def run(self):
# todo: filter fasta to keep just the largest contig.
# run the fasta through barrnap
fd, barrnap_outputfile = mkstemp()
self.files_to_cleanup.append(barrnap_outputfile)
b = Barrnap(self.input_file, self.threads)
subprocess.check_output(
b.construct_barrnap_command(barrnap_outputfile), shell=True)
boundries = b.read_barrnap_output(barrnap_outputfile)
f = Fasta(self.input_file)
fragments = f.calc_fragment_coords(boundries)
f.populate_fragments_from_chromosome(fragments,
self.max_bases_from_ends)
ff = FragmentFiles(fragments,
self.output_directory,
fragment_order=self.fragment_order)
ff.create_fragment_fastas()
# create a default profile.txt file
default_profile = ProfileGenerator(self.output_directory,
len(ff.ordered_fragments),
self.dnaa_fasta, self.threads)
default_profile.write_output_file()
def test_orphan_5s(self):
barrnap = Barrnap('xxx', 1, False, chromosome_length=2500000)
b = barrnap.read_barrnap_output(os.path.join(data_dir,
'orphan_5S.txt'))
self.assertEqual(
b, [[804629, 809557], [809807, 814769], [854058, 859048],
[1947089, 1952017], [2063399, 2068327], [2241391, 2246490]])
def test_barrnap_normal(self):
barrnap = Barrnap('xxx', 1, False)
b = barrnap.read_barrnap_output(
os.path.join(data_dir, 'barrnap_output.txt'))
self.assertEqual(
b, [[36740, 42014], [185730, 190843], [698430, 703543],
[1535716, 1540829], [3935714, 3940989], [4651666, 4657321]])
def test_repeated_5s(self):
barrnap = Barrnap(os.path.join(data_dir, 'test.fa'), 1, False)
b = barrnap.read_barrnap_output(
os.path.join(data_dir, 'repeated_5S.txt'))
boundries = []
for bobj in b:
boundries.append([bobj.start, bobj.end, bobj.direction])
self.assertEqual(boundries, [[1254, 6909, True]])
def test_barrnap_70s_over_end(self):
barrnap = Barrnap(os.path.join(data_dir, 'test.fa'), 1, False)
b = barrnap.read_barrnap_output(
os.path.join(data_dir, '70s_over_end.txt'))
boundries = []
for bobj in b:
boundries.append([bobj.start, bobj.end, bobj.direction])
self.assertEqual(boundries, [[2805, 5721, True], [9200, 1889, True]])
def test_orphan_5s(self):
barrnap = Barrnap('xxx', 1, False, chromosome_length=2500000)
b = barrnap.read_barrnap_output(os.path.join(data_dir,
'orphan_5S.txt'))
boundries = []
for bobj in b:
boundries.append([bobj.start, bobj.end, bobj.direction])
self.assertEqual(boundries,
[[804629, 809557, False], [809807, 814769, False],
[854058, 859048, False], [1947089, 1952017, True],
[2063399, 2068327, True], [2241391, 2246490, True]])
def test_barrnap_normal(self):
barrnap = Barrnap('xxx', 1, False)
b = barrnap.read_barrnap_output(
os.path.join(data_dir, 'barrnap_output.txt'))
boundries = []
for bobj in b:
boundries.append([bobj.start, bobj.end, bobj.direction])
self.assertEqual(
boundries, [[36740, 42014, False], [185730, 190843, False],
[698430, 703543, True], [1535716, 1540829, True],
[3935714, 3940989, False], [4651666, 4657321, False]])
def run_analysis(self, input_file, p, d):
# run the fasta through barrnap
fd, barrnap_outputfile = mkstemp()
b = Barrnap(input_file, self.threads)
subprocess.check_output(
b.construct_barrnap_command(barrnap_outputfile),
shell=True)
boundries = b.read_barrnap_output(barrnap_outputfile)
f = Fasta(input_file, is_circular = self.is_circular)
fragments = f.calc_fragment_coords( boundries)
f.populate_fragments_from_chromosome(fragments, self.max_bases_from_ends)
tmpdir = mkdtemp()
self.dirs_to_cleanup.append(tmpdir)
ff = FragmentFiles(fragments, tmpdir)
ff.create_fragment_fastas()
# take each fasta file and blast it against the database
blast = Blast(d.db_prefix, self.threads)
gat_profile = GATProfile(fragments = [])
for fasta_file in ff.output_filenames:
blast_results = blast.run_blast(fasta_file)
fb = FilterBlast(blast_results, self.min_bit_score, self.min_alignment_length)
top_result = fb.return_top_result()
if top_result is None:
gat_profile.fragments.append('?')
fasta_file
with open(fasta_file, "r") as fasta_file_fh:
with open(self.new_fragments, "a+") as newfrag_fh:
newfrag_fh.write(fasta_file_fh.read())
continue
else:
self.top_results.append(top_result)
if top_result.is_forward():
gat_profile.fragments.append( str(top_result.subject))
else:
gat_profile.fragments.append( str(top_result.subject)+ '\'')
gat_profile.orientate_for_dnaA()
# lookup the gat_profile to get the number
tg = TypeGenerator(p, gat_profile)
type_output_string = tg.calculate_type() + "\t" + str(gat_profile)
if not tg.has_previously_seen:
with open(self.novel_profiles, "a+") as output_fh:
output_fh.write(self.db_dir + "\t" + type_output_string + "\n")
return type_output_string
def find_rrna_boundries(self, input_file):
# run the fasta through barrnap
fd, barrnap_outputfile = mkstemp()
b = Barrnap(input_file, self.threads, self.verbose)
cmd = b.construct_barrnap_command(barrnap_outputfile)
if self.verbose:
print("Finding rRNA boundries:\t" + cmd)
subprocess.check_output(cmd, shell=True)
boundries = b.read_barrnap_output(barrnap_outputfile)
if self.verbose:
print("Boundries:\t" + boundries)
os.close(fd)
return boundries
def test_repeated_5s(self):
barrnap = Barrnap(os.path.join(data_dir, 'test.fa'), 1, False)
b = barrnap.read_barrnap_output(
os.path.join(data_dir, 'repeated_5S.txt'))
self.assertEqual(b, [[1254, 6909]])
def test_barrnap_70s_over_end(self):
barrnap = Barrnap(os.path.join(data_dir, 'test.fa'), 1, False)
b = barrnap.read_barrnap_output(
os.path.join(data_dir, '70s_over_end.txt'))
self.assertEqual(b, [[2805, 5721], [9200, 1889]])