def test_find_by_patterns(self):
patterns = {3: 'a', 2: 'bc'}
result = find_by_patterns(patterns, 'abcd')
self.assertEqual(list(result[3]), list(patterns[3]))
self.assertEqual(list(result[2]), list(patterns[2]))
def shmir_from_transcript_sequence(
transcript_name, minimum_CG, maximum_CG, maximum_offtarget, scaffold, immunostimulatory
):
"""Generating function of shmir from transcript sequence.
Args:
transcript_name(str): Name of transcipt.
minimum_CG(int): Minimum number of 'C' and 'G' nucleotide in sequence.
maximum_CG(int): Maximum number of 'C' and 'G' nucleotide in sequence.
maximum_offtarget(int): Maximum offtarget.
scaffold(str): Name of frame of miRNA or 'all'.
stimulatory_sequences(str): One of 'yes', 'no', 'no_difference'.
Returns:
list of sh-miR(s).
"""
# check if results are in database
results = get_results(transcript_name, minimum_CG, maximum_CG, maximum_offtarget, scaffold, immunostimulatory)
# sometimes results is an empty list
if results is not None:
return results
path = create_path_string(transcript_name, minimum_CG, maximum_CG, maximum_offtarget, scaffold, immunostimulatory)
mRNA = ncbi_api.get_mRNA(transcript_name)
reversed_mRNA = reverse_complement(mRNA)
original_frames = frames_by_scaffold(scaffold)
frames_by_name = {frame.name: frame for frame in original_frames}
# best patters should be choosen first
patterns = {
frame.name: OrderedDict(sorted(json.loads(frame.regexp).items(), reverse=True)) for frame in original_frames
}
with allow_join_result():
validated = (
group(
validate_sequences.s(
list(sequences), # generators are not serializable
regexp_type,
name,
minimum_CG,
maximum_CG,
maximum_offtarget,
immunostimulatory,
).set(queue="score")
for name, patterns_dict in patterns.iteritems()
for regexp_type, sequences in find_by_patterns(patterns_dict, reversed_mRNA).iteritems()
)
.apply_async()
.get()
)
best_sequences = merge_results(validated)
with allow_join_result():
results = (
group(
shmir_from_fasta.s(
siRNA["sequence"], siRNA["offtarget"], siRNA["regexp"], [frames_by_name[name]], path
).set(queue="score")
for name, siRNA in unpack_dict_to_list(best_sequences)
)
.apply_async()
.get()
)
# merge
results = list(chain(*results))
if not results:
with allow_join_result():
validated = (
validate_sequences.s(
list(all_possible_sequences(reversed_mRNA, 21)), # not serializable
0,
"all",
minimum_CG,
maximum_CG,
maximum_offtarget,
immunostimulatory,
)
.apply_async(queue="subtasks")
.get()
)
best_sequences = merge_results([validated])
with allow_join_result():
results = (
group(
shmir_from_fasta.s(
siRNA["sequence"], siRNA["offtarget"], siRNA["regexp"], original_frames, path
).set(queue="score")
for name, siRNA in unpack_dict_to_list(best_sequences)
)
.apply_async()
.get()
)
# merge
results = chain(*results)
sorted_results = sorted(results, key=lambda result: result["score"]["all"], reverse=True)[:TRANSCRIPT_RESULT_LIMIT]
db_results = store_results(
transcript_name, minimum_CG, maximum_CG, maximum_offtarget, scaffold, immunostimulatory, sorted_results
)
remove_bad_foldings(path, [result.get_task_id() for result in db_results])
return [result.as_json() for result in db_results]
