def expectedOutcomes(self, search_results, expected_outcomes):
best_from_grouped_results = [
get_best_match_in_group(group)
for group in group_matches(search_results)
]
best_from_grouped_exepected_outcomes = [
get_best_match_in_group(group)
for group in group_matches(expected_outcomes)
]
return self.assertEqual(best_from_grouped_results,
best_from_grouped_exepected_outcomes)
def expectedOutcomes(self, search_results, expected_outcomes, *args, **kwargs):
best_from_grouped_results = [
get_best_match_in_group(group)
for group in group_matches(search_results)
]
best_from_grouped_exepected_outcomes = [
get_best_match_in_group(group)
for group in group_matches(expected_outcomes)
]
return self.assertEqual(best_from_grouped_results,
best_from_grouped_exepected_outcomes,
*args, **kwargs)
def trim_primer(
seq_record: SeqIO.SeqRecord,
primer_seqs: List[str],
max_mismatch: Union[float, int] = 0.14,
) -> SeqIO.SeqRecord:
"""
Trim primer sequences.
Parameters
----------
seq_record : Bio.Seq.SeqRecord
input sequence record
primer_seqs : list
list of the foward and reverse primer sequnces
max_mismatch : float
Maximum number (or proportion) of mismatches allowed for searching primer
sequeces (default: 0.14)
"""
seq = seq_record.seq
fwd, rev = primer_seqs
rev_rc = revc(rev)
len_fwd, len_rev = len(fwd), len(rev)
if max_mismatch > 1:
max_l_dist1 = max_l_dist2 = max_mismatch
elif max_mismatch > 0:
max_l_dist1 = round(len_fwd * max_mismatch)
max_l_dist2 = round(len_rev * max_mismatch)
else:
raise ValueError("max_mismatch must be a positive value")
m0 = find_near_matches(fwd, str(seq), max_l_dist=max_l_dist1)
m1 = find_near_matches(rev_rc, str(seq), max_l_dist=max_l_dist2)
if len(m0) > 0:
match_fwd = get_best_match_in_group(m0)
if len(m1) > 0:
match_rev_rc = get_best_match_in_group(m1)
if len(m0) > 0 and len(m1) > 0:
tr = seq_record[match_fwd.end : match_rev_rc.start]
elif len(m0) > 0:
tr = seq_record[match_fwd.end :]
elif len(m1) > 0:
tr = seq_record[: match_rev_rc.start]
else:
tr = seq_record[:]
return tr
def find_near_matches_levenshtein(subsequence, sequence, max_l_dist):
"""Find near-matches of the subsequence in the sequence.
This chooses a suitable fuzzy search implementation according to the given
parameters.
Returns a list of fuzzysearch.Match objects describing the matching parts
of the sequence.
"""
if not subsequence:
raise ValueError('Given subsequence is empty!')
if max_l_dist < 0:
raise ValueError('Maximum Levenshtein distance must be >= 0!')
if max_l_dist == 0:
return [
Match(start_index, start_index + len(subsequence), 0)
for start_index in search_exact(subsequence, sequence)
]
elif len(subsequence) // (max_l_dist + 1) >= 3:
return find_near_matches_levenshtein_ngrams(subsequence, sequence,
max_l_dist)
else:
matches = find_near_matches_levenshtein_linear_programming(
subsequence, sequence, max_l_dist)
match_groups = group_matches(matches)
best_matches = [
get_best_match_in_group(group) for group in match_groups
]
return sorted(best_matches)
def expectedOutcomes(self, search_result, expected_outcomes, *args,
**kwargs):
best_from_groups = [
get_best_match_in_group(group)
for group in group_matches(search_result)
]
self.assertEqual(search_result, best_from_groups, *args, **kwargs)
def expectedOutcomes(self, search_result, expected_outcomes,
*args, **kwargs):
best_from_groups = [
get_best_match_in_group(group)
for group in group_matches(search_result)
]
self.assertEqual(search_result, best_from_groups, *args, **kwargs)
def search(self, subsequence, sequence, max_subs):
return [
get_best_match_in_group(group) for group in group_matches(
c_fnm_generic_ngrams(
subsequence, sequence,
LevenshteinSearchParams(max_subs, 0, 0, max_subs)))
]
def find_near_matches_substitutions_ngrams(subsequence, sequence,
max_substitutions):
if not (
isinstance(subsequence, text_type) or
isinstance(sequence, text_type)
):
try:
results = _subs_only_fnm_ngram_byteslike(
subsequence, sequence, max_substitutions)
except TypeError:
pass
else:
matches = [
Match(
index,
index + len(subsequence),
count_differences_with_maximum(
sequence[index:index+len(subsequence)],
subsequence,
max_substitutions + 1,
),
)
for index in results
]
return [
get_best_match_in_group(group)
for group in group_matches(matches)
]
return py_find_near_matches_substitutions_ngrams(
subsequence, sequence, max_substitutions)
def search(self, subsequence, sequence, max_l_dist):
return [
get_best_match_in_group(group) for group in group_matches(
fnm_generic_lp(
subsequence, sequence,
LevenshteinSearchParams(max_l_dist, max_l_dist, max_l_dist,
max_l_dist)))
]
def search(self, subsequence, sequence, max_l_dist):
return [
get_best_match_in_group(group)
for group in group_matches(
c_fnm_generic_lp(subsequence,
sequence,
LevenshteinSearchParams(max_l_dist, max_l_dist, max_l_dist, max_l_dist))
)
]
def search(self, subsequence, sequence, max_subs):
if max_subs >= len(subsequence):
self.skipTest("avoiding calling c_fnm_generic_ngrams() " +
"with max_subs >= len(subsequence)")
return [
get_best_match_in_group(group) for group in group_matches(
c_fnm_generic_ngrams(
subsequence, sequence,
LevenshteinSearchParams(max_subs, 0, 0, max_subs)))
]
def expectedOutcomes(self, search_results, expected_outcomes, *args, **kwargs):
consolidated_results = [
get_best_match_in_group(group)
for group in group_matches(search_results)
]
consolidated_expected_outcomes = \
consolidate_overlapping_matches(expected_outcomes)
return self.assertEqual(consolidated_results,
consolidated_expected_outcomes,
*args, **kwargs)
def search(self, subsequence, sequence, max_subs):
if max_subs >= len(subsequence):
self.skipTest("avoiding calling c_fnm_generic_ngrams() " +
"with max_subs >= len(subsequence)")
return [
get_best_match_in_group(group)
for group in group_matches(
c_fnm_generic_ngrams(subsequence,
sequence,
LevenshteinSearchParams(max_subs, 0, 0, max_subs))
)
]
def search(self, pattern, sequence, max_subs, max_ins, max_dels,
max_l_dist=None):
return [
get_best_match_in_group(group)
for group in group_matches(
c_fnm_generic_ngrams(pattern,
sequence,
LevenshteinSearchParams(
max_subs, max_ins,
max_dels, max_l_dist,
))
)
]
def find_near_matches_levenshtein_ngrams(subsequence, sequence, max_l_dist):
subseq_len = len(subsequence)
seq_len = len(sequence)
ngram_len = subseq_len // (max_l_dist + 1)
if ngram_len == 0:
raise ValueError(
'the subsequence length must be greater than max_l_dist')
matches = []
for ngram_start in xrange(0, subseq_len - ngram_len + 1, ngram_len):
ngram_end = ngram_start + ngram_len
subseq_before_reversed = subsequence[:ngram_start][::-1]
subseq_after = subsequence[ngram_end:]
start_index = max(0, ngram_start - max_l_dist)
end_index = min(seq_len, seq_len - subseq_len + ngram_end + max_l_dist)
for index in search_exact(subsequence[ngram_start:ngram_end], sequence,
start_index, end_index):
# try to expand left and/or right according to n_ngram
dist_right, right_expand_size = _expand(
subseq_after,
sequence[index + ngram_len:index - ngram_start + subseq_len +
max_l_dist],
max_l_dist,
)
if dist_right is None:
continue
dist_left, left_expand_size = _expand(
subseq_before_reversed,
sequence[max(0, index - ngram_start -
(max_l_dist - dist_right)):index][::-1],
max_l_dist - dist_right,
)
if dist_left is None:
continue
assert dist_left + dist_right <= max_l_dist
matches.append(
Match(
start=index - left_expand_size,
end=index + ngram_len + right_expand_size,
dist=dist_left + dist_right,
))
# don't return overlapping matches; instead, group overlapping matches
# together and return the best match from each group
match_groups = group_matches(matches)
best_matches = [get_best_match_in_group(group) for group in match_groups]
return sorted(best_matches)
def search(self, subsequence, sequence, max_subs):
results = fnm_subs_ngrams_byteslike(subsequence, sequence,
max_subs)
matches = [
Match(index,
index + len(subsequence),
count_differences_with_maximum(
sequence[index:index + len(subsequence)],
subsequence,
max_subs + 1,
),
matched=sequence[index:index + len(subsequence)])
for index in results
]
return [
get_best_match_in_group(group)
for group in group_matches(matches)
]
def search(self,
pattern,
sequence,
max_subs,
max_ins,
max_dels,
max_l_dist=None):
return [
get_best_match_in_group(group) for group in group_matches(
c_fnm_generic_ngrams(
pattern, sequence,
LevenshteinSearchParams(
max_subs,
max_ins,
max_dels,
max_l_dist,
)))
]
def search(self, subsequence, sequence, max_subs):
results = fnm_subs_ngrams_byteslike(subsequence, sequence,
max_subs)
matches = [
Match(
index,
index + len(subsequence),
count_differences_with_maximum(
sequence[index:index+len(subsequence)],
subsequence,
max_subs + 1,
),
)
for index in results
]
return [
get_best_match_in_group(group)
for group in group_matches(matches)
]
def find_near_matches_generic_ngrams(subsequence, sequence, search_params):
"""search for near-matches of subsequence in sequence
This searches for near-matches, where the nearly-matching parts of the
sequence must meet the following limitations (relative to the subsequence):
* the maximum allowed number of character substitutions
* the maximum allowed number of new characters inserted
* and the maximum allowed number of character deletions
* the total number of substitutions, insertions and deletions
"""
if not subsequence:
raise ValueError('Given subsequence is empty!')
matches = list(
_find_near_matches_generic_ngrams(subsequence, sequence,
search_params))
# don't return overlapping matches; instead, group overlapping matches
# together and return the best match from each group
match_groups = group_matches(matches)
best_matches = [get_best_match_in_group(group) for group in match_groups]
return sorted(best_matches)
def find_near_matches_generic(subsequence, sequence, search_params):
"""search for near-matches of subsequence in sequence
This searches for near-matches, where the nearly-matching parts of the
sequence must meet the following limitations (relative to the subsequence):
* the maximum allowed number of character substitutions
* the maximum allowed number of new characters inserted
* and the maximum allowed number of character deletions
* the total number of substitutions, insertions and deletions
"""
if not subsequence:
raise ValueError('Given subsequence is empty!')
# if the limitations are so strict that only exact matches are allowed,
# use search_exact()
if search_params.max_l_dist == 0:
return [
Match(start_index, start_index + len(subsequence), 0)
for start_index in search_exact(subsequence, sequence)
]
# if the n-gram length would be at least 3, use the n-gram search method
elif len(subsequence) // (search_params.max_l_dist + 1) >= 3:
return find_near_matches_generic_ngrams(subsequence, sequence,
search_params)
# use the linear programming search method
else:
matches = find_near_matches_generic_linear_programming(
subsequence, sequence, search_params)
match_groups = group_matches(matches)
best_matches = [
get_best_match_in_group(group) for group in match_groups
]
return sorted(best_matches)
def search(self, subsequence, sequence, max_l_dist):
return [
get_best_match_in_group(group) for group in group_matches(
fnm_levenshtein_lp(subsequence, sequence, max_l_dist))
]
