def _collapse(in_file):
out_file = append_stem(in_file, ".trimming").replace(".gz", "")
if file_exists(out_file):
return out_file
seqs = collapse(in_file)
write_output(out_file, seqs)
return out_file
def _collapse(in_file):
out_file = append_stem(in_file, ".trimming").replace(".gz", "")
if file_exists(out_file):
return out_file
seqs = collapse(in_file)
write_output(out_file, seqs)
return out_file
def collapse_fastq(args):
"""collapse fasq files after adapter trimming
"""
try:
umi_fn = args.fastq
if _is_umi(args.fastq):
umis = collapse(args.fastq)
umi_fn = os.path.join(args.out, splitext_plus(os.path.basename(args.fastq))[0] + "_umi_trimmed.fastq")
write_output(umi_fn, umis, args.minimum)
seqs = collapse(umi_fn)
out_file = splitext_plus(os.path.basename(args.fastq))[0] + "_trimmed.fastq"
except IOError as e:
logger.error("I/O error({0}): {1}".format(e.errno, e.strerror))
raise "Can not read file"
out_file = os.path.join(args.out, out_file)
write_output(out_file, seqs, args.minimum)
return out_file
def _collapse(in_file):
"""
Collpase reads into unique sequences with seqcluster
"""
out_file = append_stem(in_file, ".trimming").replace(".gz", "")
if file_exists(out_file):
return out_file
seqs = collapse(in_file)
write_output(out_file, seqs, minimum=1, size=16)
return out_file
def _collapse(in_file):
"""
Collpase reads into unique sequences with seqcluster
"""
out_file = append_stem(in_file, ".trimming").replace(".gz", "")
if file_exists(out_file):
return out_file
seqs = collapse(in_file)
write_output(out_file, seqs, minimum=1, size=16)
return out_file
def test_umis(self):
from seqcluster.libs.fastq import collapse, write_output
umis = collapse(os.path.abspath("data/examples/umis/sample.fastq"))
if len(umis.keys()) != 2:
raise ValueError("umis didn't detect two unique sequences")
out_dir = "test/test_automated_output"
if os.path.exists(out_dir):
shutil.rmtree(out_dir)
os.mkdir(out_dir)
write_output(os.path.join(out_dir, "umis.fastq"), umis)
def test_umis(self):
from seqcluster.libs.fastq import collapse, write_output
umis = collapse(os.path.abspath("data/examples/umis/sample.fastq"))
if len(umis.keys()) != 2:
raise ValueError("umis didn't detect two unique sequences")
out_dir = "test/test_automated_output"
if os.path.exists(out_dir):
shutil.rmtree(out_dir)
os.mkdir(out_dir)
write_output(os.path.join(out_dir, "umis.fastq"), umis)
def collapse_fastq(args):
"""collapse fasq files after adapter trimming
"""
try:
umi_fn = args.fastq
if _is_umi(args.fastq):
umis = collapse(args.fastq)
umi_fn = os.path.join(
args.out,
splitext_plus(os.path.basename(args.fastq))[0] +
"_umi_trimmed.fastq")
write_output(umi_fn, umis, args.minimum)
seqs = collapse(umi_fn)
out_file = splitext_plus(os.path.basename(
args.fastq))[0] + "_trimmed.fastq"
except IOError as e:
logger.error("I/O error({0}): {1}".format(e.errno, e.strerror))
raise "Can not read file"
out_file = os.path.join(args.out, out_file)
write_output(out_file, seqs, args.minimum)
return out_file
def _collapse(in_file):
seqs = collapse(in_file)
out_file = append_stem(in_file, ".trimming").replace(".gz", "")
write_output(out_file, seqs)
return out_file
def _collapse(in_file):
seqs = collapse(in_file)
out_file = append_stem(in_file, ".trimming").replace(".gz", "")
write_output(out_file, seqs)
return out_file
from seqcluster.libs.fastq import collapse, splitext_plus, write_output
from bcbio.distributed.transaction import file_transaction, tx_tmpdir
from bcbio.utils import (file_exists, append_stem, replace_directory, symlink_plus, local_path_export)
from collections import Counter
if __name__ == "__main__":
in_file = sys.argv[1]
"""
Collpase reads into unique sequences with seqcluster
"""
out_file = append_stem(in_file, ".trimming").replace(".gz", "")
#out_file = splitext_plus(os.path.basename(fastq))[0] + ".fq"
seqs = collapse(in_file)
write_output(out_file, seqs, 1)
"""
Calculate size distribution after adapter removal
"""
data = Counter()
out_stat_file = out_file + "_size_stats"
with open(out_file) as in_handle:
for line in in_handle:
counts = int(line.strip().split("_x")[1])
line = in_handle.next()
l = len(line.strip())
in_handle.next()
in_handle.next()