from FASTA import *
import numpy
import pylab as P
P.ion()
nucleotides = ['G', 'A', 'T', 'C']
nucleotide_to_index = {}
for i, nuc in enumerate(nucleotides):
nucleotide_to_index[nuc] = i
# build PSSM on yeast genome:
yeast = FASTA('s_cerevisiae.fasta')
# motif is TATAwxyzuv
motif_start = 'TATA'
motif_length = 10
pseudo_count = 1
count_pssm = numpy.zeros((motif_length, 4)) + 1
num_matches = 0
for chromosome_name, chromosome_sequence in yeast.accession_to_sequence.items(
):
print 'processing', chromosome_name
for i in xrange(len(chromosome_sequence) - motif_length):
sl = chromosome_sequence[i:i + motif_length]
if sl.startswith(motif_start):
num_matches += 1
for i, nuc in enumerate(sl):
nuc_index = nucleotide_to_index[nuc]
# (at your option) any later version.
#
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
# GNU General Public License for more details.
#
# You should have received a copy of the GNU General Public License
# along with this program; if not, write to the Free Software
# Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
import FASTA
import sys
recs = FASTA.readFasta(sys.stdin)
maxLen = max([len(rec.sequence) for rec in recs])
titleWidth = 10
seqWidth = 60
start = 0
while start < maxLen:
for rec in recs:
if start == 0:
print "%s%s" % (rec.title.ljust(titleWidth)[0:titleWidth],
rec.sequence[start : start + seqWidth])
else:
print "%s%s" % (' ' * titleWidth,
rec.sequence[start : start + seqWidth])
anchors = {}
for line in strm:
fields = line.split()
anchors[fields[0]] = fields[3:5]
return anchors
# Test for existence of genscan parameter file
if not os.path.exists(options.genscanParamFile):
sys.stderr.write("Error: Genscan parameter file %s does not exist\n" %
options.genscanParamFile)
sys.exit(1)
# Read in the sequences from the multi-fasta file
sys.stderr.write("Reading in multi-fasta file...")
multiFastaFile = file(multiFastaFilename)
fastaRecs = FASTA.readFasta(multiFastaFile)
multiFastaFile.close()
sys.stderr.write("done\n")
# Make protein anchors for each sequence
for rec in fastaRecs:
rec.title = firstWord(rec.title)
chromFile = file(os.path.join(workdir, rec.title + ".chroms"), 'w')
chromFile.write("%s\t%d\n" % (rec.title, len(rec.sequence)))
chromFile.close()
sys.stderr.write("Writing single-fasta file...")
fastaFilename = os.path.join(workdir, rec.title + ".fa")
fastaFile = file(fastaFilename, 'w')
fastaFile.write(str(rec))
fastaFile.close()
