1 | <tool id="vcf_to_maf_customtrack1" name="VCF to MAF Custom Track"> |
---|
2 | <description>for display at UCSC</description> |
---|
3 | <command interpreter="python">vcf_to_maf_customtrack.py '$out_file1' |
---|
4 | #if $vcf_source_type.vcf_file |
---|
5 | '${vcf_source_type.vcf_file[0].vcf_input.dbkey}' |
---|
6 | #else |
---|
7 | '?' |
---|
8 | #end if |
---|
9 | ${vcf_source_type.vcf_source} -n '$track_name' |
---|
10 | #for $vcf_repeat in $vcf_source_type.vcf_file |
---|
11 | '${vcf_repeat.vcf_input}' |
---|
12 | #if $vcf_source_type.vcf_source == '-p' |
---|
13 | '${vcf_repeat.population_name}' |
---|
14 | #end if |
---|
15 | #end for |
---|
16 | -g |
---|
17 | </command> |
---|
18 | <inputs> |
---|
19 | <param name="track_name" type="text" label="Custom Track Name" value="Galaxy Custom Track" size="30" /> |
---|
20 | <conditional name="vcf_source_type"> |
---|
21 | <param name="vcf_source" type="select" label="VCF Source Source Type"> |
---|
22 | <option value="-p" selected="true">Per Population (file)</option> |
---|
23 | <option value="-s">Per Sample</option> |
---|
24 | </param> |
---|
25 | <when value="-p"> |
---|
26 | <repeat name="vcf_file" title="VCF population file" min="1"> |
---|
27 | <param format="tabular" name="vcf_input" type="data" label="VCF file"/> |
---|
28 | <param name="population_name" type="text" label="Name for this population" value=""/> |
---|
29 | </repeat> |
---|
30 | </when> |
---|
31 | <when value="-s"> |
---|
32 | <repeat name="vcf_file" title="VCF sample file" min="1"> |
---|
33 | <param format="tabular" name="vcf_input" type="data" label="VCF file"/> |
---|
34 | <!-- add column count validator >= 8? --> |
---|
35 | </repeat> |
---|
36 | </when> |
---|
37 | </conditional> |
---|
38 | </inputs> |
---|
39 | <outputs> |
---|
40 | <data format="mafcustomtrack" name="out_file1" /> |
---|
41 | </outputs> |
---|
42 | <!-- <tests> |
---|
43 | <test> |
---|
44 | <param name="track_name" value="Galaxy Custom Track"/> |
---|
45 | <param name="vcf_source" value="Per Population"/> |
---|
46 | <param name="vcf_input" value="vcf_to_maf_in.vcf" ftype="tabular"/> |
---|
47 | <param name="population_name" value=""/> |
---|
48 | <output name="out_file1" file="vcf_to_maf_population_out.mafcustomtrack"/> |
---|
49 | </test> |
---|
50 | <test> |
---|
51 | <param name="track_name" value="Galaxy Custom Track"/> |
---|
52 | <param name="vcf_source" value="Per Sample"/> |
---|
53 | <param name="vcf_input" value="vcf_to_maf_in.vcf" ftype="tabular"/> |
---|
54 | <output name="out_file1" file="vcf_to_maf_sample_out.mafcustomtrack"/> |
---|
55 | </test> |
---|
56 | </tests> --> |
---|
57 | <help> |
---|
58 | **What it does** |
---|
59 | |
---|
60 | This tool converts a Variant Call Format (VCF) file into a Multiple Alignment Format (MAF) custom track file suitable for display at genome browsers. |
---|
61 | |
---|
62 | This file should be used for display purposes only (e.g as a UCSC Custom Track). Performing an analysis using the output created by this tool as input is not recommended; the source VCF file should be used when performing an analysis. |
---|
63 | |
---|
64 | *Unknown nucleotides* are represented as '*' as required to allow the display to draw properly; these include e.g. reference bases which appear before a deletion and are not available without querying the original reference sequence. |
---|
65 | |
---|
66 | **Example** |
---|
67 | |
---|
68 | Starting with a VCF:: |
---|
69 | |
---|
70 | ##fileformat=VCFv3.3 |
---|
71 | ##fileDate=20090805 |
---|
72 | ##source=myImputationProgramV3.1 |
---|
73 | ##reference=1000GenomesPilot-NCBI36 |
---|
74 | ##phasing=partial |
---|
75 | ##INFO=NS,1,Integer,"Number of Samples With Data" |
---|
76 | ##INFO=DP,1,Integer,"Total Depth" |
---|
77 | ##INFO=AF,-1,Float,"Allele Frequency" |
---|
78 | ##INFO=AA,1,String,"Ancestral Allele" |
---|
79 | ##INFO=DB,0,Flag,"dbSNP membership, build 129" |
---|
80 | ##INFO=H2,0,Flag,"HapMap2 membership" |
---|
81 | ##FILTER=q10,"Quality below 10" |
---|
82 | ##FILTER=s50,"Less than 50% of samples have data" |
---|
83 | ##FORMAT=GT,1,String,"Genotype" |
---|
84 | ##FORMAT=GQ,1,Integer,"Genotype Quality" |
---|
85 | ##FORMAT=DP,1,Integer,"Read Depth" |
---|
86 | ##FORMAT=HQ,2,Integer,"Haplotype Quality" |
---|
87 | #CHROM POS ID REF ALT QUAL FILTER INFO FORMAT NA00001 NA00002 NA00003 |
---|
88 | 20 14370 rs6054257 G A 29 0 NS=3;DP=14;AF=0.5;DB;H2 GT:GQ:DP:HQ 0|0:48:1:51,51 1|0:48:8:51,51 1/1:43:5:-1,-1 |
---|
89 | 20 17330 . T A 3 q10 NS=3;DP=11;AF=0.017 GT:GQ:DP:HQ 0|0:49:3:58,50 0|1:3:5:65,3 0/0:41:3:-1,-1 |
---|
90 | 20 1110696 rs6040355 A G,T 67 0 NS=2;DP=10;AF=0.333,0.667;AA=T;DB GT:GQ:DP:HQ 1|2:21:6:23,27 2|1:2:0:18,2 2/2:35:4:-1,-1 |
---|
91 | 20 1230237 . T . 47 0 NS=3;DP=13;AA=T GT:GQ:DP:HQ 0|0:54:7:56,60 0|0:48:4:51,51 0/0:61:2:-1,-1 |
---|
92 | 20 1234567 microsat1 G D4,IGA 50 0 NS=3;DP=9;AA=G GT:GQ:DP 0/1:35:4 0/2:17:2 1/1:40:3 |
---|
93 | |
---|
94 | |
---|
95 | |
---|
96 | |
---|
97 | Under the following conditions: **VCF Source type:** *Per Population (file)*, **Name for this population:** *CHB+JPT* |
---|
98 | Results in the following MAF custom track:: |
---|
99 | |
---|
100 | track name="Galaxy Custom Track" visibility=pack |
---|
101 | ##maf version=1 |
---|
102 | a score=0 |
---|
103 | s hg18.chr20 14369 1 + 14370 G |
---|
104 | s CHB+JPT_1.1 0 1 + 1 A |
---|
105 | |
---|
106 | a score=0 |
---|
107 | s hg18.chr20 17329 1 + 17330 T |
---|
108 | s CHB+JPT_1.2 0 1 + 1 A |
---|
109 | |
---|
110 | a score=0 |
---|
111 | s hg18.chr20 1110695 1 + 1110696 A |
---|
112 | s CHB+JPT_1.3 0 1 + 1 G |
---|
113 | s CHB+JPT_2.3 0 1 + 1 T |
---|
114 | |
---|
115 | a score=0 |
---|
116 | s hg18.chr20 1230236 1 + 1230237 T |
---|
117 | s CHB+JPT_1.4 0 1 + 1 . |
---|
118 | |
---|
119 | a score=0 |
---|
120 | s hg18.chr20 1234565 5 + 1234572 *G--*** |
---|
121 | s CHB+JPT_1.5 0 1 + 1 *------ |
---|
122 | s CHB+JPT_2.5 0 7 + 7 *GGA*** |
---|
123 | |
---|
124 | |
---|
125 | </help> |
---|
126 | </tool> |
---|
127 | |
---|