def main(argv=None):
"""script main.
parses command line options in sys.argv, unless *argv* is given.
"""
if argv is None:
argv = sys.argv
parser.add_option("-n",
"--vertices",
dest="vertices",
action="append",
help="filename with vertices.")
parser.add_option("-e",
"--extra",
dest="filename_extra",
type="string",
help="filename to store extra vertices in.")
parser.add_option("-m",
"--missed",
dest="filename_missed",
type="string",
help="filename to store missed vertices in.")
parser.set_defaults(
vertices=[],
filename_extra=None,
filename_missed=None,
)
(options, args) = E.Start(parser)
if len(options.vertices) == "":
raise "please specify one set of vertices."
vertices = {}
index = 0
missed_queries = []
nvertices = [0] * len(options.vertices)
for x in range(len(options.vertices)):
f = options.vertices[x]
vv = map(lambda x: x[:-1].split("\t")[0],
filter(lambda x: x[0] != "#",
open(f, "r").readlines()))
nvertices[x] = len(vv)
missed_queries.append([])
for v in vv:
vertices[v] = [x, 0, 0]
if options.loglevel >= 1:
print "# read %i vertices from %s" % (len(vv), f)
sys.stdout.flush()
l = BlastAlignments.Link()
extra_vertices = {}
for line in sys.stdin:
if line[0] == "#":
continue
l.Read(line)
if l.mQueryToken in vertices:
vertices[l.mQueryToken][1] += 1
else:
extra_vertices[l.mQueryToken] = 1
if l.mSbjctToken in vertices:
vertices[l.mSbjctToken][2] += 1
else:
extra_vertices[l.mSbjctToken] = 1
found_queries = [0] * len(options.vertices)
found_sbjcts = [0] * len(options.vertices)
for v, vv in vertices.items():
index, nquery, nsbjct = vv
if nquery:
found_queries[index] += 1
else:
missed_queries[index].append(v)
if nsbjct:
found_sbjcts[index] += 1
headers = ("set", "name", "tvertex", "nmissed", "pmissed", "nquery",
"pquery", "nsbjct", "psbjct")
print "\t".join(headers)
for x in range(len(options.vertices)):
print "%i\t%s\t%i\t%i\t%5.2f\t%i\t%5.2f\t%i\t%5.2f" % (
x, options.vertices[x], nvertices[x], len(missed_queries[x]),
100 * float(len(missed_queries[x])) / nvertices[x],
found_queries[x], 100 * float(found_queries[x]) / nvertices[x],
found_sbjcts[x], 100 * float(found_sbjcts[x]) / nvertices[x])
print "//"
print "%i vertices not in set" % len(extra_vertices)
if options.filename_extra and len(extra_vertices) > 0:
outfile = open(options.filename_extra, "w")
for x in extra_vertices.keys():
outfile.write("%s\n" % x)
outfile.close()
if options.filename_missed:
outfile = open(options.filename_missed, "w")
for x in range(len(options.vertices)):
for y in missed_queries[x]:
outfile.write("%i\t%s\t%s\n" % (x, options.vertices[x], y))
E.Stop()
if param_loglevel >= 1:
print "# read %i cds" % (len(cds))
sys.stdout.flush()
ninput, npairs, nskipped = 0, 0, 0
for line in sys.stdin:
if line[0] == "#":
continue
if line[0] == ">":
print line[:-1]
continue
ninput += 1
link = BlastAlignments.Link()
link.Read(line)
if link.mQueryToken == link.mSbjctToken:
continue
keep = 1
if link.mQueryToken in cds and link.mSbjctToken in cds:
is_paralog, reason = IsParalogLink(link, cds[link.mQueryToken],
cds[link.mSbjctToken])
if is_paralog:
keep = 0
if param_loglevel >= 2:
print "# DISCARDED because %s: %s" % (reason, str(link))
else:
def main(argv=None):
"""script main.
parses command line options in sys.argv, unless *argv* is given.
"""
if argv == None: argv = sys.argv
parser = E.OptionParser(
version=
"%prog version: $Id: blast2fasta.py 2782 2009-09-10 11:40:29Z andreas $",
usage=globals()["__doc__"])
parser.add_option("-s",
"--sequences",
dest="filename_sequences",
type="string",
help="filename with sequences.")
parser.add_option("-f",
"--format",
dest="format",
type="string",
help="output format.")
parser.set_defaults(
filename_sequences=None,
format="fasta",
)
(options, args) = E.Start(parser)
if not options.filename_sequences:
raise "please supply filename with sequences."
sequences = Genomics.ReadPeptideSequences(
open(options.filename_sequences, "r"))
if options.loglevel >= 1:
print "# read %i sequences" % len(sequences)
for k in sequences.keys():
sequences[k] = alignlib_lite.py_makeSequence(sequences[k])
if options.loglevel >= 2:
print "# converted %i sequences" % len(sequences)
ninput, noutput, nskipped, nfailed = 0, 0, 0, 0
link = BlastAlignments.Link()
ali = alignlib_lite.py_makeAlignataVector()
for line in sys.stdin:
if line[0] == "#": continue
link.Read(line)
ninput += 1
if link.mQueryToken not in sequences or link.mSbjctToken not in sequences:
nskipped += 1
continue
ali.Clear()
alignlib_lite.py_fillAlignataCompressed(ali, link.mQueryFrom,
link.mQueryAli,
link.mSbjctFrom,
link.mSbjctAli)
result = alignlib_lite.py_writePairAlignment(
sequences[link.mQueryToken], sequences[link.mSbjctToken],
ali).split("\n")
if len(result) != 3:
nfailed += 1
if options.format == "fasta":
print ">%s %i-%i\n%s\n>%s %i-%i\n%s\n" %\
(link.mQueryToken, link.mQueryFrom, link.mQueryTo, result[0].split("\t")[1],
link.mSbjctToken, link.mSbjctFrom, link.mSbjctTo, result[1].split("\t")[1] )
noutput += 1
E.info("ninput=%i, noutput=%i, nskipped=%i, nfailed=%i" %
(ninput, noutput, nskipped, nfailed))
E.Stop()