def compile_primers(primer_alis, name_base, reverse=False): primers = [] if reverse: for pos, ali in primer_alis: primers.append( Primer.from_sequences(ali, 1, '%sR%d' % (name_base, pos))) else: for pos, ali in primer_alis: primers.append( Primer.from_sequences(ali, 1, '%sF%d' % (name_base, pos))) return primers
def compile_pairs(falis, ralis, min_len, name_base): pairs = [] for _i, (fs, fp) in enumerate(falis): fprimer = Primer.from_sequences(fp, 1, '%sF%d' % (name_base, fs)) for _j, (rs, rp) in enumerate(ralis): if rs - fs <= min_len: continue pairs.append( PrimerPair( fprimer, Primer.from_sequences(rp, 1, '%sR%d' % (name_base, rs)))) return pairs
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'