def main(blast_file, options):
qbed_file, sbed_file = options.qbed, options.sbed
# is this a self-self blast?
is_self = (qbed_file == sbed_file)
if is_self:
print >>sys.stderr, "... looks like a self-self BLAST to me"
global_density_ratio = options.global_density_ratio
tandem_Nmax = options.tandem_Nmax
filter_repeats = options.filter_repeats
cscore = options.cscore
localdups = options.localdups
print >>sys.stderr, "read annotation files %s and %s" % (qbed_file, sbed_file)
qbed = Bed(qbed_file)
sbed = Bed(sbed_file)
qorder = qbed.get_order()
sorder = sbed.get_order()
fp = file(blast_file)
print >>sys.stderr, "read BLAST file %s (total %d lines)" % \
(blast_file, sum(1 for line in fp))
fp.seek(0)
# mdb added 3/18/16 for Last v731
blasts = []
for line in fp:
if not line.startswith("#"):
blasts.append(BlastLine(line))
blasts = sorted(blasts, key=lambda b: b.score, reverse=True)
# mdb removed 3/18/16 for Last v731
# blasts = sorted([BlastLine(line) for line in fp], \
# key=lambda b: b.score, reverse=True)
filtered_blasts = []
seen = set()
ostrip = options.strip_names
for b in blasts:
query, subject = b.query, b.subject
#if ostrip:
# query, subject = gene_name(query), gene_name(subject)
if query not in qorder:
print >>sys.stderr, "WARNING: %s not in %s" % (query, qbed.filename)
continue
if subject not in sorder:
print >>sys.stderr, "WARNING: %s not in %s" % (subject, sbed.filename)
continue
qi, q = qorder[query]
si, s = sorder[subject]
if is_self and qi > si:
# move all hits to same side when doing self-self BLAST
query, subject = subject, query
qi, si = si, qi
q, s = s, q
key = query, subject
if key in seen: continue
seen.add(key)
b.query, b.subject = key
b.qi, b.si = qi, si
b.qseqid, b.sseqid = q['seqid'], s['seqid']
filtered_blasts.append(b)
if global_density_ratio:
print >>sys.stderr, "running the global_density filter" + \
"(global_density_ratio=%d)..." % options.global_density_ratio
gene_count = len(qorder) + len(sorder)
before_filter = len(filtered_blasts)
filtered_blasts = filter_to_global_density(filtered_blasts, gene_count,
global_density_ratio)
print >>sys.stderr, "after filter (%d->%d)..." % (before_filter, len(filtered_blasts))
if tandem_Nmax:
print >>sys.stderr, "running the local dups filter (tandem_Nmax=%d)..." % tandem_Nmax
qtandems = tandem_grouper(qbed, filtered_blasts,
flip=True, tandem_Nmax=tandem_Nmax)
standems = tandem_grouper(sbed, filtered_blasts,
flip=False, tandem_Nmax=tandem_Nmax)
qdups_fh = open(op.splitext(qbed_file)[0] + ".localdups", "w") if localdups else None
if is_self:
for s in standems: qtandems.join(*s)
qdups_to_mother = write_localdups(qdups_fh, qtandems, qbed)
sdups_to_mother = qdups_to_mother
else:
qdups_to_mother = write_localdups(qdups_fh, qtandems, qbed)
sdups_fh = open(op.splitext(sbed_file)[0] + ".localdups", "w") if localdups else None
sdups_to_mother = write_localdups(sdups_fh, standems, sbed)
if localdups:
# write out new .bed after tandem removal
write_new_bed(qbed, qdups_to_mother)
if not is_self:
write_new_bed(sbed, sdups_to_mother)
before_filter = len(filtered_blasts)
filtered_blasts = list(filter_tandem(filtered_blasts, \
qdups_to_mother, sdups_to_mother))
print >>sys.stderr, "after filter (%d->%d)..." % \
(before_filter, len(filtered_blasts))
qbed.beds = [x for x in qbed if x["accn"] not in qdups_to_mother]
sbed.beds = [x for x in sbed if x["accn"] not in sdups_to_mother]
qorder = qbed.get_order()
sorder = sbed.get_order()
if filter_repeats:
before_filter = len(filtered_blasts)
print >>sys.stderr, "running the repeat filter",
filtered_blasts = list(filter_repeat(filtered_blasts))
print >>sys.stderr, "after filter (%d->%d)..." % (before_filter, len(filtered_blasts))
if cscore:
before_filter = len(filtered_blasts)
print >>sys.stderr, "running the cscore filter (cscore>=%.2f)..." % cscore
filtered_blasts = list(filter_cscore(filtered_blasts, cscore=cscore))
print >>sys.stderr, "after filter (%d->%d)..." % (before_filter, len(filtered_blasts))
# this is the final output we will write to after BLAST filters
#raw_name = "%s.raw" % op.splitext(blast_file)[0]
#raw_fh = open(raw_name, "w")
#write_raw(qorder, sorder, filtered_blasts, raw_fh)
write_new_blast(filtered_blasts)
def main(blast_file, options):
qbed_file, sbed_file = options.qbed, options.sbed
# is this a self-self blast?
is_self = (qbed_file == sbed_file)
if is_self:
print >> sys.stderr, "... looks like a self-self BLAST to me"
global_density_ratio = options.global_density_ratio
tandem_Nmax = options.tandem_Nmax
filter_repeats = options.filter_repeats
cscore = options.cscore
localdups = options.localdups
print >> sys.stderr, "read annotation files %s and %s" % (qbed_file,
sbed_file)
qbed = Bed(qbed_file)
sbed = Bed(sbed_file)
qorder = qbed.get_order()
sorder = sbed.get_order()
fp = file(blast_file)
print >>sys.stderr, "read BLAST file %s (total %d lines)" % \
(blast_file, sum(1 for line in fp))
fp.seek(0)
# mdb added 3/18/16 for Last v731
blasts = []
for line in fp:
if not line.startswith("#"):
blasts.append(BlastLine(line))
blasts = sorted(blasts, key=lambda b: b.score, reverse=True)
# mdb removed 3/18/16 for Last v731
# blasts = sorted([BlastLine(line) for line in fp], \
# key=lambda b: b.score, reverse=True)
filtered_blasts = []
seen = set()
ostrip = options.strip_names
for b in blasts:
query, subject = b.query, b.subject
#if ostrip:
# query, subject = gene_name(query), gene_name(subject)
if query not in qorder:
print >> sys.stderr, "WARNING: %s not in %s" % (query,
qbed.filename)
continue
if subject not in sorder:
print >> sys.stderr, "WARNING: %s not in %s" % (subject,
sbed.filename)
continue
qi, q = qorder[query]
si, s = sorder[subject]
if is_self and qi > si:
# move all hits to same side when doing self-self BLAST
query, subject = subject, query
qi, si = si, qi
q, s = s, q
key = query, subject
if key in seen: continue
seen.add(key)
b.query, b.subject = key
b.qi, b.si = qi, si
b.qseqid, b.sseqid = q['seqid'], s['seqid']
filtered_blasts.append(b)
if global_density_ratio:
print >>sys.stderr, "running the global_density filter" + \
"(global_density_ratio=%d)..." % options.global_density_ratio
gene_count = len(qorder) + len(sorder)
before_filter = len(filtered_blasts)
filtered_blasts = filter_to_global_density(filtered_blasts, gene_count,
global_density_ratio)
print >> sys.stderr, "after filter (%d->%d)..." % (
before_filter, len(filtered_blasts))
if tandem_Nmax:
print >> sys.stderr, "running the local dups filter (tandem_Nmax=%d)..." % tandem_Nmax
qtandems = tandem_grouper(qbed,
filtered_blasts,
flip=True,
tandem_Nmax=tandem_Nmax)
standems = tandem_grouper(sbed,
filtered_blasts,
flip=False,
tandem_Nmax=tandem_Nmax)
qdups_fh = open(op.splitext(qbed_file)[0] +
".localdups", "w") if localdups else None
if is_self:
for s in standems:
qtandems.join(*s)
qdups_to_mother = write_localdups(qdups_fh, qtandems, qbed)
sdups_to_mother = qdups_to_mother
else:
qdups_to_mother = write_localdups(qdups_fh, qtandems, qbed)
sdups_fh = open(op.splitext(sbed_file)[0] +
".localdups", "w") if localdups else None
sdups_to_mother = write_localdups(sdups_fh, standems, sbed)
if localdups:
# write out new .bed after tandem removal
write_new_bed(qbed, qdups_to_mother)
if not is_self:
write_new_bed(sbed, sdups_to_mother)
before_filter = len(filtered_blasts)
filtered_blasts = list(filter_tandem(filtered_blasts, \
qdups_to_mother, sdups_to_mother))
print >>sys.stderr, "after filter (%d->%d)..." % \
(before_filter, len(filtered_blasts))
qbed.beds = [x for x in qbed if x["accn"] not in qdups_to_mother]
sbed.beds = [x for x in sbed if x["accn"] not in sdups_to_mother]
qorder = qbed.get_order()
sorder = sbed.get_order()
if filter_repeats:
before_filter = len(filtered_blasts)
print >> sys.stderr, "running the repeat filter",
filtered_blasts = list(filter_repeat(filtered_blasts))
print >> sys.stderr, "after filter (%d->%d)..." % (
before_filter, len(filtered_blasts))
if cscore:
before_filter = len(filtered_blasts)
print >> sys.stderr, "running the cscore filter (cscore>=%.2f)..." % cscore
filtered_blasts = list(filter_cscore(filtered_blasts, cscore=cscore))
print >> sys.stderr, "after filter (%d->%d)..." % (
before_filter, len(filtered_blasts))
# this is the final output we will write to after BLAST filters
#raw_name = "%s.raw" % op.splitext(blast_file)[0]
#raw_fh = open(raw_name, "w")
#write_raw(qorder, sorder, filtered_blasts, raw_fh)
write_new_blast(filtered_blasts)
