def get_matches(lastz_file, splitchar, components, fish = False):
matches = defaultdict(list)
probes = defaultdict(int)
for lz in lastz.Reader(lastz_file, long_format = True):
# skip silly hg19 mhc haplotypes
if "hap" in lz.name1:
print "Skipping: ", lz.name1
else:
if not fish:
uce_name = get_name(lz.name2, "|", 1)
probe_number = int(lz.name2.split(':')[-1])
else:
uce_name = get_name(lz.name2, "_", 1)
# add 1 because fish probe indexing starts @ 0
probe_number = int(lz.name2.split('|')[1].split('_')[1]) + 1
#pdb.set_trace()
if probe_number > probes[uce_name]:
probes[uce_name] = probe_number
matches[uce_name].append([get_name(lz.name1, splitchar = splitchar, items = components), lz.strand2, lz.zstart1, lz.end1])
return matches, probes
def main():
args = get_args()
uces = set([
get_name(read.identifier, "|", 1)
for read in fasta.FastaReader(args.query)
])
files = glob.glob(os.path.join(args.lastz, '*.lastz'))
# this prob. needs to be more robust
organisms = [
os.path.splitext(os.path.basename(f).split('-')[-1])[0].replace(
'-', "_") for f in files
]
conn, c = create_match_database(args.db, organisms, uces)
if args.dupefile:
dupes = get_dupes(args.dupefile)
else:
dupes = None
#pdb.set_trace()
for f in files:
critter = os.path.splitext(os.path.basename(f).split('-')[-1])[0]
matches, probes = get_matches(f, args.splitchar, args.components)
count = 0
for k, v in matches.iteritems():
skip = False
if len(v) > 1:
if run_checks(k, v, probes, args.verbose):
# sort by match position
v_sort = sorted(v, key=itemgetter(2))
start, end = v_sort[0][2], v_sort[-1][3]
diff = end - start
# ensure our range is less than N(probes) * probe_length - this
# still gives us a little wiggle room because probes are ~ 2X tiled
if diff > (probes[k] * 120):
skip = True
if args.verbose:
print "range longer than expected"
else:
skip = True
elif args.dupefile and k in dupes:
skip = True
if args.verbose: print "{0} is in dupefile".format(k)
else:
pass
if not skip:
store_lastz_results_in_db(c, critter, k)
count += 1
print "Entered {} matches for {}".format(count, critter)
conn.commit()
c.close()
conn.close()
def get_matches(lastz_file, splitchar, components, fish=False):
matches = defaultdict(list)
probes = defaultdict(int)
for lz in lastz.Reader(lastz_file, long_format=True):
# skip silly hg19 mhc haplotypes
if "hap" in lz.name1:
print "Skipping: ", lz.name1
else:
if not fish:
uce_name = get_name(lz.name2, "|", 1)
probe_number = int(lz.name2.split(':')[-1])
else:
uce_name = get_name(lz.name2, "_", 1)
# add 1 because fish probe indexing starts @ 0
probe_number = int(lz.name2.split('|')[1].split('_')[1]) + 1
#pdb.set_trace()
if probe_number > probes[uce_name]:
probes[uce_name] = probe_number
matches[uce_name].append([
get_name(lz.name1, splitchar=splitchar, items=components),
lz.strand2, lz.zstart1, lz.end1
])
return matches, probes
def main():
args = get_args()
uces = set([get_name(read.identifier, "|", 1) for read in fasta.FastaReader(args.query)])
files = glob.glob(os.path.join(args.lastz, '*.lastz'))
# this prob. needs to be more robust
organisms = [os.path.splitext(os.path.basename(f).split('-')[-1])[0].replace('-',"_") for f in files]
conn, c = create_match_database(args.db, organisms, uces)
if args.dupefile:
dupes = get_dupes(args.dupefile)
else:
dupes = None
#pdb.set_trace()
for f in files:
critter = os.path.splitext(os.path.basename(f).split('-')[-1])[0]
matches, probes = get_matches(f, args.splitchar, args.components)
count = 0
for k,v in matches.iteritems():
skip = False
if len(v) > 1:
if run_checks(k, v, probes, args.verbose):
# sort by match position
v_sort = sorted(v, key = itemgetter(2))
start, end = v_sort[0][2], v_sort[-1][3]
diff = end - start
# ensure our range is less than N(probes) * probe_length - this
# still gives us a little wiggle room because probes are ~ 2X tiled
if diff > (probes[k] * 120):
skip = True
if args.verbose:
print "range longer than expected"
else:
skip = True
elif args.dupefile and k in dupes:
skip = True
if args.verbose:print "{0} is in dupefile".format(k)
else:
pass
if not skip:
store_lastz_results_in_db(c, critter, k)
count += 1
print "Entered {} matches for {}".format(count, critter)
conn.commit()
c.close()
conn.close()
