## script to convert sets of fasta files to genbank format
import re
from sys import argv
from libs.common import from_dir, ensure_dir, load_fasta, write_genbank
from Bio.Alphabet import generic_dna
origin_dir = "data/"+argv[1]
destin_dir = "data/"+argv[2]+"/"
ensure_dir([destin_dir])
filenames = from_dir(origin_dir, re.compile(r'.*\.fas.*'))
for filename in filenames:
rec_name = filename[:filename.find('.fas')]
record = load_fasta(origin_dir+"/"+filename)
# make a genbank file of the contig
gbk_file = "".join([destin_dir, rec_name, ".gbk"])
record.name = rec_name
record.id = rec_name
record.seq.alphabet = generic_dna
write_genbank(gbk_file, record)
feature = SeqFeature(location=space_loc, type='contig',
id='ctg_'+str(order[0][0])+c_note, qualifiers=quals)
record.features.append(feature)
c_note = ''
for index in order[1:]:
filename = origin_dir+base_name+str(index[0])+".fas"
new_rec = load_fasta(filename)
if index[1]:
new_rec = new_rec.reverse_complement()
c_note = '_RC'
else:
c_note = ''
quals = {'locus_tag': 'ctg_'+str(index[0])+c_note}
space_loc = FeatureLocation(len(record.seq),
len(record.seq)+len(new_rec.seq))
feature = SeqFeature(location=space_loc, type='contig',
id='ctg_'+str(index[0])+c_note, qualifiers=quals)
record.features.append(feature)
record += new_rec
record += "NNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNN"
record.id = argv[2]
record.name = argv[2]
record.seq.alphabet = generic_dna
write_genbank(destin_file, record)
feature = SeqFeature(location=feat_loc,
strand=strand_pos,
id='cds_'+str(counter),
type='CDS',
qualifiers=quals)
record.features.append(feature)
counter +=1
# add annotations for Nx100 spacers
sequence = str(record.seq)
separator = "NNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNN"
regex = re.compile(separator, re.IGNORECASE)
spacers = [match.start() for match in regex.finditer(str(record.seq))]
#print spacers
for spacer in spacers:
space_loc = FeatureLocation(spacer, spacer+100)
feature = SeqFeature(location=space_loc,
type='spacer')
record.features.append(feature)
# save record with annotations
record.description = rec_name+"_with_ORFs"
record.name = rec_name
record.dbxrefs = ["Project: "+argv[1]+"/"+rec_name]
record.seq.alphabet = generic_dna
write_genbank(annot_gbk, record)
print "OK"
