asf.load_assembly(args.infile)
for segments_file in args.mask:
asf.add_mask_regions(filename=segments_file)
asf.merge_masked_regions()
if args.outfile:
of = open(args.outfile, "wt")
else:
of = sys.stdout
for ocontig in asf.ocontigs_iter():
chunk = struct.unpack(
"<L",
hashlib.md5(
ocontig.encode("utf-8")).digest()[:4])[0] % args.nchunks
if not chunk == args.chunk: continue
links = {}
asf.get_links([ocontig],
skipI=True,
mapq=args.mapq,
links=links,
contigs=False,
raw=True)
# print(ocontig,chunk,links)
process_links(links,
args.window,
args.min_links,
args.max_others,
segments=of)
of.close()
parser.add_argument(
"-o",
"--outfile",
default=False,
help="Filename for writing a list of segments on the raw contigs to mask for being promiscuous in linking.",
)
# -m 2 -w 1000 -M $( cat {input.threshold} )
args = parser.parse_args()
if args.infile:
asf = HiriseAssembly()
asf.load_assembly(args.infile)
for segments_file in args.mask:
asf.add_mask_regions(filename=segments_file)
asf.merge_masked_regions()
if args.outfile:
of = open(args.outfile, "wt")
else:
of = sys.stdout
for ocontig in asf.ocontigs_iter():
chunk = struct.unpack("<L", hashlib.md5(ocontig.encode("utf-8")).digest()[:4])[0] % args.nchunks
if not chunk == args.chunk:
continue
links = {}
asf.get_links([ocontig], skipI=True, mapq=args.mapq, links=links, contigs=False, raw=True)
# print(ocontig,chunk,links)
process_links(links, args.window, args.min_links, args.max_others, segments=of)
of.close()
