def _process_genome(self, gi, recs):
record = recs[gi]
clusters = []
for tag in self.tags:
tag_clusters = []
for f in record.features:
# cluster annotation
q = f.qualifiers.get(ClusterFinder.tag_qualifier)
if not q: continue
if tag != ' '.join(q): continue
cluster = f.extract(record)
copy_attrs(record, cluster)
if tag_clusters: cluster.description += ' cluster %d' % (len(tag_clusters)+1)
cluster = _DiagramCluster(cluster, f.location)
cluster.set_genes(f.qualifiers.get(ClusterFinder.genes_qualifier, []))
cluster.marked = record.id in self.marks
tag_clusters.append(cluster)
if tag_clusters: clusters += tag_clusters
return clusters
def add_primers_to_alignment(primers, alignment, reverse=False):
alignment = alignment.clone()
ali_len = alignment.get_alignment_length()
if reverse:
for p in primers:
alignment.append(
copy_attrs(p.master_sequence,
p.master_sequence.reverse_complement()) + '-' *
(ali_len - len(p)))
else:
for p in primers:
alignment.append(p.master_sequence + '-' * (ali_len - len(p)))
return AlignmentUtils.align(alignment)
def add_pairs_to_alignment(pairs, alignment):
added = set()
alignment = alignment.clone()
ali_len = alignment.get_alignment_length()
for i, p in enumerate(pairs):
if p.forward.id not in added:
alignment.append(p.forward.master_sequence + '-' *
(ali_len - len(p.forward)))
added.add(p.forward.id)
if p.reverse.id not in added:
alignment.append(
copy_attrs(p.reverse.master_sequence,
p.reverse.master_sequence.reverse_complement())
+ '-' * (ali_len - len(p.reverse)))
added.add(p.reverse.id)
return AlignmentUtils.align(alignment)
def reverse_complement(self):
return AlignmentExt((copy_attrs(s, s.reverse_complement())
for s in self), self._alphabet)
def _main(self):
min_prod = 400
silva_db = '/home/allis/Documents/INMI/SILVA-DB/SILVA_123_SSURef_Nr99_tax_silva.fasta'
alifile = '/home/allis/Documents/INMI/SunS-metagenome/Bathy/BA2_SunS_16S.aln.fasta'
add_filename = FilenameParser.strip_ext(alifile)+'.with_additions.fasta'
outgroups = ['Thermococcus_chitonophagus', 'SMTZ1-55', 'contig72135_1581_sunspring_meta']
add = ['KF836721.1.1270','EU635905.1.1323']
exclude = []#['Thermococcus_chitonophagus', 'SMTZ1-55', 'BA1-16S', 'contig72135_1581_sunspring_meta']
#load alignment
if os.path.isfile(add_filename):
alifile = add_filename
add_filename = ''
with user_message('Loadding initial alignment...', '\n'):
orig_ali = AlignmentUtils.load_first(alifile)
if not orig_ali: return 1
#load homologs
if add_filename:
with user_message('Loadding additional sequences...', '\n'):
add_seqs = []
db = SeqView()
if db.load(silva_db):
for sid in add:
seq = db.get(sid)
if seq: add_seqs.append(seq)
else: print '%s not found in %s' % (sid, silva_db)
#realign data if needed
if add_seqs:
with user_message('Realigning data...', '\n'):
add_filename = FilenameParser.strip_ext(alifile)+'.with_additions.fasta'
AlignmentUtils.align(list(orig_ali)+add_seqs, add_filename)
orig_ali = AlignmentUtils.load_first(add_filename)
if not orig_ali: return 2
#process the alignment
ali = orig_ali.remove(*exclude).trim()
for out in outgroups:
if not ali.index(out):
print '%s not found in the alignment' % out
return 3
ali.sort(key=lambda r: 'zzzzzzzz' if r.id in outgroups else r.id)
ali_len = ali.get_alignment_length()
AlignmentUtils.save(ali, '/home/allis/Documents/INMI/SunS-metagenome/Bathy/BA2_SunS_16S.aln.trimmed.fasta')
args = dict(plen = (20,40),
max_mismatches = 8,
min_match_mismatches = 1,
first_match_mismatches = 1,
first_may_match = 1,
AT_first=True,
outgroup=len(outgroups))
fprimers = self._find_primers(ali, **args)
rprimers = self._find_primers(ali.reverse_complement(), **args)
pairs = []
for i, (fs, fp) in enumerate(fprimers):
start = fs
fprimer = Primer.from_sequences(fp[:-1], 1, 'SSBaF%d' % fs)
for _j, (rs, rp) in enumerate(rprimers):
end = ali_len-rs
if end-start <= min_prod: continue
pairs.append((fprimer, Primer.from_sequences(rp[:-1], 1, 'SSBaR%d' % (ali_len-rs+1))))
if not pairs:
print '\nNo suitable primer pairs found'
return 3
added = set()
for i, (fp, rp) in enumerate(pairs):
print '\npair %d' % (i+1)
print '%s: %s' % (fp.id, fp)
print '%s: %s' % (rp.id, rp)
if fp.id not in added:
orig_ali.append(fp.master_sequence+'-'*(orig_ali.get_alignment_length()-len(fp)))
added.add(fp.id)
if rp.id not in added:
orig_ali.append(copy_attrs(rp.master_sequence,
rp.master_sequence.reverse_complement())+
'-'*(orig_ali.get_alignment_length()-len(rp)))
added.add(rp.id)
print
orig_ali = AlignmentUtils.align(orig_ali)
AlignmentUtils.save(orig_ali, '/home/allis/Documents/INMI/SunS-metagenome/Bathy/BA2_SunS_16S.with_primers.aln.fasta')
print 'Done'
def reverse_complement(self):
return AlignmentExt((copy_attrs(s, s.reverse_complement())
for s in self), self._alphabet)
