7
|
1 <tool id="sniplay_vcftoolsslidingwindow" name="VCF tools SlidingWindow" version="1.3.0">
|
2
|
2
|
|
3 <!-- [REQUIRED] Tool description displayed after the tool name -->
|
|
4 <description> Make diversity computation with sliding window </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>
|
|
17
|
2
|
18
|
|
19 <!-- [REQUIRED] The command to execute -->
|
3
|
20 <command interpreter="bash">
|
4
|
21 vcfToolsSlidingWindow.sh ${filein} $window $filelog ${fileout_taj} ${fileout_tstv} ${fileout_windowed} ${fileout_snp}
|
3
|
22 #if $group :
|
7
|
23 $group ${fileout_fst} ${fileout_fst_marker} ${fileout_taj_combined} ${fileout_windowed_combined} ${fileout_tstv_combined} ${fileout_snp_combined}
|
3
|
24 #else :
|
|
25 "none"
|
|
26 #end if
|
2
|
27 </command>
|
|
28
|
|
29 <!-- [REQUIRED] Input files and tool parameters -->
|
|
30 <inputs>
|
|
31 <param name="filein" type="data" format="vcf" optional="false" label="VCF input" />
|
|
32 <param name="fileout_label" type="text" value="snp_density" optional="false" label="Output file basename"/>
|
|
33 <param name="window" type="integer" value="200000" optional="false" label="Window size (in bp)"/>
|
3
|
34 <param name="group" type="data" format="tab" optional="True" label="(optionnal) Groups" help="Each line of the file should be : Indiv;Pop" />
|
2
|
35 </inputs>
|
|
36
|
|
37 <!-- [REQUIRED] Output files -->
|
|
38 <outputs>
|
5
|
39 <data name="fileout_snp" format="txt" label="${fileout_label}.snpden" />
|
|
40 <data name="fileout_taj" format="txt" label="${fileout_label}.Tajima.D" />
|
|
41 <data name="fileout_tstv" format="txt" label="${fileout_label}.TsTv" />
|
|
42 <data name="fileout_windowed" format="txt" label="${fileout_label}.windowed.pi" />
|
2
|
43 <data name="filelog" format="txt" label="${fileout_label}.log" />
|
3
|
44 <data name="fileout_fst" format="txt" label="${fileout_label}.fst.txt">
|
|
45 <filter>(group != None)</filter>
|
|
46 </data>
|
|
47 <data name="fileout_fst_marker" format="txt" label="${fileout_label}.fst.by_marker.genes.txt">
|
|
48 <filter>(group != None)</filter>
|
|
49 </data>
|
7
|
50 <data name="fileout_windowed_combined" format="txt" label="${fileout_label}.combined.pi.txt" >
|
3
|
51 <filter>(group != None)</filter>
|
|
52 </data>
|
7
|
53 <data name="fileout_taj_combined" format="txt" label="${fileout_label}.combined.dtajima.txt" >
|
|
54 <filter>(group != None)</filter>
|
|
55 </data>
|
|
56 <data name="fileout_tstv_combined" format="txt" label="${fileout_label}.combined.TsTv.txt" >
|
|
57 <filter>(group != None)</filter>
|
|
58 </data>
|
|
59 <data name="fileout_snp_combined" format="txt" label="${fileout_label}.combined.snpden.txt" >
|
3
|
60 <filter>(group != None)</filter>
|
|
61 </data>
|
2
|
62 </outputs>
|
|
63
|
|
64 <!-- [OPTIONAL] Tests to be run manually by the Galaxy admin -->
|
|
65 <tests>
|
|
66 <!-- [HELP] Test files have to be in the ~/test-data directory -->
|
3
|
67 <test>
|
4
|
68 <param name="filein" value="sliding-sample_group.vcf" />
|
|
69 <param name="group" value="sliding-groups.txt" />
|
|
70 <output name="fileout_snp" file="sliding-result2.snpden" />
|
|
71 <output name="fileout_taj" file="sliding-result2.Tajima.D" />
|
|
72 <output name="fileout_tstv" file="sliding-result2.TsTv" />
|
|
73 <output name="fileout_windowed" file="sliding-result2.windowed.pi" />
|
|
74 <output name="fileout_fst" file="sliding-result2.fst.txt" />
|
|
75 <output name="fileout_fst_marker" file="sliding-result2.fst.by_marker.genes.txt" />
|
|
76 <output name="fileout_taj_combined" file="sliding-result2.combined.dtajima.txt" />
|
|
77 <output name="fileout_windowed_combined" file="sliding-result2.combined.pi.txt" />
|
7
|
78 <output name="fileout_tstv_combined" file="sliding-result2.combined.TsTv.txt" />
|
|
79 <output name="fileout_snp_combined" file="sliding-result2.combined.snpden.txt" />
|
3
|
80 </test>
|
|
81 <test>
|
2
|
82 <param name="filein" value="sample.vcf" />
|
4
|
83 <output name="fileout_snp" file="sliding-result.snpden" />
|
|
84 <output name="fileout_taj" file="sliding-result.Tajima.D" />
|
|
85 <output name="fileout_tstv" file="sliding-result.TsTv" />
|
|
86 <output name="fileout_windowed" file="sliding-result.windowed.pi" />
|
2
|
87 </test>
|
|
88 </tests>
|
|
89
|
|
90 <!-- [OPTIONAL] Help displayed in Galaxy -->
|
|
91 <help>
|
|
92
|
|
93 .. class:: infomark
|
|
94
|
|
95 **Authors** Adam Auton, Petr Danecek and Anthony Marcketta (C++ Module) : VCFtools_
|
|
96
|
|
97 .. _VCFtools: http://vcftools.sourceforge.net
|
|
98
|
|
99 | **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
|
|
100
|
|
101 .. class:: infomark
|
|
102
|
|
103 **Galaxy integration** Andres Gwendoline, Institut Français de Bioinformatique.
|
|
104
|
|
105 .. class:: infomark
|
|
106
|
|
107 **Support** For any questions about Galaxy integration, please send an e-mail to support.abims@sb-roscoff.fr
|
|
108
|
|
109 ---------------------------------------------------
|
|
110
|
|
111
|
|
112 ================
|
|
113 VCF tools filter
|
|
114 ================
|
|
115
|
|
116 -----------
|
|
117 Description
|
|
118 -----------
|
|
119
|
|
120 | Compute statistics on VCF file
|
|
121 | For further informations on VCFtools, please visite the VCFtools website_.
|
|
122
|
|
123 .. _website: http://vcftools.sourceforge.net
|
|
124
|
|
125 -----------------
|
|
126 Workflow position
|
|
127 -----------------
|
|
128
|
|
129 **Upstream tools**
|
|
130
|
|
131 =========== ========================== =======
|
|
132 Name output file(s) format
|
|
133 =========== ========================== =======
|
|
134 =========== ========================== =======
|
|
135
|
|
136
|
|
137 **Downstream tools**
|
|
138
|
|
139 =========== ========================== =======
|
|
140 Name output file(s) format
|
|
141 =========== ========================== =======
|
|
142 =========== ========================== =======
|
|
143
|
|
144
|
|
145 ----------
|
|
146 Input file
|
|
147 ----------
|
|
148
|
|
149 VCF file
|
|
150 VCF file with all SNPs
|
|
151
|
|
152 ----------
|
|
153 Parameters
|
|
154 ----------
|
|
155
|
|
156 Output file basename
|
|
157 Prefix for the output VCF file
|
|
158
|
|
159 ------------
|
|
160 Output files
|
|
161 ------------
|
|
162
|
|
163 .snpden file
|
|
164 SNP density along chromosomes (number of variants)
|
|
165
|
|
166 .Tajima.D file
|
|
167 Tajima's D statistics
|
|
168
|
|
169 .TsTv file
|
|
170 TsTv (Transition/transversion ratio)
|
|
171 .windowed.pi file
|
|
172 Nucleotide diversity Pi
|
|
173
|
|
174 .log file
|
|
175
|
|
176 ---------------------------------------------------
|
|
177
|
|
178 ---------------
|
|
179 Working example
|
|
180 ---------------
|
|
181
|
|
182 Input files
|
|
183 ===========
|
|
184
|
|
185 VCF file
|
|
186 ---------
|
|
187
|
|
188 ::
|
|
189
|
|
190 #fileformat=VCFv4.1
|
|
191 #FILTER=<ID=LowQual,Description="Low quality">
|
|
192 #FORMAT=<ID=AD,Number=.,Type=Integer,Description="Allelic depths for the ref and alt alleles in the order listed">
|
|
193 [...]
|
|
194 CHROM POS ID REF ALT QUAL FILTER INFO FORMAT CATB1
|
|
195 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
|
|
196
|
|
197
|
|
198 Parameters
|
|
199 ==========
|
|
200
|
|
201 Output name -> snp_density
|
|
202
|
|
203
|
|
204 Output files
|
|
205 ============
|
|
206
|
|
207 .snpden file
|
|
208 ------------
|
|
209
|
|
210 ::
|
|
211
|
|
212 CHROM BIN_START SNP_COUNT VARIANTS/KB
|
|
213 chr1 0 4955 24.775
|
|
214
|
|
215
|
|
216 .Tajima.D file
|
|
217 --------------
|
|
218
|
|
219 ::
|
|
220
|
|
221 CHROM BIN_START N_SNPS TajimaD
|
|
222 chr1 0 3737 -nan
|
|
223
|
|
224 .TsTv file
|
|
225 ----------
|
|
226
|
|
227 ::
|
|
228
|
|
229 CHROM BinStart SNP_count Ts/Tv
|
|
230 chr1 0 4928 1.88356
|
|
231
|
|
232 .windowed.pi file
|
|
233 -----------------
|
|
234
|
|
235 ::
|
|
236
|
|
237 CHROM BIN_START BIN_END N_VARIANTS PI
|
|
238 chr1 1 200000 3764 0.01882
|
|
239
|
|
240
|
|
241 </help>
|
|
242 <citations>
|
|
243 <!-- [HELP] As DOI or BibTex entry -->
|
|
244 <citation type="bibtex">
|
|
245 @article{Danecek01082011,
|
|
246 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},
|
|
247 title = {The variant call format and VCFtools},
|
|
248 volume = {27},
|
|
249 number = {15},
|
|
250 pages = {2156-2158},
|
|
251 year = {2011},
|
|
252 doi = {10.1093/bioinformatics/btr330},
|
|
253 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},
|
|
254 URL = {http://bioinformatics.oxfordjournals.org/content/27/15/2156.abstract},
|
|
255 eprint = {http://bioinformatics.oxfordjournals.org/content/27/15/2156.full.pdf+html},
|
|
256 journal = {Bioinformatics}
|
|
257 }
|
|
258 </citation>
|
|
259
|
|
260 </citations>
|
|
261
|
|
262 </tool>
|
|
263
|