Mercurial > repos > gandres > vcftools_filter_stats_diversity
comparison VCFToolsSlidingWindow/vcfToolsSlidingWindow.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_vcftoolsslidingwindow" name="VCF tools SlidingWindow" version="1.0.0"> | |
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 | |
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 VCFToolsSlidingWindow.pl --input $filein --out $fileout_label --step $step --window $window && mv ${fileout_label}.vcftools.log $filelog && mv ${fileout_label}.Tajima.D ${fileout_taj} && mv ${fileout_label}.TsTv ${fileout_tstv} && mv ${fileout_label}.windowed.pi ${fileout_windowed} && mv ${fileout_label}.snpden ${fileout_snp} | |
22 </command> | |
23 | |
24 <!-- [REQUIRED] Input files and tool parameters --> | |
25 <inputs> | |
26 <param name="filein" type="data" format="vcf" optional="false" label="VCF input" /> | |
27 <param name="fileout_label" type="text" value="snp_density" optional="false" label="Output file basename"/> | |
28 <param name="window" type="integer" value="200000" optional="false" label="Window size (in bp)"/> | |
29 <param name="step" type="integer" value="50000" optional="false" label="Step size (in bp)"/> | |
30 </inputs> | |
31 | |
32 <!-- [REQUIRED] Output files --> | |
33 <outputs> | |
34 <data name="fileout_snp" format="tabular" label="${fileout_label}.snpden" /> | |
35 <data name="fileout_taj" format="tabular" label="${fileout_label}.Tajima.D" /> | |
36 <data name="fileout_tstv" format="tabular" label="${fileout_label}.TsTv" /> | |
37 <data name="fileout_windowed" format="tabular" label="${fileout_label}.windowed.pi" /> | |
38 <data name="filelog" format="txt" label="${fileout_label}.log" /> | |
39 </outputs> | |
40 | |
41 <!-- [STRONGLY RECOMMANDED] Exit code rules --> | |
42 <stdio> | |
43 <!-- [HELP] If no exit code rule is defined, the tool will stop if anything is written to STDERR --> | |
44 <exit_code range="1:" level="fatal" /> | |
45 </stdio> | |
46 | |
47 <!-- [OPTIONAL] Tests to be run manually by the Galaxy admin --> | |
48 <tests> | |
49 <!-- [HELP] Test files have to be in the ~/test-data directory --> | |
50 <test> | |
51 <param name="filein" value="sample.vcf" /> | |
52 <output name="fileout_annot" file="result.annotation" /> | |
53 <output name="fileout_het" file="result.het" /> | |
54 <output name="fileout_imiss" file="result.imiss" /> | |
55 <output name="fileout_sum" file="result.TsTv.summary" /> | |
56 <output name="filelog" file="result.log" /> | |
57 </test> | |
58 </tests> | |
59 | |
60 <!-- [OPTIONAL] Help displayed in Galaxy --> | |
61 <help> | |
62 | |
63 .. class:: infomark | |
64 | |
65 **Authors** Adam Auton, Petr Danecek and Anthony Marcketta (C++ Module) : VCFtools_ | |
66 | |
67 .. _VCFtools: http://vcftools.sourceforge.net | |
68 | |
69 | **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 | |
70 | |
71 .. class:: infomark | |
72 | |
73 **Galaxy integration** Andres Gwendoline, Institut Français de Bioinformatique. | |
74 | |
75 .. class:: infomark | |
76 | |
77 **Support** For any questions about Galaxy integration, please send an e-mail to support.abims@sb-roscoff.fr | |
78 | |
79 --------------------------------------------------- | |
80 | |
81 | |
82 ================ | |
83 VCF tools filter | |
84 ================ | |
85 | |
86 ----------- | |
87 Description | |
88 ----------- | |
89 | |
90 | Compute statistics on VCF file | |
91 | For further informations on VCFtools, please visite the VCFtools website_. | |
92 | |
93 .. _website: http://vcftools.sourceforge.net | |
94 | |
95 ----------------- | |
96 Workflow position | |
97 ----------------- | |
98 | |
99 **Upstream tools** | |
100 | |
101 =========== ========================== ======= | |
102 Name output file(s) format | |
103 =========== ========================== ======= | |
104 =========== ========================== ======= | |
105 | |
106 | |
107 **Downstream tools** | |
108 | |
109 =========== ========================== ======= | |
110 Name output file(s) format | |
111 =========== ========================== ======= | |
112 =========== ========================== ======= | |
113 | |
114 | |
115 ---------- | |
116 Input file | |
117 ---------- | |
118 | |
119 VCF file | |
120 VCF file with all SNPs | |
121 | |
122 ---------- | |
123 Parameters | |
124 ---------- | |
125 | |
126 Output file basename | |
127 Prefix for the output VCF file | |
128 | |
129 ------------ | |
130 Output files | |
131 ------------ | |
132 | |
133 .snpden file | |
134 SNP density along chromosomes (number of variants) | |
135 | |
136 .Tajima.D file | |
137 Tajima's D statistics | |
138 | |
139 .TsTv file | |
140 TsTv (Transition/transversion ratio) | |
141 .windowed.pi file | |
142 Nucleotide diversity Pi | |
143 | |
144 .log file | |
145 | |
146 --------------------------------------------------- | |
147 | |
148 --------------- | |
149 Working example | |
150 --------------- | |
151 | |
152 Input files | |
153 =========== | |
154 | |
155 VCF file | |
156 --------- | |
157 | |
158 :: | |
159 | |
160 #fileformat=VCFv4.1 | |
161 #FILTER=<ID=LowQual,Description="Low quality"> | |
162 #FORMAT=<ID=AD,Number=.,Type=Integer,Description="Allelic depths for the ref and alt alleles in the order listed"> | |
163 [...] | |
164 CHROM POS ID REF ALT QUAL FILTER INFO FORMAT CATB1 | |
165 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 | |
166 | |
167 | |
168 Parameters | |
169 ========== | |
170 | |
171 Output name -> snp_density | |
172 | |
173 | |
174 Output files | |
175 ============ | |
176 | |
177 .snpden file | |
178 ------------ | |
179 | |
180 :: | |
181 | |
182 CHROM BIN_START SNP_COUNT VARIANTS/KB | |
183 chr1 0 4955 24.775 | |
184 | |
185 | |
186 .Tajima.D file | |
187 -------------- | |
188 | |
189 :: | |
190 | |
191 CHROM BIN_START N_SNPS TajimaD | |
192 chr1 0 3737 -nan | |
193 | |
194 .TsTv file | |
195 ---------- | |
196 | |
197 :: | |
198 | |
199 CHROM BinStart SNP_count Ts/Tv | |
200 chr1 0 4928 1.88356 | |
201 | |
202 .windowed.pi file | |
203 ----------------- | |
204 | |
205 :: | |
206 | |
207 CHROM BIN_START BIN_END N_VARIANTS PI | |
208 chr1 1 200000 3764 0.01882 | |
209 | |
210 | |
211 </help> | |
212 <citations> | |
213 <!-- [HELP] As DOI or BibTex entry --> | |
214 <citation type="bibtex"> | |
215 @article{Danecek01082011, | |
216 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}, | |
217 title = {The variant call format and VCFtools}, | |
218 volume = {27}, | |
219 number = {15}, | |
220 pages = {2156-2158}, | |
221 year = {2011}, | |
222 doi = {10.1093/bioinformatics/btr330}, | |
223 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}, | |
224 URL = {http://bioinformatics.oxfordjournals.org/content/27/15/2156.abstract}, | |
225 eprint = {http://bioinformatics.oxfordjournals.org/content/27/15/2156.full.pdf+html}, | |
226 journal = {Bioinformatics} | |
227 } | |
228 </citation> | |
229 | |
230 </citations> | |
231 | |
232 </tool> | |
233 |