def blastn_annotate(self, tag_sequences, subject_record, min_identity, evalue=0.001, **kwargs):
results = self.s2s_blast_batch(tag_sequences, [subject_record], evalue=evalue, command='blastn', **kwargs)
if results is None: return False
with user_message('Adding results as annotations...'):
annotated = False
for i, tag in enumerate(tag_sequences):
if not results[i]: continue
record = results[i][0]
if not record: continue
tag_name = pretty_rec_name(tag)
if tag_name != tag.id:
tag_name += ' (%s)' % tag.id
for hit in record:
for ali in hit.alignments:
for hsp in ali.hsps:
if hsp.identities / float(hsp.align_length) < min_identity: continue
strand = 1 if hsp.sbjct_start < hsp.sbjct_end else -1
if strand == 1:
location = FeatureLocation(hsp.sbjct_start-1,
hsp.sbjct_end,
strand)
else:
location = FeatureLocation(hsp.sbjct_end-1,
hsp.sbjct_start,
strand)
feature = self.hsp2feature(tag_name,'blastn_annotations', location, hsp)
self.add_program(feature, 'blastn')
subject_record.features.append(feature)
annotated = True
return annotated
def _find_matches(self, seq_files, seq_id):
if not self._load_db(seq_files):
print 'No templates were loaded from: %s' % str(seq_files)
return False
if self.aborted(): return False
template = self._seq_db[seq_id]
self._seq_name = pretty_rec_name(template)
self._matches_list = self._searcher.find_matches(
WorkCounter(), template, self._max_mismatches,
self._PCR_ProductsFinder)
return self._matches_list is not None
def _find_matches(self, seq_files, seq_id):
if not self._load_db(seq_files):
print 'No templates were loaded from: %s' % str(seq_files)
return False
if self.aborted(): return False
template = self._seq_db[seq_id]
self._seq_name = pretty_rec_name(template)
self._matches_list = self._searcher.find_matches(WorkCounter(),
template,
self._max_mismatches,
self._PCR_ProductsFinder)
return self._matches_list is not None
def worker(template):
search_results = []
for primer in self._primers:
matches = self._searcher.find_matches(WorkCounter(), template, primer, mismatches)
if not matches: continue
duplexes = self._searcher.compile_duplexes(WorkCounter(), *matches)
if duplexes: search_results.append(duplexes)
if not search_results: return None
all_annealings = self._combine_annealings(*search_results)
tname = pretty_rec_name(template)
mixture = self.create_PCR_mixture(WorkCounter(), tname, all_annealings[0], all_annealings[1])
if not mixture: return None
return tname, mixture.save()
def fetchMore(self, index=QModelIndex()):
start = len(self._rows)
end = start + min(len(self._db) - start, self.rows_to_load)
self.beginInsertRows(QModelIndex(), start, end - 1)
self._rows.extend((sid, pretty_rec_name(self._db[sid]))
for sid in self._db.keys()[start:end])
self.endInsertRows()
if self._to_select and start <= self._to_select[0]:
selected = 0
for row in self._to_select:
if row >= end: break
self.select_row.emit(row)
selected += 1
self._to_select = self._to_select[selected:]
def _blast_feature(self, f, c1, c2, features1, features2, evalue,
max_rlen):
trans = Translator(self._abort_event)
cds = trans.translate(f.extract(c1), 11)
sixframes = trans.translate_six_frames_single(c2, 11)
if not sixframes: return [(None, None, None)]
results = []
for frame in sixframes:
res = BlastCLI.s2s_blast(cds,
frame,
evalue,
command='blastp',
task='blastp')
if res: results.extend(res)
hsps = BlastCLI.all_hsps(results, max_rlen)
if not hsps: return [(None, None, None)]
f1 = []
f2 = []
col = []
c1_name = pretty_rec_name(c1)
if 'locus_tag' in f.qualifiers:
fname = f.qualifiers['locus_tag'][0]
else:
fname = 'CDS'
cds_len = len(cds)
for hsp in hsps:
color_t = (float(hsp.identities) / hsp.align_length)
print '%s %s: %5.1f%% (%5.1f%%)' % (c1_name, fname, color_t * 100,
float(hsp.identities) /
cds_len * 100)
col.append(
colors.linearlyInterpolatedColor(colors.Color(0, 0, 1, 0.2),
colors.Color(0, 1, 0, 0.2),
0.2, 1, color_t))
qstart = (hsp.query_start - 1) * 3
qend = qstart + hsp.align_length * 3
sstart = (hsp.sbjct_start - 1) * 3
send = sstart + hsp.align_length * 3
f1.append(
SeqFeature(
FeatureLocation(f.location.start + qstart,
f.location.start + qend,
strand=hsp.strand[0])))
f2.append(
SeqFeature(FeatureLocation(sstart, send,
strand=hsp.strand[1])))
return zip(f1, f2, col)
def find(self, counter, template, mismatches):
all_annealings = []
counter.set_subwork(self._num_p+1,
self._p_weights+[0.01*self._pw_sum])
for i, primer in enumerate(self._primers):
if self.aborted(): return None
annealings = self._searcher.find(counter[i], template, primer, mismatches)
if annealings is None: continue
all_annealings.append(annealings)
if not all_annealings: return None
tname = pretty_rec_name(template)
mixture = self.create_PCR_mixture(counter[-1], tname,
*self._extract_annealings(*all_annealings))
cleanup_files(all_annealings)
counter.done()
if not mixture: return None
return {tname: mixture.save()}
def worker(template):
search_results = []
for primer in self._primers:
matches = self._searcher.find_matches(WorkCounter(), template,
primer, mismatches)
if not matches: continue
duplexes = self._searcher.compile_duplexes(
WorkCounter(), *matches)
if duplexes: search_results.append(duplexes)
if not search_results: return None
all_annealings = self._combine_annealings(*search_results)
tname = pretty_rec_name(template)
mixture = self.create_PCR_mixture(WorkCounter(), tname,
all_annealings[0],
all_annealings[1])
if not mixture: return None
return tname, mixture.save()
def find(self, counter, template, mismatches):
all_annealings = []
counter.set_subwork(self._num_p + 1,
self._p_weights + [0.01 * self._pw_sum])
for i, primer in enumerate(self._primers):
if self.aborted(): return None
annealings = self._searcher.find(counter[i], template, primer,
mismatches)
if annealings is None: continue
all_annealings.append(annealings)
if not all_annealings: return None
tname = pretty_rec_name(template)
mixture = self.create_PCR_mixture(
counter[-1], tname, *self._extract_annealings(*all_annealings))
cleanup_files(all_annealings)
counter.done()
if not mixture: return None
return {tname: mixture.save()}
def blastp_annotate(self, tag_sequences, subject_record, min_identity, evalue=0.001, table=11, **kwargs):
# translate subject in six frames
with user_message('Translating whole genome in 6 reading frames', '\n'):
translator = Translator(self._abort_event)
translation = translator.translate_six_frames(subject_record, table)
if not translation: return False
results = self.s2s_blast_batch(tag_sequences, translation, evalue=evalue, command='blastp', **kwargs)
if results is None: return False
with user_message('Adding results as annotations...'):
annotated = False
subj_len = len(subject_record)
for i, tag in enumerate(tag_sequences):
if not results[i]: continue
tag_name = pretty_rec_name(tag)
if tag_name != tag.id:
tag_name += ' (%s)' % tag.id
for frame, record in enumerate(results[i]):
if not record: continue
frec = translation[frame]
start = frec.annotations['start']
strand = frec.annotations['strand']
for hit in record:
for ali in hit.alignments:
for hsp in ali.hsps:
if hsp.identities / float(hsp.align_length) < min_identity: continue
if strand == 1:
location = FeatureLocation(start+(hsp.sbjct_start-1)*3,
start+hsp.sbjct_end*3,
strand)
else:
location = FeatureLocation(subj_len-start-hsp.sbjct_end*3,
subj_len-start-hsp.sbjct_start*3,
strand)
feature = self.hsp2feature(tag_name, 'blastp_annotations', location, hsp)
self.add_program(feature, 'blastp')
subject_record.features.append(feature)
annotated = True
return annotated
def _main(self):
email = '*****@*****.**'
genome_dir = '/home/allis/Dropbox/Science/Микра/Thermococcus/sequence/GenBank/Thermococcales/Thermococcus/'
genome = 'Thermococcus_barophilus_Ch5.gb'
gene = 'TBCH5v1_1369' #cooS
database = 'nr'
segment = [3200, 12000]
seq = SeqLoader.load_file(os.path.join(genome_dir, genome))
if not seq: raise RuntimeError('No genome loaded')
seq = seq[0]
index = get_indexes_of_genes(seq, gene)
if not index: raise RuntimeError('No gene found')
feature = seq.features[index[0]]
query = feature.extract(seq)
segments_file = 'CO-clusters.gb'
#get cluster variants if needed
if not os.path.isfile(segments_file):
blast_file = 'blast.results.xml'
if os.path.isfile(blast_file):
blast = list(parse(open(blast_file)))
else:
blast = BlastCLI.blast_seq(query,
database,
100,
remote=True,
task='blastn',
parse_results=True,
save_results_to='blast.results.xml')
if not blast: raise RuntimeError('Blast returned no results')
flt = BlastFilter(lambda hsp, r: hsp.align_length > 700,
filter_hsps=True)
flt(blast)
queries = []
for ali in BlastCLI.iter_alignments(blast):
q = BlastCLI.Query(ali,
'hsp',
start_offset=segment[0],
end_offset=segment[1])
if q: queries.append(q)
print(queries[-1])
segments = BlastWWW.fetch_queries(email, queries)
safe_write(segments, segments_file)
for r in segments:
print('[%s] %s: %dbp' % (r.id, pretty_rec_name(r), len(r)))
return 0
#find primers in alignments of the selected features
local_files = [
os.path.join(genome_dir, f)
for f in ('Thermococcus_barophilus_DT4-complete-genome.gb',
'Thermococcus_ST-423.gb', 'Thermococcus_CH1-complete.gb')
]
loader = SeqLoader(self.abort_event)
segments = loader.load_files([segments_file] + local_files)
fprimers, transF_ali = find_primers(
segments, 'transF',
dict(plen=(20, 30),
max_mismatches=5,
min_first_matches=3,
AT_first=True))
rprimers, cooS_ali = find_primers(segments,
'cooS',
dict(plen=(20, 30),
max_mismatches=4,
min_first_matches=3,
AT_first=True),
reverse=True)
if not fprimers:
print('\nNo forward primers found')
return 1
if not rprimers:
print('\nNo reverse primers found')
return 1
print('\nForward primers:')
for p in fprimers:
print('%s: %s' % (p.id, p))
print('\nReverse primers:')
for p in rprimers:
print('%s: %s' % (p.id, p))
print()
#add primers to alignments and save them
transF_ali = PrimerFinder.add_primers_to_alignment(
fprimers, transF_ali)
cooS_ali = PrimerFinder.add_primers_to_alignment(rprimers,
cooS_ali,
reverse=True)
AlignmentUtils.save(transF_ali, 'transF.aln')
AlignmentUtils.save(cooS_ali, 'cooS.aln')
