def __init__(self):
parse_args()
self.__dict__.update( vars(args) )
self.validate_settings()
self.initialize_output()
if self.debug:
initialize_logger( self.log_file, logging.DEBUG )
else:
initialize_logger( self.log_file, logging.INFO )
def __init__(self):
parse_args()
self.__dict__.update(vars(args))
self.validate_settings()
self.initialize_output()
initialize_logger(log, log_file=self.log_file, debug=self.debug)
"""
log.info(
"Filtering sequences below {0} Signal-To-Noise Ratio".format(min_snr))
seq_count = 0
pass_count = 0
raw_data = BasH5Collection(raw_data_file)
with FastqWriter(output_fastq) as writer:
for record in FastqReader(input_fastq):
seq_count += 1
zmw_name = '/'.join(record.name.strip().split('/')[:2])
zmw = raw_data[zmw_name]
zmw_snr = min(zmw.zmwMetric("HQRegionSNR"))
print zmw_name, zmw_snr
if zmw_snr >= min_snr:
pass_count += 1
writer.writeRecord(record)
percentage = round(100.0 * pass_count / seq_count)
log.info("{0} sequences of {1} ({2}%) passed filtering".format(
pass_count, seq_count, percentage))
if __name__ == '__main__':
import sys
input_file = sys.argv[1]
raw_data = sys.argv[2]
output_file = sys.argv[3]
min_snr = float(sys.argv[4])
initialize_logger()
snr_filter(input_file, raw_data, output_file, min_snr)
def __init__(self):
parse_args()
self.__dict__.update( vars(args) )
self.validate_settings()
self.initialize_output()
initialize_logger( log, log_file=self.log_file, debug=self.debug )
"""
log.info("Filtering sequences below {0} Signal-To-Noise Ratio".format(min_snr))
seq_count = 0
pass_count = 0
raw_data = BasH5Collection( raw_data_file )
with FastqWriter( output_fastq ) as writer:
for record in FastqReader( input_fastq ):
seq_count += 1
zmw_name = '/'.join( record.name.strip().split('/')[:2] )
zmw = raw_data[zmw_name]
zmw_snr = min( zmw.zmwMetric("HQRegionSNR") )
print zmw_name, zmw_snr
if zmw_snr >= min_snr:
pass_count += 1
writer.writeRecord( record )
percentage = round(100.0*pass_count/seq_count)
log.info("{0} sequences of {1} ({2}%) passed filtering".format(pass_count,
seq_count,
percentage))
if __name__ == '__main__':
import sys
input_file = sys.argv[1]
raw_data = sys.argv[2]
output_file = sys.argv[3]
min_snr = float(sys.argv[4])
initialize_logger()
snr_filter(input_file, raw_data, output_file, min_snr)
def parse_args():
"""
Parse the options for running the HLA pipeline and
"""
desc = 'A pipeline tool for analyzing PacBio sequenced rRNA amplicons'
parser = argparse.ArgumentParser(description=desc)
add = parser.add_argument
add('input_file',
metavar='FILE',
help="File of rRNA sequencing data to use")
add('-r',
'--raw_data',
metavar='FILE',
help='BasH5, BaxH5 or FOFN of raw H5-format sequence data')
add('-a',
'--min_accuracy',
type=float,
metavar='FLOAT',
default=MIN_ACCURACY,
help='Minimum predicted sequence accuracy to allow (%s)' %
MIN_ACCURACY)
add('-l',
'--min_length',
type=int,
metavar='INT',
default=MIN_LENGTH,
help='Minimum length sequence to allow (%s)' % MIN_LENGTH)
add('-s',
'--min_snr',
type=float,
metavar='FLOAT',
default=MIN_SNR,
help='Minimum Signal-to-Noise ratio to allow (%s)' % MIN_SNR)
add('-d',
'--distance',
type=float,
metavar='FLOAT',
default=DIST,
help='Distance at which to cluster sequences (%s)' % DIST)
add('-t',
'--step',
type=float,
metavar='FLOAT',
default=STEP,
help="Step-size to use when clustering iteratively")
add('-n',
'--num_processes',
type=int,
metavar='INT',
default=NPROC,
dest='nproc',
help='Number of processors to use (%s)' % NPROC)
add('-f',
'--fraction',
type=float,
metavar='FLOAT',
default=FRACTION,
help='Fraction of full-length to require of each read (%s)' % FRACTION)
add('-o',
'--output',
dest='output_dir',
metavar='DIR',
default='rna_pipeline_run',
help="Specify the output folder")
add('-q',
'--min_qv',
type=int,
metavar='INT',
default=MIN_QV,
help='Minimum QV to allow after sequence masking (%s)' % MIN_QV)
add('-c',
'--min_cluster_size',
type=int,
metavar='INT',
default=MIN_CLUSTER_SIZE,
help='Minimum cluster to generate consensus sequences (%s)' %
MIN_CLUSTER_SIZE)
add('--clustering_method',
metavar='METHOD',
dest='clusteringMethod',
default=DEFAULT_METHOD,
choices=CLUSTER_METHODS,
help="Distance algorithm to use in clustering (%s)" % DEFAULT_METHOD)
add('--precluster_diffs',
type=int,
metavar='INT',
default=PRECLUSTER_DIFFS,
help='Maximum number of differences to allow in pre-clustering (%s)' %
PRECLUSTER_DIFFS)
add('-A',
'--alignment_reference',
metavar='REF',
default='silva.both.align',
help="Reference MSA for aligning query sequences")
add('-C',
'--chimera_reference',
metavar='REF',
default='silva.gold.align',
help="Reference MSA for Chimera detection")
add('--sub_cluster',
action="store_true",
help="Subcluster each OTU to separate individual rDNA alleles")
add('--disable_iteration',
action='store_false',
dest='enable_iteration',
help="Turn off the iterative Clustering and Resequencing steps")
add('--disable_consensus',
action='store_false',
dest='enable_consensus',
help="Turn off the iterative Clustering and Resequencing steps")
add('--blasr',
metavar='BLASR_PATH',
help="Specify the path to the Blasr executable")
add('--mothur',
metavar='MOTHUR_PATH',
default='mothur',
help="Specify the path to the Mothur executable")
add('--debug', action='store_true', help="Turn on DEBUG message logging")
add('--test_mode',
action='store_true',
help="Turn on current modifications being tested")
class PrintVersionAction(argparse.Action):
def __call__(self, parser, namespace, values, option_string=None):
print "\tHLA Analysis Pipeline version: %s" % __VERSION__
raise SystemExit
add("--version", nargs=0, action=PrintVersionAction)
parser.parse_args(namespace=args)
initialize_logger(log, stream=sys.stdout, debug=args.debug)
# Validate any input files
if validate_file(args.alignment_reference) is None:
msg = 'No alignment reference specified and default 16S Alignment reference not detected!'
log.error(msg)
raise ValueError(msg)
if validate_file(args.chimera_reference) is None:
msg = 'Default Chimera Reference not detected in PATH, falling back to Alignment Reference'
log.warn(msg)
args.chimera_reference = args.alignment_reference
if args.enable_consensus and which('gcon.py') is None:
msg = 'No copies of pbdagcon/gcon.py detected in PATH, disabling consensus'
log.warn(msg)
args.enable_consensus = False
# Validate numerical parameters
validate_int('NumProc', args.nproc, minimum=0)
validate_float('Distance',
args.distance,
minimum=MIN_DIST,
maximum=MAX_DIST)