def main(config_file, fastq_dir):
with open(config_file) as in_handle:
config = yaml.load(in_handle)
barcode_info = config["barcodes"]
print "Processing %s." % (fastq_dir)
in_files = glob.glob(os.path.join(fastq_dir, "*.fastq"))
print "Found %s in %s. " % (in_files, fastq_dir)
print "Combining paired-end files, if found."
pairs = combine_pairs(in_files)
print "Calulcated pairs: %s." % (pairs)
out_files = []
for pair in pairs:
barcode = _determine_barcode_from_filename(pair[0])
print "Detected barcode: %s" % barcode
if barcode not in barcode_info.keys():
print "barcode %s not found in the YAML file, skipping." % (
barcode)
continue
print "Sample ID: %s" % (barcode_info[barcode][0])
type = barcode_info[barcode][1]
print "Sample type: %s" % (barcode_info[barcode][1])
to_trim = config["to_trim"][type]
cutadapt_dir = "cutadapt"
print("Trimming off %s and any bases before it from %s." %
(to_trim[0], pair[0]))
out_dir = os.path.join(cutadapt_dir, os.path.basename(pair[0]))
out_files.append(_trim_from_front(pair[0], to_trim[0]))
if len(pair) > 1:
print("Trimming off %s and any bases before it from %s." %
(to_trim[1], pair[1]))
out_files.append(_trim_from_front(pair[1], to_trim[1]))
out_files = list(flatten(out_files))
out_files = combine_pairs(out_files)
for pair in out_files:
if len(pair) > 1:
filter_reads_by_length(pair[0], pair[1], "fastq-sanger")
else:
filter_single_reads_by_length(pair[0], "fastq-sanger")
def main(config_file, fastq_dir):
with open(config_file) as in_handle:
config = yaml.load(in_handle)
barcode_info = config["barcodes"]
print "Processing %s." % (fastq_dir)
in_files = glob.glob(os.path.join(fastq_dir, "*.fastq"))
print "Found %s in %s. " % (in_files, fastq_dir)
print "Combining paired-end files, if found."
pairs = combine_pairs(in_files)
print "Calulcated pairs: %s." % (pairs)
out_files = []
for pair in pairs:
barcode = _determine_barcode_from_filename(pair[0])
print "Detected barcode: %s" % barcode
if barcode not in barcode_info.keys():
print "barcode %s not found in the YAML file, skipping." % (barcode)
continue
print "Sample ID: %s" % (barcode_info[barcode][0])
type = barcode_info[barcode][1]
print "Sample type: %s" % (barcode_info[barcode][1])
to_trim = config["to_trim"][type]
cutadapt_dir = "cutadapt"
print ("Trimming off %s and any bases before it from %s."
% (to_trim[0], pair[0]))
out_dir = os.path.join(cutadapt_dir, os.path.basename(pair[0]))
out_files.append(_trim_from_front(pair[0], to_trim[0]))
if len(pair) > 1:
print ("Trimming off %s and any bases before it from %s."
% (to_trim[1], pair[1]))
out_files.append(_trim_from_front(pair[1], to_trim[1]))
out_files = list(flatten(out_files))
out_files = combine_pairs(out_files)
for pair in out_files:
if len(pair) > 1:
filter_reads_by_length(pair[0], pair[1], "fastq-sanger")
else:
filter_single_reads_by_length(pair[0], "fastq-sanger")
def remove_short_reads(fastq_files, dirs, lane_config):
"""
remove reads from a single or pair of fastq files which fall below
a length threshold (30 bases)
"""
min_length = int(lane_config["algorithm"].get("min_read_length", 20))
supplied_quality_format = _get_quality_format(lane_config)
if supplied_quality_format == "illumina":
quality_format = "fastq-illumina"
else:
quality_format = "fastq-sanger"
if is_pair(fastq_files):
fastq1, fastq2 = fastq_files
out_files = fastq.filter_reads_by_length(fastq1, fastq2, quality_format, min_length)
else:
out_files = [fastq.filter_single_reads_by_length(fastq_files[0],
quality_format, min_length)]
map(os.remove, fastq_files)
return out_files
def _remove_short_reads(fastq_files, dirs, lane_config):
"""
remove reads from a single or pair of fastq files which fall below
a length threshold (30 bases)
"""
MIN_LENGTH = 20
supplied_quality_format = _get_quality_format(lane_config)
if supplied_quality_format == "illumina":
quality_format = "fastq-illumina"
else:
quality_format = "fastq-sanger"
if is_pair(fastq_files):
fastq1, fastq2 = fastq_files
out_files = fastq.filter_reads_by_length(fastq1, fastq2,
quality_format, MIN_LENGTH)
else:
out_files = fastq.filter_single_reads_by_length(
fastq_files[0], quality_format, MIN_LENGTH)
return out_files
def _remove_short_reads(fastq_files, dirs, lane_config):
"""
remove reads from a single or pair of fastq files which fall below
a length threshold (30 bases)
"""
MIN_LENGTH = 20
supplied_quality_format = _get_quality_format(lane_config)
if supplied_quality_format == "illumina":
quality_format = "fastq-illumina"
else:
quality_format = "fastq-sanger"
if is_pair(fastq_files):
fastq1, fastq2 = fastq_files
out_files = fastq.filter_reads_by_length(fastq1, fastq2, quality_format,
MIN_LENGTH)
else:
out_files = [fastq.filter_single_reads_by_length(fastq_files[0],
quality_format,
MIN_LENGTH)]
return out_files
def remove_short_reads(fastq_files, dirs, lane_config):
"""
remove reads from a single or pair of fastq files which fall below
a length threshold (30 bases)
"""
min_length = int(lane_config["algorithm"].get("min_read_length", 20))
supplied_quality_format = _get_quality_format(lane_config)
if supplied_quality_format == "illumina":
quality_format = "fastq-illumina"
else:
quality_format = "fastq-sanger"
if is_pair(fastq_files):
fastq1, fastq2 = fastq_files
out_files = fastq.filter_reads_by_length(fastq1, fastq2,
quality_format, min_length)
else:
out_files = [
fastq.filter_single_reads_by_length(fastq_files[0], quality_format,
min_length)
]
map(os.remove, fastq_files)
return out_files
