Mercurial > repos > gandres > vcftools_filter_stats_diversity
comparison VCFToolFilter/vcfToolsFilter.xml @ 2:ac7c9e40d601 draft
Uploaded
author | gandres |
---|---|
date | Fri, 10 Jul 2015 04:16:17 -0400 |
parents | |
children | 612066e3f57d |
comparison
equal
deleted
inserted
replaced
1:0f67ed444d47 | 2:ac7c9e40d601 |
---|---|
1 <tool id="sniplay_vcftoolsfilter" name="VCFtools Filter" version="1.1.1"> | |
2 | |
3 <!-- [REQUIRED] Tool description displayed after the tool name --> | |
4 <description> </description> | |
5 | |
6 <!-- [OPTIONAL] 3rd party tools, binaries, modules... required for the tool to work --> | |
7 <requirements> | |
8 <requirement type="binary">perl</requirement> | |
9 <requirement type="package" version="0.1.12b">vcftools</requirement> | |
10 </requirements> | |
11 | |
12 <!-- [OPTIONAL] Command to be executed to get the tool's version string --> | |
13 <version_command> | |
14 <!-- | |
15 tool_binary -v | |
16 --> | |
17 </version_command> | |
18 | |
19 <!-- [REQUIRED] The command to execute --> | |
20 <command interpreter="perl"> | |
21 vcfToolsFilter.sh $filein $fileout_label $fileout $filelog $export $frequency $max_freq $allow_missing $nb_alleles_min $nb_alleles_max $type_p $bound_start $bound_end | |
22 #if str( $samples ) == "": | |
23 'None' | |
24 #else | |
25 $samples | |
26 #end if | |
27 #if str( $chromosomes ) == "": | |
28 'None' | |
29 #else | |
30 $chromosomes | |
31 #end if | |
32 #if str( $export ) == "plink": | |
33 $fileout_map | |
34 #else | |
35 '' | |
36 #end if | |
37 </command> | |
38 | |
39 <!-- [REQUIRED] Input files and tool parameters --> | |
40 <inputs> | |
41 <param name="filein" type="data" format="vcf" optional="false" label="VCF input" /> | |
42 <param name="fileout_label" type="text" value="filtered" optional="false" label="Output file basename"/> | |
43 <param name="samples" type="text" optional="true" label="Samples" help="Samples to be analyzed. Comma separated list"> | |
44 <validator type="regex" message="Please enter a comma separated list.">^\w+(,\w+)*$</validator> | |
45 </param> | |
46 <param name="chromosomes" type="text" optional="true" label="Chromosomes" help="Chromosomes to be analyzed. Comma separated list"> | |
47 <validator type="regex" message="Please enter a comma separated list.">^\w+(,\w+)*$</validator> | |
48 </param> | |
49 <param name="export" type="select" label="Output format" > | |
50 <option value="VCF" selected="true">VCF</option> | |
51 <option value="freq">freq</option> | |
52 <option value="plink">plink</option> | |
53 </param> | |
54 <param name="frequency" type="float" value="0.001" label="Minimum MAF." help="Minimum frequency." /> | |
55 <param name="max_freq" type="float" value="0.5" label="Maximum MAF." help="Maximum frequency." /> | |
56 <param name="allow_missing" type="float" value="1" min="0" max="1" label="Missing data proportion" help="Allowed missing data proportion per site. Must be comprised between 0 and 1." /> | |
57 <param name="nb_alleles_min" type="integer" value="2" label="Minimum number of alleles" help="Minimum accepted number of alleles." min="2" max="4" /> | |
58 <param name="nb_alleles_max" type="integer" value="2" label="Maximum number of alleles" help="Maximum accepted number of alleles." min="2" max="4" /> | |
59 <param name="type_p" type="select" label="Polymorphisms" help="Type of polymorphisms to keep." > | |
60 <option value="ALL" selected="true">All</option> | |
61 <option value="SNP">SNP</option> | |
62 <option value="INDEL">Indel</option> | |
63 </param> | |
64 <param name="bound_start" type="integer" value="1" label="Lower bound" help="Lower bound for a range of sites to be processed." /> | |
65 <param name="bound_end" type="integer" value="100000000" label="Upper bound" help="Upper bound for a range of sites to be processed." /> | |
66 </inputs> | |
67 | |
68 <!-- [REQUIRED] Output files --> | |
69 <outputs> | |
70 <data name="fileout" format="vcf" label="${fileout_label}.#if str($export)=='plink' then 'ped' else '' # #if str($export)=='freq' then 'frq' else '' # #if str($export)=='VCF' then 'vcf' else '' #" > | |
71 <change_format> | |
72 <when input="export" value="freq" format="tabular" /> | |
73 <when input="export" value="plink" format="txt" /> | |
74 </change_format> | |
75 </data> | |
76 <data name="fileout_map" format="txt" label="${fileout_label}.map"> | |
77 <filter>(export == 'plink')</filter> | |
78 </data> | |
79 <data name="filelog" format="txt" label="${fileout_label}.log" /> | |
80 </outputs> | |
81 | |
82 <!-- [STRONGLY RECOMMANDED] Exit code rules --> | |
83 <stdio> | |
84 <!-- [HELP] If no exit code rule is defined, the tool will stop if anything is written to STDERR --> | |
85 <exit_code range="1:" level="fatal" /> | |
86 </stdio> | |
87 | |
88 <!-- [OPTIONAL] Tests to be run manually by the Galaxy admin --> | |
89 <tests> | |
90 <!-- [HELP] Test files have to be in the ~/test-data directory --> | |
91 <test> | |
92 <param name="filein" value="sample.vcf" /> | |
93 <param name="chromosomes" value="chr1" /> | |
94 <param name="export" value="VCF" /> | |
95 <param name="frequency" value="0.001" /> | |
96 <param name="max_freq" value="0.5" /> | |
97 <param name="allow_missing" value="1" /> | |
98 <param name="nb_alleles_min" value="2" /> | |
99 <param name="nb_alleles_max" value="4" /> | |
100 <param name="type_p" value="ALL" /> | |
101 <param name="bound_start" value="1" /> | |
102 <param name="bound_end" value="100000000" /> | |
103 <output name="fileout" file="result.vcf" /> | |
104 <output name="filelog" file="result.log" /> | |
105 </test> | |
106 </tests> | |
107 | |
108 <!-- [OPTIONAL] Help displayed in Galaxy --> | |
109 <help> | |
110 | |
111 .. class:: infomark | |
112 | |
113 **Authors** Adam Auton, Petr Danecek and Anthony Marcketta (C++ Module) : VCFtools_ | |
114 | |
115 .. _VCFtools: http://vcftools.sourceforge.net | |
116 | |
117 | **Please cite** "The Variant Call Format and VCFtools", Petr Danecek, Adam Auton, Goncalo Abecasis, Cornelis A. Albers, Eric Banks, Mark A. DePristo, Robert Handsaker, Gerton Lunter, Gabor Marth, Stephen T. Sherry, Gilean McVean, Richard Durbin and 1000 Genomes Project Analysis Group, **Bioinformatics**, 2011 | |
118 | |
119 .. class:: infomark | |
120 | |
121 **Galaxy integration** Andres Gwendoline, Institut Français de Bioinformatique. | |
122 | |
123 .. class:: infomark | |
124 | |
125 **Support** For any questions about Galaxy integration, please send an e-mail to support.abims@sb-roscoff.fr | |
126 | |
127 --------------------------------------------------- | |
128 | |
129 | |
130 | |
131 ================ | |
132 VCF tools filter | |
133 ================ | |
134 | |
135 ----------- | |
136 Description | |
137 ----------- | |
138 | |
139 | Filter VCF file | |
140 | For further informations on VCFtools, please visite the VCFtools website_. | |
141 | |
142 .. _website: http://vcftools.sourceforge.net | |
143 | |
144 ----------------- | |
145 Workflow position | |
146 ----------------- | |
147 | |
148 **Upstream tools** | |
149 | |
150 =========== ========================== ======= | |
151 Name output file(s) format | |
152 =========== ========================== ======= | |
153 =========== ========================== ======= | |
154 | |
155 | |
156 **Downstream tools** | |
157 | |
158 =========== ========================== ======= | |
159 Name output file(s) format | |
160 =========== ========================== ======= | |
161 =========== ========================== ======= | |
162 | |
163 | |
164 ---------- | |
165 Input file | |
166 ---------- | |
167 | |
168 VCF file | |
169 VCF file with all SNPs | |
170 | |
171 ---------- | |
172 Parameters | |
173 ---------- | |
174 | |
175 Output file basename | |
176 Prefix for the output VCF file | |
177 | |
178 Samples | |
179 Samples to be analyzed. Comma separated list | |
180 | |
181 Chromosomes | |
182 Chromosomes to be analyzed. Comma separated list | |
183 | |
184 Output format | |
185 VCF/freq/plink | |
186 | |
187 Minimum MAF | |
188 Minimum frequency | |
189 | |
190 Maximum MAF | |
191 Maximum frequency | |
192 | |
193 Missing data proportion | |
194 Allowed missing data proportion per site. Must be comprised between 0 and 1. | |
195 | |
196 Number of alleles | |
197 Accepted number of alleles min and max. | |
198 | |
199 Polymorphisms | |
200 Type of polymorphisms to keep (ALL/SNP/INDEL). | |
201 Bounds | |
202 Lower bound and upper bound for a range of sites to be processed. | |
203 | |
204 ------------ | |
205 Output files | |
206 ------------ | |
207 | |
208 VCF file | |
209 VCF file filtered | |
210 | |
211 Log file | |
212 | |
213 --------------------------------------------------- | |
214 | |
215 --------------- | |
216 Working example | |
217 --------------- | |
218 | |
219 Input files | |
220 =========== | |
221 | |
222 VCF file | |
223 --------- | |
224 | |
225 :: | |
226 | |
227 #fileformat=VCFv4.1 | |
228 #FILTER=<ID=LowQual,Description="Low quality"> | |
229 #FORMAT=<ID=AD,Number=.,Type=Integer,Description="Allelic depths for the ref and alt alleles in the order listed"> | |
230 [...] | |
231 CHROM POS ID REF ALT QUAL FILTER INFO FORMAT CATB1 | |
232 chr1 2209 . G T 213.84 . AC=2;AF=1.00;AN=2;DP=7;Dels=0.00;FS=0.000;HaplotypeScore=0.0000;MLEAC=2;MLEAF=1.00;MQ=41.50;MQ0=0;QD=30.55;EFF=DOWNSTREAM(MODIFIER||||Cc01g00020|mRNA||GSCOCT00012438001|),UPSTREAM(MODIFIER||||Cc01g00010|mRNA||GSCOCT00012439001|) GT:AD:DP:GQ:PL 1/1:0,7:7:18:242,18,0 | |
233 | |
234 | |
235 Parameters | |
236 ========== | |
237 | |
238 Output name -> filtered_chr1 | |
239 | |
240 Chromosomes -> chr1 | |
241 | |
242 Output format -> VCF | |
243 | |
244 Minimum MAF -> 0.001 | |
245 | |
246 Maximum MAF -> 0.5 | |
247 | |
248 Missing data proportion -> 1 | |
249 | |
250 Number of alleles min -> 2 | |
251 | |
252 Number of alleles max -> 4 | |
253 | |
254 Polymorphisms -> All | |
255 | |
256 Lower bound -> 1 | |
257 | |
258 Upper bound -> 100000000 | |
259 | |
260 | |
261 Output files | |
262 ============ | |
263 | |
264 filtered_genelist_intron.vcf | |
265 ---------------------------- | |
266 | |
267 :: | |
268 | |
269 #fileformat=VCFv4.1 | |
270 #FILTER=<ID=LowQual,Description="Low quality"> | |
271 #FORMAT=<ID=AD,Number=.,Type=Integer,Description="Allelic depths for the ref and alt alleles in the order listed"> | |
272 [...] | |
273 CHROM POS ID REF ALT QUAL FILTER INFO FORMAT CATB1 | |
274 chr1 5059 . C G 146.84 . AC=2;AF=1.00;AN=2;DP=8;Dels=0.00;FS=0.000;HaplotypeScore=0.0000;MLEAC=2;MLEAF=1.00;MQ=24.14;MQ0=1;QD=18.35;EFF=INTRON(MODIFIER||||Cc01g00020|mRNA||GSCOCT00012438001|),UPSTREAM(MODIFIER||||Cc01g00010|mRNA||GSCOCT00012439001|) GT:AD:DP:GQ:PL 1/1:0,8:8:18:175,18,0 | |
275 | |
276 | |
277 </help> | |
278 <citations> | |
279 <!-- [HELP] As DOI or BibTex entry --> | |
280 <citation type="bibtex"> | |
281 @article{Danecek01082011, | |
282 author = {Danecek, Petr and Auton, Adam and Abecasis, Goncalo and Albers, Cornelis A. and Banks, Eric and DePristo, Mark A. and Handsaker, Robert E. and Lunter, Gerton and Marth, Gabor T. and Sherry, Stephen T. and McVean, Gilean and Durbin, Richard and 1000 Genomes Project Analysis Group}, | |
283 title = {The variant call format and VCFtools}, | |
284 volume = {27}, | |
285 number = {15}, | |
286 pages = {2156-2158}, | |
287 year = {2011}, | |
288 doi = {10.1093/bioinformatics/btr330}, | |
289 abstract ={Summary: The variant call format (VCF) is a generic format for storing DNA polymorphism data such as SNPs, insertions, deletions and structural variants, together with rich annotations. VCF is usually stored in a compressed manner and can be indexed for fast data retrieval of variants from a range of positions on the reference genome. The format was developed for the 1000 Genomes Project, and has also been adopted by other projects such as UK10K, dbSNP and the NHLBI Exome Project. VCFtools is a software suite that implements various utilities for processing VCF files, including validation, merging, comparing and also provides a general Perl API.Availability: http://vcftools.sourceforge.netContact: rd@sanger.ac.uk}, | |
290 URL = {http://bioinformatics.oxfordjournals.org/content/27/15/2156.abstract}, | |
291 eprint = {http://bioinformatics.oxfordjournals.org/content/27/15/2156.full.pdf+html}, | |
292 journal = {Bioinformatics} | |
293 } | |
294 </citation> | |
295 | |
296 </citations> | |
297 | |
298 </tool> |