Mercurial > repos > crs4 > ssake
diff ssake.py @ 1:386166019772 draft
Uploaded
author | crs4 |
---|---|
date | Tue, 07 Jan 2014 04:48:50 -0500 |
parents | 0ec408bcfc80 |
children |
line wrap: on
line diff
--- a/ssake.py Wed Sep 11 12:51:21 2013 -0400 +++ b/ssake.py Tue Jan 07 04:48:50 2014 -0500 @@ -35,90 +35,12 @@ return result -class SSAKE: - def __init__(self, logger, options): - self.logger = logger - self.executables = ('SSAKE', 'makePairedOutput2EQUALfiles.pl', 'makePairedOutput2UNEQUALfiles.pl') - self.logger.debug(which(self.executables[0])) - self.logger.debug(which(self.executables[1])) - self.logger.debug(which(self.executables[2])) - self.logger.debug('Creating temp dir') - self.wd = tempfile.mkdtemp() - - self.kind_of_reads = int(options.kind_of_reads) - if not (self.kind_of_reads): - self.infile = options.if_unpaired - self.paired = 0 - else: - self.infile_r1 = options.if_paired_r1 - self.infile_r2 = options.if_paired_r2 - self.paired = 1 - self.insert_size = options.insert_size - self.minnumlinks = options.minnumlinks - self.error = options.error - self.maxlinkratio = options.maxlinkratio - self.minoverlap = options.minoverlap - self.mindepthofcoverage = options.mindepthofcoverage - self.minoverlappingbases = options.minoverlappingbases - self.mincall = options.mincall - self.baseratio = options.baseratio - self.ignore_header = options.ignore_header - self.prefix = options.prefix - self.contigs = options.contigs - self.log = options.logfile - self.short = options.short - self.singlets = options.singlets - if options.seeds_file: - self.seeds_file = options.seeds_file - - def run(self): - """ """ - os.chdir(self.wd) - seeds = '' - if hasattr(self, 'seeds_file'): - seeds = " -s %s" % self.seeds_file - if self.kind_of_reads == 1: - cmd = "%s %s %s %d" % ( - self.executables[1], self.infile_r1, self.infile_r2, - self.insert_size) - self.logger.info("Preparing data") - execute(cmd) - paired_file = "%s/paired.fa" % self.wd - command = "%s -f %s -k %d -e %s -a %s -x %d" % (self.executables[0], paired_file, self.minnumlinks, self.error, self.maxlinkratio, self.minoverlap) - elif self.kind_of_reads == 2: - cmd = "%s %s %s %d" % ( - self.executables[2], self.infile_r1, self.infile_r2, - self.insert_size) - self.logger.info("Preparing data") - execute(cmd) - paired_file = "%s/paired.fa" % self.wd - unpaired_file = "%s/unpaired.fa" % self.wd - command = "%s -f %s -g %s -k %d -e %s -a %s -x %d" % (self.executables[0], paired_file, unpaired_file, self.minnumlinks, self.error, self.maxlinkratio, self.minoverlap) - else: - command = "%s -f %s" % (self.executables[0], self.infile) - command += " %s -w %d -m %d -o %d -r %s -h %s -b %s -p %s" % (seeds, self.mindepthofcoverage, self.minoverlappingbases, self.mincall, self.baseratio, self.ignore_header, self.prefix, self.paired) - self.logger.debug(command) - self.logger.info("Executing SSAKE") - execute(command) - - with open("%s.log" % os.path.join(self.wd, self.prefix), 'rb') as ssake_log_file: - self.logger.info("\n".join(["Log from SSAKE", ssake_log_file.read()])) - self.logger.info("Moving result files") - shutil.move("%s.contigs" % os.path.join(self.wd, self.prefix), self.contigs) - shutil.move("%s.short" % os.path.join(self.wd, self.prefix), self.short) - shutil.move("%s.singlets" % os.path.join(self.wd, self.prefix), self.singlets) - - def __del__(self): - shutil.rmtree(self.wd) - - LOG_FORMAT = '%(asctime)s|%(levelname)-8s|%(message)s' LOG_DATEFMT = '%Y-%m-%d %H:%M:%S' LOG_LEVELS = ['DEBUG', 'INFO', 'WARNING', 'ERROR', 'CRITICAL'] def __main__(): - """ main function """ parser = optparse.OptionParser() parser.add_option('--if_unpaired', dest='if_unpaired', help='Unpaired FASTA input file name') parser.add_option('--if_paired_r1', dest='if_paired_r1', help='Paired FASTA reads 1 input file name') @@ -154,9 +76,70 @@ logging.basicConfig(**kwargs) logger = logging.getLogger('SSAKE scaffold assembly') - S = SSAKE(logger, options) - S.run() - return + executables = ('SSAKE', 'makePairedOutput2EQUALfiles.pl', 'makePairedOutput2UNEQUALfiles.pl') + logger.debug(which(executables[0])) + logger.debug(which(executables[1])) + logger.debug(which(executables[2])) + logger.debug('Creating temp dir') + kind_of_reads = int(options.kind_of_reads) + if not (kind_of_reads): + infile = options.if_unpaired + paired = 0 + else: + infile_r1 = options.if_paired_r1 + infile_r2 = options.if_paired_r2 + paired = 1 + insert_size = options.insert_size + minnumlinks = options.minnumlinks + error = options.error + maxlinkratio = options.maxlinkratio + minoverlap = options.minoverlap + mindepthofcoverage = options.mindepthofcoverage + minoverlappingbases = options.minoverlappingbases + mincall = options.mincall + baseratio = options.baseratio + ignore_header = options.ignore_header + prefix = options.prefix + contigs = options.contigs + short = options.short + singlets = options.singlets + seeds = " -s %s" % options.seeds_file if options.seeds_file else '' + wd = tempfile.mkdtemp() + try: + os.chdir(wd) + if kind_of_reads == 1: + cmd = "%s %s %s %d" % ( + executables[1], infile_r1, infile_r2, + insert_size) + logger.info("Preparing data") + execute(cmd) + paired_file = "%s/paired.fa" % wd + command = "%s -f %s -k %d -e %s -a %s -x %d" % (executables[0], paired_file, minnumlinks, error, maxlinkratio, minoverlap) + elif kind_of_reads == 2: + cmd = "%s %s %s %d" % ( + executables[2], infile_r1, infile_r2, + insert_size) + logger.info("Preparing data") + execute(cmd) + paired_file = "%s/paired.fa" % wd + unpaired_file = "%s/unpaired.fa" % wd + command = "%s -f %s -g %s -k %d -e %s -a %s -x %d" % (executables[0], paired_file, unpaired_file, minnumlinks, error, maxlinkratio, minoverlap) + else: + command = "%s -f %s" % (executables[0], infile) + command += " %s -w %d -m %d -o %d -r %s -h %s -b %s -p %s" % (seeds, mindepthofcoverage, minoverlappingbases, mincall, baseratio, ignore_header, prefix, paired) + logger.debug(command) + logger.info("Executing SSAKE") + execute(command) + + with open("%s.log" % os.path.join(wd, prefix), 'rb') as ssake_log_file: + logger.info("\n".join(["Log from SSAKE", ssake_log_file.read()])) + logger.info("Moving result files") + shutil.move("%s.contigs" % os.path.join(wd, prefix), contigs) + shutil.move("%s.short" % os.path.join(wd, prefix), short) + shutil.move("%s.singlets" % os.path.join(wd, prefix), singlets) + finally: + shutil.rmtree(wd) + if __name__ == "__main__": __main__()