3
|
1 <tool id="sniplay_vcftoolsstats" name="VCFtools Stats" version="1.1.0">
|
2
|
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
|
3
|
12 <!-- [STRONGLY RECOMMANDED] Exit code rules -->
|
|
13 <stdio>
|
|
14 <!-- [HELP] If no exit code rule is defined, the tool will stop if anything is written to STDERR -->
|
|
15 <exit_code range="1:" level="fatal" />
|
|
16 </stdio>
|
2
|
17
|
|
18 <!-- [REQUIRED] The command to execute -->
|
|
19 <command interpreter="perl">
|
3
|
20 vcfToolsStats.sh $filein $fileout_annot $fileout_het $fileout_imiss $fileout_sum $filelog
|
2
|
21 </command>
|
|
22
|
|
23 <!-- [REQUIRED] Input files and tool parameters -->
|
|
24 <inputs>
|
|
25 <param name="filein" type="data" format="vcf" optional="false" label="VCF input" />
|
|
26 <param name="fileout_label" type="text" value="vcf_stats" optional="false" label="Output file basename"/>
|
|
27 </inputs>
|
|
28
|
|
29 <!-- [REQUIRED] Output files -->
|
|
30 <outputs>
|
|
31 <data name="fileout_annot" format="txt" label="${fileout_label}.annotation" />
|
|
32 <data name="fileout_het" format="txt" label="${fileout_label}.het" />
|
|
33 <data name="fileout_imiss" format="txt" label="${fileout_label}.imiss" />
|
|
34 <data name="fileout_sum" format="txt" label="${fileout_label}.TsTv.summary" />
|
|
35 <data name="filelog" format="txt" label="${fileout_label}.log" />
|
|
36 </outputs>
|
|
37
|
|
38 <!-- [OPTIONAL] Tests to be run manually by the Galaxy admin -->
|
|
39 <tests>
|
|
40 <!-- [HELP] Test files have to be in the ~/test-data directory -->
|
|
41 <test>
|
|
42 <param name="filein" value="sample.vcf" />
|
4
|
43 <output name="fileout_annot" file="stats-result.annotation" />
|
|
44 <output name="fileout_het" file="stats-result.het" />
|
|
45 <output name="fileout_imiss" file="stats-result.imiss" />
|
|
46 <output name="fileout_sum" file="stats-result.TsTv.summary" />
|
2
|
47 </test>
|
|
48 </tests>
|
|
49
|
|
50 <!-- [OPTIONAL] Help displayed in Galaxy -->
|
|
51 <help>
|
|
52
|
|
53 .. class:: infomark
|
|
54
|
|
55 **Authors** Adam Auton, Petr Danecek and Anthony Marcketta (C++ Module) : VCFtools_
|
|
56
|
|
57 .. _VCFtools: http://vcftools.sourceforge.net
|
|
58
|
|
59 | **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
|
|
60
|
|
61 .. class:: infomark
|
|
62
|
|
63 **Galaxy integration** Andres Gwendoline, Institut Français de Bioinformatique.
|
|
64
|
|
65 .. class:: infomark
|
|
66
|
|
67 **Support** For any questions about Galaxy integration, please send an e-mail to support.abims@sb-roscoff.fr
|
|
68
|
|
69 ---------------------------------------------------
|
|
70
|
|
71
|
|
72 ================
|
|
73 VCF tools filter
|
|
74 ================
|
|
75
|
|
76 -----------
|
|
77 Description
|
|
78 -----------
|
|
79
|
|
80 | Compute statistics on VCF file
|
|
81 | For further informations on VCFtools, please visite the VCFtools website_.
|
|
82
|
|
83 .. _website: http://vcftools.sourceforge.net
|
|
84
|
|
85 -----------------
|
|
86 Workflow position
|
|
87 -----------------
|
|
88
|
|
89 **Upstream tools**
|
|
90
|
|
91 =========== ========================== =======
|
|
92 Name output file(s) format
|
|
93 =========== ========================== =======
|
|
94 =========== ========================== =======
|
|
95
|
|
96
|
|
97 **Downstream tools**
|
|
98
|
|
99 =========== ========================== =======
|
|
100 Name output file(s) format
|
|
101 =========== ========================== =======
|
|
102 =========== ========================== =======
|
|
103
|
|
104
|
|
105 ----------
|
|
106 Input file
|
|
107 ----------
|
|
108
|
|
109 VCF file
|
|
110 VCF file with all SNPs
|
|
111
|
|
112 ----------
|
|
113 Parameters
|
|
114 ----------
|
|
115
|
|
116 Output file basename
|
|
117 Prefix for the output VCF file
|
|
118
|
|
119 ------------
|
|
120 Output files
|
|
121 ------------
|
|
122
|
|
123 .annotation file
|
|
124 Statistics on annotation/location along genome
|
|
125
|
|
126 .het file
|
|
127 Statistics on heterozygosity of the individuals
|
|
128
|
|
129 .imiss
|
|
130 Statistics on missing data of the inidividuals
|
|
131 .TsTv.summary
|
|
132 Statistics on mutation types and transition/transvertion number
|
|
133
|
|
134 .log file
|
|
135
|
|
136 ---------------------------------------------------
|
|
137
|
|
138 ---------------
|
|
139 Working example
|
|
140 ---------------
|
|
141
|
|
142 Input files
|
|
143 ===========
|
|
144
|
|
145 VCF file
|
|
146 ---------
|
|
147
|
|
148 ::
|
|
149
|
|
150 #fileformat=VCFv4.1
|
|
151 #FILTER=<ID=LowQual,Description="Low quality">
|
|
152 #FORMAT=<ID=AD,Number=.,Type=Integer,Description="Allelic depths for the ref and alt alleles in the order listed">
|
|
153 [...]
|
|
154 CHROM POS ID REF ALT QUAL FILTER INFO FORMAT CATB1
|
|
155 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
|
|
156
|
|
157
|
|
158 Parameters
|
|
159 ==========
|
|
160
|
|
161 Output name -> vcf_stat
|
|
162
|
|
163
|
|
164 Output files
|
|
165 ============
|
|
166
|
|
167 .annotation file
|
|
168 ----------------
|
|
169
|
|
170 ::
|
|
171
|
|
172 Genic 4489
|
|
173 Intergenic 466
|
|
174 ========
|
|
175 Intron 960
|
|
176 Exon 3248
|
|
177 UTR 281
|
|
178 ========
|
|
179 Non-syn 226
|
|
180 Synonym 3022
|
|
181
|
|
182 .het file
|
|
183 ---------
|
|
184
|
|
185 ::
|
|
186
|
|
187 INDV O(HOM) E(HOM) N_SITES F
|
|
188 CATB1 0 0.0 3616 0.00000
|
|
189
|
|
190 .imiss file
|
|
191 -----------
|
|
192
|
|
193 ::
|
|
194
|
|
195 INDV N_DATA N_GENOTYPES_FILTERED N_MISS F_MISS
|
|
196 CATB1 4813 0 0 0
|
|
197
|
|
198 .TsTv.summary file
|
|
199 ------------------
|
|
200
|
|
201 ::
|
|
202
|
|
203 MODEL COUNT
|
|
204 AC 371
|
|
205 AG 1467
|
|
206 AT 562
|
|
207 CG 330
|
|
208 CT 1659
|
|
209 GT 397
|
|
210 Ts 3126
|
|
211 Tv 1660
|
|
212
|
|
213
|
|
214 </help>
|
|
215 <citations>
|
|
216 <!-- [HELP] As DOI or BibTex entry -->
|
|
217 <citation type="bibtex">
|
|
218 @article{Danecek01082011,
|
|
219 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},
|
|
220 title = {The variant call format and VCFtools},
|
|
221 volume = {27},
|
|
222 number = {15},
|
|
223 pages = {2156-2158},
|
|
224 year = {2011},
|
|
225 doi = {10.1093/bioinformatics/btr330},
|
|
226 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},
|
|
227 URL = {http://bioinformatics.oxfordjournals.org/content/27/15/2156.abstract},
|
|
228 eprint = {http://bioinformatics.oxfordjournals.org/content/27/15/2156.full.pdf+html},
|
|
229 journal = {Bioinformatics}
|
|
230 }
|
|
231 </citation>
|
|
232
|
|
233 </citations>
|
|
234
|
|
235 </tool>
|