annotate VCFFiltering_wrapper.xml @ 7:a6b557df86db draft

Uploaded
author urgi-team
date Tue, 15 Dec 2015 05:35:36 -0500
parents
children
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
7
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
1 <tool id="VCFFiltering" name="VCFFiltering" version="0.01">
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
2 <description>Filters SNP on a VCF depending on depth, allele number and allele frequency</description>
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
3 <requirements>
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
4 <requirement type="package" version="1.0">VCF_Gandalf_Tools</requirement>
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
5 </requirements>
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
6 <version_command>
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
7 VCFFiltering.py --version
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
8 </version_command>
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
9 <command interpreter="python">
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
10 #if $DP_auto.is_DP_auto
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
11 VCFFiltering_wrapper.py -f $inputVCF -o $outputVCF -F $AF -N $AN
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
12 #else
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
13 VCFFiltering_wrapper.py -f $inputVCF -o $outputVCF -F $AF -N $AN -m $DP_auto.DPmin -M $DP_auto.DPmax
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
14 #end if
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
15 ## Bed files
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
16 #if $BedFile_List.is_BedFile
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
17 #for $bed in $BedFile_List.BedFiles
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
18 -b $bed.inputBed
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
19 #end for
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
20 #end if
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
21 --graphHTML $output_html --dirGraphs "$output_html.files_path"
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
22
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
23 </command>
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
24 <inputs>
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
25 <param name="inputVCF" type="data" format="vcf" label="Input VCF File name (from FreeBayes)"/>
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
26 <conditional name="DP_auto">
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
27 <param name="is_DP_auto" type="boolean" label="Calculate optimal depth range automatically" truevalue="yes" falsevalue="no" checked="on" />
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
28 <when value="yes"/>
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
29 <when value="no">
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
30 <param name="DPmin" type="integer" label="minumum Depth" value="1" help="default = 1">
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
31 <validator type="in_range" min="0" message="DP can't be negative" />
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
32 </param>
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
33 <param name="DPmax" type="integer" label="maximum Depth" value="200" help="default = 200">
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
34 <validator type="in_range" min="0" message="DP can't be negative" />
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
35 </param>
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
36 </when>
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
37 </conditional>
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
38 <param name="AF" type="float" value="0.9" label="minimum allele frequency" help="default = 0.9">
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
39 <validator type="in_range" min="0.0" max="1.0"/>
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
40 </param>
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
41 <param name="AN" type="integer" value="2" label="maximum allele number" help="default = 2">
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
42 <validator type="in_range" min="1" message="Allele number can't be negative" />
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
43 </param>
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
44 <conditional name="BedFile_List">
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
45 <param name="is_BedFile" type="boolean" label="bed files : list of coordinates to filter, multiple beds allowed" truevalue="yes" falsevalue="no" checked="off" />
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
46 <when value="no"/>
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
47 <when value="yes">
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
48 <repeat name="BedFiles" title="bed files : list of coordinates to filter, multiple beds allowed" min="1">
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
49 <param name="inputBed" type="data" format="bed" label="Select Bed file "/>
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
50 </repeat>
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
51 </when>
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
52 </conditional>
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
53 </inputs>
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
54 <outputs>
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
55 <data format="vcf" name="outputVCF" label="${tool.name} on ${on_string} (vcf)"/>
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
56 <data format="html" name="output_html" label="${tool.name} graphs on ${on_string} (html)">
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
57 </data>
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
58 </outputs>
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
59 <tests>
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
60 <test>
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
61 <param name="is_DP_auto" value="yes" />
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
62 <param name="AF" value="0.9"/>
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
63 <param name="AN" value="2"/>
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
64 <param name="inputVCF" ftype="vcf" value="VCFFiltering_input.vcf" />
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
65 <output name="outputVCF" file="VCFFiltering_DPauto_output.vcf"/>
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
66 </test>
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
67 <test>
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
68 <param name="is_DP_auto" value="no" />
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
69 <param name="DPmin" value="4"/>
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
70 <param name="DPmax" value="200"/>
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
71 <param name="AF" value="0.9"/>
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
72 <param name="AN" value="2"/>
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
73 <param name="inputVCF" ftype="vcf" value="VCFFiltering_input.vcf" />
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
74 <output name="outputVCF" file="VCFFiltering_DP_4_200_output.vcf"/>
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
75 </test>
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
76 </tests>
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
77 <help><![CDATA[
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
78 **Filters SNP on a VCF depending on depth, allele number and allele frequency**
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
79
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
80 -----
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
81
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
82 **what it does :**
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
83
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
84 VCFFiltering is a python script that allows to filter SNP results from freebayes on multiple criterias as once. The filters are :
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
85
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
86 - Allele number : number of possible allele at the genomic position
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
87 - Allele frequency : frenquency of the most represented allele ; note that if the most represented allele is the reference (a "." in the 4th column of the VCF, the allele frequency will still work but allele frequency should be under 1-x)
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
88 - Depth : Higher and lower bound of the depth ; the depth is the number of reads mapped on the genomic positions.
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
89
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
90 Depth can be automatically detected. If you do so, The 90 % of the positions with a depth closest to the most frequent depth will pass the filter.
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
91
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
92 This script has been developped to be used with freebayes output, on haploïd data.
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
93
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
94
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
95 .. class:: infomark
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
96
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
97 the VCF source is detected from the header. Please keep the header of your VCF file if you want to use this tool
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
98
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
99 -----
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
100
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
101 **input and output formats :**
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
102
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
103 input format is a VCF file obtaines with freebayes ; headers are necessary
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
104 you can also add some bed files to filter some specific regions.
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
105
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
106 output format is a filtered VCF file.
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
107
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
108 -----
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
109
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
110 **example :**
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
111
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
112
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
113 VCF input file: ::
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
114
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
115 ##fileformat=VCFv4.1
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
116 ##fileDate=20150126
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
117 ##source=freeBayes v0.9.13-2-ga830efd
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
118 ##reference=ref.fsa
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
119 ##phasing=none
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
120 ##commandline="freebayes --report-monomorphic --ploidy 2 -X -u -f ref.fsa strain_1.bam"
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
121 #CHROM POS ID REF ALT QUAL FILTER INFO FORMAT strain_1
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
122 chrom1 1 . T . . . DP=4;DPB=1;EPPR=5.18177;GTI=0;MQMR=36;NS=1;NUMALT=0;ODDS=0;PAIREDR=1;PQR=0;PRO=0;QR=38;RO=4;RPPR=5.18177 GT:DP:RO:QR:AO:QA:GL 0/0:4:4:38:.:.:0
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
123 chrom1 2 . A . . . DP=12;DPB=1;EPPR=5.18177;GTI=0;MQMR=36;NS=1;NUMALT=0;ODDS=0;PAIREDR=1;PQR=0;PRO=0;QR=38;RO=11;RPPR=5.18177 GT:DP:RO:QR:AO:QA:GL 0/0:12:11:38:.:.:0
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
124 chrom1 3 . T A . . DP=5;DPB=1;EPPR=5.18177;GTI=0;MQMR=36;NS=1;NUMALT=0;ODDS=0;PAIREDR=1;PQR=0;PRO=0;QR=38;AO=5;RPPR=5.18177 GT:DP:RO:QR:AO:QA:GL 0/0:5:0:38:5:.:0
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
125 chrom1 4 . G T . . DP=6;DPB=1;EPPR=5.18177;GTI=0;MQMR=36;NS=1;NUMALT=0;ODDS=0;PAIREDR=1;PQR=0;PRO=0;QR=38;AO=5;RPPR=5.18177 GT:DP:RO:QR:AO:QA:GL 0/0:6:1:38:5:.:0
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
126 chrom1 5 . C C . . DP=12;DPB=1;EPPR=5.18177;GTI=0;MQMR=36;NS=1;NUMALT=0;ODDS=0;PAIREDR=1;PQR=0;PRO=0;QR=38;AO=11;RPPR=5.18177 GT:DP:RO:QR:AO:QA:GL 0/0:12:1:38:11:.:0
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
127
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
128 purposed options: ::
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
129
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
130 - Calculate optimal depth range automatically = no
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
131 - minumum Depth = 5
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
132 - maximum Depth = 14
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
133 - minimum allele frequency = 0.9
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
134 - maximum allele number = 2
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
135
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
136 exemple result : ::
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
137
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
138 ##fileformat=VCFv4.1
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
139 ##fileDate=20150126
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
140 ##source=freeBayes v0.9.13-2-ga830efd
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
141 ##reference=ref.fsa
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
142 ##phasing=none
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
143 ##commandline="freebayes --report-monomorphic --ploidy 2 -X -u -f ref.fsa strain_1.bam"
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
144 #CHROM POS ID REF ALT QUAL FILTER INFO FORMAT strain_1
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
145 chrom1 1 . T . . G_DP DP=4;DPB=1;EPPR=5.18177;GTI=0;MQMR=36;NS=1;NUMALT=0;ODDS=0;PAIREDR=1;PQR=0;PRO=0;QR=38;RO=4;RPPR=5.18177;G_AN=0;G_AF=0.00;G_DP=4;G_Base=T GT:DP:RO:QR:AO:QA:GL 0/0:4:4:38:.:.:0
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
146 chrom1 2 . A . . . DP=12;DPB=1;EPPR=5.18177;GTI=0;MQMR=36;NS=1;NUMALT=0;ODDS=0;PAIREDR=1;PQR=0;PRO=0;QR=38;RO=11;RPPR=5.18177;G_AN=0;G_AF=0.08;G_DP=12;G_Base=A GT:DP:RO:QR:AO:QA:GL 0/0:12:11:38:.:.:0
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
147 chrom1 3 . T A . . DP=5;DPB=1;EPPR=5.18177;GTI=0;MQMR=36;NS=1;NUMALT=0;ODDS=0;PAIREDR=1;PQR=0;PRO=0;QR=38;AO=5;RPPR=5.18177;G_AN=0;G_AF=1.00;G_DP=5;G_Base=A GT:DP:RO:QR:AO:QA:GL 0/0:5:0:38:5:.:0
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
148 chrom1 4 . G T . G_AF DP=6;DPB=1;EPPR=5.18177;GTI=0;MQMR=36;NS=1;NUMALT=0;ODDS=0;PAIREDR=1;PQR=0;PRO=0;QR=38;AO=5;RPPR=5.18177;G_AN=0;G_AF=0.83;G_DP=6;G_Base=T GT:DP:RO:QR:AO:QA:GL 0/0:6:1:38:5:.:0
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
149 chrom1 5 . C C . . DP=12;DPB=1;EPPR=5.18177;GTI=0;MQMR=36;NS=1;NUMALT=0;ODDS=0;PAIREDR=1;PQR=0;PRO=0;QR=38;AO=11;RPPR=5.18177;G_AN=0;G_AF=0.92;G_DP=12;G_Base=C GT:DP:RO:QR:AO:QA:GL 0/0:12:1:38:11:.:0
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
150
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
151 -----
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
152
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
153 **reference :**
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
154
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
155 ]]>
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
156 </help>
a6b557df86db Uploaded
urgi-team
parents:
diff changeset
157 </tool>