def write_sequence(args):
_, ext = os.path.splitext(args.fasta)
if ext:
ext = ext[1:] # remove the dot from extension
fasta = Fasta(args.fasta, default_seq=args.default_seq, strict_bounds=not args.lazy, split_char=args.delimiter)
regions_to_fetch, split_function = split_regions(args)
if not regions_to_fetch:
regions_to_fetch = tuple(fasta.keys())
for region in regions_to_fetch:
name, start, end = split_function(region)
if args.split_files: # open output file based on sequence name
filename = '.'.join(str(e) for e in (name, start, end, ext) if e)
filename = ''.join(c for c in filename if c.isalnum() or c in keepcharacters)
outfile = open(filename, 'w')
else:
outfile = sys.stdout
try:
for line in fetch_sequence(args, fasta, name, start, end):
outfile.write(line)
except FetchError as e:
raise FetchError(e.msg.rstrip() + "Try setting --lazy.\n")
if args.split_files:
outfile.close()
fasta.__exit__()
def write_sequence(args):
_, ext = os.path.splitext(args.fasta)
if ext:
ext = ext[1:] # remove the dot from extension
filt_function = re.compile(args.regex).search
if args.invert_match:
filt_function = lambda x: not re.compile(args.regex).search(x)
fasta = Fasta(args.fasta,
default_seq=args.default_seq,
key_function=eval(args.header_function),
strict_bounds=not args.lazy,
split_char=args.delimiter,
filt_function=filt_function,
read_long_names=args.long_names,
rebuild=not args.no_rebuild)
regions_to_fetch, split_function = split_regions(args)
if not regions_to_fetch:
regions_to_fetch = fasta.keys()
header = False
for region in regions_to_fetch:
name, start, end = split_function(region)
if args.size_range:
if start is not None and end is not None:
sequence_len = end - start
else:
sequence_len = len(fasta[name])
if args.size_range[0] > sequence_len or args.size_range[
1] < sequence_len:
continue
if args.split_files: # open output file based on sequence name
filename = '.'.join(str(e) for e in (name, start, end, ext) if e)
filename = ''.join(c for c in filename
if c.isalnum() or c in keepcharacters)
outfile = smart_open(filename, 'w', s3_upload=s3_config)
elif args.out:
outfile = args.out
else:
outfile = sys.stdout
try:
if args.transform:
if not header and args.transform == 'nucleotide':
outfile.write("name\tstart\tend\tA\tT\tC\tG\tN\tothers\n")
header = True
outfile.write(transform_sequence(args, fasta, name, start,
end))
else:
for line in fetch_sequence(args, fasta, name, start, end):
outfile.write(line)
except FetchError as e:
raise FetchError(str(e) + " Try setting --lazy.\n")
if args.split_files:
outfile.close()
fasta.__exit__()
def write_sequence(args):
_, ext = os.path.splitext(args.fasta)
if ext:
ext = ext[1:] # remove the dot from extension
filt_function = re.compile(args.regex).search
fasta = Fasta(args.fasta, default_seq=args.default_seq, strict_bounds=not args.lazy, split_char=args.delimiter, filt_function=filt_function, rebuild=not args.no_rebuild)
regions_to_fetch, split_function = split_regions(args)
if not regions_to_fetch:
regions_to_fetch = fasta.keys()
if args.invert_match:
sequences_to_exclude = set([split_function(region)[0] for region in regions_to_fetch])
fasta = Fasta(args.fasta, default_seq=args.default_seq, strict_bounds=not args.lazy, split_char=args.delimiter, rebuild=not args.no_rebuild)
regions_to_fetch = (key for key in fasta.keys() if key not in sequences_to_exclude)
split_function = ucsc_split
header = False
for region in regions_to_fetch:
name, start, end = split_function(region)
if args.size_range:
if start is not None and end is not None:
sequence_len = end - start
else:
sequence_len = len(fasta[name])
if args.size_range[0] > sequence_len or args.size_range[1] < sequence_len:
continue
if args.split_files: # open output file based on sequence name
filename = '.'.join(str(e) for e in (name, start, end, ext) if e)
filename = ''.join(c for c in filename if c.isalnum() or c in keepcharacters)
outfile = open(filename, 'w')
elif args.out:
outfile = args.out
else:
outfile = sys.stdout
try:
if args.transform:
if not header and args.transform == 'nucleotide':
outfile.write("name\tstart\tend\tA\tT\tC\tG\tN\n")
header = True
outfile.write(transform_sequence(args, fasta, name, start, end))
else:
for line in fetch_sequence(args, fasta, name, start, end):
outfile.write(line)
except FetchError as e:
raise FetchError(e.msg.rstrip() + "Try setting --lazy.\n")
if args.split_files:
outfile.close()
fasta.__exit__()
def write_sequence(args):
_, ext = os.path.splitext(args.fasta)
if ext:
ext = ext[1:] # remove the dot from extension
filt_function = re.compile(args.regex).search
fasta = Fasta(args.fasta, default_seq=args.default_seq, strict_bounds=not args.lazy, split_char=args.delimiter, filt_function=filt_function)
regions_to_fetch, split_function = split_regions(args)
if not regions_to_fetch:
regions_to_fetch = fasta.keys()
if args.invert_match:
sequences_to_exclude = set([split_function(region)[0] for region in regions_to_fetch])
fasta = Fasta(args.fasta, default_seq=args.default_seq, strict_bounds=not args.lazy, split_char=args.delimiter)
regions_to_fetch = (key for key in fasta.keys() if key not in sequences_to_exclude)
split_function = ucsc_split
header = False
for region in regions_to_fetch:
name, start, end = split_function(region)
if args.size_range:
if start is not None and end is not None:
sequence_len = end - start
else:
sequence_len = len(fasta[name])
if args.size_range[0] > sequence_len or args.size_range[1] < sequence_len:
continue
if args.split_files: # open output file based on sequence name
filename = '.'.join(str(e) for e in (name, start, end, ext) if e)
filename = ''.join(c for c in filename if c.isalnum() or c in keepcharacters)
outfile = open(filename, 'w')
elif args.out:
outfile = args.out
else:
outfile = sys.stdout
try:
if args.transform:
if not header and args.transform == 'nucleotide':
outfile.write("name\tstart\tend\tA\tT\tC\tG\tN\n")
header = True
outfile.write(transform_sequence(args, fasta, name, start, end))
else:
for line in fetch_sequence(args, fasta, name, start, end):
outfile.write(line)
except FetchError as e:
raise FetchError(e.msg.rstrip() + "Try setting --lazy.\n")
if args.split_files:
outfile.close()
fasta.__exit__()
