annotate pileup_to_vcf.xml @ 9:c0a6e8f595ec default tip

Add option to set VCF ID field value, this can be used to ID germline variants for SnpSift
author Jim Johnson <jj@umn.edu>
date Thu, 11 Apr 2013 10:28:10 -0500
parents 8688e29ba96f
children
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
9
c0a6e8f595ec Add option to set VCF ID field value, this can be used to ID germline variants for SnpSift
Jim Johnson <jj@umn.edu>
parents: 5
diff changeset
1 <tool id="pileup_to_vcf" name="Pileup to VCF" version="2.2">
0
3890f8ba0e4d Uploaded
jjohnson
parents:
diff changeset
2 <description>Converts a pileup to VCF with filtering</description>
3890f8ba0e4d Uploaded
jjohnson
parents:
diff changeset
3 <command interpreter="python">pileup_to_vcf.py -i $input_file -o $output_file
3890f8ba0e4d Uploaded
jjohnson
parents:
diff changeset
4 #if $min_cvrg.__str__ != '':
3890f8ba0e4d Uploaded
jjohnson
parents:
diff changeset
5 --min_coverage $min_cvrg
3890f8ba0e4d Uploaded
jjohnson
parents:
diff changeset
6 #end if
3890f8ba0e4d Uploaded
jjohnson
parents:
diff changeset
7 #if $min_base_qual.__str__ != '':
3890f8ba0e4d Uploaded
jjohnson
parents:
diff changeset
8 --min_base_qual $min_base_qual
3890f8ba0e4d Uploaded
jjohnson
parents:
diff changeset
9 #end if
3890f8ba0e4d Uploaded
jjohnson
parents:
diff changeset
10 #if $min_var_pct.__str__ != '':
3890f8ba0e4d Uploaded
jjohnson
parents:
diff changeset
11 --min_allele_freq $min_var_pct
3890f8ba0e4d Uploaded
jjohnson
parents:
diff changeset
12 #end if
3890f8ba0e4d Uploaded
jjohnson
parents:
diff changeset
13 #if $depth_as.__str__ != 'None':
3890f8ba0e4d Uploaded
jjohnson
parents:
diff changeset
14 --report_depth $depth_as
3890f8ba0e4d Uploaded
jjohnson
parents:
diff changeset
15 #end if
3890f8ba0e4d Uploaded
jjohnson
parents:
diff changeset
16 $allow_multiples
3890f8ba0e4d Uploaded
jjohnson
parents:
diff changeset
17 $snps_only
9
c0a6e8f595ec Add option to set VCF ID field value, this can be used to ID germline variants for SnpSift
Jim Johnson <jj@umn.edu>
parents: 5
diff changeset
18 #if $vcf_id.__str__ != '':
c0a6e8f595ec Add option to set VCF ID field value, this can be used to ID germline variants for SnpSift
Jim Johnson <jj@umn.edu>
parents: 5
diff changeset
19 --id $vcf_id
c0a6e8f595ec Add option to set VCF ID field value, this can be used to ID germline variants for SnpSift
Jim Johnson <jj@umn.edu>
parents: 5
diff changeset
20 #end if
0
3890f8ba0e4d Uploaded
jjohnson
parents:
diff changeset
21 #if $cols.select_order == 'yes' :
3890f8ba0e4d Uploaded
jjohnson
parents:
diff changeset
22 #if $chrom_col.__str__ != '':
3890f8ba0e4d Uploaded
jjohnson
parents:
diff changeset
23 --chrom_col $chrom_col
3890f8ba0e4d Uploaded
jjohnson
parents:
diff changeset
24 #end if
3890f8ba0e4d Uploaded
jjohnson
parents:
diff changeset
25 #if $pos_col.__str__ != '':
3890f8ba0e4d Uploaded
jjohnson
parents:
diff changeset
26 --pos_col $pos_col
3890f8ba0e4d Uploaded
jjohnson
parents:
diff changeset
27 #end if
3890f8ba0e4d Uploaded
jjohnson
parents:
diff changeset
28 #if $ref_col.__str__ != '':
3890f8ba0e4d Uploaded
jjohnson
parents:
diff changeset
29 --ref_col $ref_col
3890f8ba0e4d Uploaded
jjohnson
parents:
diff changeset
30 #end if
3890f8ba0e4d Uploaded
jjohnson
parents:
diff changeset
31 #if $cvrg_col.__str__ != '':
3890f8ba0e4d Uploaded
jjohnson
parents:
diff changeset
32 --coverage_col $cvrg_col
3890f8ba0e4d Uploaded
jjohnson
parents:
diff changeset
33 #end if
3890f8ba0e4d Uploaded
jjohnson
parents:
diff changeset
34 #if $base_call_col.__str__ != '':
3890f8ba0e4d Uploaded
jjohnson
parents:
diff changeset
35 --base_call_col $base_call_col
3890f8ba0e4d Uploaded
jjohnson
parents:
diff changeset
36 #end if
3890f8ba0e4d Uploaded
jjohnson
parents:
diff changeset
37 #if $base_qual_col.__str__ != '':
3890f8ba0e4d Uploaded
jjohnson
parents:
diff changeset
38 --base_qual_col $base_qual_col
3890f8ba0e4d Uploaded
jjohnson
parents:
diff changeset
39 #end if
3890f8ba0e4d Uploaded
jjohnson
parents:
diff changeset
40 #end if
3890f8ba0e4d Uploaded
jjohnson
parents:
diff changeset
41 </command>
3890f8ba0e4d Uploaded
jjohnson
parents:
diff changeset
42 <inputs>
3890f8ba0e4d Uploaded
jjohnson
parents:
diff changeset
43 <param name="input_file" type="data" format="pileup,tabular" label="Source File" optional="false"/>
3890f8ba0e4d Uploaded
jjohnson
parents:
diff changeset
44 <conditional name="cols">
3890f8ba0e4d Uploaded
jjohnson
parents:
diff changeset
45 <param name="select_order" type="select" label="Set column positions for non-standard pileup">
3890f8ba0e4d Uploaded
jjohnson
parents:
diff changeset
46 <option value="no" selected="true">Use the default pileup columns</option>
3890f8ba0e4d Uploaded
jjohnson
parents:
diff changeset
47 <option value="yes">Select the column position that represents each pileup column</option>
3890f8ba0e4d Uploaded
jjohnson
parents:
diff changeset
48 </param>
3890f8ba0e4d Uploaded
jjohnson
parents:
diff changeset
49 <when value="no"/>
3890f8ba0e4d Uploaded
jjohnson
parents:
diff changeset
50 <when value="yes">
3890f8ba0e4d Uploaded
jjohnson
parents:
diff changeset
51 <param name="chrom_col" type="data_column" data_ref="input_file" label="Chromosome Column"/>
3890f8ba0e4d Uploaded
jjohnson
parents:
diff changeset
52 <param name="pos_col" type="data_column" data_ref="input_file" label="Position Column"/>
3890f8ba0e4d Uploaded
jjohnson
parents:
diff changeset
53 <param name="ref_col" type="data_column" data_ref="input_file" label="Reference Base Column"/>
3890f8ba0e4d Uploaded
jjohnson
parents:
diff changeset
54 <param name="cvrg_col" type="data_column" data_ref="input_file" label="Depth Column"/>
3890f8ba0e4d Uploaded
jjohnson
parents:
diff changeset
55 <param name="base_call_col" type="data_column" data_ref="input_file" label="Base Call Column"/>
3890f8ba0e4d Uploaded
jjohnson
parents:
diff changeset
56 <param name="base_qual_col" type="data_column" data_ref="input_file" label="Base Quality Column"/>
3890f8ba0e4d Uploaded
jjohnson
parents:
diff changeset
57 </when>
3890f8ba0e4d Uploaded
jjohnson
parents:
diff changeset
58 </conditional>
3890f8ba0e4d Uploaded
jjohnson
parents:
diff changeset
59 <param name="min_base_qual" type="integer" label="Minimum Base Quality" optional="true" value="20" help="Don't consider a read if the base call quality is below this threshold"/>
3890f8ba0e4d Uploaded
jjohnson
parents:
diff changeset
60 <param name="min_cvrg" type="integer" label="Minimum Coverage Depth" optional="true" value="5" help="Any position below the threshold will be omitted from the resulting VCF"/>
3890f8ba0e4d Uploaded
jjohnson
parents:
diff changeset
61 <param name="min_var_pct" type="float" label="Minimum Frequency of a Specific Allele" option="true" value="0.5" help="If an allele does not meet the minimum frequency it will be omitted from the resulting VCF."/>
3890f8ba0e4d Uploaded
jjohnson
parents:
diff changeset
62 <param name="allow_multiples" type="boolean" truevalue="-m" falsevalue="" chacked="true" label="Allow Multiple Alleles for a Position?"
3890f8ba0e4d Uploaded
jjohnson
parents:
diff changeset
63 help="Multiple alleles may be output in the VCF if the allowable frequency is below 0.5, otherwise only one will be reported"/>
3890f8ba0e4d Uploaded
jjohnson
parents:
diff changeset
64 <param name="snps_only" type="boolean" truevalue="-s" falsevalue="" chacked="false" label="Only report SNPs, not indels" />
3890f8ba0e4d Uploaded
jjohnson
parents:
diff changeset
65 <param name="depth_as" type="select" label="Report DP and SAF with read coverage of" help="The reported read voverage depth: DP, and the calculation of specific allele frequency (SAF) of variants">
2
d6de2d1f4af9 Fix read depth reporting
Jim Johnson <jj@umn.edu>
parents: 0
diff changeset
66 <option value="source">Read coverage reported in pileup</option>
d6de2d1f4af9 Fix read depth reporting
Jim Johnson <jj@umn.edu>
parents: 0
diff changeset
67 <option value="ref" selected="true">Reads at this position that have a base call</option>
0
3890f8ba0e4d Uploaded
jjohnson
parents:
diff changeset
68 <option value="qual">Reads at this position taht pass the base call quality threshold</option>
2
d6de2d1f4af9 Fix read depth reporting
Jim Johnson <jj@umn.edu>
parents: 0
diff changeset
69 <option value="all">All reads and indels</option>
0
3890f8ba0e4d Uploaded
jjohnson
parents:
diff changeset
70 </param>
9
c0a6e8f595ec Add option to set VCF ID field value, this can be used to ID germline variants for SnpSift
Jim Johnson <jj@umn.edu>
parents: 5
diff changeset
71 <param name="vcf_id" type="text" optional="true" value="" label="The VCF ID" help="The VCF output will use this as the ID field value">
c0a6e8f595ec Add option to set VCF ID field value, this can be used to ID germline variants for SnpSift
Jim Johnson <jj@umn.edu>
parents: 5
diff changeset
72 <validator type="regex" message="whitespace characters not allowed">^\S*$</validator>
c0a6e8f595ec Add option to set VCF ID field value, this can be used to ID germline variants for SnpSift
Jim Johnson <jj@umn.edu>
parents: 5
diff changeset
73 </param>
0
3890f8ba0e4d Uploaded
jjohnson
parents:
diff changeset
74 </inputs>
3890f8ba0e4d Uploaded
jjohnson
parents:
diff changeset
75 <outputs>
3890f8ba0e4d Uploaded
jjohnson
parents:
diff changeset
76 <data format="vcf" metadata_source="input_file" name="output_file" />
3890f8ba0e4d Uploaded
jjohnson
parents:
diff changeset
77 </outputs>
3890f8ba0e4d Uploaded
jjohnson
parents:
diff changeset
78 <stdio>
3890f8ba0e4d Uploaded
jjohnson
parents:
diff changeset
79 <exit_code range="1:" level="fatal" description="Bad input dataset" />
3890f8ba0e4d Uploaded
jjohnson
parents:
diff changeset
80 </stdio>
3890f8ba0e4d Uploaded
jjohnson
parents:
diff changeset
81 <tests>
3890f8ba0e4d Uploaded
jjohnson
parents:
diff changeset
82 <test>
3890f8ba0e4d Uploaded
jjohnson
parents:
diff changeset
83 <param name="input_file" ftype="pileup" value="test.pileup" />
3890f8ba0e4d Uploaded
jjohnson
parents:
diff changeset
84 <param name="select_order" value="no"/>
3890f8ba0e4d Uploaded
jjohnson
parents:
diff changeset
85 <param name="min_base_qual" value="0"/>
3890f8ba0e4d Uploaded
jjohnson
parents:
diff changeset
86 <param name="min_cvrg" value="0"/>
3890f8ba0e4d Uploaded
jjohnson
parents:
diff changeset
87 <param name="min_var_pct" value=".1"/>
3890f8ba0e4d Uploaded
jjohnson
parents:
diff changeset
88 <param name="allow_multiples" value="True"/>
3890f8ba0e4d Uploaded
jjohnson
parents:
diff changeset
89 <param name="snps_only" value="False"/>
3890f8ba0e4d Uploaded
jjohnson
parents:
diff changeset
90 <param name="depth_as" value="ref"/>
3890f8ba0e4d Uploaded
jjohnson
parents:
diff changeset
91 <output name="output_file">
3890f8ba0e4d Uploaded
jjohnson
parents:
diff changeset
92 <assert_contents>
3890f8ba0e4d Uploaded
jjohnson
parents:
diff changeset
93 <has_text_matching expression="seq2\t156\t.\tA\tG,AAG\t.\tPASS\t.*" />
3890f8ba0e4d Uploaded
jjohnson
parents:
diff changeset
94 <has_text_matching expression="chr1\t158571283\t.\tA\tC,T\t.\tPASS\t.*" />
3890f8ba0e4d Uploaded
jjohnson
parents:
diff changeset
95 </assert_contents>
3890f8ba0e4d Uploaded
jjohnson
parents:
diff changeset
96 </output>
3890f8ba0e4d Uploaded
jjohnson
parents:
diff changeset
97 </test>
3890f8ba0e4d Uploaded
jjohnson
parents:
diff changeset
98 <test>
3890f8ba0e4d Uploaded
jjohnson
parents:
diff changeset
99 <param name="input_file" ftype="pileup" value="test.pileup" />
3890f8ba0e4d Uploaded
jjohnson
parents:
diff changeset
100 <param name="select_order" value="no"/>
5
8688e29ba96f Fix test 2
Jim Johnson <jj@umn.edu>
parents: 4
diff changeset
101 <param name="min_base_qual" value="5"/>
0
3890f8ba0e4d Uploaded
jjohnson
parents:
diff changeset
102 <param name="min_cvrg" value="5"/>
3890f8ba0e4d Uploaded
jjohnson
parents:
diff changeset
103 <param name="min_var_pct" value=".1"/>
3890f8ba0e4d Uploaded
jjohnson
parents:
diff changeset
104 <param name="allow_multiples" value="True"/>
3890f8ba0e4d Uploaded
jjohnson
parents:
diff changeset
105 <param name="snps_only" value="False"/>
3890f8ba0e4d Uploaded
jjohnson
parents:
diff changeset
106 <param name="depth_as" value="ref"/>
3890f8ba0e4d Uploaded
jjohnson
parents:
diff changeset
107 <output name="output_file">
3890f8ba0e4d Uploaded
jjohnson
parents:
diff changeset
108 <assert_contents>
3890f8ba0e4d Uploaded
jjohnson
parents:
diff changeset
109 <has_text_matching expression="seq2\t156\t.\tA\tG,AAG\t.\tPASS\t.*" />
5
8688e29ba96f Fix test 2
Jim Johnson <jj@umn.edu>
parents: 4
diff changeset
110 <has_text_matching expression="chr1\t158571283\t.\tA\tT\t.\tPASS\t.*" />
8688e29ba96f Fix test 2
Jim Johnson <jj@umn.edu>
parents: 4
diff changeset
111 <not_has_text text="125070485" />
0
3890f8ba0e4d Uploaded
jjohnson
parents:
diff changeset
112 </assert_contents>
3890f8ba0e4d Uploaded
jjohnson
parents:
diff changeset
113 </output>
3890f8ba0e4d Uploaded
jjohnson
parents:
diff changeset
114 </test>
3890f8ba0e4d Uploaded
jjohnson
parents:
diff changeset
115
3890f8ba0e4d Uploaded
jjohnson
parents:
diff changeset
116 </tests>
3890f8ba0e4d Uploaded
jjohnson
parents:
diff changeset
117 <help>
3890f8ba0e4d Uploaded
jjohnson
parents:
diff changeset
118 Pileup to VCF converts the output of a pileup tool to a VCF representing any alleles that surpass a user specified frequency, optionally presenting multiple alleles for a given position if the allele frequency is set below 0.5. This tool assumes that any filtering for base call quality and mapping quality has been done in previous processing.
3890f8ba0e4d Uploaded
jjohnson
parents:
diff changeset
119 </help>
3890f8ba0e4d Uploaded
jjohnson
parents:
diff changeset
120 </tool>