def _match(insert_match, offset, insert_match_size,
prob): # pylint disable=unused-argument
if offset < self.min_adapter_overlap:
# The reads are mostly overlapping, to the point where
# there's not enough overhang to do a confident adapter
# match. We return just the insert match to signal that
# error correction can be done even though no adapter
# trimming is required.
return (insert_match, None, None)
# TODO: this is very sensitive to the exact correct choice of
# adapter. For example, if you specifiy GATCGGAA... and the correct
# adapter is AGATCGGAA..., the prefixes will not match exactly and
# the alignment will fail. We need to use a comparison that is a bit
# more forgiving.
a1_match = compare_prefixes(seq1[insert_match_size:],
self.adapter1,
wildcard_ref=self.adapter_wildcards,
wildcard_query=self.read_wildcards)
a2_match = compare_prefixes(seq2[insert_match_size:],
self.adapter2,
wildcard_ref=self.adapter_wildcards,
wildcard_query=self.read_wildcards)
adapter_len = min(offset, self.adapter1_len, self.adapter2_len)
max_adapter_mismatches = round(adapter_len *
self.max_adapter_mismatch_frac)
if (a1_match[5] > max_adapter_mismatches
and a2_match[5] > max_adapter_mismatches):
return None
a1_prob = self.match_probability(a1_match[4], adapter_len)
a2_prob = self.match_probability(a2_match[4], adapter_len)
if ((adapter_len > self.adapter_check_cutoff)
and ((a1_prob * a2_prob) > self.adapter_max_rmp)):
return None
adapter_len1 = min(self.adapter1_len, len1 - insert_match_size)
adapter_len2 = min(self.adapter2_len, len2 - insert_match_size)
best_adapter_matches, best_adapter_mismatches = (
a1_match if a1_prob < a2_prob else a2_match)[4:6]
return (insert_match,
Match(0, adapter_len1, insert_match_size, len1,
best_adapter_matches, best_adapter_mismatches),
Match(0, adapter_len2, insert_match_size, len2,
best_adapter_matches, best_adapter_mismatches))
def _adapter_match(insert_seq, adapter_seq, adapter_len):
amatch = compare_prefixes(insert_seq[_insert_match_size:],
adapter_seq,
wildcard_ref=self.adapter_wildcards,
wildcard_query=self.read_wildcards)
alen = min(_offset, adapter_len)
return amatch, alen, round(alen *
self.max_adapter_mismatch_frac)
def compare_suffixes(suffix_ref,
suffix_query,
wildcard_ref=False,
wildcard_query=False):
"""Find out whether one string is the suffix of the other one, allowing
mismatches. Used to find an anchored 3' adapter when no indels are allowed.
Args:
suffix_ref, suffix_query: The suffices to compare.
wildcard_ref, wildcard_query: Whether wildcards are valid in either of
the suffices.
"""
suffix_ref = suffix_ref[::-1]
suffix_query = suffix_query[::-1]
_, length, _, _, matches, errors = compare_prefixes(
suffix_ref, suffix_query, wildcard_ref, wildcard_query)
return (len(suffix_ref) - length, len(suffix_ref),
len(suffix_query) - length, len(suffix_query), matches, errors)