mirror of
https://github.com/galaxyproject/galaxy.git
synced 2026-09-24 16:30:27 +08:00
378 lines
20 KiB
XML
378 lines
20 KiB
XML
<tool id="bwa_wrapper" name="Map with BWA" version="1.2.1">
|
|
<description>for Illumina</description>
|
|
<parallelism method="basic"></parallelism>
|
|
<command interpreter="python">
|
|
bwa_wrapper.py
|
|
--threads="4"
|
|
|
|
## reference source
|
|
--fileSource=$genomeSource.refGenomeSource
|
|
#if $genomeSource.refGenomeSource == "history":
|
|
##build index on the fly
|
|
--ref="${genomeSource.ownFile}"
|
|
--dbkey=$dbkey
|
|
#else:
|
|
##use precomputed indexes
|
|
--ref="${ filter( lambda x: str( x[0] ) == str( $genomeSource.indices ), $__app__.tool_data_tables[ 'bwa_indexes' ].get_fields() )[0][-1] }"
|
|
--do_not_build_index
|
|
#end if
|
|
|
|
## input file(s)
|
|
--input1=$paired.input1
|
|
#if $paired.sPaired == "paired":
|
|
--input2=$paired.input2
|
|
#end if
|
|
|
|
## output file
|
|
--output=$output
|
|
|
|
## run parameters
|
|
--genAlignType=$paired.sPaired
|
|
--params=$params.source_select
|
|
#if $params.source_select != "pre_set":
|
|
--maxEditDist=$params.maxEditDist
|
|
--fracMissingAligns=$params.fracMissingAligns
|
|
--maxGapOpens=$params.maxGapOpens
|
|
--maxGapExtens=$params.maxGapExtens
|
|
--disallowLongDel=$params.disallowLongDel
|
|
--disallowIndel=$params.disallowIndel
|
|
--seed=$params.seed
|
|
--maxEditDistSeed=$params.maxEditDistSeed
|
|
--mismatchPenalty=$params.mismatchPenalty
|
|
--gapOpenPenalty=$params.gapOpenPenalty
|
|
--gapExtensPenalty=$params.gapExtensPenalty
|
|
--suboptAlign=$params.suboptAlign
|
|
--noIterSearch=$params.noIterSearch
|
|
--outputTopN=$params.outputTopN
|
|
--maxInsertSize=$params.maxInsertSize
|
|
--maxOccurPairing=$params.maxOccurPairing
|
|
#end if
|
|
|
|
## suppress output SAM header
|
|
--suppressHeader=$suppressHeader
|
|
</command>
|
|
<requirements>
|
|
<requirement type='package'>bwa</requirement>
|
|
</requirements>
|
|
<inputs>
|
|
<conditional name="genomeSource">
|
|
<param name="refGenomeSource" type="select" label="Will you select a reference genome from your history or use a built-in index?">
|
|
<option value="indexed">Use a built-in index</option>
|
|
<option value="history">Use one from the history</option>
|
|
</param>
|
|
<when value="indexed">
|
|
<param name="indices" type="select" label="Select a reference genome">
|
|
<options from_data_table="bwa_indexes">
|
|
<filter type="sort_by" column="3" />
|
|
<validator type="no_options" message="No indexes are available for the selected input dataset" />
|
|
</options>
|
|
</param>
|
|
</when>
|
|
<when value="history">
|
|
<param name="ownFile" type="data" format="fasta" metadata_name="dbkey" label="Select a reference from history" />
|
|
</when>
|
|
</conditional>
|
|
<conditional name="paired">
|
|
<param name="sPaired" type="select" label="Is this library mate-paired?">
|
|
<option value="single">Single-end</option>
|
|
<option value="paired">Paired-end</option>
|
|
</param>
|
|
<when value="single">
|
|
<param name="input1" type="data" format="fastqsanger" label="FASTQ file" help="Must have Sanger-scaled quality values with ASCII offset 33" />
|
|
</when>
|
|
<when value="paired">
|
|
<param name="input1" type="data" format="fastqsanger" label="Forward FASTQ file" help="Must have Sanger-scaled quality values with ASCII offset 33" />
|
|
<param name="input2" type="data" format="fastqsanger" label="Reverse FASTQ file" help="Must have Sanger-scaled quality values with ASCII offset 33" />
|
|
</when>
|
|
</conditional>
|
|
<conditional name="params">
|
|
<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">
|
|
<option value="pre_set">Commonly Used</option>
|
|
<option value="full">Full Parameter List</option>
|
|
</param>
|
|
<when value="pre_set" />
|
|
<when value="full">
|
|
<param name="maxEditDist" type="integer" value="0" label="Maximum edit distance (-n)" help="Enter this value OR a fraction of missing alignments, not both" />
|
|
<param name="fracMissingAligns" type="float" value="0.04" label="Fraction of missing alignments given 2% uniform base error rate (-n)" help="Enter this value OR maximum edit distance, not both" />
|
|
<param name="maxGapOpens" type="integer" value="1" label="Maximum number of gap opens (-o)" />
|
|
<param name="maxGapExtens" type="integer" value="-1" label="Maximum number of gap extensions (-e)" help="-1 for k-difference mode (disallowing long gaps)" />
|
|
<param name="disallowLongDel" type="integer" value="16" label="Disallow long deletion within [value] bp towards the 3'-end (-d)" />
|
|
<param name="disallowIndel" type="integer" value="5" label="Disallow insertion/deletion within [value] bp towards the end (-i)" />
|
|
<param name="seed" type="integer" value="-1" label="Number of first subsequences to take as seed (-l)" help="Enter -1 for infinity" />
|
|
<param name="maxEditDistSeed" type="integer" value="2" label="Maximum edit distance in the seed (-k)" />
|
|
<param name="mismatchPenalty" type="integer" value="3" label="Mismatch penalty (-M)" help="BWA will not search for suboptimal hits with a score lower than [value]" />
|
|
<param name="gapOpenPenalty" type="integer" value="11" label="Gap open penalty (-O)" />
|
|
<param name="gapExtensPenalty" type="integer" value="4" label="Gap extension penalty (-E)" />
|
|
<param name="suboptAlign" type="boolean" truevalue="true" falsevalue="false" checked="no" label="Proceed with suboptimal alignments even if the top hit is a repeat" help="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) (-R)" />
|
|
<param name="noIterSearch" type="boolean" truevalue="true" falsevalue="false" checked="no" label="Disable iterative search" help="All hits with no more than maxDiff differences will be found. This mode is much slower than the default (-N)" />
|
|
<param name="outputTopN" type="integer" value="-1" label="Output top [value] hits" help="For single-end reads only. Enter -1 to disable outputting multiple hits. NOTE: If you put in a positive value here, your output will NOT be in SAM format (-n)" />
|
|
<param name="maxInsertSize" type="integer" value="500" label="Maximum insert size for a read pair to be considered as being mapped properly" help="For paired-end reads only. Only used when there are not enough good alignments to infer the distribution of insert sizes (-a)" />
|
|
<param name="maxOccurPairing" type="integer" value="100000" label="Maximum occurrences of a read for pairing" 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 (-o)" />
|
|
</when>
|
|
</conditional>
|
|
<param name="suppressHeader" type="boolean" truevalue="true" falsevalue="false" checked="true" label="Suppress the header in the output SAM file" help="BWA produces SAM with several lines of header information" />
|
|
</inputs>
|
|
<outputs>
|
|
<data format="sam" name="output" label="${tool.name} on ${on_string}: mapped reads">
|
|
<actions>
|
|
<conditional name="genomeSource.refGenomeSource">
|
|
<when value="indexed">
|
|
<action type="metadata" name="dbkey">
|
|
<option type="from_data_table" name="bwa_indexes" column="0">
|
|
<filter type="param_value" ref="genomeSource.indices" column="1"/>
|
|
</option>
|
|
</action>
|
|
</when>
|
|
</conditional>
|
|
</actions>
|
|
</data>
|
|
</outputs>
|
|
<tests>
|
|
<test>
|
|
<!--
|
|
BWA commands:
|
|
bwa aln -t 4 phiX.fasta test-data/bwa_wrapper_in1.fastqsanger > bwa_wrapper_out1.sai
|
|
bwa samse phiX.fasta bwa_wrapper_out1.sai test-data/bwa_wrapper_in1.fastqsanger > bwa_wrapper_out1.sam
|
|
phiX.fasta is the prefix for the reference files (phiX.fasta.amb, phiX.fasta.ann, phiX.fasta.bwt, ...)
|
|
remove the comment lines (beginning with '@') from the resulting sam file
|
|
plain old sort doesn't handle underscores like python:
|
|
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
|
|
-->
|
|
<param name="refGenomeSource" value="indexed" />
|
|
<param name="indices" value="phiX" />
|
|
<param name="sPaired" value="single" />
|
|
<param name="input1" value="bwa_wrapper_in1.fastqsanger" ftype="fastqsanger" />
|
|
<param name="source_select" value="pre_set" />
|
|
<param name="suppressHeader" value="true" />
|
|
<output name="output" file="bwa_wrapper_out1.sam" ftype="sam" sort="True" />
|
|
</test>
|
|
<test>
|
|
<!--
|
|
BWA commands:
|
|
cp test-data/phiX.fasta phiX.fasta
|
|
bwa index -a is phiX.fasta
|
|
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
|
|
bwa samse phiX.fasta bwa_wrapper_out2.sai test-data/bwa_wrapper_in1.fastqsanger > bwa_wrapper_out2.u.sam
|
|
phiX.fasta is the prefix for the reference files (phiX.fasta.amb, phiX.fasta.ann, phiX.fasta.bwt, ...)
|
|
remove the comment lines (beginning with '@') from the resulting sam file
|
|
plain old sort doesn't handle underscores like python:
|
|
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
|
|
-->
|
|
<param name="refGenomeSource" value="history" />
|
|
<param name="ownFile" value="phiX.fasta" />
|
|
<param name="sPaired" value="single" />
|
|
<param name="input1" value="bwa_wrapper_in1.fastqsanger" ftype="fastqsanger" />
|
|
<param name="source_select" value="full" />
|
|
<param name="maxEditDist" value="0" />
|
|
<param name="fracMissingAligns" value="0.04" />
|
|
<param name="maxGapOpens" value="1" />
|
|
<param name="maxGapExtens" value="-1" />
|
|
<param name="disallowLongDel" value="16" />
|
|
<param name="disallowIndel" value="5" />
|
|
<param name="seed" value="-1" />
|
|
<param name="maxEditDistSeed" value="2" />
|
|
<param name="mismatchPenalty" value="3" />
|
|
<param name="gapOpenPenalty" value="11" />
|
|
<param name="gapExtensPenalty" value="4" />
|
|
<param name="suboptAlign" value="true" />
|
|
<param name="noIterSearch" value="true" />
|
|
<param name="outputTopN" value="-1" />
|
|
<param name="maxInsertSize" value="500" />
|
|
<param name="maxOccurPairing" value="100000" />
|
|
<param name="suppressHeader" value="true" />
|
|
<output name="output" file="bwa_wrapper_out2.sam" ftype="sam" sort="True" />
|
|
</test>
|
|
<test>
|
|
<!--
|
|
BWA commands:
|
|
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
|
|
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
|
|
bwa sampe -a 500 -o 100000 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
|
|
phiX.fasta is the prefix for the reference
|
|
remove the comment lines (beginning with '@') from the resulting sam file
|
|
plain old sort doesn't handle underscores like python:
|
|
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
|
|
-->
|
|
<param name="refGenomeSource" value="indexed" />
|
|
<param name="indices" value="phiX" />
|
|
<param name="sPaired" value="paired" />
|
|
<param name="input1" value="bwa_wrapper_in2.fastqsanger" ftype="fastqsanger" />
|
|
<param name="input2" value="bwa_wrapper_in3.fastqsanger" ftype="fastqsanger" />
|
|
<param name="source_select" value="full" />
|
|
<param name="maxEditDist" value="0" />
|
|
<param name="fracMissingAligns" value="0.04" />
|
|
<param name="maxGapOpens" value="1" />
|
|
<param name="maxGapExtens" value="-1" />
|
|
<param name="disallowLongDel" value="16" />
|
|
<param name="disallowIndel" value="5" />
|
|
<param name="seed" value="-1" />
|
|
<param name="maxEditDistSeed" value="2" />
|
|
<param name="mismatchPenalty" value="3" />
|
|
<param name="gapOpenPenalty" value="11" />
|
|
<param name="gapExtensPenalty" value="4" />
|
|
<param name="suboptAlign" value="true" />
|
|
<param name="noIterSearch" value="true" />
|
|
<param name="outputTopN" value="-1" />
|
|
<param name="maxInsertSize" value="500" />
|
|
<param name="maxOccurPairing" value="100000" />
|
|
<param name="suppressHeader" value="true" />
|
|
<output name="output" file="bwa_wrapper_out3.sam" ftype="sam" sort="True" />
|
|
</test>
|
|
<test>
|
|
<!--
|
|
BWA commands:
|
|
cp test-data/phiX.fasta phiX.fasta
|
|
bwa index -a is phiX.fasta
|
|
bwa aln -t 4 phiX.fasta test-data/bwa_wrapper_in2.fastqsanger > bwa_wrapper_out8a.sai
|
|
bwa aln -t 4 phiX.fasta test-data/bwa_wrapper_in3.fastqsanger > bwa_wrapper_out8b.sai
|
|
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
|
|
phiX.fa is the prefix for the reference
|
|
remove the comment lines (beginning with '@') from the resulting sam file
|
|
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
|
|
-->
|
|
<param name="refGenomeSource" value="history" />
|
|
<!-- this is the backwards-compatible "unique value" for this index, not an actual path -->
|
|
<param name="ownFile" value="phiX.fasta" />
|
|
<param name="sPaired" value="paired" />
|
|
<param name="input1" value="bwa_wrapper_in2.fastqsanger" ftype="fastqsanger" />
|
|
<param name="input2" value="bwa_wrapper_in3.fastqsanger" ftype="fastqsanger" />
|
|
<param name="source_select" value="preSet" />
|
|
<param name="suppressHeader" value="true" />
|
|
<output name="output" file="bwa_wrapper_out8.sam" ftype="sam" sort="True" />
|
|
</test>
|
|
</tests>
|
|
<help>
|
|
|
|
**What it does**
|
|
|
|
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.
|
|
|
|
------
|
|
|
|
**Know what you are doing**
|
|
|
|
.. class:: warningmark
|
|
|
|
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.
|
|
|
|
.. __: http://bio-bwa.sourceforge.net/
|
|
|
|
------
|
|
|
|
**Input formats**
|
|
|
|
BWA accepts files in Sanger FASTQ format. Use the FASTQ Groomer to prepare your files.
|
|
|
|
------
|
|
|
|
**A Note on Built-in Reference Genomes**
|
|
|
|
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).
|
|
|
|
------
|
|
|
|
**Outputs**
|
|
|
|
The output is in SAM format, and has the following columns::
|
|
|
|
Column Description
|
|
-------- --------------------------------------------------------
|
|
1 QNAME Query (pair) NAME
|
|
2 FLAG bitwise FLAG
|
|
3 RNAME Reference sequence NAME
|
|
4 POS 1-based leftmost POSition/coordinate of clipped sequence
|
|
5 MAPQ MAPping Quality (Phred-scaled)
|
|
6 CIGAR extended CIGAR string
|
|
7 MRNM Mate Reference sequence NaMe ('=' if same as RNAME)
|
|
8 MPOS 1-based Mate POSition
|
|
9 ISIZE Inferred insert SIZE
|
|
10 SEQ query SEQuence on the same strand as the reference
|
|
11 QUAL query QUALity (ASCII-33 gives the Phred base quality)
|
|
12 OPT variable OPTional fields in the format TAG:VTYPE:VALU
|
|
|
|
The flags are as follows::
|
|
|
|
Flag Description
|
|
------ -------------------------------------
|
|
0x0001 the read is paired in sequencing
|
|
0x0002 the read is mapped in a proper pair
|
|
0x0004 the query sequence itself is unmapped
|
|
0x0008 the mate is unmapped
|
|
0x0010 strand of the query (1 for reverse)
|
|
0x0020 strand of the mate
|
|
0x0040 the read is the first read in a pair
|
|
0x0080 the read is the second read in a pair
|
|
0x0100 the alignment is not primary
|
|
|
|
It looks like this (scroll sideways to see the entire example)::
|
|
|
|
QNAME FLAG RNAME POS MAPQ CIAGR MRNM MPOS ISIZE SEQ QUAL OPT
|
|
HWI-EAS91_1_30788AAXX:1:1:1761:343 4 * 0 0 * * 0 0 AAAAAAANNAAAAAAAAAAAAAAAAAAAAAAAAAAACNNANNGAGTNGNNNNNNNGCTTCCCACAGNNCTGG hhhhhhh;;hhhhhhhhhhh^hOhhhhghhhfhhhgh;;h;;hhhh;h;;;;;;;hhhhhhghhhh;;Phhh
|
|
HWI-EAS91_1_30788AAXX:1:1:1578:331 4 * 0 0 * * 0 0 GTATAGANNAATAAGAAAAAAAAAAATGAAGACTTTCNNANNTCTGNANNNNNNNTCTTTTTTCAGNNGTAG hhhhhhh;;hhhhhhhhhhhhhhhhhhhhhhhhhhhh;;h;;hhhh;h;;;;;;;hhhhhhhhhhh;;hhVh
|
|
|
|
-------
|
|
|
|
**BWA settings**
|
|
|
|
All of the options have a default value. You can change any of them. All of the options in BWA have been implemented here.
|
|
|
|
------
|
|
|
|
**BWA parameter list**
|
|
|
|
This is an exhaustive list of BWA options:
|
|
|
|
For **aln**::
|
|
|
|
-n NUM Maximum edit distance if the value is INT, or the fraction of missing
|
|
alignments given 2% uniform base error rate if FLOAT. In the latter
|
|
case, the maximum edit distance is automatically chosen for different
|
|
read lengths. [0.04]
|
|
-o INT Maximum number of gap opens [1]
|
|
-e INT Maximum number of gap extensions, -1 for k-difference mode
|
|
(disallowing long gaps) [-1]
|
|
-d INT Disallow a long deletion within INT bp towards the 3'-end [16]
|
|
-i INT Disallow an indel within INT bp towards the ends [5]
|
|
-l INT Take the first INT subsequence as seed. If INT is larger than the
|
|
query sequence, seeding will be disabled. For long reads, this option
|
|
is typically ranged from 25 to 35 for '-k 2'. [inf]
|
|
-k INT Maximum edit distance in the seed [2]
|
|
-t INT Number of threads (multi-threading mode) [1]
|
|
-M INT Mismatch penalty. BWA will not search for suboptimal hits with a score
|
|
lower than (bestScore-misMsc). [3]
|
|
-O INT Gap open penalty [11]
|
|
-E INT Gap extension penalty [4]
|
|
-c Reverse query but not complement it, which is required for alignment
|
|
in the color space.
|
|
-R Proceed with suboptimal alignments even if the top hit is a repeat. 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).
|
|
-N Disable iterative search. All hits with no more than maxDiff
|
|
differences will be found. This mode is much slower than the default.
|
|
|
|
For **samse**::
|
|
|
|
-n INT Output up to INT top hits. Value -1 to disable outputting multiple
|
|
hits. NOTE: Entering a value other than -1 will result in output that
|
|
is not in SAM format, and therefore not usable further down the
|
|
pipeline. Check the BWA documentation for details on the format of
|
|
the output. [-1]
|
|
|
|
For **sampe**::
|
|
|
|
-a INT Maximum insert size for a read pair to be considered as being mapped
|
|
properly. Since version 0.4.5, this option is only used when there
|
|
are not enough good alignment to infer the distribution of insert
|
|
sizes. [500]
|
|
-o INT Maximum occurrences of a read for pairing. A read with more
|
|
occurrences will be treated as a single-end read. Reducing this
|
|
parameter helps faster pairing. [100000]
|
|
|
|
</help>
|
|
</tool>
|
|
|
|
|