Mercurial > repos > crs4 > bwa_mem

comparison bwa_mem.xml @ 0:6820983ba5d5 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded
author crs4
date Tue, 18 Mar 2014 07:49:22 -0400
parents
children ebb02ba5987c
comparison
equal deleted inserted replaced
-1:000000000000 0:6820983ba5d5
1 <tool id="bwa_mem" name="Map with BWA-MEM" version="0.7.7">
2 <requirements>
3 <requirement type="package" version="0.7.7">bwa</requirement>
4 </requirements>
5 <description></description>
6 <parallelism method="basic"></parallelism>
7 <version_command>bwa 2&gt;&amp;1 | grep "Version: " | sed -e 's/Version: //'</version_command>
8 <command interpreter="python">
9 bwa_mem.py
10 --threads="\${GALAXY_SLOTS:-1}"
11 --fileSource="${genomeSource.refGenomeSource}"
12 #if $genomeSource.refGenomeSource == "history":
13 ##build index on the fly
14 --ref="${genomeSource.ownFile}"
15 --dbkey="${dbkey}"
16 #else:
17 ##use precomputed indexes
18 --ref="${genomeSource.indices.fields.path}"
19 #end if
20
21 ## input file(s)
22 --fastq="${paired.fastq}"
23 #if $paired.sPaired == "paired":
24 --rfastq="${paired.rfastq}"
25 #end if
26
27 ## output file
28 --output="${output}"
29
30 ## run parameters
31 --genAlignType="${paired.sPaired}"
32 --params="${params.source_select}"
33 #if $params.source_select != "pre_set":
34 --minEditDistSeed="${params.minEditDistSeed}"
35 --bandWidth="${params.bandWidth}"
36 --offDiagonal="${params.offDiagonal}"
37 --internalSeeds="${params.internalSeeds}"
38 --seedsOccurrence="${params.seedsOccurrence}"
39 --mateRescue="${params.mateRescue}"
40 --skipPairing="${params.skipPairing}"
41 --seqMatch="${params.seqMatch}"
42 --mismatch="${params.mismatch}"
43 --gapOpen="${params.gapOpen}"
44 --gapExtension="${params.gapExtension}"
45 --clipping="${params.clipping}"
46 --unpairedReadpair="${params.unpairedReadpair}"
47 --interPairEnd="${params.interPairEnd}"
48 --minScore="${params.minScore}"
49 --mark="${params.mark}"
50
51 #if $params.readGroup.specReadGroup == "yes"
52 --rgid="${params.readGroup.rgid}"
53 --rgsm="${params.readGroup.rgsm}"
54 --rgpl="${params.readGroup.rgpl}"
55 --rglb="${params.readGroup.rglb}"
56 --rgpu="${params.readGroup.rgpu}"
57 --rgcn="${params.readGroup.rgcn}"
58 --rgds="${params.readGroup.rgds}"
59 --rgdt="${params.readGroup.rgdt}"
60 --rgfo="${params.readGroup.rgfo}"
61 --rgks="${params.readGroup.rgks}"
62 --rgpg="${params.readGroup.rgpg}"
63 --rgpi="${params.readGroup.rgpi}"
64 #end if
65 #end if
66
67 ## suppress output SAM header
68 --suppressHeader="${suppressHeader}"
69 </command>
70
71 <inputs>
72 <conditional name="genomeSource">
73 <param name="refGenomeSource" type="select" label="Will you select a reference genome from your history or use a built-in index?">
74 <option value="indexed">Use a built-in index</option>
75 <option value="history">Use one from the history</option>
76 </param>
77 <when value="indexed">
78 <param name="indices" type="select" label="Select a reference genome">
79 <options from_data_table="bwa_indexes">
80 <filter type="sort_by" column="2" />
81 <validator type="no_options" message="No indexes are available" />
82 </options>
83 </param>
84 </when>
85 <when value="history">
86 <param name="ownFile" type="data" format="fasta" metadata_name="dbkey" label="Select a reference from history" />
87 </when>
88 </conditional>
89 <conditional name="paired">
90 <param name="sPaired" type="select" label="Is this library mate-paired?">
91 <option value="single">Single-end</option>
92 <option value="paired">Paired-end</option>
93 </param>
94 <when value="single">
95 <param name="fastq" type="data" format="fastqsanger,fastqillumina" label="FASTQ file" help="FASTQ with either Sanger-scaled quality values (fastqsanger) or Illumina-scaled quality values (fastqillumina)" />
96 </when>
97 <when value="paired">
98 <param name="fastq" type="data" format="fastqsanger,fastqillumina" label="Forward FASTQ file" help="FASTQ with either Sanger-scaled quality values (fastqsanger) or Illumina-scaled quality values (fastqillumina)" />
99 <param name="rfastq" type="data" format="fastqsanger,fastqillumina" label="Reverse FASTQ file" help="FASTQ with either Sanger-scaled quality values (fastqsanger) or Illumina-scaled quality values (fastqillumina)" />
100 </when>
101 </conditional>
102 <conditional name="params">
103 <param name="source_select" type="select" label="BWA settings to use" help="For most mapping needs use Commonly Used settings. If you want full control use Full Parameter List">
104 <option value="pre_set">Commonly Used</option>
105 <option value="full">Full Parameter List</option>
106 </param>
107 <when value="pre_set" />
108 <when value="full">
109 <param name="minEditDistSeed" type="integer" value="19" label="Minimum seed length" />
110 <param name="bandWidth" type="integer" value="100" label="Band width for banded alignment" />
111 <param name="offDiagonal" type="integer" value="100" label="off-diagonal X-dropoff" />
112 <param name="internalSeeds" type="float" value="1.5" label="look for internal seeds inside a seed longer than {-k} * FLOAT [1.5]" />
113 <param name="seedsOccurrence" type="integer" value="10000" label="skip seeds with more than INT occurrences" />
114 <param name="mateRescue" type="boolean" truevalue="True" falsevalue="False" checked="False" label="skip seeds with more than INT occurrences" />
115 <param name="skipPairing" type="boolean" truevalue="True" falsevalue="False" checked="False" label="skpe pairing, mate rescue performed unless -S also in use" />
116 <param name="seqMatch" type="integer" value="1" label="score of a sequence match" />
117 <param name="mismatch" type="integer" value="4" label="penalty for a mismatch" />
118 <param name="gapOpen" type="integer" value="6" label="gap open penalty" />
119 <param name="gapExtension" type="text" value="None" label="gap extension penalty; a gap of size k cost {-O} + {-E}*k [1]" />
120 <param name="clipping" type="integer" value="5" label="penalty for clipping" />
121 <param name="unpairedReadpair" type="integer" value="17" label="penalty for an unpaired read pair" />
122 <param name="interPairEnd" type="boolean" truevalue="True" falsevalue="False" checked="False" label="first query file consists of interleaved paired-end sequences" />
123 <param name="minScore" type="integer" value="30" label="minimum score to output" />
124 <param name="mark" type="boolean" truevalue="True" falsevalue="False" checked="False" label="mark shorter split hits as secondary (for Picard/GATK compatibility)" />
125
126 <conditional name="readGroup">
127 <param name="specReadGroup" type="select" label="Specify the read group for this file? (samse/sampe -r)">
128 <option value="yes">Yes</option>
129 <option value="no" selected="True">No</option>
130 </param>
131 <when value="yes">
132 <param name="rgid" type="text" size="25" label="[Essential]Read group identifier (ID). Each @RG line must have a unique ID. The value of ID is used in the RG
133 tags of alignment records. Must be unique among all read groups in header section." help="Required if RG specified. Read group
134 IDs may be modified when merging SAM files in order to handle collisions." />
135 <param name="rgpl" type="text" size="25" label="[Essential]Platform/technology used to produce the reads (PL)" help="Required if RG specified. Valid values : CAPILLARY, LS454, ILLUMINA,
136 SOLID, HELICOS, IONTORRENT and PACBIO" />
137 <param name="rglb" type="text" size="25" label="[Essential]Library name (LB)" help="Required if RG specified" />
138 <param name="rgsm" type="text" size="25" label="[Essential]Sample (SM)" help="Required if RG specified. Use pool name where a pool is being sequenced" />
139 <param name="rgpu" type="text" size="25" label="Platform unit (PU)" help="Optional. Unique identifier (e.g. flowcell-barcode.lane for Illumina or slide for SOLiD)" />
140 <param name="rgcn" type="text" size="25" label="Sequencing center that produced the read (CN)" help="Optional" />
141 <param name="rgds" type="text" size="25" label="Description (DS)" help="Optional" />
142 <param name="rgdt" type="text" size="25" label="Date that run was produced (DT)" help="Optional. ISO8601 format date or date/time, like YYYY-MM-DD" />
143 <param name="rgfo" type="text" size="25" label="Flow order (FO). The array of nucleotide bases that correspond to the nucleotides used for each
144 flow of each read." help="Optional. Multi-base flows are encoded in IUPAC format, and non-nucleotide flows by
145 various other characters. Format : /\*|[ACMGRSVTWYHKDBN]+/" />
146 <param name="rgks" type="text" size="25" label="The array of nucleotide bases that correspond to the key sequence of each read (KS)" help="Optional" />
147 <param name="rgpg" type="text" size="25" label="Programs used for processing the read group (PG)" help="Optional" />
148 <param name="rgpi" type="text" size="25" label="Predicted median insert size (PI)" help="Optional" />
149 </when>
150 <when value="no" />
151 </conditional>
152 </when>
153 </conditional>
154 <param name="suppressHeader" type="boolean" truevalue="true" falsevalue="false" checked="False" label="Suppress the header in the output SAM file" help="BWA produces SAM with several lines of header information" />
155 </inputs>
156
157 <outputs>
158 <data format="sam" name="output" label="${tool.name} on ${on_string}: mapped reads">
159 <actions>
160 <conditional name="genomeSource.refGenomeSource">
161 <when value="indexed">
162 <action type="metadata" name="dbkey">
163 <option type="from_data_table" name="bwa_indexes" column="1">
164 <filter type="param_value" column="0" value="#" compare="startswith" keep="False"/>
165 <filter type="param_value" ref="genomeSource.indices" column="0"/>
166 </option>
167 </action>
168 </when>
169 <when value="history">
170 <action type="metadata" name="dbkey">
171 <option type="from_param" name="genomeSource.ownFile" param_attribute="dbkey" />
172 </action>
173 </when>
174 </conditional>
175 </actions>
176 </data>
177 </outputs>
178
179 <tests>
180 <test>
181 </test>
182 <test>
183 </test>
184 <test>
185 </test>
186 </tests>
187 <help>
188 **What it does**
189
190 BWA is a software package for mapping low-divergent sequences against a large reference genome, such as the human genome. BWA-MEM, which is the latest algorithm, is generally recommended for high-quality queries as it is faster and more accurate. BWA-MEM also has better performance than BWA-backtrack for 70-100bp Illumina reads.
191
192 ------
193
194 **Input formats**
195
196 BWA accepts files in either Sanger FASTQ format (galaxy type *fastqsanger*) or Illumina FASTQ format (galaxy type *fastqillumina*). Use the FASTQ Groomer to prepare your files.
197
198 ------
199
200 **License and citation**
201
202 This tool uses `BWA`_, which is licensed separately. Please cite |Li2013|_.
203
204 .. _BWA: http://bio-bwa.sourceforge.net/
205 .. |Li2013| replace:: Li, H. (2013) Aligning sequence reads, clone sequences and assembly contigs with BWA-MEM. arXiv:1303.3997 [q-bio.GN]
206 .. _Li2013: http://arxiv.org/abs/1303.3997
207 </help>
208 </tool>