOut throws exception in twilltestcase.py
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="genomeSrc" value="named"/>
305 <param name="genome_version" value="testCase"/>
306 <param name="udLength" value="0"/>
307 <param name="filterHomHet" value="no_filter"/>
308 <param name="filterIn" value="no_filter"/>
309 <param name="filterOut" value="+-no-upstream"/>
310 <param name="generate_stats" value="False"/>
311 <output name="snpeff_output">
312 <assert_contents>
313 <not_has_text text="UPSTREAM" />
314 </assert_contents>
315 </output>
316 </test>
317 -->
318
319 </tests>
320 <help>
321
322 This tool calculate the effect of variants (SNPs/MNPs/Insertions) and deletions.
323
324 @EXTERNAL_DOCUMENTATION@
325
326 @CITATION_SECTION@
327
328 </help>
329 </tool>
330