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]
