def match_events_with_eventalign(events=None, event_detections=None, minus=False, rna=False):
"""Match event index with event detection data to label segments of signal for each kmer
# RNA is sequenced 3'-5'
# reversed for fasta/q sequence
# if mapped to reverse strand
# reverse reverse complement = complement
# DNA is sequenced 5'-3'
# if mapped to reverse strand
# reverse complement
:param events: events table reference_index', 'event_index', 'aligned_kmer', 'posterior_probability
:param event_detections: event detection event table
:param minus: boolean option to for minus strand mapping
:param rna: boolean for RNA read
"""
assert events is not None, "Must pass signal alignment events"
assert event_detections is not None, "Must pass event_detections events"
check_numpy_table(events, req_fields=('position', 'event_index',
'reference_kmer'))
check_numpy_table(event_detections, req_fields=('start', 'length'))
label = np.zeros(len(events), dtype=[('raw_start', int), ('raw_length', int), ('reference_index', int),
('posterior_probability', float), ('kmer', 'S6')])
label['raw_start'] = [event_detections[x]["start"] for x in events["event_index"]]
label['raw_length'] = [event_detections[x]["length"] for x in events["event_index"]]
label['reference_index'] = events["position"]
def convert_to_str(string):
"""Helper function to catch bytes as strings"""
if type(string) is str:
return string
else:
return bytes.decode(string)
flip = ReverseComplement()
if minus:
if rna:
kmers = [flip.complement(convert_to_str(x)) for x in events["reference_kmer"]]
else:
kmers = [flip.reverse_complement(convert_to_str(x)) for x in events["reference_kmer"]]
else:
if rna:
kmers = [flip.reverse(convert_to_str(x)) for x in events["reference_kmer"]]
else:
kmers = events["reference_kmer"]
label['kmer'] = kmers
label['posterior_probability'] = np.ones(len(events))
# np.sort(label, order='raw_start', kind='mergesort')
return label
def test_reverse_complement(self):
rev_comp = ReverseComplement(find="ACGTMKRYBVDHNacgtmkrybvdhn", replace="TGCAKMYRVBHDNtgcakmyrvbhdn")
for x in range(10):
rand_len = np.random.randint(0, 1000)
random_dna = get_random_string(rand_len, chars=list(set("ACGTMKRYBVDHN")))
self.assertEqual(reverse_complement(random_dna, reverse=True, complement=True),
rev_comp.reverse_complement(random_dna))
self.assertEqual(reverse_complement(random_dna, reverse=False, complement=True),
rev_comp.complement(random_dna))
self.assertEqual(reverse_complement(random_dna, reverse=True, complement=False),
rev_comp.reverse(random_dna))
self.assertEqual(reverse_complement(random_dna, reverse=False, complement=False),
random_dna)