def __call__(self, sequences):
"""
Run the motif finding algorithm.
"""
preprocessed_sequences = hmm.preprocess_sequences(sequences)
# how big are the sequences
num_bases = sum(len(s) for s in sequences)
# find all K-mers collapsed with their reverse complements
logging.info("Finding all %d-mers in sequences", self.init_K_mer_length)
start = time.time()
nmer_counts = hmm.ReverseComplementCollapsingCounter(self.init_K_mer_length)
hmm.count_mers(sequences, n=self.init_K_mer_length, callback=nmer_counts)
logging.info("Took %f seconds to find %d-mers", time.time() - start, self.init_K_mer_length)
p_binding_site = (self.expected_sites_per_sequence * len(sequences)) / num_bases
logging.info("Found %d %d-mers", nmer_counts.num_counts(), self.init_K_mer_length)
start = time.time()
best_starting_point = max(self.yield_evaluations(nmer_counts, preprocessed_sequences), key=lambda x: x[1])
logging.info("Evaluation took %f seconds", time.time() - start)
logging.info("Best starting point: %s: %f" % best_starting_point)
model = self.model_for_initialisation_K_mer(best_starting_point[0], p_binding_site)
logging.info("Running Baum-Welch")
start = time.time()
LL, num_iterations = model.baum_welch(preprocessed_sequences)
logging.info("Baum-Welch took %f seconds", time.time() - start)
logging.info("Achieved LL: %f in %d iterations", LL, num_iterations)
return model
logging.info('Calculating complementary scores')
comp_scores = hmm.calculate_complementary_scores(pssm_scores)
logging.info('Preprocessing sequence')
seq = hmm.preprocess_sequence(
N.array([0, 1, 2, 3, 0, 1, 2, 3, 0, 1, 2, 3, 0, 1, 2, 3, 4]))
logging.info('Scoring sequence')
logging.info(hmm.score_sequence(pssm_scores, seq))
logging.info('Scoring sequence with complementary scores')
logging.info(hmm.score_sequence(comp_scores, seq))
logging.info(hmm.max_score_in_sequence(pssm_scores, seq))
logging.info(hmm.max_score_in_sequence(comp_scores, seq))
long_seqs = [R.random_integers(0, 4, size=10000) for i in xrange(100)]
long_seqs_preprocessed = hmm.preprocess_sequences(long_seqs)
logging.info('Starting to time max scores on long sequences.')
start = time.time()
max_scores = hmm.max_scores_in_sequences(pssm_scores,
long_seqs_preprocessed)
max_comp_scores = hmm.max_scores_in_sequences(comp_scores,
long_seqs_preprocessed)
logging.info(
'Max scores (and complementary scores) over sequences took %f secs' %
(time.time() - start))
long_seq = R.random_integers(0, 4, size=1000000)
long_seq_preprocessed = hmm.preprocess_sequence(long_seq)
logging.info('Starting to time max scores on long sequence.')
pssm_scores = hmm.calculate_log_scores(nucleo_dists)
logging.info('Calculating complementary scores')
comp_scores = hmm.calculate_complementary_scores(pssm_scores)
logging.info('Preprocessing sequence')
seq = hmm.preprocess_sequence(N.array([0,1,2,3,0,1,2,3,0,1,2,3,0,1,2,3,4]))
logging.info('Scoring sequence')
logging.info(hmm.score_sequence(pssm_scores, seq))
logging.info('Scoring sequence with complementary scores')
logging.info(hmm.score_sequence(comp_scores, seq))
logging.info(hmm.max_score_in_sequence(pssm_scores, seq))
logging.info(hmm.max_score_in_sequence(comp_scores, seq))
long_seqs = [R.random_integers(0,4,size=10000) for i in xrange(100)]
long_seqs_preprocessed = hmm.preprocess_sequences(long_seqs)
logging.info('Starting to time max scores on long sequences.')
start = time.time()
max_scores = hmm.max_scores_in_sequences(pssm_scores, long_seqs_preprocessed)
max_comp_scores = hmm.max_scores_in_sequences(comp_scores, long_seqs_preprocessed)
logging.info('Max scores (and complementary scores) over sequences took %f secs' % (time.time()-start))
long_seq = R.random_integers(0,4,size=1000000)
long_seq_preprocessed = hmm.preprocess_sequence(long_seq)
logging.info('Starting to time max scores on long sequence.')
start = time.time()
logging.info(hmm.max_score_in_sequence(pssm_scores, long_seq_preprocessed))
logging.info(hmm.max_score_in_sequence(comp_scores, long_seq_preprocessed))
logging.info('Max scores (and complementary scores) for %d bases took %f secs' % (len(long_seq), time.time()-start))