0
|
1 <tool id="bwa_color_wrapper" name="Map with BWA for SOLiD" version="1.0.1">
|
|
2 <description></description>
|
|
3 <parallelism method="basic"></parallelism>
|
|
4 <command interpreter="python">
|
|
5 bwa_wrapper.py
|
|
6 --threads="4"
|
|
7 --color-space
|
|
8
|
|
9 ## reference source
|
|
10 --fileSource=$genomeSource.refGenomeSource
|
|
11 #if $genomeSource.refGenomeSource == "history":
|
|
12 ##build index on the fly
|
|
13 --ref="${genomeSource.ownFile}"
|
|
14 --dbkey=$dbkey
|
|
15 #else:
|
|
16 ##use precomputed indexes
|
|
17 --ref="${ filter( lambda x: str( x[0] ) == str( $genomeSource.indices ), $__app__.tool_data_tables[ 'bwa_indexes_color' ].get_fields() )[0][-1] }"
|
|
18 --do_not_build_index
|
|
19 #end if
|
|
20
|
|
21 ## input file(s)
|
|
22 --input1=$paired.input1
|
|
23 #if $paired.sPaired == "paired":
|
|
24 --input2=$paired.input2
|
|
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 $params.source_select != "pre_set":
|
|
34 --maxEditDist=$params.maxEditDist
|
|
35 --fracMissingAligns=$params.fracMissingAligns
|
|
36 --maxGapOpens=$params.maxGapOpens
|
|
37 --maxGapExtens=$params.maxGapExtens
|
|
38 --disallowLongDel=$params.disallowLongDel
|
|
39 --disallowIndel=$params.disallowIndel
|
|
40 --seed=$params.seed
|
|
41 --maxEditDistSeed=$params.maxEditDistSeed
|
|
42 --mismatchPenalty=$params.mismatchPenalty
|
|
43 --gapOpenPenalty=$params.gapOpenPenalty
|
|
44 --gapExtensPenalty=$params.gapExtensPenalty
|
|
45 --suboptAlign=$params.suboptAlign
|
|
46 --noIterSearch=$params.noIterSearch
|
|
47 --outputTopN=$params.outputTopN
|
|
48 --outputTopNDisc=$params.outputTopNDisc
|
|
49 --maxInsertSize=$params.maxInsertSize
|
|
50 --maxOccurPairing=$params.maxOccurPairing
|
|
51 #if $params.readGroup.specReadGroup == "yes"
|
|
52 --rgid="$params.readGroup.rgid"
|
|
53 --rgcn="$params.readGroup.rgcn"
|
|
54 --rgds="$params.readGroup.rgds"
|
|
55 --rgdt="$params.readGroup.rgdt"
|
|
56 --rgfo="$params.readGroup.rgfo"
|
|
57 --rgks="$params.readGroup.rgks"
|
|
58 --rglb="$params.readGroup.rglb"
|
|
59 --rgpg="$params.readGroup.rgpg"
|
|
60 --rgpi="$params.readGroup.rgpi"
|
|
61 --rgpl="$params.readGroup.rgpl"
|
|
62 --rgpu="$params.readGroup.rgpu"
|
|
63 --rgsm="$params.readGroup.rgsm"
|
|
64 #end if
|
|
65 #end if
|
|
66
|
|
67 ## suppress output SAM header
|
|
68 --suppressHeader=$suppressHeader
|
|
69 </command>
|
|
70 <requirements>
|
|
71 <requirement type="package">bwa</requirement>
|
|
72 </requirements>
|
|
73 <inputs>
|
|
74 <conditional name="genomeSource">
|
|
75 <param name="refGenomeSource" type="select" label="Will you select a reference genome from your history or use a built-in index?">
|
|
76 <option value="indexed">Use a built-in index</option>
|
|
77 <option value="history">Use one from the history</option>
|
|
78 </param>
|
|
79 <when value="indexed">
|
|
80 <param name="indices" type="select" label="Select a reference genome">
|
|
81 <options from_data_table="bwa_indexes_color">
|
|
82 <filter type="sort_by" column="2" />
|
|
83 <validator type="no_options" message="No indexes are available for the selected input dataset" />
|
|
84 </options>
|
|
85 </param>
|
|
86 </when>
|
|
87 <when value="history">
|
|
88 <param name="ownFile" type="data" format="fasta" metadata_name="dbkey" label="Select a reference from history" />
|
|
89 </when>
|
|
90 </conditional>
|
|
91 <conditional name="paired">
|
|
92 <param name="sPaired" type="select" label="Is this library mate-paired?">
|
|
93 <option value="single">Single-end</option>
|
|
94 <option value="paired">Paired-end</option>
|
|
95 </param>
|
|
96 <when value="single">
|
|
97 <param name="input1" type="data" format="fastqcssanger" label="FASTQ file (Nucleotide-space recoded from color-space)">
|
|
98 <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>
|
|
99 </param>
|
|
100 </when>
|
|
101 <when value="paired">
|
|
102 <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">
|
|
103 <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>
|
|
104 </param>
|
|
105 <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">
|
|
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 </when>
|
|
109 </conditional>
|
|
110 <conditional name="params">
|
|
111 <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">
|
|
112 <option value="pre_set">Commonly Used</option>
|
|
113 <option value="full">Full Parameter List</option>
|
|
114 </param>
|
|
115 <when value="pre_set" />
|
|
116 <when value="full">
|
|
117 <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" />
|
|
118 <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" />
|
|
119 <param name="maxGapOpens" type="integer" value="1" label="Maximum number of gap opens (aln -o)" />
|
|
120 <param name="maxGapExtens" type="integer" value="-1" label="Maximum number of gap extensions (aln -e)" help="-1 for k-difference mode (disallowing long gaps)" />
|
|
121 <param name="disallowLongDel" type="integer" value="16" label="Disallow long deletion within [value] bp towards the 3'-end (aln -d)" />
|
|
122 <param name="disallowIndel" type="integer" value="5" label="Disallow insertion/deletion within [value] bp towards the end (aln -i)" />
|
|
123 <param name="seed" type="integer" value="-1" label="Number of first subsequences to take as seed (aln -l)" help="Enter -1 for infinity" />
|
|
124 <param name="maxEditDistSeed" type="integer" value="2" label="Maximum edit distance in the seed (aln -k)" />
|
|
125 <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]" />
|
|
126 <param name="gapOpenPenalty" type="integer" value="11" label="Gap open penalty (aln -O)" />
|
|
127 <param name="gapExtensPenalty" type="integer" value="4" label="Gap extension penalty (aln -E)" />
|
|
128 <param name="suboptAlign" type="boolean" truevalue="true" falsevalue="false" checked="no" label="Proceed with suboptimal alignments even if the top hit is a repeat (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)" />
|
|
129 <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" />
|
|
130 <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" />
|
|
131 <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" />
|
|
132 <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" />
|
|
133 <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" />
|
|
134 <conditional name="readGroup">
|
|
135 <param name="specReadGroup" type="select" label="Specify the read group for this file? (samse/sampe -r)">
|
|
136 <option value="yes">Yes</option>
|
|
137 <option value="no" selected="True">No</option>
|
|
138 </param>
|
|
139 <when value="yes">
|
|
140 <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
|
|
141 tags of alignment records. Must be unique among all read groups in header section." help="Required if RG specified. Read group
|
|
142 IDs may be modified when merging SAM files in order to handle collisions." />
|
|
143 <param name="rgcn" type="text" size="25" label="Sequencing center that produced the read (CN)" help="Optional" />
|
|
144 <param name="rgds" type="text" size="25" label="Description (DS)" help="Optional" />
|
|
145 <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" />
|
|
146 <param name="rgfo" type="text" size="25" label="Flow order (FO). The array of nucleotide bases that correspond to the nucleotides used for each
|
|
147 flow of each read." help="Optional. Multi-base flows are encoded in IUPAC format, and non-nucleotide flows by
|
|
148 various other characters. Format : /\*|[ACMGRSVTWYHKDBN]+/" />
|
|
149 <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" />
|
|
150 <param name="rglb" type="text" size="25" label="Library name (LB)" help="Required if RG specified" />
|
|
151 <param name="rgpg" type="text" size="25" label="Programs used for processing the read group (PG)" help="Optional" />
|
|
152 <param name="rgpi" type="text" size="25" label="Predicted median insert size (PI)" help="Optional" />
|
|
153 <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,
|
|
154 SOLID, HELICOS, IONTORRENT and PACBIO" />
|
|
155 <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)" />
|
|
156 <param name="rgsm" type="text" size="25" label="Sample (SM)" help="Required if RG specified. Use pool name where a pool is being sequenced" />
|
|
157 </when>
|
|
158 <when value="no" />
|
|
159 </conditional>
|
|
160 </when>
|
|
161 </conditional>
|
|
162 <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" />
|
|
163 </inputs>
|
|
164 <outputs>
|
|
165 <data format="sam" name="output" label="${tool.name} on ${on_string}: mapped reads">
|
|
166 <actions>
|
|
167 <conditional name="genomeSource.refGenomeSource">
|
|
168 <when value="indexed">
|
|
169 <action type="metadata" name="dbkey">
|
|
170 <option type="from_data_table" name="bwa_indexes_color" column="1">
|
|
171 <filter type="param_value" column="0" value="#" compare="startswith" keep="False"/>
|
|
172 <filter type="param_value" ref="genomeSource.indices" column="0" />
|
|
173 </option>
|
|
174 </action>
|
|
175 </when>
|
|
176 <when value="history">
|
|
177 <action type="metadata" name="dbkey">
|
|
178 <option type="from_param" name="genomeSource.ownFile" param_attribute="dbkey" />
|
|
179 </action>
|
|
180 </when>
|
|
181 </conditional>
|
|
182 </actions>
|
|
183 </data>
|
|
184 </outputs>
|
|
185 <tests>
|
|
186 <test>
|
|
187 <!--
|
|
188 BWA commands:
|
|
189 cp test-data/hg19chrX_midpart.fasta hg19chrX_midpart.fasta
|
|
190 bwa index -c -a is hg19chrX_midpart.fasta
|
|
191 bwa aln -t 4 -c hg19chrX_midpart.fasta test-data/bwa_wrapper_in4.fastqcssanger > bwa_wrapper_out4.sai
|
|
192 bwa samse hg19chrX_midpart.fasta bwa_wrapper_out4.sai test-data/bwa_wrapper_in4.fastqcssanger > bwa_wrapper_out4.u.sam
|
|
193 hg19chrX_midpart.fasta is the prefix for the reference files (hg19chrX_midpart.fasta.amb, hg19chrX_midpart.fasta.ann, hg19chrX_midpart.fasta.bwt, ...)
|
|
194 It's just part of hg19 chrX, from the middle of the chromosome
|
|
195 plain old sort doesn't handle underscores like python:
|
|
196 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
|
|
197 -->
|
|
198 <param name="refGenomeSource" value="history" />
|
|
199 <param name="ownFile" value="hg19chrX_midpart.fasta" />
|
|
200 <param name="sPaired" value="single" />
|
|
201 <param name="input1" value="bwa_wrapper_in4.fastqcssanger" ftype="fastqcssanger" />
|
|
202 <param name="source_select" value="pre_set" />
|
|
203 <param name="suppressHeader" value="false" />
|
|
204 <output name="output" file="bwa_wrapper_out4.sam" ftype="sam" sort="True" lines_diff="2" />
|
|
205 </test>
|
|
206 <test>
|
|
207 <!--
|
|
208 BWA commands:
|
|
209 bwa aln -t 4 -c equCab2chrM_cs.fa test-data/bwa_wrapper_in5.fastqcssanger > bwa_wrapper_out5a.sai
|
|
210 bwa aln -t 4 -c equCab2chrM_cs.fa test-data/bwa_wrapper_in6.fastqcssanger > bwa_wrapper_out5b.sai
|
|
211 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
|
|
212 equCab2chrM_cs.fa is the prefix of the index files (equCab2chrM_cs.fa.amb, equCab2chrM_cs.fa.ann, ...)
|
|
213 remove the comment lines (beginning with '@') from the resulting sam file
|
|
214 plain old sort doesn't handle underscores like python:
|
|
215 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
|
|
216 -->
|
|
217 <param name="refGenomeSource" value="indexed" />
|
|
218 <param name="indices" value="equCab2chrM" />
|
|
219 <param name="sPaired" value="paired" />
|
|
220 <param name="input1" value="bwa_wrapper_in5.fastqcssanger" ftype="fastqcssanger" />
|
|
221 <param name="input2" value="bwa_wrapper_in6.fastqcssanger" ftype="fastqcssanger" />
|
|
222 <param name="source_select" value="pre_set" />
|
|
223 <param name="suppressHeader" value="true" />
|
|
224 <output name="output" file="bwa_wrapper_out5.sam" ftype="sam" sort="True" />
|
|
225 </test>
|
|
226 <test>
|
|
227 <!--
|
|
228 BWA commands:
|
|
229 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
|
|
230 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
|
|
231 hg19chrX_midpart_cs.fa is the prefix of the index files (hg19chrX_midpart.fa.amb, hg19chrX_midpart.fa.ann, ...)
|
|
232 (It's just part of hg19 chrX, from the middle of the chromosome)
|
|
233 plain old sort doesn't handle underscores like python:
|
|
234 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
|
|
235 -->
|
|
236 <param name="refGenomeSource" value="indexed" />
|
|
237 <param name="indices" value="hg19chrX_midpart" />
|
|
238 <param name="sPaired" value="single" />
|
|
239 <param name="input1" value="bwa_wrapper_in4.fastqcssanger" ftype="fastqcssanger" />
|
|
240 <param name="source_select" value="full" />
|
|
241 <param name="maxEditDist" value="0" />
|
|
242 <param name="fracMissingAligns" value="0.04" />
|
|
243 <param name="maxGapOpens" value="1" />
|
|
244 <param name="maxGapExtens" value="-1" />
|
|
245 <param name="disallowLongDel" value="16" />
|
|
246 <param name="disallowIndel" value="5" />
|
|
247 <param name="seed" value="-1" />
|
|
248 <param name="maxEditDistSeed" value="2" />
|
|
249 <param name="mismatchPenalty" value="3" />
|
|
250 <param name="gapOpenPenalty" value="11" />
|
|
251 <param name="gapExtensPenalty" value="4" />
|
|
252 <param name="suboptAlign" value="true" />
|
|
253 <param name="noIterSearch" value="true" />
|
|
254 <param name="outputTopN" value="3" />
|
|
255 <param name="outputTopNDisc" value="10" />
|
|
256 <param name="maxInsertSize" value="500" />
|
|
257 <param name="maxOccurPairing" value="100000" />
|
|
258 <param name="specReadGroup" value="yes" />
|
|
259 <param name="rgid" value="474747" />
|
|
260 <param name="rgcn" value="" />
|
|
261 <param name="rgds" value="description" />
|
|
262 <param name="rgdt" value="2011-03-14" />
|
|
263 <param name="rgfo" value="" />
|
|
264 <param name="rgks" value="" />
|
|
265 <param name="rglb" value="lib-child-1-A" />
|
|
266 <param name="rgpg" value="" />
|
|
267 <param name="rgpi" value="200" />
|
|
268 <param name="rgpl" value="SOLID" />
|
|
269 <param name="rgpu" value="" />
|
|
270 <param name="rgsm" value="child-1" />
|
|
271 <param name="suppressHeader" value="false" />
|
|
272 <output name="output" file="bwa_wrapper_out6.sam" ftype="sam" sort="True" lines_diff="2" />
|
|
273 </test>
|
|
274 <test>
|
|
275 <!--
|
|
276 BWA commands:
|
|
277 cp test-data/chr_m.fasta chr_m.fasta
|
|
278 bwa index -c -a is chr_m.fasta
|
|
279 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
|
|
280 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
|
|
281 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
|
|
282 chr_m.fasta is the prefix of the index files (chr_m.fasta.amb, chr_m.fasta.ann, ...)
|
|
283 plain old sort doesn't handle underscores like python:
|
|
284 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
|
|
285 -->
|
|
286 <param name="refGenomeSource" value="history" />
|
|
287 <param name="ownFile" value="chr_m.fasta" />
|
|
288 <param name="sPaired" value="paired" />
|
|
289 <param name="input1" value="bwa_wrapper_in5.fastqcssanger" ftype="fastqcssanger" />
|
|
290 <param name="input2" value="bwa_wrapper_in6.fastqcssanger" ftype="fastqcssanger" />
|
|
291 <param name="source_select" value="full" />
|
|
292 <param name="maxEditDist" value="0" />
|
|
293 <param name="fracMissingAligns" value="0.04" />
|
|
294 <param name="maxGapOpens" value="1" />
|
|
295 <param name="maxGapExtens" value="-1" />
|
|
296 <param name="disallowLongDel" value="16" />
|
|
297 <param name="disallowIndel" value="5" />
|
|
298 <param name="seed" value="-1" />
|
|
299 <param name="maxEditDistSeed" value="2" />
|
|
300 <param name="mismatchPenalty" value="3" />
|
|
301 <param name="gapOpenPenalty" value="11" />
|
|
302 <param name="gapExtensPenalty" value="4" />
|
|
303 <param name="suboptAlign" value="true" />
|
|
304 <param name="noIterSearch" value="true" />
|
|
305 <param name="outputTopN" value="3" />
|
|
306 <param name="outputTopNDisc" value="10" />
|
|
307 <param name="maxInsertSize" value="100" />
|
|
308 <param name="maxOccurPairing" value="2" />
|
|
309 <param name="specReadGroup" value="no" />
|
|
310 <param name="suppressHeader" value="false" />
|
|
311 <output name="output" file="bwa_wrapper_out7.sam" ftype="sam" sort="True" lines_diff="2" />
|
|
312 </test>
|
|
313 </tests>
|
|
314 <help>
|
|
315
|
|
316 **What it does**
|
|
317
|
|
318 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.
|
|
319
|
|
320 ------
|
|
321
|
|
322 **Know what you are doing**
|
|
323
|
|
324 .. class:: warningmark
|
|
325
|
|
326 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.
|
|
327
|
|
328 .. __: http://bio-bwa.sourceforge.net/
|
|
329
|
|
330 ------
|
|
331
|
|
332 **Input formats**
|
|
333
|
|
334 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.
|
|
335
|
|
336 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:
|
|
337 Manipulate reads on Sequence Content, choosing Change Adapter Base, and having the text box empty.
|
|
338 Manipulate reads on Sequence Content, doing a String Translate from "01234." to "ACGTN".
|
|
339
|
|
340
|
|
341 ------
|
|
342
|
|
343 **A Note on Built-in Reference Genomes**
|
|
344
|
|
345 Some genomes have multiple variants. If only one "type" of genome is listed, it is the Full version, which means that everything that came in the original genome data download (possibly with mitochondrial and plasmid DNA added if it wasn't already included). The Full version is available for every genome. Some genomes also come in the Canonical variant, which contains only the "canonical" (well-defined) chromosomes or segments, such as chr1-chr22, chrX, chrY, and chrM for human. Other variations include gender. These will come in the canonical form only, so the general Canonical variant is actually Canonical Female and the other is Canonical Male (identical to female excluding chrX).
|
|
346
|
|
347 ------
|
|
348
|
|
349 **Outputs**
|
|
350
|
|
351 The output is in SAM format, and has the following columns::
|
|
352
|
|
353 Column Description
|
|
354 -------- --------------------------------------------------------
|
|
355 1 QNAME Query (pair) NAME
|
|
356 2 FLAG bitwise FLAG
|
|
357 3 RNAME Reference sequence NAME
|
|
358 4 POS 1-based leftmost POSition/coordinate of clipped sequence
|
|
359 5 MAPQ MAPping Quality (Phred-scaled)
|
|
360 6 CIGAR extended CIGAR string
|
|
361 7 MRNM Mate Reference sequence NaMe ('=' if same as RNAME)
|
|
362 8 MPOS 1-based Mate POSition
|
|
363 9 ISIZE Inferred insert SIZE
|
|
364 10 SEQ query SEQuence on the same strand as the reference
|
|
365 11 QUAL query QUALity (ASCII-33 gives the Phred base quality)
|
|
366 12 OPT variable OPTional fields in the format TAG:VTYPE:VALU
|
|
367
|
|
368 The flags are as follows::
|
|
369
|
|
370 Flag Description
|
|
371 ------ -------------------------------------
|
|
372 0x0001 the read is paired in sequencing
|
|
373 0x0002 the read is mapped in a proper pair
|
|
374 0x0004 the query sequence itself is unmapped
|
|
375 0x0008 the mate is unmapped
|
|
376 0x0010 strand of the query (1 for reverse)
|
|
377 0x0020 strand of the mate
|
|
378 0x0040 the read is the first read in a pair
|
|
379 0x0080 the read is the second read in a pair
|
|
380 0x0100 the alignment is not primary
|
|
381
|
|
382 It looks like this (scroll sideways to see the entire example)::
|
|
383
|
|
384 QNAME FLAG RNAME POS MAPQ CIAGR MRNM MPOS ISIZE SEQ QUAL OPT
|
|
385 HWI-EAS91_1_30788AAXX:1:1:1761:343 4 * 0 0 * * 0 0 AAAAAAANNAAAAAAAAAAAAAAAAAAAAAAAAAAACNNANNGAGTNGNNNNNNNGCTTCCCACAGNNCTGG hhhhhhh;;hhhhhhhhhhh^hOhhhhghhhfhhhgh;;h;;hhhh;h;;;;;;;hhhhhhghhhh;;Phhh
|
|
386 HWI-EAS91_1_30788AAXX:1:1:1578:331 4 * 0 0 * * 0 0 GTATAGANNAATAAGAAAAAAAAAAATGAAGACTTTCNNANNTCTGNANNNNNNNTCTTTTTTCAGNNGTAG hhhhhhh;;hhhhhhhhhhhhhhhhhhhhhhhhhhhh;;h;;hhhh;h;;;;;;;hhhhhhhhhhh;;hhVh
|
|
387
|
|
388 -------
|
|
389
|
|
390 **BWA settings**
|
|
391
|
|
392 All of the options have a default value. You can change any of them. All of the options in BWA have been implemented here.
|
|
393
|
|
394 ------
|
|
395
|
|
396 **BWA parameter list**
|
|
397
|
|
398 This is an exhaustive list of BWA options:
|
|
399
|
|
400 For **aln**::
|
|
401
|
|
402 -n NUM Maximum edit distance if the value is INT, or the fraction of missing
|
|
403 alignments given 2% uniform base error rate if FLOAT. In the latter
|
|
404 case, the maximum edit distance is automatically chosen for different
|
|
405 read lengths. [0.04]
|
|
406 -o INT Maximum number of gap opens [1]
|
|
407 -e INT Maximum number of gap extensions, -1 for k-difference mode
|
|
408 (disallowing long gaps) [-1]
|
|
409 -d INT Disallow a long deletion within INT bp towards the 3'-end [16]
|
|
410 -i INT Disallow an indel within INT bp towards the ends [5]
|
|
411 -l INT Take the first INT subsequence as seed. If INT is larger than the
|
|
412 query sequence, seeding will be disabled. For long reads, this option
|
|
413 is typically ranged from 25 to 35 for '-k 2'. [inf]
|
|
414 -k INT Maximum edit distance in the seed [2]
|
|
415 -t INT Number of threads (multi-threading mode) [1]
|
|
416 -M INT Mismatch penalty. BWA will not search for suboptimal hits with a score
|
|
417 lower than (bestScore-misMsc). [3]
|
|
418 -O INT Gap open penalty [11]
|
|
419 -E INT Gap extension penalty [4]
|
|
420 -c Reverse query but not complement it, which is required for alignment
|
|
421 in the color space.
|
|
422 -R Proceed with suboptimal alignments even if the top hit is a repeat. By
|
|
423 default, BWA only searches for suboptimal alignments if the top hit is
|
|
424 unique. Using this option has no effect on accuracy for single-end
|
|
425 reads. It is mainly designed for improving the alignment accuracy of
|
|
426 paired-end reads. However, the pairing procedure will be slowed down,
|
|
427 especially for very short reads (~32bp).
|
|
428 -N Disable iterative search. All hits with no more than maxDiff
|
|
429 differences will be found. This mode is much slower than the default.
|
|
430
|
|
431 For **samse**::
|
|
432
|
|
433 -n INT Maximum number of alignments to output in the XA tag for reads paired
|
|
434 properly. If a read has more than INT hits, the XA tag will not be
|
|
435 written. [3]
|
|
436 -r STR Specify the read group in a format like '@RG\tID:foo\tSM:bar' [null]
|
|
437
|
|
438 For **sampe**::
|
|
439
|
|
440 -a INT Maximum insert size for a read pair to be considered as being mapped
|
|
441 properly. Since version 0.4.5, this option is only used when there
|
|
442 are not enough good alignment to infer the distribution of insert
|
|
443 sizes. [500]
|
|
444 -n INT Maximum number of alignments to output in the XA tag for reads paired
|
|
445 properly. If a read has more than INT hits, the XA tag will not be
|
|
446 written. [3]
|
|
447 -N INT Maximum number of alignments to output in the XA tag for disconcordant
|
|
448 read pairs (excluding singletons). If a read has more than INT hits,
|
|
449 the XA tag will not be written. [10]
|
|
450 -o INT Maximum occurrences of a read for pairing. A read with more
|
|
451 occurrences will be treated as a single-end read. Reducing this
|
|
452 parameter helps faster pairing. [100000]
|
|
453 -r STR Specify the read group in a format like '@RG\tID:foo\tSM:bar' [null]
|
|
454
|
|
455 For specifying the read group in **samse** or **sampe**, use the following::
|
|
456
|
|
457 @RG Read group. Unordered multiple @RG lines are allowed.
|
|
458 ID Read group identifier. Each @RG line must have a unique ID. The value of
|
|
459 ID is used in the RG tags of alignment records. Must be unique among all
|
|
460 read groups in header section. Read group IDs may be modified when
|
|
461 merging SAM files in order to handle collisions.
|
|
462 CN Name of sequencing center producing the read.
|
|
463 DS Description.
|
|
464 DT Date the run was produced (ISO8601 date or date/time).
|
|
465 FO Flow order. The array of nucleotide bases that correspond to the
|
|
466 nucleotides used for each flow of each read. Multi-base flows are encoded
|
|
467 in IUPAC format, and non-nucleotide flows by various other characters.
|
|
468 Format : /\*|[ACMGRSVTWYHKDBN]+/
|
|
469 KS The array of nucleotide bases that correspond to the key sequence of each read.
|
|
470 LB Library.
|
|
471 PG Programs used for processing the read group.
|
|
472 PI Predicted median insert size.
|
|
473 PL Platform/technology used to produce the reads. Valid values : CAPILLARY,
|
|
474 LS454, ILLUMINA, SOLID, HELICOS, IONTORRENT and PACBIO.
|
|
475 PU Platform unit (e.g. flowcell-barcode.lane for Illumina or slide for
|
|
476 SOLiD). Unique identifier.
|
|
477 SM Sample. Use pool name where a pool is being sequenced.
|
|
478
|
|
479 </help>
|
|
480 </tool>
|
|
481
|
|
482
|