alignator = alignlib_lite.py_makeAlignatorDPFull(alignlib_lite.py_ALIGNMENT_LOCAL, param_gop, param_gep)
map_query2token = alignlib_lite.py_makeAlignmentVector()
for line in sys.stdin:
if line[0] == "#":
continue
query_token, sbjct_token, query_sequence, sbjct_sequence = string.split(line[:-1], "\t")
map_query2token.clear()
row = alignlib_lite.py_makeSequence(query_sequence)
col = alignlib_lite.py_makeSequence(sbjct_sequence)
alignator.align(map_query2token, row, col)
pidentity = 100.0 * alignlib_lite.py_calculatePercentIdentity(map_query2token, row, col)
psimilarity = 100.0 * alignlib_lite.py_calculatePercentSimilarity(map_query2token)
print string.join(
map(
str,
(
query_token,
sbjct_token,
map_query2token.getScore(),
alignlib_lite.py_AlignmentFormatEmissions(map_query2token),
pidentity,
psimilarity,
map_query2token.getNumGaps(),
),
),
"\t",
alignator = alignlib_lite.py_makeAlignatorDPFull(
alignlib_lite.py_ALIGNMENT_LOCAL, param_gop, param_gep)
map_query2token = alignlib_lite.py_makeAlignmentVector()
for line in sys.stdin:
if line[0] == "#":
continue
query_token, sbjct_token, query_sequence, sbjct_sequence = string.split(
line[:-1], "\t")
map_query2token.clear()
row = alignlib_lite.py_makeSequence(query_sequence)
col = alignlib_lite.py_makeSequence(sbjct_sequence)
alignator.align(map_query2token, row, col)
pidentity = 100.0 * \
alignlib_lite.py_calculatePercentIdentity(
map_query2token, row, col)
psimilarity = 100.0 * \
alignlib_lite.py_calculatePercentSimilarity(map_query2token)
print string.join(
map(str,
(query_token, sbjct_token, map_query2token.getScore(),
alignlib_lite.py_AlignmentFormatEmissions(map_query2token),
pidentity, psimilarity, map_query2token.getNumGaps())), "\t")
if __name__ == "__main__":
sys.exit(main(sys.argv))
def main(argv=None):
if argv is None:
argv = sys.argv
parser = E.OptionParser(
version=
"%prog version: $Id: align_all_vs_all.py 2782 2009-09-10 11:40:29Z andreas $",
usage=globals()["__doc__"])
parser.add_option("-s",
"--sequences",
dest="filename_sequences",
type="string",
help="input file with sequences")
parser.set_defaults(
filename_sequences=None,
gop=-10.0,
gep=-1.0,
)
(options, args) = E.Start(parser, add_pipe_options=True)
if options.filename_sequences:
infile = open(options.filename_sequences, "r")
else:
infile = sys.stdin
parser = FastaIterator.FastaIterator(infile)
sequences = []
while 1:
cur_record = iterator.next()
if cur_record is None:
break
sequences.append(
(cur_record.title,
alignlib_lite.py_makeSequence(re.sub(" ", "",
cur_record.sequence))))
if options.filename_sequences:
infile.close()
alignator = alignlib_lite.py_makeAlignatorFullDP(options.gop, options.gep)
map_a2b = alignlib_lite.py_makeAlignataVector()
nsequences = len(sequences)
for x in range(0, nsequences - 1):
for y in range(x + 1, nsequences):
alignator.Align(sequences[x][1], sequences[y][1], map_a2b)
row_ali, col_ali = alignlib_lite.py_writeAlignataCompressed(
map_a2b)
options.stdout.write(
"%s\t%s\t%i\t%i\t%i\t%s\t%i\t%i\t%s\t%i\t%i\t%i\t%i\n" %
(sequences[x][0], sequences[y][0], map_a2b.getScore(),
map_a2b.getRowFrom(), map_a2b.getRowTo(), row_ali,
map_a2b.getColFrom(), map_a2b.getColTo(), col_ali,
map_a2b.getScore(),
100 * alignlib_lite.py_calculatePercentIdentity(
map_a2b, sequences[x][1], sequences[y][1]),
sequences[x][1].getLength(), sequences[y][1].getLength()))
E.Stop()
def main( argv = None ):
if argv == None: argv = sys.argv
parser = E.OptionParser( version = "%prog version: $Id: align_all_vs_all.py 2782 2009-09-10 11:40:29Z andreas $",
usage = globals()["__doc__"] )
parser.add_option("-s", "--sequences", dest="filename_sequences", type="string",
help="input file with sequences" )
parser.set_defaults(
filename_sequences = None,
gop = -10.0,
gep = -1.0,
)
(options, args) = E.Start( parser, add_pipe_options = True )
if options.filename_sequences:
infile = open(options.filename_sequences, "r")
else:
infile = sys.stdin
parser = FastaIterator.FastaIterator( infile )
sequences = []
while 1:
cur_record = iterator.next()
if cur_record is None: break
sequences.append( (cur_record.title, alignlib_lite.py_makeSequence(re.sub( " ", "", cur_record.sequence)) ) )
if options.filename_sequences:
infile.close()
alignator = alignlib_lite.py_makeAlignatorFullDP( options.gop, options.gep )
map_a2b = alignlib_lite.py_makeAlignataVector()
nsequences = len(sequences)
for x in range(0,nsequences-1):
for y in range(x+1, nsequences):
alignator.Align( sequences[x][1], sequences[y][1], map_a2b)
row_ali, col_ali = alignlib_lite.py_writeAlignataCompressed( map_a2b )
options.stdout.write( "%s\t%s\t%i\t%i\t%i\t%s\t%i\t%i\t%s\t%i\t%i\t%i\t%i\n" % (\
sequences[x][0], sequences[y][0],
map_a2b.getScore(),
map_a2b.getRowFrom(),
map_a2b.getRowTo(),
row_ali,
map_a2b.getColFrom(),
map_a2b.getColTo(),
col_ali,
map_a2b.getScore(),
100 * alignlib_lite.py_calculatePercentIdentity( map_a2b, sequences[x][1], sequences[y][1]),
sequences[x][1].getLength(),
sequences[y][1].getLength() ))
E.Stop()
