def shmir_from_sirna_score(seq1, seq2, shift_left, shift_right):
"""Main function takes string input and returns the best results depending
on scoring. Single result include sh-miR sequence,
score and link to 2D structure from mfold program
Args:
input_str(str): Input string contains one or two sequences.
Returns:
List of sh-miR(s) sorted by score.
"""
original_frames = frames_by_scaffold('all')
frames = adjusted_frames(seq1, seq2,
shift_left, shift_right,
deepcopy(original_frames))
shmirs = [frame.template() for frame in frames]
# folding via mfold
with allow_join_result():
foldings = group(
fold.s(
shmir
).set(queue="subtasks") for shmir in shmirs
).apply_async().get()
# scoring results
with allow_join_result():
scores = group(
score_from_sirna.s(
frame,
original,
folding['ss']
).set(queue="subtasks")
for frame, original, folding in izip(frames, original_frames, foldings)
).apply_async().get()
full_reference = [
{
'score': score,
'shmir': shmir,
'scaffold_name': frame.name,
'pdf_reference': folding['path_id'],
'sequences': (frame.siRNA1, frame.siRNA2),
}
for score, shmir, frame, folding in izip(scores, shmirs, frames, foldings)
if score['all'] > 60
]
return sorted(
full_reference,
key=lambda elem: elem['score']['all'],
reverse=True
)[:SIRNA_RESULT_LIMIT]
def shmir_from_fasta(siRNA, offtarget, regexp, original_frames, prefix):
siRNA2 = reverse_complement(siRNA)
frames = adjusted_frames(siRNA, siRNA2, 0, 0, deepcopy(original_frames)) # we do not have shifts here
shmirs = [frame.template() for frame in frames]
with allow_join_result():
foldings = group(fold.s(shmir, prefix=prefix).set(queue="subtasks") for shmir in shmirs).apply_async().get()
results = []
iter_frames = izip(frames, original_frames, foldings)
for frame, original_frame, folding in iter_frames:
score = score_from_transcript(frame, original_frame, folding["ss"], offtarget, regexp)
if validate_transcript_by_score(score):
results.append({"score": score, "frame": frame, "folding": folding, "found_sequence": siRNA})
return results