def test_no_results_get_mRNA(self, mock_get_data):
data_from_transcript = "ptaki.lataja.kluczem.GACTGACTG"
mock_get_data.return_value = data_from_transcript
with self.assertRaises(errors.NoResultError):
ncbi_api.get_mRNA(self.GOOD_MRNA)
mock_get_data.assert_called_once_with(self.GOOD_MRNA)
def test_no_results_get_mRNA(self, mock_get_data):
data_from_transcript = 'ptaki.lataja.kluczem.GACTGACTG'
mock_get_data.return_value = data_from_transcript
with self.assertRaises(errors.NoResultError):
ncbi_api.get_mRNA(self.GOOD_MRNA)
mock_get_data.assert_called_once_with(self.GOOD_MRNA)
def test_get_mRNA(self, mock_get_data):
data_from_transcript = "ptaki.lataja.kluczem.mRNAGACTGACTG"
mock_get_data.return_value = data_from_transcript
expected_string = data_from_transcript.split("mRNA")[1]
data = ncbi_api.get_mRNA(self.GOOD_MRNA)
mock_get_data.assert_called_once_with(self.GOOD_MRNA)
self.assertEqual(expected_string, data)
def test_get_mRNA(self, mock_get_data):
data_from_transcript = 'ptaki.lataja.kluczem.mRNAGACTGACTG'
mock_get_data.return_value = data_from_transcript
expected_string = data_from_transcript.split('mRNA')[1]
data = ncbi_api.get_mRNA(self.GOOD_MRNA)
mock_get_data.assert_called_once_with(self.GOOD_MRNA)
self.assertEqual(expected_string, data)
def test_incorrect_get_mRNA(self, mock_get_data):
with self.assertRaises(errors.IncorrectDataError):
ncbi_api.get_mRNA(self.BAD_MNRA)
self.assertEqual(len(mock_get_data.mock_calls), 0)
def test_incorrect_get_mRNA(self, mock_get_data):
with self.assertRaises(errors.IncorrectDataError):
ncbi_api.get_mRNA(self.BAD_MNRA)
self.assertEqual(len(mock_get_data.mock_calls), 0)
def shmir_from_transcript_sequence(
transcript_name, minimum_CG, maximum_CG, maximum_offtarget, scaffold,
stimulatory_sequences
):
"""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
try:
stored_input = db_session.query(InputData).filter(
func.lower(InputData.transcript_name) == transcript_name.lower(),
InputData.minimum_CG == minimum_CG,
InputData.maximum_CG == maximum_CG,
InputData.maximum_offtarget == maximum_offtarget,
func.lower(InputData.scaffold) == scaffold.lower(),
func.lower(
InputData.stimulatory_sequences
) == stimulatory_sequences.lower()
).outerjoin(InputData.results).one()
except NoResultFound:
pass
else:
return [result.as_json() for result in stored_input.results]
# create path string
path = "_".join(
map(
str,
[transcript_name, minimum_CG, maximum_CG, maximum_offtarget,
scaffold, stimulatory_sequences]
)
)
mRNA = ncbi_api.get_mRNA(transcript_name)
if scaffold == 'all':
original_frames = db_session.query(Backbone).all()
else:
original_frames = db_session.query(Backbone).filter(
func.lower(Backbone.name) == scaffold.lower()
).all()
frames_by_name = {frame.name: frame for frame in original_frames}
patterns = {
frame.name: OrderedDict(
sorted(
json.loads(frame.regexp).items(),
reverse=True
)
) for frame in original_frames
}
best_sequences = defaultdict(list)
for name, patterns_dict in patterns.iteritems():
for regexp_type, sequences in find_by_patterns(patterns_dict, mRNA).iteritems():
with allow_join_result():
is_empty, sequences = generator_is_empty(sequences)
if not is_empty:
best_sequences[name] = remove_none(
group(
validate_and_offtarget.s(
sequence,
maximum_offtarget,
minimum_CG,
maximum_CG,
stimulatory_sequences,
int(regexp_type)
).set(queue="blast")
for sequence in sequences
).apply_async().get()
)
results = []
for name, seq_dict in unpack_dict_to_list(best_sequences):
if len(results) == 20:
break
with allow_join_result():
shmir_result = shmir_from_fasta_string.s(
seq_dict['sequence'],
[frames_by_name[name]],
seq_dict['offtarget'],
seq_dict['regexp'],
path
).set(queue="score").apply_async().get()
if shmir_result:
results.extend(shmir_result)
if not results:
best_sequences = []
sequences = all_possible_sequences(mRNA, 19, 21)
with allow_join_result():
is_empty, sequences = generator_is_empty(sequences)
if not is_empty:
best_sequences = remove_none(
group(
validate_and_offtarget.s(
sequence,
maximum_offtarget,
minimum_CG,
maximum_CG,
stimulatory_sequences,
0
).set(queue="blast")
for sequence in sequences
).apply_async().get()
)
if best_sequences:
with allow_join_result():
results = chain(*remove_none(
group(
shmir_from_fasta_string.s(
seq_dict['sequence'], original_frames,
seq_dict['offtarget'], seq_dict['regexp'], path
).set(queue="score")
for seq_dict in best_sequences
).apply_async().get()
))
sorted_results = sorted(
results,
key=operator.itemgetter(0),
reverse=True
)[:10]
db_results = [Result(
score=score,
sh_mir=shmir,
pdf=path_id,
backbone=frames_by_name[frame_name].id,
sequence=found_sequences[0],
) for score, shmir, frame_name, path_id, found_sequences in sorted_results]
remove_bad_foldings(path, (result.get_task_id() for result in db_results))
db_input = InputData(
transcript_name=transcript_name,
minimum_CG=minimum_CG,
maximum_CG=maximum_CG,
maximum_offtarget=maximum_offtarget,
scaffold=scaffold,
stimulatory_sequences=stimulatory_sequences,
results=db_results
)
db_session.add(db_input)
db_session.add_all(db_results)
db_session.commit()
return [result.as_json() for result in db_results]
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]
