Mercurial > repos > blankenberg > naive_variant_caller

annotate tools/naive_variant_caller.xml @ 2:e69151df910c

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Fix for handling Longs.
author Daniel Blankenberg <dan@bx.psu.edu>
date Mon, 09 Sep 2013 10:54:22 -0400
parents ae6edc0012ba
children 8398666758e3
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 --coverage_dtype "${coverage_dtype}"
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
47
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
48 --allow_out_of_bounds_positions
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
49
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
50 </command>
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
51 <inputs>
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
52 <conditional name="reference_source">
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
53 <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
54 <option value="cached">Locally cached</option>
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
55 <option value="history">History</option>
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
56 </param>
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
57 <when value="cached">
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
58 <repeat name="input_bams" title="BAM file" min="1" >
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
59 <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
60 <validator type="unspecified_build" />
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
61 <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
62 </param>
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
63 </repeat>
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
64 <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
65 <options from_data_table="sam_fa_indexes">
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
66 <!-- <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
67 </options>
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
68 <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
69 </param>
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
70 </when>
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
71 <when value="history"> <!-- FIX ME!!!! -->
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
72 <repeat name="input_bams" title="BAM file" min="1" >
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
73 <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
74 </param>
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
75 </repeat>
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
76 <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
77 </when>
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
78 </conditional>
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
79
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
80 <repeat name="regions" title="Restrict to regions" min="0" >
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
81 <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
82 <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
83 <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
84 </repeat>
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
85
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
86 <!-- TODO: enhance filtering -->
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
87 <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
88 <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
89 <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
90
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
91 <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
92 <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
93
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
94 <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
95
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
96 <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">
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
97 <option value="uint8">uint8</option>
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
98 <option value="uint16" selected="True">uint16</option>
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
99 <option value="uint32">uint32</option>
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
100 <option value="uint64">uint64</option>
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
101 </param>
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
102
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
103 </inputs>
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
104 <outputs>
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
105 <data format="vcf" name="output_vcf" />
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
106 </outputs>
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
107 <help>
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
108 **What it does**
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
109
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
110 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
111
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
112 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
113
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
114 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
115
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
116
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
117 ------
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
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
121 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
122
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
123
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
124 **Outputs**
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 The output is in VCF format.
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 Example VCF output line, without reporting by strand:
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
129 ``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
130
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
131 Example VCF output line, when reporting by strand:
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
132 ``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
133
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
134 **Options**
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
135
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
136 Reference Genome:
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
137
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
138 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
139
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
140 Restrict to regions:
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 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
143
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
144 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
145
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
146 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
147
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
148 Minimum base quality:
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 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
151
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
152 Minimum mapping quality:
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 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
155
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
156 Ploidy:
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 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
159
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
160 Only write out positions with with possible alternate alleles:
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 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
163
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
164 Report counts by strand:
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 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
167
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
168 Choose the dtype to use for storing coverage information:
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 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
171
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
172 +--------+----------------------------+
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
173 | name | maximum coverage value |
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
174 +========+============================+
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
175 | uint8 | 255 |
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
176 +--------+----------------------------+
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
177 | uint16 | 65,535 |
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
178 +--------+----------------------------+
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
179 | uint32 | 4,294,967,295 |
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
180 +--------+----------------------------+
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
181 | uint64 | 18,446,744,073,709,551,615 |
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
182 +--------+----------------------------+
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 ------
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 **Citation**
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 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
189
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
190 </help>
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
191 <tests>
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
192 <test>
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
193 <param name="reference_source_selector" value="history" />
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
194 <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
195 <param name="ref_file" value="phiX174.fasta" ftype="fasta" />
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
196 <param name="regions" value="0" />
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
197 <param name="min_support_depth" value="0" />
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
198 <param name="min_base_quality" value="" />
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
199 <param name="min_mapping_quality" value="" />
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
200 <param name="ploidy" value="2" />
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
201 <param name="variants_only" value="False" />
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
202 <param name="use_strand" value="False" />
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
203 <param name="coverage_dtype" value="uint8" />
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
204 <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
205 </test>
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
206 </tests>
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
207
ae6edc0012ba Populate naive_variant_caller repository.
Daniel Blankenberg <dan@bx.psu.edu>
parents:
diff changeset
208 </tool>