def remap(read_ref, ev, min_prob, kmer_len, prior, slip):
inMat = sloika.features.from_events(ev, tag='')
inMat = np.expand_dims(inMat, axis=1)
post = sloika.decode.prepare_post(calc_post(inMat),
min_prob=min_prob,
drop_bad=False)
kmers = np.array(bio.seq_to_kmers(read_ref, kmer_len))
seq = [kmer_to_state[k] + 1 for k in kmers]
prior0 = None if prior[0] is None else sloika.util.geometric_prior(
len(seq), prior[0])
prior1 = None if prior[1] is None else sloika.util.geometric_prior(
len(seq), prior[1], rev=True)
score, path = sloika.transducer.map_to_sequence(post,
seq,
slip=slip,
prior_initial=prior0,
prior_final=prior1,
log=False)
ev = nprf.append_fields(
ev, ['seq_pos', 'kmer', 'good_emission'],
[path, kmers[path], np.repeat(True, len(ev))])
return (score, ev, path, seq)
def test_de_bruijn_allkmers(self):
alpha = 4
dblen = 2
debruijn_seq = ''.join(
[str(y) for y in bio.de_bruijn(alpha, dblen, pad=True)])
kmers = bio.seq_to_kmers(debruijn_seq, dblen)
self.assertEqual(len(kmers), alpha**dblen)
def test_de_bruijn_noduplicates(self):
alpha = 4
dblen = 2
debruijn_seq = ''.join(
[str(y) for y in bio.de_bruijn(alpha, dblen, pad=True)])
all_kmers = bio.seq_to_kmers(debruijn_seq, dblen)
self.assertTrue(len(all_kmers) == len(set(all_kmers)))
def raw_remap(ref, signal, min_prob, kmer_len, prior, slip):
""" Map raw signal to reference sequence using transducer model"""
from sloika import config # local import to avoid CUDA init in main thread
inMat = (signal - np.median(signal)) / mad(signal)
inMat = inMat[:, None, None].astype(config.sloika_dtype)
post = sloika.decode.prepare_post(batch.calc_post(inMat),
min_prob=min_prob,
drop_bad=False)
kmers = np.array(bio.seq_to_kmers(ref, kmer_len))
seq = [batch.kmer_to_state[k] + 1 for k in kmers]
prior0 = None if prior[0] is None else sloika.util.geometric_prior(
len(seq), prior[0])
prior1 = None if prior[1] is None else sloika.util.geometric_prior(
len(seq), prior[1], rev=True)
score, path = sloika.transducer.map_to_sequence(post,
seq,
slip=slip,
prior_initial=prior0,
prior_final=prior1,
log=False)
mapping_dtype = [
('start', '<i8'),
('length', '<i8'),
('seq_pos', '<i8'),
('move', '<i8'),
('kmer', 'S{}'.format(kmer_len)),
('good_emission', '?'),
]
mapping_table = np.zeros(post.shape[0], dtype=mapping_dtype)
stride = int(np.ceil(signal.shape[0] / float(post.shape[0])))
mapping_table['start'] = np.arange(
0, signal.shape[0], stride, dtype=np.int) - stride // 2
mapping_table['length'] = stride
mapping_table['seq_pos'] = path
mapping_table['move'] = np.ediff1d(path, to_begin=1)
mapping_table['kmer'] = kmers[path]
# We set 'good_emission' for compatability only
mapping_table['good_emission'] = True
_, mapping_table = trim_signal_and_mapping(signal, mapping_table, 0,
len(signal))
return (score, mapping_table, path, seq)
def test_seq_to_kmers_returns_correct(self):
self.assertEqual(bio.seq_to_kmers(self.base_seq, 10), self.kmers1)