mirror of
https://github.com/galaxyproject/galaxy.git
synced 2026-09-19 10:51:34 +08:00
Skeleton wrapper for Bowtie2.
This commit is contained in:
Jeremy Goecks
@@ -0,0 +1,37 @@
|
||||
#This is a sample file distributed with Galaxy that enables tools
|
||||
#to use a directory of Bowtie2 indexed sequences data files. You will
|
||||
#need to create these data files and then create a bowtie_indices.loc
|
||||
#file similar to this one (store it in this directory) that points to
|
||||
#the directories in which those files are stored. The bowtie2_indices.loc
|
||||
#file has this format (longer white space characters are TAB characters):
|
||||
#
|
||||
#<unique_build_id> <dbkey> <display_name> <file_base_path>
|
||||
#
|
||||
#So, for example, if you had hg18 indexed stored in
|
||||
#/depot/data2/galaxy/bowtie2/hg18/,
|
||||
#then the bowtie2_indices.loc entry would look like this:
|
||||
#
|
||||
#hg18 hg18 hg18 /depot/data2/galaxy/bowtie2/hg18/hg18
|
||||
#
|
||||
#and your /depot/data2/galaxy/bowtie2/hg18/ directory
|
||||
#would contain hg18.*.ebwt files:
|
||||
#
|
||||
#-rw-r--r-- 1 james universe 830134 2005-09-13 10:12 hg18.1.ebwt
|
||||
#-rw-r--r-- 1 james universe 527388 2005-09-13 10:12 hg18.2.ebwt
|
||||
#-rw-r--r-- 1 james universe 269808 2005-09-13 10:12 hg18.3.ebwt
|
||||
#...etc...
|
||||
#
|
||||
#Your bowtie2_indices.loc file should include an entry per line for each
|
||||
#index set you have stored. The "file" in the path does not actually
|
||||
#exist, but it is the prefix for the actual index files. For example:
|
||||
#
|
||||
#hg18canon hg18 hg18 Canonical /depot/data2/galaxy/bowtie2/hg18/hg18canon
|
||||
#hg18full hg18 hg18 Full /depot/data2/galaxy/bowtie2/hg18/hg18full
|
||||
#/orig/path/hg19 hg19 hg19 /depot/data2/galaxy/bowtie2/hg19/hg19
|
||||
#...etc...
|
||||
#
|
||||
#Note that for backwards compatibility with workflows, the unique ID of
|
||||
#an entry must be the path that was in the original loc file, because that
|
||||
#is the value stored in the workflow for that parameter. That is why the
|
||||
#hg19 entry above looks odd. New genomes can be better-looking.
|
||||
#
|
||||
@@ -336,6 +336,7 @@
|
||||
<tool file="sr_mapping/lastz_wrapper.xml" />
|
||||
<tool file="sr_mapping/lastz_paired_reads_wrapper.xml" />
|
||||
<tool file="sr_mapping/bowtie_wrapper.xml" />
|
||||
<tool file="sr_mapping/bowtie2_wrapper.xml" />
|
||||
<tool file="sr_mapping/bowtie_color_wrapper.xml" />
|
||||
<tool file="sr_mapping/bwa_wrapper.xml" />
|
||||
<tool file="sr_mapping/bwa_color_wrapper.xml" />
|
||||
|
||||
@@ -25,6 +25,11 @@
|
||||
<columns>value, dbkey, name, path</columns>
|
||||
<file path="tool-data/bowtie_indices.loc" />
|
||||
</table>
|
||||
<!-- Locations of indexes in the Bowtie2 mapper format -->
|
||||
<table name="bowtie2_indexes" comment_char="#">
|
||||
<columns>value, dbkey, name, path</columns>
|
||||
<file path="tool-data/bowtie2_indices.loc" />
|
||||
</table>
|
||||
<!-- Locations of indexes in the Bowtie color-space mapper format -->
|
||||
<table name="bowtie_indexes_color" comment_char="#">
|
||||
<columns>value, dbkey, name, path</columns>
|
||||
|
||||
@@ -0,0 +1,115 @@
|
||||
#!/usr/bin/env python
|
||||
|
||||
import optparse, os, shutil, subprocess, sys, tempfile, fileinput
|
||||
|
||||
def stop_err( msg ):
|
||||
sys.stderr.write( "%s\n" % msg )
|
||||
sys.exit()
|
||||
|
||||
def __main__():
|
||||
#Parse Command Line
|
||||
parser = optparse.OptionParser()
|
||||
parser.add_option( '-p', '--num-threads', dest='num_threads', help='Use this many threads to align reads. The default is 1.' )
|
||||
parser.add_option( '', '--own-file', dest='own_file', help='' )
|
||||
parser.add_option( '-D', '--indexes-path', dest='index_path', help='Indexes directory; location of .ebwt and .fa files.' )
|
||||
|
||||
# Wrapper options.
|
||||
parser.add_option( '-O', '--output', dest='output' )
|
||||
parser.add_option( '-1', '--input1', dest='input1', help='The (forward or single-end) reads file in Sanger FASTQ format' )
|
||||
parser.add_option( '-2', '--input2', dest='input2', help='The reverse reads file in Sanger FASTQ format' )
|
||||
parser.add_option( '', '--single-paired', dest='single_paired', help='' )
|
||||
parser.add_option( '', '--settings', dest='settings', help='' )
|
||||
|
||||
(options, args) = parser.parse_args()
|
||||
|
||||
# Creat bowtie index if necessary.
|
||||
tmp_index_dir = tempfile.mkdtemp()
|
||||
if options.own_file:
|
||||
index_path = os.path.join( tmp_index_dir, '.'.join( os.path.split( options.own_file )[1].split( '.' )[:-1] ) )
|
||||
try:
|
||||
os.link( options.own_file, index_path + '.fa' )
|
||||
except:
|
||||
# Bowtie prefers (but doesn't require) fasta file to be in same directory, with .fa extension
|
||||
pass
|
||||
cmd_index = 'bowtie2-build -f %s %s' % ( options.own_file, index_path )
|
||||
try:
|
||||
tmp = tempfile.NamedTemporaryFile( dir=tmp_index_dir ).name
|
||||
tmp_stderr = open( tmp, 'wb' )
|
||||
proc = subprocess.Popen( args=cmd_index, shell=True, cwd=tmp_index_dir, stderr=tmp_stderr.fileno() )
|
||||
returncode = proc.wait()
|
||||
tmp_stderr.close()
|
||||
# get stderr, allowing for case where it's very large
|
||||
tmp_stderr = open( tmp, 'rb' )
|
||||
stderr = ''
|
||||
buffsize = 1048576
|
||||
try:
|
||||
while True:
|
||||
stderr += tmp_stderr.read( buffsize )
|
||||
if not stderr or len( stderr ) % buffsize != 0:
|
||||
break
|
||||
except OverflowError:
|
||||
pass
|
||||
tmp_stderr.close()
|
||||
if returncode != 0:
|
||||
raise Exception, stderr
|
||||
except Exception, e:
|
||||
if os.path.exists( tmp_index_dir ):
|
||||
shutil.rmtree( tmp_index_dir )
|
||||
stop_err( 'Error indexing reference sequence\n' + str( e ) )
|
||||
else:
|
||||
index_path = options.index_path
|
||||
|
||||
# Build bowtie command.
|
||||
cmd = 'bowtie2 %s -x %s %s -S %s'
|
||||
|
||||
# Set up reads.
|
||||
if options.single_paired == 'paired':
|
||||
reads = " -1 %s -2 %s" % ( options.input1, options.input2 )
|
||||
else:
|
||||
reads = " -U %s" % ( options.input1 )
|
||||
|
||||
# Set up options.
|
||||
opts = '-p %s' % ( options.num_threads )
|
||||
if options.settings == 'preSet':
|
||||
pass
|
||||
else:
|
||||
pass
|
||||
|
||||
# Final command:
|
||||
cmd = cmd % ( opts, index_path, reads, options.output )
|
||||
print cmd
|
||||
|
||||
# Run
|
||||
try:
|
||||
tmp_out = tempfile.NamedTemporaryFile().name
|
||||
tmp_stdout = open( tmp_out, 'wb' )
|
||||
tmp_err = tempfile.NamedTemporaryFile().name
|
||||
tmp_stderr = open( tmp_err, 'wb' )
|
||||
proc = subprocess.Popen( args=cmd, shell=True, cwd=".", stdout=tmp_stdout, stderr=tmp_stderr )
|
||||
returncode = proc.wait()
|
||||
tmp_stderr.close()
|
||||
# get stderr, allowing for case where it's very large
|
||||
tmp_stderr = open( tmp_err, 'rb' )
|
||||
stderr = ''
|
||||
buffsize = 1048576
|
||||
try:
|
||||
while True:
|
||||
stderr += tmp_stderr.read( buffsize )
|
||||
if not stderr or len( stderr ) % buffsize != 0:
|
||||
break
|
||||
except OverflowError:
|
||||
pass
|
||||
tmp_stdout.close()
|
||||
tmp_stderr.close()
|
||||
if returncode != 0:
|
||||
raise Exception, stderr
|
||||
|
||||
# TODO: look for errors in program output.
|
||||
except Exception, e:
|
||||
stop_err( 'Error in bowtie2:\n' + str( e ) )
|
||||
|
||||
# Clean up temp dirs
|
||||
if os.path.exists( tmp_index_dir ):
|
||||
shutil.rmtree( tmp_index_dir )
|
||||
|
||||
if __name__=="__main__": __main__()
|
||||
@@ -0,0 +1,109 @@
|
||||
<tool id="bowtie2" name="Bowtie2" version="0.1">
|
||||
<!-- Wrapper compatible with Bowtie version 2.0.0 -->
|
||||
<description>is a short-read mapper</description>
|
||||
<version_command>bowtie2 --version</version_command>
|
||||
<requirements>
|
||||
<requirement type="package">bowtie2</requirement>
|
||||
</requirements>
|
||||
<command interpreter="python">
|
||||
bowtie2_wrapper.py
|
||||
|
||||
## Change this to accommodate the number of threads you have available.
|
||||
--num-threads="4"
|
||||
|
||||
## Outputs.
|
||||
--output=$output
|
||||
|
||||
## Handle reference file.
|
||||
#if $refGenomeSource.genomeSource == "history":
|
||||
--own-file=$refGenomeSource.ownFile
|
||||
#else:
|
||||
--indexes-path="${refGenomeSource.index.fields.path}"
|
||||
#end if
|
||||
|
||||
## Are reads single-end or paired?
|
||||
--single-paired=$singlePaired.sPaired
|
||||
|
||||
## First input file always required.
|
||||
--input1=$input1
|
||||
|
||||
## Second input only if input is paired-end.
|
||||
#if $singlePaired.sPaired == "paired"
|
||||
--input2=$singlePaired.input2
|
||||
#end if
|
||||
|
||||
## Set params.
|
||||
--settings=$params.settingsType
|
||||
</command>
|
||||
<inputs>
|
||||
<conditional name="singlePaired">
|
||||
<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 format="fastqsanger" name="input1" type="data" label="FASTQ file" help="Nucleotide-space: Must have Sanger-scaled quality values with ASCII offset 33"/>
|
||||
</when>
|
||||
<when value="paired">
|
||||
<param format="fastqsanger" name="input1" type="data" label="FASTQ file" help="Nucleotide-space: Must have Sanger-scaled quality values with ASCII offset 33" />
|
||||
<param format="fastqsanger" name="input2" type="data" label="FASTQ file" help="Nucleotide-space: Must have Sanger-scaled quality values with ASCII offset 33" />
|
||||
<!-- TODO: paired-end specific parameters. -->
|
||||
</when>
|
||||
</conditional>
|
||||
<conditional name="refGenomeSource">
|
||||
<param name="genomeSource" type="select" label="Will you select a reference genome from your history or use a built-in index?" help="Built-ins were indexed using default options">
|
||||
<option value="indexed">Use a built-in index</option>
|
||||
<option value="history">Use one from the history</option>
|
||||
</param>
|
||||
<when value="indexed">
|
||||
<param name="index" type="select" label="Select a reference genome" help="If your genome of interest is not listed, contact the Galaxy team">
|
||||
<options from_data_table="bowtie2_indexes">
|
||||
<filter type="sort_by" column="2"/>
|
||||
<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 the reference genome" />
|
||||
</when> <!-- history -->
|
||||
</conditional> <!-- refGenomeSource -->
|
||||
<conditional name="params">
|
||||
<param name="settingsType" type="select" label="Bowtie settings to use" help="You can use the default settings or set custom values for any of Bowtie's parameters.">
|
||||
<option value="preSet">Use Defaults</option>
|
||||
<option value="full">Full parameter list</option>
|
||||
</param>
|
||||
<when value="preSet" />
|
||||
<!-- Full/advanced params. -->
|
||||
<when value="full">
|
||||
</when> <!-- full -->
|
||||
</conditional> <!-- params -->
|
||||
</inputs>
|
||||
|
||||
<outputs>
|
||||
<data format="sam" name="output" label="${tool.name} on ${on_string}: mapped reads">
|
||||
<actions>
|
||||
<conditional name="refGenomeSource.genomeSource">
|
||||
<when value="indexed">
|
||||
<action type="metadata" name="dbkey">
|
||||
<option type="from_data_table" name="bowtie2_indexes" column="1" offset="0">
|
||||
<filter type="param_value" column="0" value="#" compare="startswith" keep="False"/>
|
||||
<filter type="param_value" ref="refGenomeSource.index" column="0"/>
|
||||
</option>
|
||||
</action>
|
||||
</when>
|
||||
<when value="history">
|
||||
<action type="metadata" name="dbkey">
|
||||
<option type="from_param" name="refGenomeSource.ownFile" param_attribute="dbkey" />
|
||||
</action>
|
||||
</when>
|
||||
</conditional>
|
||||
</actions>
|
||||
</data>
|
||||
</outputs>
|
||||
|
||||
<tests>
|
||||
</tests>
|
||||
|
||||
<help>
|
||||
</help>
|
||||
</tool>
|
||||
Reference in New Issue
Block a user