|
4
|
1 <tool id="test2" name="Stupid Test 2" version="1.2.3">
|
|
|
2 <requirements>
|
|
|
3 <requirement type="set_environment">BWA_PATH</requirement>
|
|
|
4 <requirement type="set_environment">PYTHON_PATH</requirement>
|
|
|
5 </requirements>
|
|
|
6 <description></description>
|
|
|
7 <parallelism method="basic"></parallelism>
|
|
|
8 <command interpreter="sh">
|
|
|
9 bwa_wrapper.sh
|
|
|
10 --threads="4"
|
|
|
11
|
|
|
12 #if $input1.ext == "fastqillumina":
|
|
|
13 --illumina1.3
|
|
|
14 #end if
|
|
|
15
|
|
|
16 ## reference source
|
|
|
17 --fileSource=$genomeSource.refGenomeSource
|
|
|
18 #if $genomeSource.refGenomeSource == "history":
|
|
|
19 ##build index on the fly
|
|
|
20 --ref="${genomeSource.ownFile}"
|
|
|
21 --dbkey=$dbkey
|
|
|
22 #else:
|
|
|
23 ##use precomputed indexes
|
|
|
24 --ref="${genomeSource.indices.fields.path}"
|
|
|
25 --do_not_build_index
|
|
|
26 #end if
|
|
|
27
|
|
|
28 ## input file(s)
|
|
|
29 --input1=$paired.input1
|
|
|
30 #if $paired.sPaired == "paired":
|
|
|
31 --input2=$paired.input2
|
|
|
32 #end if
|
|
|
33
|
|
|
34 ## output file
|
|
|
35 --output=$output
|
|
|
36
|
|
|
37 ## run parameters
|
|
|
38 --genAlignType=$paired.sPaired
|
|
|
39 --params=$params.source_select
|
|
|
40 #if $params.source_select != "pre_set":
|
|
|
41 --maxEditDist=$params.maxEditDist
|
|
|
42 --fracMissingAligns=$params.fracMissingAligns
|
|
|
43 --maxGapOpens=$params.maxGapOpens
|
|
|
44 --maxGapExtens=$params.maxGapExtens
|
|
|
45 --disallowLongDel=$params.disallowLongDel
|
|
|
46 --disallowIndel=$params.disallowIndel
|
|
|
47 --seed=$params.seed
|
|
|
48 --maxEditDistSeed=$params.maxEditDistSeed
|
|
|
49 --mismatchPenalty=$params.mismatchPenalty
|
|
|
50 --gapOpenPenalty=$params.gapOpenPenalty
|
|
|
51 --gapExtensPenalty=$params.gapExtensPenalty
|
|
|
52 --suboptAlign="${params.suboptAlign}"
|
|
|
53 --noIterSearch=$params.noIterSearch
|
|
|
54 --outputTopN=$params.outputTopN
|
|
|
55 --outputTopNDisc=$params.outputTopNDisc
|
|
|
56 --maxInsertSize=$params.maxInsertSize
|
|
|
57 --maxOccurPairing=$params.maxOccurPairing
|
|
|
58 #if $params.readGroup.specReadGroup == "yes"
|
|
|
59 --rgid="$params.readGroup.rgid"
|
|
|
60 --rgcn="$params.readGroup.rgcn"
|
|
|
61 --rgds="$params.readGroup.rgds"
|
|
|
62 --rgdt="$params.readGroup.rgdt"
|
|
|
63 --rgfo="$params.readGroup.rgfo"
|
|
|
64 --rgks="$params.readGroup.rgks"
|
|
|
65 --rglb="$params.readGroup.rglb"
|
|
|
66 --rgpg="$params.readGroup.rgpg"
|
|
|
67 --rgpi="$params.readGroup.rgpi"
|
|
|
68 --rgpl="$params.readGroup.rgpl"
|
|
|
69 --rgpu="$params.readGroup.rgpu"
|
|
|
70 --rgsm="$params.readGroup.rgsm"
|
|
|
71 #end if
|
|
|
72 #end if
|
|
|
73
|
|
|
74 ## suppress output SAM header
|
|
|
75 --suppressHeader=$suppressHeader
|
|
|
76 </command>
|
|
|
77 <inputs>
|
|
|
78 <conditional name="genomeSource">
|
|
|
79 <param name="refGenomeSource" type="select" label="Will you select a reference genome from your history or use a built-in index?">
|
|
|
80 <option value="indexed">Use a built-in index</option>
|
|
|
81 <option value="history">Use one from the history</option>
|
|
|
82 </param>
|
|
|
83 <when value="indexed">
|
|
|
84 <param name="indices" type="select" label="Select a reference genome">
|
|
|
85 <options from_data_table="bwa_indexes">
|
|
|
86 <filter type="sort_by" column="2" />
|
|
|
87 <validator type="no_options" message="No indexes are available" />
|
|
|
88 </options>
|
|
|
89 </param>
|
|
|
90 </when>
|
|
|
91 <when value="history">
|
|
|
92 <param name="ownFile" type="data" format="fasta" metadata_name="dbkey" label="Select a reference from history" />
|
|
|
93 </when>
|
|
|
94 </conditional>
|
|
|
95 <conditional name="paired">
|
|
|
96 <param name="sPaired" type="select" label="Is this library mate-paired?">
|
|
|
97 <option value="single">Single-end</option>
|
|
|
98 <option value="paired">Paired-end</option>
|
|
|
99 </param>
|
|
|
100 <when value="single">
|
|
|
101 <param name="input1" type="data" format="fastqsanger,fastqillumina" label="FASTQ file" help="FASTQ with either Sanger-scaled quality values (fastqsanger) or Illumina-scaled quality values (fastqillumina)" />
|
|
|
102 </when>
|
|
|
103 <when value="paired">
|
|
|
104 <param name="input1" type="data" format="fastqsanger,fastqillumina" label="Forward FASTQ file" help="FASTQ with either Sanger-scaled quality values (fastqsanger) or Illumina-scaled quality values (fastqillumina)" />
|
|
|
105 <param name="input2" type="data" format="fastqsanger,fastqillumina" label="Reverse FASTQ file" help="FASTQ with either Sanger-scaled quality values (fastqsanger) or Illumina-scaled quality values (fastqillumina)" />
|
|
|
106 </when>
|
|
|
107 </conditional>
|
|
|
108 <conditional name="params">
|
|
|
109 <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">
|
|
|
110 <option value="pre_set">Commonly Used</option>
|
|
|
111 <option value="full">Full Parameter List</option>
|
|
|
112 </param>
|
|
|
113 <when value="pre_set" />
|
|
|
114 <when value="full">
|
|
|
115 <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" />
|
|
|
116 <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" />
|
|
|
117 <param name="maxGapOpens" type="integer" value="1" label="Maximum number of gap opens (aln -o)" />
|
|
|
118 <param name="maxGapExtens" type="integer" value="-1" label="Maximum number of gap extensions (aln -e)" help="-1 for k-difference mode (disallowing long gaps)" />
|
|
|
119 <param name="disallowLongDel" type="integer" value="16" label="Disallow long deletion within [value] bp towards the 3'-end (aln -d)" />
|
|
|
120 <param name="disallowIndel" type="integer" value="5" label="Disallow insertion/deletion within [value] bp towards the end (aln -i)" />
|
|
|
121 <param name="seed" type="integer" value="-1" label="Number of first subsequences to take as seed (aln -l)" help="Enter -1 for infinity" />
|
|
|
122 <param name="maxEditDistSeed" type="integer" value="2" label="Maximum edit distance in the seed (aln -k)" />
|
|
|
123 <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]" />
|
|
|
124 <param name="gapOpenPenalty" type="integer" value="11" label="Gap open penalty (aln -O)" />
|
|
|
125 <param name="gapExtensPenalty" type="integer" value="4" label="Gap extension penalty (aln -E)" />
|
|
|
126 <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)" />
|
|
|
127 <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" />
|
|
|
128 <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" />
|
|
|
129 <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" />
|
|
|
130 <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" />
|
|
|
131 <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" />
|
|
|
132 <conditional name="readGroup">
|
|
|
133 <param name="specReadGroup" type="select" label="Specify the read group for this file? (samse/sampe -r)">
|
|
|
134 <option value="yes">Yes</option>
|
|
|
135 <option value="no" selected="True">No</option>
|
|
|
136 </param>
|
|
|
137 <when value="yes">
|
|
|
138 <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
|
|
|
139 tags of alignment records. Must be unique among all read groups in header section." help="Required if RG specified. Read group
|
|
|
140 IDs may be modified when merging SAM files in order to handle collisions." />
|
|
|
141 <param name="rgcn" type="text" size="25" label="Sequencing center that produced the read (CN)" help="Optional" />
|
|
|
142 <param name="rgds" type="text" size="25" label="Description (DS)" help="Optional" />
|
|
|
143 <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" />
|
|
|
144 <param name="rgfo" type="text" size="25" label="Flow order (FO). The array of nucleotide bases that correspond to the nucleotides used for each
|
|
|
145 flow of each read." help="Optional. Multi-base flows are encoded in IUPAC format, and non-nucleotide flows by
|
|
|
146 various other characters. Format : /\*|[ACMGRSVTWYHKDBN]+/" />
|
|
|
147 <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" />
|
|
|
148 <param name="rglb" type="text" size="25" label="Library name (LB)" help="Required if RG specified" />
|
|
|
149 <param name="rgpg" type="text" size="25" label="Programs used for processing the read group (PG)" help="Optional" />
|
|
|
150 <param name="rgpi" type="text" size="25" label="Predicted median insert size (PI)" help="Optional" />
|
|
|
151 <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,
|
|
|
152 SOLID, HELICOS, IONTORRENT and PACBIO" />
|
|
|
153 <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)" />
|
|
|
154 <param name="rgsm" type="text" size="25" label="Sample (SM)" help="Required if RG specified. Use pool name where a pool is being sequenced" />
|
|
|
155 </when>
|
|
|
156 <when value="no" />
|
|
|
157 </conditional>
|
|
|
158 </when>
|
|
|
159 </conditional>
|
|
|
160 <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" />
|
|
|
161 </inputs>
|
|
|
162 <outputs>
|
|
|
163 <data format="sam" name="output" label="${tool.name} on ${on_string}: mapped reads">
|
|
|
164 <actions>
|
|
|
165 <conditional name="genomeSource.refGenomeSource">
|
|
|
166 <when value="indexed">
|
|
|
167 <action type="metadata" name="dbkey">
|
|
|
168 <option type="from_data_table" name="bwa_indexes" column="1">
|
|
|
169 <filter type="param_value" column="0" value="#" compare="startswith" keep="False"/>
|
|
|
170 <filter type="param_value" ref="genomeSource.indices" column="0"/>
|
|
|
171 </option>
|
|
|
172 </action>
|
|
|
173 </when>
|
|
|
174 <when value="history">
|
|
|
175 <action type="metadata" name="dbkey">
|
|
|
176 <option type="from_param" name="genomeSource.ownFile" param_attribute="dbkey" />
|
|
|
177 </action>
|
|
|
178 </when>
|
|
|
179 </conditional>
|
|
|
180 </actions>
|
|
|
181 </data>
|
|
|
182 </outputs>
|
|
|
183 <tests>
|
|
|
184 <test>
|
|
|
185 <!--
|
|
|
186 BWA commands:
|
|
|
187 bwa aln -t 4 phiX.fasta test-data/bwa_wrapper_in1.fastqsanger > bwa_wrapper_out1.sai
|
|
|
188 bwa samse phiX.fasta bwa_wrapper_out1.sai test-data/bwa_wrapper_in1.fastqsanger > bwa_wrapper_out1.sam
|
|
|
189 phiX.fasta is the prefix for the reference files (phiX.fasta.amb, phiX.fasta.ann, phiX.fasta.bwt, ...)
|
|
|
190 remove the comment lines (beginning with '@') from the resulting sam file
|
|
|
191 plain old sort doesn't handle underscores like python:
|
|
|
192 python -c "import sys; lines=file(sys.argv[1],'rb').readlines(); lines.sort(); file(sys.argv[2],'wb').write(''.join(lines))" bwa_wrapper_out1.u.sam bwa_wrapper_out1.sam
|
|
|
193 -->
|
|
|
194 <param name="refGenomeSource" value="indexed" />
|
|
|
195 <param name="indices" value="phiX" />
|
|
|
196 <param name="sPaired" value="single" />
|
|
|
197 <param name="input1" value="bwa_wrapper_in1.fastqsanger" ftype="fastqsanger" />
|
|
|
198 <param name="source_select" value="pre_set" />
|
|
|
199 <param name="suppressHeader" value="true" />
|
|
|
200 <output name="output" file="bwa_wrapper_out1.sam" ftype="sam" sort="True" />
|
|
|
201 </test>
|
|
|
202 <test>
|
|
|
203 <!--
|
|
|
204 BWA commands:
|
|
|
205 cp test-data/phiX.fasta phiX.fasta
|
|
|
206 bwa index -a is phiX.fasta
|
|
|
207 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 phiX.fasta test-data/bwa_wrapper_in1.fastqsanger > bwa_wrapper_out2.sai
|
|
|
208 bwa samse -n 3 phiX.fasta bwa_wrapper_out2.sai test-data/bwa_wrapper_in1.fastqsanger > bwa_wrapper_out2.u.sam
|
|
|
209 phiX.fasta is the prefix for the reference files (phiX.fasta.amb, phiX.fasta.ann, phiX.fasta.bwt, ...)
|
|
|
210 remove the comment lines (beginning with '@') from the resulting sam file
|
|
|
211 plain old sort doesn't handle underscores like python:
|
|
|
212 python -c "import sys; lines=file(sys.argv[1],'rb').readlines(); lines.sort(); file(sys.argv[2],'wb').write(''.join(lines))" bwa_wrapper_out2.u.sam bwa_wrapper_out2.sam
|
|
|
213 -->
|
|
|
214 <param name="refGenomeSource" value="history" />
|
|
|
215 <param name="ownFile" value="phiX.fasta" />
|
|
|
216 <param name="sPaired" value="single" />
|
|
|
217 <param name="input1" value="bwa_wrapper_in1.fastqsanger" ftype="fastqsanger" />
|
|
|
218 <param name="source_select" value="full" />
|
|
|
219 <param name="maxEditDist" value="0" />
|
|
|
220 <param name="fracMissingAligns" value="0.04" />
|
|
|
221 <param name="maxGapOpens" value="1" />
|
|
|
222 <param name="maxGapExtens" value="-1" />
|
|
|
223 <param name="disallowLongDel" value="16" />
|
|
|
224 <param name="disallowIndel" value="5" />
|
|
|
225 <param name="seed" value="-1" />
|
|
|
226 <param name="maxEditDistSeed" value="2" />
|
|
|
227 <param name="mismatchPenalty" value="3" />
|
|
|
228 <param name="gapOpenPenalty" value="11" />
|
|
|
229 <param name="gapExtensPenalty" value="4" />
|
|
|
230 <param name="suboptAlign" value="" />
|
|
|
231 <param name="noIterSearch" value="true" />
|
|
|
232 <param name="outputTopN" value="3" />
|
|
|
233 <param name="outputTopNDisc" value="10" />
|
|
|
234 <param name="maxInsertSize" value="500" />
|
|
|
235 <param name="maxOccurPairing" value="100000" />
|
|
|
236 <param name="specReadGroup" value="no" />
|
|
|
237 <param name="suppressHeader" value="true" />
|
|
|
238 <output name="output" file="bwa_wrapper_out2.sam" ftype="sam" sort="True" />
|
|
|
239 </test>
|
|
|
240 <test>
|
|
|
241 <!--
|
|
|
242 BWA commands:
|
|
|
243 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 phiX.fasta test-data/bwa_wrapper_in2.fastqsanger > bwa_wrapper_out3a.sai
|
|
|
244 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 phiX.fasta test-data/bwa_wrapper_in3.fastqsanger > bwa_wrapper_out3b.sai
|
|
|
245 bwa sampe -a 500 -o 100000 -n 3 -N 10 -r "@RG\tID:abcdefg\tDS:descrip\tDT:2010-11-01\tLB:lib-mom-A\tPI:400\tPL:ILLUMINA\tSM:mom" phiX.fasta bwa_wrapper_out3a.sai bwa_wrapper_out3b.sai test-data/bwa_wrapper_in2.fastqsanger test-data/bwa_wrapper_in3.fastqsanger > bwa_wrapper_out3.u.sam
|
|
|
246 phiX.fasta is the prefix for the reference
|
|
|
247 plain old sort doesn't handle underscores like python:
|
|
|
248 python -c "import sys; lines=file(sys.argv[1],'rb').readlines(); lines.sort(); file(sys.argv[2],'wb').write(''.join(lines))" bwa_wrapper_out3.u.sam bwa_wrapper_out3.sam
|
|
|
249 -->
|
|
|
250 <param name="refGenomeSource" value="indexed" />
|
|
|
251 <param name="indices" value="phiX" />
|
|
|
252 <param name="sPaired" value="paired" />
|
|
|
253 <param name="input1" value="bwa_wrapper_in2.fastqsanger" ftype="fastqsanger" />
|
|
|
254 <param name="input2" value="bwa_wrapper_in3.fastqsanger" ftype="fastqsanger" />
|
|
|
255 <param name="source_select" value="full" />
|
|
|
256 <param name="maxEditDist" value="0" />
|
|
|
257 <param name="fracMissingAligns" value="0.04" />
|
|
|
258 <param name="maxGapOpens" value="1" />
|
|
|
259 <param name="maxGapExtens" value="-1" />
|
|
|
260 <param name="disallowLongDel" value="16" />
|
|
|
261 <param name="disallowIndel" value="5" />
|
|
|
262 <param name="seed" value="-1" />
|
|
|
263 <param name="maxEditDistSeed" value="2" />
|
|
|
264 <param name="mismatchPenalty" value="3" />
|
|
|
265 <param name="gapOpenPenalty" value="11" />
|
|
|
266 <param name="gapExtensPenalty" value="4" />
|
|
|
267 <param name="suboptAlign" value="" />
|
|
|
268 <param name="noIterSearch" value="true" />
|
|
|
269 <param name="outputTopN" value="3" />
|
|
|
270 <param name="outputTopNDisc" value="10" />
|
|
|
271 <param name="maxInsertSize" value="500" />
|
|
|
272 <param name="maxOccurPairing" value="100000" />
|
|
|
273 <param name="specReadGroup" value="yes" />
|
|
|
274 <param name="rgid" value="abcdefg" />
|
|
|
275 <param name="rgcn" value="" />
|
|
|
276 <param name="rgds" value="descrip" />
|
|
|
277 <param name="rgdt" value="2010-11-01" />
|
|
|
278 <param name="rgfo" value="" />
|
|
|
279 <param name="rgks" value="" />
|
|
|
280 <param name="rglb" value="lib-mom-A" />
|
|
|
281 <param name="rgpg" value="" />
|
|
|
282 <param name="rgpi" value="400" />
|
|
|
283 <param name="rgpl" value="ILLUMINA" />
|
|
|
284 <param name="rgpu" value="" />
|
|
|
285 <param name="rgsm" value="mom" />
|
|
|
286 <param name="suppressHeader" value="false" />
|
|
|
287 <output name="output" file="bwa_wrapper_out3.sam" ftype="sam" sort="True" lines_diff="2" />
|
|
|
288 </test>
|
|
|
289 <test>
|
|
|
290 <!--
|
|
|
291 BWA commands:
|
|
|
292 cp test-data/phiX.fasta phiX.fasta
|
|
|
293 bwa index -a is phiX.fasta
|
|
|
294 bwa aln -t 4 phiX.fasta test-data/bwa_wrapper_in2.fastqsanger > bwa_wrapper_out8a.sai
|
|
|
295 bwa aln -t 4 phiX.fasta test-data/bwa_wrapper_in3.fastqsanger > bwa_wrapper_out8b.sai
|
|
|
296 bwa sampe -a 500 -o 100000 phiX.fasta bwa_wrapper_out8a.sai bwa_wrapper_out8b.sai test-data/bwa_wrapper_in2.fastqsanger test-data/bwa_wrapper_in3.fastqsanger > bwa_wrapper_out8.u.sam
|
|
|
297 phiX.fa is the prefix for the reference
|
|
|
298 remove the comment lines (beginning with '@') from the resulting sam file
|
|
|
299 python -c "import sys; lines=file(sys.argv[1],'rb').readlines(); lines.sort(); file(sys.argv[2],'wb').write(''.join(lines))" bwa_wrapper_out8.u.sam bwa_wrapper_out8.sam
|
|
|
300 -->
|
|
|
301 <param name="refGenomeSource" value="history" />
|
|
|
302 <!-- this is the backwards-compatible "unique value" for this index, not an actual path -->
|
|
|
303 <param name="ownFile" value="phiX.fasta" />
|
|
|
304 <param name="sPaired" value="paired" />
|
|
|
305 <param name="input1" value="bwa_wrapper_in2.fastqsanger" ftype="fastqsanger" />
|
|
|
306 <param name="input2" value="bwa_wrapper_in3.fastqsanger" ftype="fastqsanger" />
|
|
|
307 <param name="source_select" value="preSet" />
|
|
|
308 <param name="suppressHeader" value="true" />
|
|
|
309 <output name="output" file="bwa_wrapper_out8.sam" ftype="sam" sort="True" />
|
|
|
310 </test>
|
|
|
311 </tests>
|
|
|
312 <help>
|
|
|
313
|
|
|
314 **What it does**
|
|
|
315
|
|
|
316 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.
|
|
|
317
|
|
|
318 ------
|
|
|
319
|
|
|
320 **Know what you are doing**
|
|
|
321
|
|
|
322 .. class:: warningmark
|
|
|
323
|
|
|
324 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.
|
|
|
325
|
|
|
326 .. __: http://bio-bwa.sourceforge.net/
|
|
|
327
|
|
|
328 ------
|
|
|
329
|
|
|
330 **Input formats**
|
|
|
331
|
|
|
332 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.
|
|
|
333
|
|
|
334 ------
|
|
|
335
|
|
|
336 **A Note on Built-in Reference Genomes**
|
|
|
337
|
|
|
338 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.
|
|
|
339
|
|
|
340 ------
|
|
|
341
|
|
|
342 **Outputs**
|
|
|
343
|
|
|
344 The output is in SAM format, and has the following columns::
|
|
|
345
|
|
|
346 Column Description
|
|
|
347 -------- --------------------------------------------------------
|
|
|
348 1 QNAME Query (pair) NAME
|
|
|
349 2 FLAG bitwise FLAG
|
|
|
350 3 RNAME Reference sequence NAME
|
|
|
351 4 POS 1-based leftmost POSition/coordinate of clipped sequence
|
|
|
352 5 MAPQ MAPping Quality (Phred-scaled)
|
|
|
353 6 CIGAR extended CIGAR string
|
|
|
354 7 MRNM Mate Reference sequence NaMe ('=' if same as RNAME)
|
|
|
355 8 MPOS 1-based Mate POSition
|
|
|
356 9 ISIZE Inferred insert SIZE
|
|
|
357 10 SEQ query SEQuence on the same strand as the reference
|
|
|
358 11 QUAL query QUALity (ASCII-33 gives the Phred base quality)
|
|
|
359 12 OPT variable OPTional fields in the format TAG:VTYPE:VALU
|
|
|
360
|
|
|
361 The flags are as follows::
|
|
|
362
|
|
|
363 Flag Description
|
|
|
364 ------ -------------------------------------
|
|
|
365 0x0001 the read is paired in sequencing
|
|
|
366 0x0002 the read is mapped in a proper pair
|
|
|
367 0x0004 the query sequence itself is unmapped
|
|
|
368 0x0008 the mate is unmapped
|
|
|
369 0x0010 strand of the query (1 for reverse)
|
|
|
370 0x0020 strand of the mate
|
|
|
371 0x0040 the read is the first read in a pair
|
|
|
372 0x0080 the read is the second read in a pair
|
|
|
373 0x0100 the alignment is not primary
|
|
|
374
|
|
|
375 It looks like this (scroll sideways to see the entire example)::
|
|
|
376
|
|
|
377 QNAME FLAG RNAME POS MAPQ CIAGR MRNM MPOS ISIZE SEQ QUAL OPT
|
|
|
378 HWI-EAS91_1_30788AAXX:1:1:1761:343 4 * 0 0 * * 0 0 AAAAAAANNAAAAAAAAAAAAAAAAAAAAAAAAAAACNNANNGAGTNGNNNNNNNGCTTCCCACAGNNCTGG hhhhhhh;;hhhhhhhhhhh^hOhhhhghhhfhhhgh;;h;;hhhh;h;;;;;;;hhhhhhghhhh;;Phhh
|
|
|
379 HWI-EAS91_1_30788AAXX:1:1:1578:331 4 * 0 0 * * 0 0 GTATAGANNAATAAGAAAAAAAAAAATGAAGACTTTCNNANNTCTGNANNNNNNNTCTTTTTTCAGNNGTAG hhhhhhh;;hhhhhhhhhhhhhhhhhhhhhhhhhhhh;;h;;hhhh;h;;;;;;;hhhhhhhhhhh;;hhVh
|
|
|
380
|
|
|
381 -------
|
|
|
382
|
|
|
383 **BWA settings**
|
|
|
384
|
|
|
385 All of the options have a default value. You can change any of them. All of the options in BWA have been implemented here.
|
|
|
386
|
|
|
387 ------
|
|
|
388
|
|
|
389 **BWA parameter list**
|
|
|
390
|
|
|
391 This is an exhaustive list of BWA options:
|
|
|
392
|
|
|
393 For **aln**::
|
|
|
394
|
|
|
395 -n NUM Maximum edit distance if the value is INT, or the fraction of missing
|
|
|
396 alignments given 2% uniform base error rate if FLOAT. In the latter
|
|
|
397 case, the maximum edit distance is automatically chosen for different
|
|
|
398 read lengths. [0.04]
|
|
|
399 -o INT Maximum number of gap opens [1]
|
|
|
400 -e INT Maximum number of gap extensions, -1 for k-difference mode
|
|
|
401 (disallowing long gaps) [-1]
|
|
|
402 -d INT Disallow a long deletion within INT bp towards the 3'-end [16]
|
|
|
403 -i INT Disallow an indel within INT bp towards the ends [5]
|
|
|
404 -l INT Take the first INT subsequence as seed. If INT is larger than the
|
|
|
405 query sequence, seeding will be disabled. For long reads, this option
|
|
|
406 is typically ranged from 25 to 35 for '-k 2'. [inf]
|
|
|
407 -k INT Maximum edit distance in the seed [2]
|
|
|
408 -t INT Number of threads (multi-threading mode) [1]
|
|
|
409 -M INT Mismatch penalty. BWA will not search for suboptimal hits with a score
|
|
|
410 lower than (bestScore-misMsc). [3]
|
|
|
411 -O INT Gap open penalty [11]
|
|
|
412 -E INT Gap extension penalty [4]
|
|
|
413 -c Reverse query but not complement it, which is required for alignment
|
|
|
414 in the color space.
|
|
|
415 -R Proceed with suboptimal alignments even if the top hit is a repeat. By
|
|
|
416 default, BWA only searches for suboptimal alignments if the top hit is
|
|
|
417 unique. Using this option has no effect on accuracy for single-end
|
|
|
418 reads. It is mainly designed for improving the alignment accuracy of
|
|
|
419 paired-end reads. However, the pairing procedure will be slowed down,
|
|
|
420 especially for very short reads (~32bp).
|
|
|
421 -N Disable iterative search. All hits with no more than maxDiff
|
|
|
422 differences will be found. This mode is much slower than the default.
|
|
|
423
|
|
|
424 For **samse**::
|
|
|
425
|
|
|
426 -n INT Maximum number of alignments to output in the XA tag for reads paired
|
|
|
427 properly. If a read has more than INT hits, the XA tag will not be
|
|
|
428 written. [3]
|
|
|
429 -r STR Specify the read group in a format like '@RG\tID:foo\tSM:bar' [null]
|
|
|
430
|
|
|
431 For **sampe**::
|
|
|
432
|
|
|
433 -a INT Maximum insert size for a read pair to be considered as being mapped
|
|
|
434 properly. Since version 0.4.5, this option is only used when there
|
|
|
435 are not enough good alignment to infer the distribution of insert
|
|
|
436 sizes. [500]
|
|
|
437 -n INT Maximum number of alignments to output in the XA tag for reads paired
|
|
|
438 properly. If a read has more than INT hits, the XA tag will not be
|
|
|
439 written. [3]
|
|
|
440 -N INT Maximum number of alignments to output in the XA tag for disconcordant
|
|
|
441 read pairs (excluding singletons). If a read has more than INT hits,
|
|
|
442 the XA tag will not be written. [10]
|
|
|
443 -o INT Maximum occurrences of a read for pairing. A read with more
|
|
|
444 occurrences will be treated as a single-end read. Reducing this
|
|
|
445 parameter helps faster pairing. [100000]
|
|
|
446 -r STR Specify the read group in a format like '@RG\tID:foo\tSM:bar' [null]
|
|
|
447
|
|
|
448 For specifying the read group in **samse** or **sampe**, use the following::
|
|
|
449
|
|
|
450 @RG Read group. Unordered multiple @RG lines are allowed.
|
|
|
451 ID Read group identifier. Each @RG line must have a unique ID. The value of
|
|
|
452 ID is used in the RG tags of alignment records. Must be unique among all
|
|
|
453 read groups in header section. Read group IDs may be modified when
|
|
|
454 merging SAM files in order to handle collisions.
|
|
|
455 CN Name of sequencing center producing the read.
|
|
|
456 DS Description.
|
|
|
457 DT Date the run was produced (ISO8601 date or date/time).
|
|
|
458 FO Flow order. The array of nucleotide bases that correspond to the
|
|
|
459 nucleotides used for each flow of each read. Multi-base flows are encoded
|
|
|
460 in IUPAC format, and non-nucleotide flows by various other characters.
|
|
|
461 Format : /\*|[ACMGRSVTWYHKDBN]+/
|
|
|
462 KS The array of nucleotide bases that correspond to the key sequence of each read.
|
|
|
463 LB Library.
|
|
|
464 PG Programs used for processing the read group.
|
|
|
465 PI Predicted median insert size.
|
|
|
466 PL Platform/technology used to produce the reads. Valid values : CAPILLARY,
|
|
|
467 LS454, ILLUMINA, SOLID, HELICOS, IONTORRENT and PACBIO.
|
|
|
468 PU Platform unit (e.g. flowcell-barcode.lane for Illumina or slide for
|
|
|
469 SOLiD). Unique identifier.
|
|
|
470 SM Sample. Use pool name where a pool is being sequenced.
|
|
|
471
|
|
|
472 </help>
|
|
|
473 </tool>
|
|
|
474
|
|
|
475
|
