# HG changeset patch # User crs4 # Date 1393864121 18000 # Node ID 87ffe493b6c1cd6361bee90ffab69727330b11a0 # Parent d180348fe9dbd424ff3be64b811026d18bbf98fe Use GALAXY_SLOTS for multithreading in Bowtie. Create symlinks instead of copying files. Specify in help that Bowtie is used to align the reads to the contigs. Add readme.rst . diff -r d180348fe9db -r 87ffe493b6c1 COPYING --- a/COPYING Tue Oct 29 05:27:29 2013 -0400 +++ b/COPYING Mon Mar 03 11:28:41 2014 -0500 @@ -1,4 +1,4 @@ -Copyright © 2013 CRS4 Srl. http://www.crs4.it/ +Copyright © 2013-2014 CRS4 Srl. http://www.crs4.it/ Created by: Gianmauro Cuccuru Nicola Soranzo diff -r d180348fe9db -r 87ffe493b6c1 readme.rst --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/readme.rst Mon Mar 03 11:28:41 2014 -0500 @@ -0,0 +1,29 @@ +SOPRA wrapper +============= + +Configuration +------------- + +sopra_wpc tool may be configured to use more than one CPU core by selecting an appropriate destination for this tool in Galaxy job_conf.xml file (see https://wiki.galaxyproject.org/Admin/Config/Jobs and https://wiki.galaxyproject.org/Admin/Config/Performance/Cluster ). + +If you are using Galaxy release_2013.11.04 or later, this tool will automatically use the number of CPU cores allocated by the job runner according to the configuration of the destination selected for this tool. + +If instead you are using an older Galaxy release, you should also add a line + + GALAXY_SLOTS=N; export GALAXY_SLOTS + +(where N is the number of CPU cores allocated by the job runner for this tool) to the file + + /bowtie/1.0.0/crs4/sopra_wpc//env.sh + +Version history +--------------- + +- Release 2: Use GALAXY_SLOTS for multithreading in Bowtie. Create symlinks instead of copying files. Specify in help that Bowtie is used to align the reads to the contigs. Add readme.rst . +- Release 1: Depend on package_bowtie_1_0_0 . +- Release 0: Initial release in the Tool Shed. + +Development +----------- + +Development is hosted at https://bitbucket.org/crs4/orione-tools . Contributions and bug reports are very welcome! diff -r d180348fe9db -r 87ffe493b6c1 sopra_wpc.py --- a/sopra_wpc.py Tue Oct 29 05:27:29 2013 -0400 +++ b/sopra_wpc.py Mon Mar 03 11:28:41 2014 -0500 @@ -32,6 +32,7 @@ def __main__(): parser = optparse.OptionParser(description='SOPRA with prebuilt contigs') + parser.add_option('-p', dest='num_threads', type='int', help='Number of threads for Bowtie') parser.add_option('--contigs', action='append', dest='contigs', help='Contigs FASTA files, at least 1') parser.add_option('--mate', action='append', dest='mates', help='Paired-end Illumina libraries, at least 1 FASTA file') parser.add_option('-d', action='append', dest='insert_sizes', type='int', help='List of insert sizes for the corresponding mate pair libraries') @@ -49,7 +50,6 @@ contigs = options.contigs # a list of file paths mates = options.mates # a list of file paths insert_sizes = options.insert_sizes # a list of integers - max_mismatches = options.max_mismatches c_option = options.c_option w_option = options.w_option L_option = options.L_option @@ -58,7 +58,7 @@ logfile = options.logfile s_scaf_path = which('s_scaf_v1.4.6.pl').pop() - print 'Creating temp dir' + print 'Creating temporary directory' wd = tempfile.mkdtemp() try: fake_mates = [os.path.join(wd, os.path.basename(mate) + '.fasta') for mate in mates] # s_prep_contigAseq_v1.4.6.pl wants a mate file with extension [Ff][Aa][Ss][Tt][Aa] or [Ff][Aa] @@ -67,12 +67,12 @@ mate_sopras = [os.path.splitext(fake_mate)[0] + '_sopra.fasta' for fake_mate in fake_mates] # s_prep_contigAseq_v1.4.6.pl writes the prepared paired reads to these files mysam_mates = [mate_sopra + '.sam' for mate_sopra in mate_sopras] # arbitrary filenames for bowtie output in SAM format mysam_mates_parsed = [mysam_mate + '_parsed' for mysam_mate in mysam_mates] # s_parse_sam_v1.4.6.pl writes its output to these files - orientdistinfo = os.path.join(wd, 'orientdistinfo_c%d' % c_option) # s_read_parsed_sam_v1.4.6.pl writes its output to this file + orientdistinfo = os.path.join(wd, "orientdistinfo_c%d" % c_option) # s_read_parsed_sam_v1.4.6.pl writes its output to this file scaffolds_file = os.path.join(wd, "scaffolds_h%s_L%d_w%d.fasta" % (h_option, L_option, w_option)) # s_scaf_v1.4.6.pl writes its output to this file for i in range(len(mates)): - print "Copying mate %s to %s" % (mates[i], fake_mates[i]) - shutil.copy2(mates[i], fake_mates[i]) + print "Creating symbolic link %s pointing to %s" % (fake_mates[i], mates[i]) + os.symlink(mates[i], fake_mates[i]) log = open(logfile, 'w') if logfile else sys.stdout try: @@ -85,7 +85,7 @@ subprocess.check_call(args=cmd_step2, stdout=log, shell=True) for i in range(len(mate_sopras)): - cmd_step3 = "bowtie -v %d -m 1 -f --sam %s %s %s" % (max_mismatches, bowtie_build, mate_sopras[i], mysam_mates[i]) + cmd_step3 = "bowtie -p %d -v %d -m 1 -f --sam %s %s %s" % (options.num_threads, options.max_mismatches, bowtie_build, mate_sopras[i], mysam_mates[i]) print "SOPRA with prebuilt contigs (Bowtie alignment of library %d) command to be executed:\n %s" % (i+1, cmd_step3) subprocess.check_call(args=cmd_step3, stdout=log, stderr=subprocess.STDOUT, shell=True) # need to redirect stderr because bowtie writes some logging info there @@ -106,7 +106,7 @@ if log != sys.stdout: log.close() - print 'Moving result file %s to %s' % (scaffolds_file, scaffolds) + print "Moving result file %s to %s" % (scaffolds_file, scaffolds) shutil.move(scaffolds_file, scaffolds) finally: shutil.rmtree(wd) diff -r d180348fe9db -r 87ffe493b6c1 sopra_wpc.xml --- a/sopra_wpc.xml Tue Oct 29 05:27:29 2013 -0400 +++ b/sopra_wpc.xml Mon Mar 03 11:28:41 2014 -0500 @@ -1,11 +1,11 @@ - for Illumina workflow + for Illumina libraries sopra bowtie - sopra_wpc.py + sopra_wpc.py -p \${GALAXY_SLOTS:-1} #for $cr in $contigs_repeat --contigs ${cr.contigs_file} #end for @@ -36,7 +36,9 @@ **What it does** -SOPRA is an assembly tool for mate pair/paired-end data generated by high-throughput sequencing technologies, e.g. Illumina and SOLiD platforms. +SOPRA is a scaffold assembly tool for paired-end/mate pair data generated by high-throughput sequencing technologies, e.g. Illumina and SOLiD platforms. This wrapper currently supports only Illumina paired-end data. + +Bowtie is used to align the reads to the contigs. The input paired-end FASTA file can be obtained with: FR reads -> *FASTQ interlacer on paired end reads* followed by *FASTQ to FASTA* converter