def extend_simple_core(analyzed_hits, query, args_inner, all_short,
multi_query, iteration, ih_model):
# the extra here is given "pro forma" the sequence is extended exactly by lenghts of unaligned portions of query
if args_inner.db_type == "blastdb":
shorts_expanded, _ = rna_blast_analyze.BR_core.extend_hits.expand_hits(
all_short,
args_inner.blast_db,
len(query),
extra=0,
blast_regexp=args_inner.blast_regexp,
skip_missing=args_inner.skip_missing,
msgs=analyzed_hits.msgs,
)
elif args_inner.db_type in ["fasta", "gb", "server", "entrez"]:
shorts_expanded, _ = rna_blast_analyze.BR_core.extend_hits.expand_hits_from_fasta(
all_short,
args_inner.blast_db,
len(query),
extra=0,
blast_regexp=args_inner.blast_regexp,
skip_missing=args_inner.skip_missing,
msgs=analyzed_hits.msgs,
format=args_inner.db_type,
entrez_email=args_inner.entrez,
blast_input_file=args_inner.blast_in,
)
else:
raise exceptions.IncorrectDatabaseChoice()
# check, if blast hits are non - overlapping, if so, add the overlapping hit info to the longer hit
# reflect this in user output
# shorts_expanded = merge_blast_hits(shorts_expanded)
shorts_expanded = trim_before(shorts_expanded)
shorts_expanded = BA_support.rc_hits_2_rna(shorts_expanded)
query_seq = query.seq.transcribe()
# blast only extension
for exp_hit in shorts_expanded:
try:
_out = create_blast_only_report_object(exp_hit, len(query_seq))
analyzed_hits.hits.append(_out)
except AssertionError as e:
exp_hit.annotations['msgs'] += [str(e)]
analyzed_hits.hits_failed.append(BA_support.Subsequences(exp_hit))
except exceptions.UnknownStrand as e:
exp_hit.annotations['msgs'] += [str(e)]
analyzed_hits.hits_failed.append(BA_support.Subsequences(exp_hit))
except Exception as e:
ml.error("Unexpected error when extending with 'simple'.")
exp_hit.annotations['msgs'] += [str(e)]
analyzed_hits.hits_failed.append(BA_support.Subsequences(exp_hit))
if len(analyzed_hits.hits) == 0:
ml.error(
"Extension failed for all sequences. Please see the error message. You can also try '--mode locarna'."
)
sys.exit(1)
# assign Locarna score to None as it is not directly accessible from mlocarna
for hit in analyzed_hits.hits:
hit.extension.annotations['score'] = None
# this part predicts homology - it is not truly part of repredict
homology_prediction, homol_seqs, cm_file_rfam_user = infer_homology(
analyzed_hits=analyzed_hits,
args=args_inner,
cm_model_file=ih_model,
multi_query=multi_query,
iteration=iteration)
for hit, pred in zip(analyzed_hits.hits, homology_prediction):
hit.hpred = pred
return analyzed_hits, homology_prediction, homol_seqs, cm_file_rfam_user
def extend_locarna_core(analyzed_hits, query, args_inner, all_short, multi_query, iteration, ih_model):
# expand hits according to query + 10 nucleotides +-
if args_inner.db_type == "blastdb":
shorts_expanded, _ = rna_blast_analyze.BR_core.extend_hits.expand_hits(
all_short,
args_inner.blast_db,
len(query),
extra=args_inner.subseq_window_locarna,
blast_regexp=args_inner.blast_regexp,
skip_missing=args_inner.skip_missing,
msgs=analyzed_hits.msgs,
)
elif args_inner.db_type in ["fasta", "gb", "server", "entrez"]:
shorts_expanded, _ = rna_blast_analyze.BR_core.extend_hits.expand_hits_from_fasta(
all_short,
args_inner.blast_db,
len(query),
extra=args_inner.subseq_window_locarna,
blast_regexp=args_inner.blast_regexp,
skip_missing=args_inner.skip_missing,
msgs=analyzed_hits.msgs,
format=args_inner.db_type,
entrez_email=args_inner.entrez,
blast_input_file=args_inner.blast_in,
)
else:
raise exceptions.IncorrectDatabaseChoice()
shorts_expanded = BA_support.rc_hits_2_rna(shorts_expanded)
query_seq = query.seq.transcribe()
# compute alignment here
if args_inner.threads == 1:
result = []
for oeh in shorts_expanded:
result.append(
locarna_worker(
(
oeh,
query_seq,
args_inner.locarna_params,
args_inner.locarna_anchor_length
)
)
)
else:
pack = []
for oeh in shorts_expanded:
pack.append(
(
oeh,
query_seq,
args_inner.locarna_params,
args_inner.locarna_anchor_length
)
)
pool = Pool(processes=args_inner.threads)
result = pool.map(locarna_worker, pack)
pool.close()
for res in result:
if res.extension is None:
analyzed_hits.hits_failed.append(res)
else:
analyzed_hits.hits.append(res)
# this part predicts homology - it is not truly part of repredict
homology_prediction, homol_seqs, cm_file_rfam_user = infer_homology(
analyzed_hits=analyzed_hits, args=args_inner, cm_model_file=ih_model, multi_query=multi_query,
iteration=iteration
)
# add homology prediction to the data
for hit, pred in zip(analyzed_hits.hits, homology_prediction):
hit.hpred = pred
return analyzed_hits, homology_prediction, homol_seqs, cm_file_rfam_user