|
0
|
1 <tool id="bwa_color_wrapper" name="Map with BWA for SOLiD" version="1.0.2">
|
|
|
2 <requirements>
|
|
|
3 <requirement type="package" version="0.5.9">bwa</requirement>
|
|
|
4 </requirements>
|
|
|
5 <description></description>
|
|
|
6 <parallelism method="basic"></parallelism>
|
|
|
7 <command interpreter="python">
|
|
|
8 bwa_wrapper.py
|
|
|
9 --threads="4"
|
|
|
10 --color-space
|
|
|
11
|
|
|
12 ## reference source
|
|
|
13 --fileSource="${genomeSource.refGenomeSource}"
|
|
|
14 #if $genomeSource.refGenomeSource == "history":
|
|
|
15 ##build index on the fly
|
|
|
16 --ref="${genomeSource.ownFile}"
|
|
|
17 --dbkey="${dbkey}"
|
|
|
18 #else:
|
|
|
19 ##use precomputed indexes
|
|
|
20 --ref="${genomeSource.indices.fields.path}"
|
|
|
21 --do_not_build_index
|
|
|
22 #end if
|
|
|
23
|
|
|
24 ## input file(s)
|
|
|
25 --input1="${paired.input1}"
|
|
|
26 #if $paired.sPaired == "paired":
|
|
|
27 --input2="${paired.input2}"
|
|
|
28 #end if
|
|
|
29
|
|
|
30 ## output file
|
|
|
31 --output="${output}"
|
|
|
32
|
|
|
33 ## run parameters
|
|
|
34 --genAlignType="${paired.sPaired}"
|
|
|
35 --params="${params.source_select}"
|
|
|
36 #if $params.source_select != "pre_set":
|
|
|
37 --maxEditDist="${params.maxEditDist}"
|
|
|
38 --fracMissingAligns="${params.fracMissingAligns}"
|
|
|
39 --maxGapOpens="${params.maxGapOpens}"
|
|
|
40 --maxGapExtens="${params.maxGapExtens}"
|
|
|
41 --disallowLongDel="${params.disallowLongDel}"
|
|
|
42 --disallowIndel="${params.disallowIndel}"
|
|
|
43 --seed="${params.seed}"
|
|
|
44 --maxEditDistSeed="${params.maxEditDistSeed}"
|
|
|
45 --mismatchPenalty="${params.mismatchPenalty}"
|
|
|
46 --gapOpenPenalty="${params.gapOpenPenalty}"
|
|
|
47 --gapExtensPenalty="${params.gapExtensPenalty}"
|
|
|
48 --suboptAlign="${params.suboptAlign}"
|
|
|
49 --noIterSearch="${params.noIterSearch}"
|
|
|
50 --outputTopN="${params.outputTopN}"
|
|
|
51 --outputTopNDisc="${params.outputTopNDisc}"
|
|
|
52 --maxInsertSize="${params.maxInsertSize}"
|
|
|
53 --maxOccurPairing="${params.maxOccurPairing}"
|
|
|
54 #if $params.readGroup.specReadGroup == "yes"
|
|
|
55 --rgid="${params.readGroup.rgid}"
|
|
|
56 --rgcn="${params.readGroup.rgcn}"
|
|
|
57 --rgds="${params.readGroup.rgds}"
|
|
|
58 --rgdt="${params.readGroup.rgdt}"
|
|
|
59 --rgfo="${params.readGroup.rgfo}"
|
|
|
60 --rgks="${params.readGroup.rgks}"
|
|
|
61 --rglb="${params.readGroup.rglb}"
|
|
|
62 --rgpg="${params.readGroup.rgpg}"
|
|
|
63 --rgpi="${params.readGroup.rgpi}"
|
|
|
64 --rgpl="${params.readGroup.rgpl}"
|
|
|
65 --rgpu="${params.readGroup.rgpu}"
|
|
|
66 --rgsm="${params.readGroup.rgsm}"
|
|
|
67 #end if
|
|
|
68 #end if
|
|
|
69
|
|
|
70 ## suppress output SAM header
|
|
|
71 --suppressHeader="${suppressHeader}"
|
|
|
72 </command>
|
|
|
73 <requirements>
|
|
|
74 <requirement type="package">bwa</requirement>
|
|
|
75 </requirements>
|
|
|
76 <inputs>
|
|
|
77 <conditional name="genomeSource">
|
|
|
78 <param name="refGenomeSource" type="select" label="Will you select a reference genome from your history or use a built-in index?">
|
|
|
79 <option value="indexed">Use a built-in index</option>
|
|
|
80 <option value="history">Use one from the history</option>
|
|
|
81 </param>
|
|
|
82 <when value="indexed">
|
|
|
83 <param name="indices" type="select" label="Select a reference genome">
|
|
|
84 <options from_data_table="bwa_indexes_color">
|
|
|
85 <filter type="sort_by" column="2" />
|
|
|
86 <validator type="no_options" message="No indexes are available for the selected input dataset" />
|
|
|
87 </options>
|
|
|
88 </param>
|
|
|
89 </when>
|
|
|
90 <when value="history">
|
|
|
91 <param name="ownFile" type="data" format="fasta" metadata_name="dbkey" label="Select a reference from history" />
|
|
|
92 </when>
|
|
|
93 </conditional>
|
|
|
94 <conditional name="paired">
|
|
|
95 <param name="sPaired" type="select" label="Is this library mate-paired?">
|
|
|
96 <option value="single">Single-end</option>
|
|
|
97 <option value="paired">Paired-end</option>
|
|
|
98 </param>
|
|
|
99 <when value="single">
|
|
|
100 <param name="input1" type="data" format="fastqcssanger" label="FASTQ file (Nucleotide-space recoded from color-space)">
|
|
|
101 <help>Convert color-space data to nucleotide-space (see help section below for steps). Must have Sanger-scaled quality values with ASCII offset 33</help>
|
|
|
102 </param>
|
|
|
103 </when>
|
|
|
104 <when value="paired">
|
|
|
105 <param name="input1" type="data" format="fastqcssanger" label="Forward FASTQ file (Nucleotide-space recoded from color-space)" help="Must have Sanger-scaled quality values with ASCII offset 33">
|
|
|
106 <help>Convert color-space data to nucleotide-space (see help section below for steps). Must have Sanger-scaled quality values with ASCII offset 33</help>
|
|
|
107 </param>
|
|
|
108 <param name="input2" type="data" format="fastqcssanger" label="Reverse FASTQ file (Nucleotide-space recoded from color-space)" help="Must have Sanger-scaled quality values with ASCII offset 33">
|
|
|
109 <help>Convert color-space data to nucleotide-space (see help section below for steps). Must have Sanger-scaled quality values with ASCII offset 33</help>
|
|
|
110 </param>
|
|
|
111 </when>
|
|
|
112 </conditional>
|
|
|
113 <conditional name="params">
|
|
|
114 <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">
|
|
|
115 <option value="pre_set">Commonly Used</option>
|
|
|
116 <option value="full">Full Parameter List</option>
|
|
|
117 </param>
|
|
|
118 <when value="pre_set" />
|
|
|
119 <when value="full">
|
|
|
120 <param name="maxEditDist" type="integer" value="0" label="Maximum edit distance (aln -n)" help="Enter this value OR a fraction of missing alignments, not both" />
|
|
|
121 <param name="fracMissingAligns" type="float" value="0.04" label="Fraction of missing alignments given 2% uniform base error rate (aln -n)" help="Enter this value OR maximum edit distance, not both" />
|
|
|
122 <param name="maxGapOpens" type="integer" value="1" label="Maximum number of gap opens (aln -o)" />
|
|
|
123 <param name="maxGapExtens" type="integer" value="-1" label="Maximum number of gap extensions (aln -e)" help="-1 for k-difference mode (disallowing long gaps)" />
|
|
|
124 <param name="disallowLongDel" type="integer" value="16" label="Disallow long deletion within [value] bp towards the 3'-end (aln -d)" />
|
|
|
125 <param name="disallowIndel" type="integer" value="5" label="Disallow insertion/deletion within [value] bp towards the end (aln -i)" />
|
|
|
126 <param name="seed" type="integer" value="-1" label="Number of first subsequences to take as seed (aln -l)" help="Enter -1 for infinity" />
|
|
|
127 <param name="maxEditDistSeed" type="integer" value="2" label="Maximum edit distance in the seed (aln -k)" />
|
|
|
128 <param name="mismatchPenalty" type="integer" value="3" label="Mismatch penalty (aln -M)" help="BWA will not search for suboptimal hits with a score lower than [value]" />
|
|
|
129 <param name="gapOpenPenalty" type="integer" value="11" label="Gap open penalty (aln -O)" />
|
|
|
130 <param name="gapExtensPenalty" type="integer" value="4" label="Gap extension penalty (aln -E)" />
|
|
|
131 <param name="suboptAlign" type="integer" optional="True" label="Proceed with suboptimal alignments if there are no more than INT equally best hits. (aln -R)" help="For paired-end reads only. By default, BWA only searches for suboptimal alignments if the top hit is unique. Using this option has no effect on accuracy for single-end reads. It is mainly designed for improving the alignment accuracy of paired-end reads. However, the pairing procedure will be slowed down, especially for very short reads (~32bp)" />
|
|
|
132 <param name="noIterSearch" type="boolean" truevalue="true" falsevalue="false" checked="no" label="Disable iterative search (aln -N)" help="All hits with no more than maxDiff differences will be found. This mode is much slower than the default" />
|
|
|
133 <param name="outputTopN" type="integer" value="3" label="Maximum number of alignments to output in the XA tag for reads paired properly (samse/sampe -n)" help="If a read has more than INT hits, the XA tag will not be written" />
|
|
|
134 <param name="outputTopNDisc" type="integer" value="10" label="Maximum number of alignments to output in the XA tag for disconcordant read pairs (excluding singletons) (sampe -N)" help="For paired-end reads only. If a read has more than INT hits, the XA tag will not be written" />
|
|
|
135 <param name="maxInsertSize" type="integer" value="500" label="Maximum insert size for a read pair to be considered as being mapped properly (sampe -a)" help="For paired-end reads only. Only used when there are not enough good alignments to infer the distribution of insert sizes" />
|
|
|
136 <param name="maxOccurPairing" type="integer" value="100000" label="Maximum occurrences of a read for pairing (sampe -o)" help="For paired-end reads only. A read with more occurrences will be treated as a single-end read. Reducing this parameter helps faster pairing" />
|
|
|
137 <conditional name="readGroup">
|
|
|
138 <param name="specReadGroup" type="select" label="Specify the read group for this file? (samse/sampe -r)">
|
|
|
139 <option value="yes">Yes</option>
|
|
|
140 <option value="no" selected="True">No</option>
|
|
|
141 </param>
|
|
|
142 <when value="yes">
|
|
|
143 <param name="rgid" type="text" size="25" label="Read group identifier (ID). Each @RG line must have a unique ID. The value of ID is used in the RG
|
|
|
144 tags of alignment records. Must be unique among all read groups in header section." help="Required if RG specified. Read group
|
|
|
145 IDs may be modified when merging SAM files in order to handle collisions." />
|
|
|
146 <param name="rgcn" type="text" size="25" label="Sequencing center that produced the read (CN)" help="Optional" />
|
|
|
147 <param name="rgds" type="text" size="25" label="Description (DS)" help="Optional" />
|
|
|
148 <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" />
|
|
|
149 <param name="rgfo" type="text" size="25" label="Flow order (FO). The array of nucleotide bases that correspond to the nucleotides used for each
|
|
|
150 flow of each read." help="Optional. Multi-base flows are encoded in IUPAC format, and non-nucleotide flows by
|
|
|
151 various other characters. Format : /\*|[ACMGRSVTWYHKDBN]+/" />
|
|
|
152 <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" />
|
|
|
153 <param name="rglb" type="text" size="25" label="Library name (LB)" help="Required if RG specified" />
|
|
|
154 <param name="rgpg" type="text" size="25" label="Programs used for processing the read group (PG)" help="Optional" />
|
|
|
155 <param name="rgpi" type="text" size="25" label="Predicted median insert size (PI)" help="Optional" />
|
|
|
156 <param name="rgpl" type="text" size="25" label="Platform/technology used to produce the reads (PL)" help="Required if RG specified. Valid values : CAPILLARY, LS454, ILLUMINA,
|
|
|
157 SOLID, HELICOS, IONTORRENT and PACBIO" />
|
|
|
158 <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)" />
|
|
|
159 <param name="rgsm" type="text" size="25" label="Sample (SM)" help="Required if RG specified. Use pool name where a pool is being sequenced" />
|
|
|
160 </when>
|
|
|
161 <when value="no" />
|
|
|
162 </conditional>
|
|
|
163 </when>
|
|
|
164 </conditional>
|
|
|
165 <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" />
|
|
|
166 </inputs>
|
|
|
167 <outputs>
|
|
|
168 <data format="sam" name="output" label="${tool.name} on ${on_string}: mapped reads">
|
|
|
169 <actions>
|
|
|
170 <conditional name="genomeSource.refGenomeSource">
|
|
|
171 <when value="indexed">
|
|
|
172 <action type="metadata" name="dbkey">
|
|
|
173 <option type="from_data_table" name="bwa_indexes_color" column="1">
|
|
|
174 <filter type="param_value" column="0" value="#" compare="startswith" keep="False"/>
|
|
|
175 <filter type="param_value" ref="genomeSource.indices" column="0" />
|
|
|
176 </option>
|
|
|
177 </action>
|
|
|
178 </when>
|
|
|
179 <when value="history">
|
|
|
180 <action type="metadata" name="dbkey">
|
|
|
181 <option type="from_param" name="genomeSource.ownFile" param_attribute="dbkey" />
|
|
|
182 </action>
|
|
|
183 </when>
|
|
|
184 </conditional>
|
|
|
185 </actions>
|
|
|
186 </data>
|
|
|
187 </outputs>
|
|
|
188 <tests>
|
|
|
189 <test>
|
|
|
190 <!--
|
|
|
191 BWA commands:
|
|
|
192 cp test-data/hg19chrX_midpart.fasta hg19chrX_midpart.fasta
|
|
|
193 bwa index -c -a is hg19chrX_midpart.fasta
|
|
|
194 bwa aln -t 4 -c hg19chrX_midpart.fasta test-data/bwa_wrapper_in4.fastqcssanger > bwa_wrapper_out4.sai
|
|
|
195 bwa samse hg19chrX_midpart.fasta bwa_wrapper_out4.sai test-data/bwa_wrapper_in4.fastqcssanger > bwa_wrapper_out4.u.sam
|
|
|
196 hg19chrX_midpart.fasta is the prefix for the reference files (hg19chrX_midpart.fasta.amb, hg19chrX_midpart.fasta.ann, hg19chrX_midpart.fasta.bwt, ...)
|
|
|
197 It's just part of hg19 chrX, from the middle of the chromosome
|
|
|
198 plain old sort doesn't handle underscores like python:
|
|
|
199 python -c "import sys; lines=file(sys.argv[1],'rb').readlines(); lines.sort(); file(sys.argv[2],'wb').write(''.join(lines))" bwa_wrapper_out4.u.sam bwa_wrapper_out4.sam
|
|
|
200 -->
|
|
|
201 <param name="refGenomeSource" value="history" />
|
|
|
202 <param name="ownFile" value="hg19chrX_midpart.fasta" />
|
|
|
203 <param name="sPaired" value="single" />
|
|
|
204 <param name="input1" value="bwa_wrapper_in4.fastqcssanger" ftype="fastqcssanger" />
|
|
|
205 <param name="source_select" value="pre_set" />
|
|
|
206 <param name="suppressHeader" value="false" />
|
|
|
207 <output name="output" file="bwa_wrapper_out4.sam" ftype="sam" sort="True" lines_diff="2" />
|
|
|
208 </test>
|
|
|
209 <test>
|
|
|
210 <!--
|
|
|
211 BWA commands:
|
|
|
212 bwa aln -t 4 -c equCab2chrM_cs.fa test-data/bwa_wrapper_in5.fastqcssanger > bwa_wrapper_out5a.sai
|
|
|
213 bwa aln -t 4 -c equCab2chrM_cs.fa test-data/bwa_wrapper_in6.fastqcssanger > bwa_wrapper_out5b.sai
|
|
|
214 bwa sampe equCab2chrM_cs.fa bwa_wrapper_out5a.sai bwa_wrapper_out5b.sai test-data/bwa_wrapper_in5.fastqcssanger test-data/bwa_wrapper_in6.fastqcssanger > bwa_wrapper_out5.u.sam
|
|
|
215 equCab2chrM_cs.fa is the prefix of the index files (equCab2chrM_cs.fa.amb, equCab2chrM_cs.fa.ann, ...)
|
|
|
216 remove the comment lines (beginning with '@') from the resulting sam file
|
|
|
217 plain old sort doesn't handle underscores like python:
|
|
|
218 python -c "import sys; lines=file(sys.argv[1],'rb').readlines(); lines.sort(); file(sys.argv[2],'wb').write(''.join(lines))" bwa_wrapper_out5.u.sam bwa_wrapper_out5.sam
|
|
|
219 -->
|
|
|
220 <param name="refGenomeSource" value="indexed" />
|
|
|
221 <param name="indices" value="equCab2chrM" />
|
|
|
222 <param name="sPaired" value="paired" />
|
|
|
223 <param name="input1" value="bwa_wrapper_in5.fastqcssanger" ftype="fastqcssanger" />
|
|
|
224 <param name="input2" value="bwa_wrapper_in6.fastqcssanger" ftype="fastqcssanger" />
|
|
|
225 <param name="source_select" value="pre_set" />
|
|
|
226 <param name="suppressHeader" value="true" />
|
|
|
227 <output name="output" file="bwa_wrapper_out5.sam" ftype="sam" sort="True" />
|
|
|
228 </test>
|
|
|
229 <test>
|
|
|
230 <!--
|
|
|
231 BWA commands:
|
|
|
232 bwa aln -n 0.04 -o 1 -e -1 -d 16 -i 5 -k 2 -t 4 -M 3 -O 11 -E 4 -R -N -c hg19chrX_midpart.fasta test-data/bwa_wrapper_in4.fastqcssanger > bwa_wrapper_out6.sai
|
|
|
233 bwa samse -n 3 -r "@RG\tID:474747\tDS:description\tDT:2011-03-14\tLB:lib-child-1-A\tPI:200\tPL:SOLID\tSM:child-1" hg19chrX_midpart.fasta bwa_wrapper_out6.sai test-data/bwa_wrapper_in4.fastqcssanger > bwa_wrapper_out6.u.sam
|
|
|
234 hg19chrX_midpart_cs.fa is the prefix of the index files (hg19chrX_midpart.fa.amb, hg19chrX_midpart.fa.ann, ...)
|
|
|
235 (It's just part of hg19 chrX, from the middle of the chromosome)
|
|
|
236 plain old sort doesn't handle underscores like python:
|
|
|
237 python -c "import sys; lines=file(sys.argv[1],'rb').readlines(); lines.sort(); file(sys.argv[2],'wb').write(''.join(lines))" bwa_wrapper_out6.u.sam bwa_wrapper_out6.sam
|
|
|
238 -->
|
|
|
239 <param name="refGenomeSource" value="indexed" />
|
|
|
240 <param name="indices" value="hg19chrX_midpart" />
|
|
|
241 <param name="sPaired" value="single" />
|
|
|
242 <param name="input1" value="bwa_wrapper_in4.fastqcssanger" ftype="fastqcssanger" />
|
|
|
243 <param name="source_select" value="full" />
|
|
|
244 <param name="maxEditDist" value="0" />
|
|
|
245 <param name="fracMissingAligns" value="0.04" />
|
|
|
246 <param name="maxGapOpens" value="1" />
|
|
|
247 <param name="maxGapExtens" value="-1" />
|
|
|
248 <param name="disallowLongDel" value="16" />
|
|
|
249 <param name="disallowIndel" value="5" />
|
|
|
250 <param name="seed" value="-1" />
|
|
|
251 <param name="maxEditDistSeed" value="2" />
|
|
|
252 <param name="mismatchPenalty" value="3" />
|
|
|
253 <param name="gapOpenPenalty" value="11" />
|
|
|
254 <param name="gapExtensPenalty" value="4" />
|
|
|
255 <param name="suboptAlign" value="" />
|
|
|
256 <param name="noIterSearch" value="true" />
|
|
|
257 <param name="outputTopN" value="3" />
|
|
|
258 <param name="outputTopNDisc" value="10" />
|
|
|
259 <param name="maxInsertSize" value="500" />
|
|
|
260 <param name="maxOccurPairing" value="100000" />
|
|
|
261 <param name="specReadGroup" value="yes" />
|
|
|
262 <param name="rgid" value="474747" />
|
|
|
263 <param name="rgcn" value="" />
|
|
|
264 <param name="rgds" value="description" />
|
|
|
265 <param name="rgdt" value="2011-03-14" />
|
|
|
266 <param name="rgfo" value="" />
|
|
|
267 <param name="rgks" value="" />
|
|
|
268 <param name="rglb" value="lib-child-1-A" />
|
|
|
269 <param name="rgpg" value="" />
|
|
|
270 <param name="rgpi" value="200" />
|
|
|
271 <param name="rgpl" value="SOLID" />
|
|
|
272 <param name="rgpu" value="" />
|
|
|
273 <param name="rgsm" value="child-1" />
|
|
|
274 <param name="suppressHeader" value="false" />
|
|
|
275 <output name="output" file="bwa_wrapper_out6.sam" ftype="sam" sort="True" lines_diff="2" />
|
|
|
276 </test>
|
|
|
277 <test>
|
|
|
278 <!--
|
|
|
279 BWA commands:
|
|
|
280 cp test-data/chr_m.fasta chr_m.fasta
|
|
|
281 bwa index -c -a is chr_m.fasta
|
|
|
282 bwa aln -n 0.04 -o 1 -e -1 -d 16 -i 5 -k 2 -t 4 -M 3 -O 11 -E 4 -R -N -c chr_m.fasta test-data/bwa_wrapper_in5.fastqcssanger > bwa_wrapper_out7a.sai
|
|
|
283 bwa aln -n 0.04 -o 1 -e -1 -d 16 -i 5 -k 2 -t 4 -M 3 -O 11 -E 4 -R -N -c chr_m.fasta test-data/bwa_wrapper_in6.fastqcssanger > bwa_wrapper_out7b.sai
|
|
|
284 bwa sampe -a 100 -o 2 -n 3 -N 10 chr_m.fasta bwa_wrapper_out7a.sai bwa_wrapper_out7b.sai test-data/bwa_wrapper_in5.fastqcssanger test-data/bwa_wrapper_in6.fastqcssanger > bwa_wrapper_out7.u.sam
|
|
|
285 chr_m.fasta is the prefix of the index files (chr_m.fasta.amb, chr_m.fasta.ann, ...)
|
|
|
286 plain old sort doesn't handle underscores like python:
|
|
|
287 python -c "import sys; lines=file(sys.argv[1],'rb').readlines(); lines.sort(); file(sys.argv[2],'wb').write(''.join(lines))" bwa_wrapper_out7.u.sam bwa_wrapper_out7.sam
|
|
|
288 -->
|
|
|
289 <param name="refGenomeSource" value="history" />
|
|
|
290 <param name="ownFile" value="chr_m.fasta" />
|
|
|
291 <param name="sPaired" value="paired" />
|
|
|
292 <param name="input1" value="bwa_wrapper_in5.fastqcssanger" ftype="fastqcssanger" />
|
|
|
293 <param name="input2" value="bwa_wrapper_in6.fastqcssanger" ftype="fastqcssanger" />
|
|
|
294 <param name="source_select" value="full" />
|
|
|
295 <param name="maxEditDist" value="0" />
|
|
|
296 <param name="fracMissingAligns" value="0.04" />
|
|
|
297 <param name="maxGapOpens" value="1" />
|
|
|
298 <param name="maxGapExtens" value="-1" />
|
|
|
299 <param name="disallowLongDel" value="16" />
|
|
|
300 <param name="disallowIndel" value="5" />
|
|
|
301 <param name="seed" value="-1" />
|
|
|
302 <param name="maxEditDistSeed" value="2" />
|
|
|
303 <param name="mismatchPenalty" value="3" />
|
|
|
304 <param name="gapOpenPenalty" value="11" />
|
|
|
305 <param name="gapExtensPenalty" value="4" />
|
|
|
306 <param name="suboptAlign" value="" />
|
|
|
307 <param name="noIterSearch" value="true" />
|
|
|
308 <param name="outputTopN" value="3" />
|
|
|
309 <param name="outputTopNDisc" value="10" />
|
|
|
310 <param name="maxInsertSize" value="100" />
|
|
|
311 <param name="maxOccurPairing" value="2" />
|
|
|
312 <param name="specReadGroup" value="no" />
|
|
|
313 <param name="suppressHeader" value="false" />
|
|
|
314 <output name="output" file="bwa_wrapper_out7.sam" ftype="sam" sort="True" lines_diff="2" />
|
|
|
315 </test>
|
|
|
316 </tests>
|
|
|
317 <help>
|
|
|
318
|
|
|
319 **What it does**
|
|
|
320
|
|
|
321 BWA is a fast light-weighted tool that aligns relatively short sequences (queries) to a sequence database (large), such as the human reference genome. It is developed by Heng Li at the Sanger Insitute. Li H. and Durbin R. (2009) Fast and accurate short read alignment with Burrows-Wheeler transform. Bioinformatics, 25, 1754-60.
|
|
|
322
|
|
|
323 ------
|
|
|
324
|
|
|
325 **Know what you are doing**
|
|
|
326
|
|
|
327 .. class:: warningmark
|
|
|
328
|
|
|
329 There is no such thing (yet) as an automated gearshift in short read mapping. It is all like stick-shift driving in San Francisco. In other words = running this tool with default parameters will probably not give you meaningful results. A way to deal with this is to **understand** the parameters by carefully reading the `documentation`__ and experimenting. Fortunately, Galaxy makes experimenting easy.
|
|
|
330
|
|
|
331 .. __: http://bio-bwa.sourceforge.net/
|
|
|
332
|
|
|
333 ------
|
|
|
334
|
|
|
335 **Input formats**
|
|
|
336
|
|
|
337 BWA accepts files in Sanger FASTQ format. Use the FASTQ Groomer to prepare your files, set to either FASTQ Sanger or FASTQ Color Space Sanger as appropriate.
|
|
|
338
|
|
|
339 If you have Color Space Sanger, it must be converted to nucleotide-space first. To do this, use the Manipulate FASTQ tool under NGS: QC and manipulation, with the following settings:
|
|
|
340 Manipulate reads on Sequence Content, choosing Change Adapter Base, and having the text box empty.
|
|
|
341 Manipulate reads on Sequence Content, doing a String Translate from "01234." to "ACGTN".
|
|
|
342
|
|
|
343
|
|
|
344 ------
|
|
|
345
|
|
|
346 **A Note on Built-in Reference Genomes**
|
|
|
347
|
|
|
348 The default variant for all genomes is "Full", defined as all primary chromosomes (or scaffolds/contigs) including mitochondrial plus associated unmapped, plasmid, and other segments. When only one version of a genome is available in this tool, it represents the default "Full" variant. Some genomes will have more than one variant available. The "Canonical Male" or sometimes simply "Canonical" variant contains the primary chromosomes for a genome. For example a human "Canonical" variant contains chr1-chr22, chrX, chrY, and chrM. The "Canonical Female" variant contains the primary chromosomes excluding chrY.
|
|
|
349
|
|
|
350 ------
|
|
|
351
|
|
|
352 **Outputs**
|
|
|
353
|
|
|
354 The output is in SAM format, and has the following columns::
|
|
|
355
|
|
|
356 Column Description
|
|
|
357 -------- --------------------------------------------------------
|
|
|
358 1 QNAME Query (pair) NAME
|
|
|
359 2 FLAG bitwise FLAG
|
|
|
360 3 RNAME Reference sequence NAME
|
|
|
361 4 POS 1-based leftmost POSition/coordinate of clipped sequence
|
|
|
362 5 MAPQ MAPping Quality (Phred-scaled)
|
|
|
363 6 CIGAR extended CIGAR string
|
|
|
364 7 MRNM Mate Reference sequence NaMe ('=' if same as RNAME)
|
|
|
365 8 MPOS 1-based Mate POSition
|
|
|
366 9 ISIZE Inferred insert SIZE
|
|
|
367 10 SEQ query SEQuence on the same strand as the reference
|
|
|
368 11 QUAL query QUALity (ASCII-33 gives the Phred base quality)
|
|
|
369 12 OPT variable OPTional fields in the format TAG:VTYPE:VALU
|
|
|
370
|
|
|
371 The flags are as follows::
|
|
|
372
|
|
|
373 Flag Description
|
|
|
374 ------ -------------------------------------
|
|
|
375 0x0001 the read is paired in sequencing
|
|
|
376 0x0002 the read is mapped in a proper pair
|
|
|
377 0x0004 the query sequence itself is unmapped
|
|
|
378 0x0008 the mate is unmapped
|
|
|
379 0x0010 strand of the query (1 for reverse)
|
|
|
380 0x0020 strand of the mate
|
|
|
381 0x0040 the read is the first read in a pair
|
|
|
382 0x0080 the read is the second read in a pair
|
|
|
383 0x0100 the alignment is not primary
|
|
|
384
|
|
|
385 It looks like this (scroll sideways to see the entire example)::
|
|
|
386
|
|
|
387 QNAME FLAG RNAME POS MAPQ CIAGR MRNM MPOS ISIZE SEQ QUAL OPT
|
|
|
388 HWI-EAS91_1_30788AAXX:1:1:1761:343 4 * 0 0 * * 0 0 AAAAAAANNAAAAAAAAAAAAAAAAAAAAAAAAAAACNNANNGAGTNGNNNNNNNGCTTCCCACAGNNCTGG hhhhhhh;;hhhhhhhhhhh^hOhhhhghhhfhhhgh;;h;;hhhh;h;;;;;;;hhhhhhghhhh;;Phhh
|
|
|
389 HWI-EAS91_1_30788AAXX:1:1:1578:331 4 * 0 0 * * 0 0 GTATAGANNAATAAGAAAAAAAAAAATGAAGACTTTCNNANNTCTGNANNNNNNNTCTTTTTTCAGNNGTAG hhhhhhh;;hhhhhhhhhhhhhhhhhhhhhhhhhhhh;;h;;hhhh;h;;;;;;;hhhhhhhhhhh;;hhVh
|
|
|
390
|
|
|
391 -------
|
|
|
392
|
|
|
393 **BWA settings**
|
|
|
394
|
|
|
395 All of the options have a default value. You can change any of them. All of the options in BWA have been implemented here.
|
|
|
396
|
|
|
397 ------
|
|
|
398
|
|
|
399 **BWA parameter list**
|
|
|
400
|
|
|
401 This is an exhaustive list of BWA options:
|
|
|
402
|
|
|
403 For **aln**::
|
|
|
404
|
|
|
405 -n NUM Maximum edit distance if the value is INT, or the fraction of missing
|
|
|
406 alignments given 2% uniform base error rate if FLOAT. In the latter
|
|
|
407 case, the maximum edit distance is automatically chosen for different
|
|
|
408 read lengths. [0.04]
|
|
|
409 -o INT Maximum number of gap opens [1]
|
|
|
410 -e INT Maximum number of gap extensions, -1 for k-difference mode
|
|
|
411 (disallowing long gaps) [-1]
|
|
|
412 -d INT Disallow a long deletion within INT bp towards the 3'-end [16]
|
|
|
413 -i INT Disallow an indel within INT bp towards the ends [5]
|
|
|
414 -l INT Take the first INT subsequence as seed. If INT is larger than the
|
|
|
415 query sequence, seeding will be disabled. For long reads, this option
|
|
|
416 is typically ranged from 25 to 35 for '-k 2'. [inf]
|
|
|
417 -k INT Maximum edit distance in the seed [2]
|
|
|
418 -t INT Number of threads (multi-threading mode) [1]
|
|
|
419 -M INT Mismatch penalty. BWA will not search for suboptimal hits with a score
|
|
|
420 lower than (bestScore-misMsc). [3]
|
|
|
421 -O INT Gap open penalty [11]
|
|
|
422 -E INT Gap extension penalty [4]
|
|
|
423 -c Reverse query but not complement it, which is required for alignment
|
|
|
424 in the color space.
|
|
|
425 -R Proceed with suboptimal alignments even if the top hit is a repeat. By
|
|
|
426 default, BWA only searches for suboptimal alignments if the top hit is
|
|
|
427 unique. Using this option has no effect on accuracy for single-end
|
|
|
428 reads. It is mainly designed for improving the alignment accuracy of
|
|
|
429 paired-end reads. However, the pairing procedure will be slowed down,
|
|
|
430 especially for very short reads (~32bp).
|
|
|
431 -N Disable iterative search. All hits with no more than maxDiff
|
|
|
432 differences will be found. This mode is much slower than the default.
|
|
|
433
|
|
|
434 For **samse**::
|
|
|
435
|
|
|
436 -n INT Maximum number of alignments to output in the XA tag for reads paired
|
|
|
437 properly. If a read has more than INT hits, the XA tag will not be
|
|
|
438 written. [3]
|
|
|
439 -r STR Specify the read group in a format like '@RG\tID:foo\tSM:bar' [null]
|
|
|
440
|
|
|
441 For **sampe**::
|
|
|
442
|
|
|
443 -a INT Maximum insert size for a read pair to be considered as being mapped
|
|
|
444 properly. Since version 0.4.5, this option is only used when there
|
|
|
445 are not enough good alignment to infer the distribution of insert
|
|
|
446 sizes. [500]
|
|
|
447 -n INT Maximum number of alignments to output in the XA tag for reads paired
|
|
|
448 properly. If a read has more than INT hits, the XA tag will not be
|
|
|
449 written. [3]
|
|
|
450 -N INT Maximum number of alignments to output in the XA tag for disconcordant
|
|
|
451 read pairs (excluding singletons). If a read has more than INT hits,
|
|
|
452 the XA tag will not be written. [10]
|
|
|
453 -o INT Maximum occurrences of a read for pairing. A read with more
|
|
|
454 occurrences will be treated as a single-end read. Reducing this
|
|
|
455 parameter helps faster pairing. [100000]
|
|
|
456 -r STR Specify the read group in a format like '@RG\tID:foo\tSM:bar' [null]
|
|
|
457
|
|
|
458 For specifying the read group in **samse** or **sampe**, use the following::
|
|
|
459
|
|
|
460 @RG Read group. Unordered multiple @RG lines are allowed.
|
|
|
461 ID Read group identifier. Each @RG line must have a unique ID. The value of
|
|
|
462 ID is used in the RG tags of alignment records. Must be unique among all
|
|
|
463 read groups in header section. Read group IDs may be modified when
|
|
|
464 merging SAM files in order to handle collisions.
|
|
|
465 CN Name of sequencing center producing the read.
|
|
|
466 DS Description.
|
|
|
467 DT Date the run was produced (ISO8601 date or date/time).
|
|
|
468 FO Flow order. The array of nucleotide bases that correspond to the
|
|
|
469 nucleotides used for each flow of each read. Multi-base flows are encoded
|
|
|
470 in IUPAC format, and non-nucleotide flows by various other characters.
|
|
|
471 Format : /\*|[ACMGRSVTWYHKDBN]+/
|
|
|
472 KS The array of nucleotide bases that correspond to the key sequence of each read.
|
|
|
473 LB Library.
|
|
|
474 PG Programs used for processing the read group.
|
|
|
475 PI Predicted median insert size.
|
|
|
476 PL Platform/technology used to produce the reads. Valid values : CAPILLARY,
|
|
|
477 LS454, ILLUMINA, SOLID, HELICOS, IONTORRENT and PACBIO.
|
|
|
478 PU Platform unit (e.g. flowcell-barcode.lane for Illumina or slide for
|
|
|
479 SOLiD). Unique identifier.
|
|
|
480 SM Sample. Use pool name where a pool is being sequenced.
|
|
|
481
|
|
|
482 </help>
|
|
|
483 </tool>
|
|
|
484
|
|
|
485
|
