Mercurial > repos > blankenberg > naive_variant_caller

annotate tools/naive_variant_caller.xml @ 7:3c3ef33b9d56

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Update dependencies.
author Daniel Blankenberg <dan@bx.psu.edu>
date Wed, 26 Feb 2014 12:37:00 -0500
parents 8398666758e3
children d5f866df45ae
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
1
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
1 <tool id="naive_variant_caller" name="Naive Variant Caller" version="0.0.1">
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
2 <description> - tabulate variable sites from BAM datasets</description>
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
3 <requirements>
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
4 <requirement type="package" version="1.7.1">numpy</requirement>
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
5 <requirement type="package" version="0.0.1">pyBamParser</requirement>
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
6 <requirement type="package" version="0.0.1">pyBamTools</requirement>
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
7 </requirements>
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
8 <stdio>
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
9 <exit_code range="1:" err_level="fatal" />
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
10 <exit_code range=":-1" err_level="fatal" />
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
11 </stdio>
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
12 <command interpreter="python">naive_variant_caller.py
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
13 -o "${output_vcf}"
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
14
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
15 #for $input_bam in $reference_source.input_bams:
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
16 -b "${input_bam.input_bam}"
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
17 -i "${input_bam.input_bam.metadata.bam_index}"
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
18 #end for
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
19
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
20 #if $reference_source.reference_source_selector != "history":
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
21 -r "${reference_source.ref_file.fields.path}"
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
22 #elif $reference_source.ref_file:
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
23 -r "${reference_source.ref_file}"
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
24 #end if
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
25
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
26 #for $region in $regions:
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
27 --region "${region.chromosome}:${region.start}-${region.end}"
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
28 #end for
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
29
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
30 ${variants_only}
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
31
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
32 ${use_strand}
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
33
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
34 --ploidy "${$ploidy}"
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
35
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
36 --min_support_depth "${min_support_depth}"
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
37
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
38 #if str($min_base_quality):
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
39 --min_base_quality "${min_base_quality}"
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
40 #end if
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
41
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
42 #if str($min_mapping_quality):
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
43 --min_mapping_quality "${min_mapping_quality}"
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
44 #end if
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
45
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
46 --allow_out_of_bounds_positions
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
47
5
8398666758e3 Update options.
Daniel Blankenberg <dan@bx.psu.edu>
parents: 1
diff changeset
48 #if str( $advanced_options.advanced_options_selector ) == "advanced":
8398666758e3 Update options.
Daniel Blankenberg <dan@bx.psu.edu>
parents: 1
diff changeset
49 --coverage_dtype "${advanced_options.coverage_dtype}"
8398666758e3 Update options.
Daniel Blankenberg <dan@bx.psu.edu>
parents: 1
diff changeset
50 ${advanced_options.safe}
8398666758e3 Update options.
Daniel Blankenberg <dan@bx.psu.edu>
parents: 1
diff changeset
51 #else
8398666758e3 Update options.
Daniel Blankenberg <dan@bx.psu.edu>
parents: 1
diff changeset
52 --coverage_dtype "uint64"
8398666758e3 Update options.
Daniel Blankenberg <dan@bx.psu.edu>
parents: 1
diff changeset
53 #end if
1
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
54 </command>
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
55 <inputs>
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
56 <conditional name="reference_source">
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
57 <param name="reference_source_selector" type="select" label="Choose the source for the reference list">
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
58 <option value="cached">Locally cached</option>
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
59 <option value="history">History</option>
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
60 </param>
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
61 <when value="cached">
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
62 <repeat name="input_bams" title="BAM file" min="1" >
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
63 <param name="input_bam" type="data" format="bam" label="BAM file">
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
64 <validator type="unspecified_build" />
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
65 <validator type="dataset_metadata_in_data_table" table_name="sam_fa_indexes" metadata_name="dbkey" metadata_column="value" message="Sequences are not currently available for the specified build." /> <!-- fixme!!! this needs to be a select -->
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
66 </param>
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
67 </repeat>
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
68 <param name="ref_file" type="select" label="Using reference genome" >
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
69 <options from_data_table="sam_fa_indexes">
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
70 <!-- <filter type="data_meta" key="dbkey" ref="input_bam" column="dbkey"/> does not yet work in a repeat...-->
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
71 </options>
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
72 <validator type="no_options" message="A built-in reference genome is not available for the build associated with the selected input file"/>
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
73 </param>
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
74 </when>
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
75 <when value="history"> <!-- FIX ME!!!! -->
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
76 <repeat name="input_bams" title="BAM file" min="1" >
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
77 <param name="input_bam" type="data" format="bam" label="BAM file" >
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
78 </param>
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
79 </repeat>
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
80 <param name="ref_file" type="data" format="fasta" label="Using reference file" optional="True" />
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
81 </when>
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
82 </conditional>
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
83
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
84 <repeat name="regions" title="Restrict to regions" min="0" >
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
85 <param name="chromosome" type="text" value="" optional="False" label="Chromosome" />
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
86 <param name="start" type="integer" value="" optional="True" label="Start" />
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
87 <param name="end" type="integer" value="" optional="True" label="End" />
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
88 </repeat>
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
89
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
90 <!-- TODO: enhance filtering -->
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
91 <param name="min_support_depth" type="integer" value="0" min="0" label="Minimum number of reads needed to consider a REF/ALT" />
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
92 <param name="min_base_quality" type="integer" value="" label="Minimum base quality" optional="True" />
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
93 <param name="min_mapping_quality" type="integer" value="" label="Minimum mapping quality" optional="True" />
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
94
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
95 <param name="ploidy" type="integer" value="2" min="1" label="Ploidy" />
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
96 <param name="variants_only" type="boolean" truevalue="--variants_only" falsevalue="" checked="False" label="Only write out positions with with possible alternate alleles"/>
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
97
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
98 <param name="use_strand" type="boolean" truevalue="--use_strand" falsevalue="" checked="False" label="Report counts by strand"/>
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
99
5
8398666758e3 Update options.
Daniel Blankenberg <dan@bx.psu.edu>
parents: 1
diff changeset
100 <conditional name="advanced_options">
8398666758e3 Update options.
Daniel Blankenberg <dan@bx.psu.edu>
parents: 1
diff changeset
101 <param name="advanced_options_selector" type="select" label="Show Advanced Options">
8398666758e3 Update options.
Daniel Blankenberg <dan@bx.psu.edu>
parents: 1
diff changeset
102 <option value="basic" selected="True">Hide Advanced Options</option>
8398666758e3 Update options.
Daniel Blankenberg <dan@bx.psu.edu>
parents: 1
diff changeset
103 <option value="advanced">Show Advanced Options</option>
8398666758e3 Update options.
Daniel Blankenberg <dan@bx.psu.edu>
parents: 1
diff changeset
104 </param>
8398666758e3 Update options.
Daniel Blankenberg <dan@bx.psu.edu>
parents: 1
diff changeset
105 <when value="basic">
8398666758e3 Update options.
Daniel Blankenberg <dan@bx.psu.edu>
parents: 1
diff changeset
106 <!-- Do nothing here -->
8398666758e3 Update options.
Daniel Blankenberg <dan@bx.psu.edu>
parents: 1
diff changeset
107 </when>
8398666758e3 Update options.
Daniel Blankenberg <dan@bx.psu.edu>
parents: 1
diff changeset
108 <when value="advanced">
8398666758e3 Update options.
Daniel Blankenberg <dan@bx.psu.edu>
parents: 1
diff changeset
109 <param name="coverage_dtype" type="select" label="Choose the dtype to use for storing coverage information" help="This affects the maximum recorded value for a position, e.g. uint8 would be 255 coverage, but will require the least amount of RAM">
8398666758e3 Update options.
Daniel Blankenberg <dan@bx.psu.edu>
parents: 1
diff changeset
110 <option value="uint8">uint8</option>
8398666758e3 Update options.
Daniel Blankenberg <dan@bx.psu.edu>
parents: 1
diff changeset
111 <option value="uint16">uint16</option>
8398666758e3 Update options.
Daniel Blankenberg <dan@bx.psu.edu>
parents: 1
diff changeset
112 <option value="uint32">uint32</option>
8398666758e3 Update options.
Daniel Blankenberg <dan@bx.psu.edu>
parents: 1
diff changeset
113 <option value="uint64" selected="True">uint64</option>
8398666758e3 Update options.
Daniel Blankenberg <dan@bx.psu.edu>
parents: 1
diff changeset
114 </param>
8398666758e3 Update options.
Daniel Blankenberg <dan@bx.psu.edu>
parents: 1
diff changeset
115 <param name="safe" type="boolean" truevalue="--safe" falsevalue="" checked="False" label="Be extra safe"/>
8398666758e3 Update options.
Daniel Blankenberg <dan@bx.psu.edu>
parents: 1
diff changeset
116 </when>
8398666758e3 Update options.
Daniel Blankenberg <dan@bx.psu.edu>
parents: 1
diff changeset
117 </conditional>
1
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
118
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
119 </inputs>
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
120 <outputs>
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
121 <data format="vcf" name="output_vcf" />
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
122 </outputs>
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
123 <help>
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
124 **What it does**
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
125
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
126 This tool is a naive variant caller that processes aligned sequencing reads from the BAM format and produces a VCF file containing per position variant calls. This tool allows multiple BAM files to be provided as input and utilizes read group information to make calls for individual samples.
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
127
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
128 User configurable options allow filtering reads that do not pass mapping or base quality thresholds and minimum per base read depth; user's can also specify the ploidy and whether to consider each strand separately.
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
129
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
130 In addition to calling alternate alleles based upon simple ratios of nucleotides at a position, per base nucleotide counts are also provided. A custom tag, NC, is used within the Genotype fields. The NC field is a comma-separated listing of nucleotide counts in the form of &lt;nucleotide&gt;=&lt;count&gt;, where a plus or minus character is prepended to indicate strand, if the strandedness option was specified.
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
131
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
132
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
133 ------
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
134
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
135 **Inputs**
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
136
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
137 Accepts one or more BAM input files and a reference genome from the built-in list or from a FASTA file in your history.
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
138
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
139
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
140 **Outputs**
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
141
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
142 The output is in VCF format.
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
143
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
144 Example VCF output line, without reporting by strand:
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
145 ``chrM 16029 . T G,A,C . . AC=15,9,5;AF=0.00155311658729,0.000931869952371,0.000517705529095 GT:AC:AF:NC 0/0:15,9,5:0.00155311658729,0.000931869952371,0.000517705529095:A=9,C=5,T=9629,G=15,``
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
146
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
147 Example VCF output line, when reporting by strand:
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
148 ``chrM 16029 . T G,A,C . . AC=15,9,5;AF=0.00155311658729,0.000931869952371,0.000517705529095 GT:AC:AF:NC 0/0:15,9,5:0.00155311658729,0.000931869952371,0.000517705529095:+T=3972,-A=9,-C=5,-T=5657,-G=15,``
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
149
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
150 **Options**
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
151
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
152 Reference Genome:
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
153
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
154 Ensure that you have selected the correct reference genome, either from the list of built-in genomes or by selecting the corresponding FASTA file from your history.
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
155
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
156 Restrict to regions:
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
157
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
158 You can specify any number of regions on which you would like to receive results. You can specify just a chromosome name, or a chromosome name and start postion, or a chromosome name and start and end position for the set of desired regions.
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
159
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
160 Minimum number of reads needed to consider a REF/ALT:
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
161
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
162 This value declares the minimum number of reads containing a particular base at each position in order to list and use said allele in genotyping calls. Default is 0.
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
163
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
164 Minimum base quality:
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
165
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
166 The minimum base quality score needed for the position in a read to be used for nucleotide counts and genotyping. Default is no filter.
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
167
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
168 Minimum mapping quality:
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
169
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
170 The minimum mapping quality score needed to consider a read for nucleotide counts and genotyping. Default is no filter.
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
171
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
172 Ploidy:
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
173
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
174 The number of genotype calls to make at each reported position.
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
175
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
176 Only write out positions with with possible alternate alleles:
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
177
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
178 When set, only positions which have at least one non-reference nucleotide which passes declare filters will be present in the output.
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
179
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
180 Report counts by strand:
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
181
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
182 When set, nucleotide counts (NC) will be reported in reference to the aligned read's source strand. Reported as: &lt;strand&gt;&lt;BASE&gt;=&lt;COUNT&gt;.
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
183
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
184 Choose the dtype to use for storing coverage information:
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
185
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
186 This controls the maximum depth value for each nucleotide/position/strand (when specified). Smaller values require the least amount of memory, but have smaller maximal limits.
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
187
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
188 +--------+----------------------------+
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
189 | name | maximum coverage value |
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
190 +========+============================+
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
191 | uint8 | 255 |
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
192 +--------+----------------------------+
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
193 | uint16 | 65,535 |
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
194 +--------+----------------------------+
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
195 | uint32 | 4,294,967,295 |
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
196 +--------+----------------------------+
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
197 | uint64 | 18,446,744,073,709,551,615 |
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
198 +--------+----------------------------+
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
199
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
200 ------
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
201
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
202 **Citation**
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
203
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
204 If you use this tool, please cite Blankenberg D, et al. *In preparation.*
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
205
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
206 </help>
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
207 <tests>
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
208 <test>
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
209 <param name="reference_source_selector" value="history" />
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
210 <param name="input_bam" value="fake_phiX174_reads_1.bam" ftype="bam" />
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
211 <param name="ref_file" value="phiX174.fasta" ftype="fasta" />
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
212 <param name="regions" value="0" />
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
213 <param name="min_support_depth" value="0" />
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
214 <param name="min_base_quality" value="" />
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
215 <param name="min_mapping_quality" value="" />
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
216 <param name="ploidy" value="2" />
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
217 <param name="variants_only" value="False" />
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
218 <param name="use_strand" value="False" />
5
8398666758e3 Update options.
Daniel Blankenberg <dan@bx.psu.edu>
parents: 1
diff changeset
219 <param name="advanced_options_selector" value="advanced" />
1
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
220 <param name="coverage_dtype" value="uint8" />
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
221 <output name="output_vcf" file="fake_phiX174_reads_1_test_out_1.vcf" compare="contains" />
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
222 </test>
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
223 </tests>
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
224
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
225 </tool>