def shogun_bt2_db(input, output, annotater, extract_id, prefixes, depth, depth_force):
verify_make_dir(output)
# Verify the FASTA is annotated
if input == '-':
output_fn = 'stdin'
else:
output_fn = '.'.join(str(os.path.basename(input)).split('.')[:-1])
outf_fasta = os.path.join(output, output_fn + '.annotated.fna')
outf_map = os.path.join(output, output_fn + '.annotated.map')
if not os.path.isfile(outf_fasta) or not os.path.isfile(outf_map):
tree = NCBITree()
db = RefSeqDatabase()
if annotater == 'refseq':
annotater_class = RefSeqAnnotater(extract_id, prefixes, db, tree, depth=depth, depth_force=depth_force)
elif annotater == 'nt':
annotater_class = NTAnnotater(extract_id, prefixes, db, tree, depth=depth, depth_force=depth_force)
else:
annotater_class = GIAnnotater(extract_id, db, tree, depth=depth, depth_force=depth_force)
with open(outf_fasta, 'w') as output_fna:
with open(outf_map, 'w') as output_map:
with open(input) as inf:
inf_fasta = FASTA(inf)
for lines_fna, lines_map in annotater_class.annotate(inf_fasta.read()):
output_fna.write(lines_fna)
output_map.write(lines_map)
else:
print("Found the output files \"%s\" and \"%s\". Skipping the annotation phase for this file." % (
outf_fasta, outf_map))
# Build the output BT2 database
verify_make_dir(os.path.join(output, 'bt2'))
print(bowtie2_build(outf_fasta, os.path.join(output, 'bt2', output_fn)))
def shogun_utree_db(input, output, annotater, extract_id, threads, prefixes, depth, depth_force):
verify_make_dir(output)
# Verify the FASTA is annotated
if input == '-':
output_fn = 'stdin'
else:
output_fn = '.'.join(str(os.path.basename(input)).split('.')[:-1])
outf_fasta = os.path.join(output, output_fn + '.annotated.fna')
outf_map = os.path.join(output, output_fn + '.annotated.map')
if not os.path.isfile(outf_fasta) or not os.path.isfile(outf_map):
tree = NCBITree()
db = RefSeqDatabase()
if annotater == 'refseq':
annotater_class = RefSeqAnnotater(extract_id, prefixes, db, tree, depth=depth, depth_force=depth_force)
elif annotater == 'nt':
annotater_class = NTAnnotater(extract_id, prefixes, db, tree, depth=depth, depth_force=depth_force)
else:
annotater_class = GIAnnotater(extract_id, db, tree, depth=depth, depth_force=depth_force)
with open(outf_fasta, 'w') as output_fna:
with open(outf_map, 'w') as output_map:
with open(input) as inf:
inf_fasta = FASTA(inf)
for lines_fna, lines_map in annotater_class.annotate(inf_fasta.read()):
output_fna.write(lines_fna)
output_map.write(lines_map)
else:
print("Found the output files \"%s\" and \"%s\". Skipping the annotation phase for this file." % (
outf_fasta, outf_map))
# Build the output CTR
verify_make_dir(os.path.join(output, 'utree'))
path_uncompressed_tree = os.path.join(output, 'utree', output_fn + '.utr')
path_compressed_tree = os.path.join(output, 'utree', output_fn + '.ctr')
if os.path.exists(path_compressed_tree):
print('Compressed tree database file %s exists, skipping this step.' % path_compressed_tree)
else:
if not os.path.exists(path_uncompressed_tree):
print(utree_build(outf_fasta, outf_map, path_uncompressed_tree, threads=threads))
print(utree_compress(path_uncompressed_tree, path_compressed_tree))
os.remove(path_uncompressed_tree)
