def test_find_integron_calin_threshold(self):
replicon_name = 'ESCO001.B.00018.P002'
replicon_path = self.find_data(
os.path.join('Replicons', replicon_name + '.fst'))
prot_file = self.find_data(
os.path.join('Proteins', replicon_name + '.prt'))
topologies = Topology('circ')
with FastaIterator(replicon_path) as sequences_db:
sequences_db.topologies = topologies
replicon = next(sequences_db)
replicon_results_path = self.find_data(
os.path.join('Results_Integron_Finder_{}'.format(replicon_name),
'tmp_{}'.format(replicon.id)))
attc_file = os.path.join(replicon_results_path,
'{}_attc_table.res'.format(replicon.id))
intI_file = os.path.join(replicon_results_path,
'{}_intI.res'.format(replicon.id))
phageI_file = os.path.join(replicon_results_path,
'{}_phage_int.res'.format(replicon.id))
args = argparse.Namespace()
args.no_proteins = False
args.keep_palindromes = True
args.distance_threshold = 4000
args.attc_model = 'attc_4.cm'
args.evalue_attc = 1.0
args.max_attc_size = 200
args.min_attc_size = 40
args.local_max = False
args.gembase = False
args.union_integrases = False
args.calin_threshold = 2
cfg = Config(args)
cfg._prefix_data = os.path.join(os.path.dirname(__file__), 'data')
prot_db = ProdigalDB(replicon, cfg, prot_file=prot_file)
with self.catch_log() as log:
integrons = find_integron(replicon, prot_db, attc_file, intI_file,
phageI_file, cfg)
self.assertEqual(len(integrons), 2)
args.calin_threshold = 3
cfg = Config(args)
cfg._prefix_data = os.path.join(os.path.dirname(__file__), 'data')
with self.catch_log() as log:
integrons = find_integron(replicon, prot_db, attc_file, intI_file,
phageI_file, cfg)
self.assertEqual(len(integrons), 1)
def test_find_integrase_gembase(self):
cfg = Config(self.args)
self.args.gembase = True
cfg._prefix_data = os.path.join(os.path.dirname(__file__), 'data')
replicon_name = 'acba.007.p01.13'
replicon_path = self.find_data(
os.path.join('Replicons', replicon_name + '.fst'))
topologies = Topology('lin')
with FastaIterator(replicon_path) as sequences_db:
sequences_db.topologies = topologies
replicon = next(sequences_db)
prot_file = os.path.join(self.tmp_dir, replicon_name + ".prt")
shutil.copyfile(
self.find_data(os.path.join('Proteins', replicon.id + ".prt")),
prot_file)
integrase.find_integrase(replicon.id, prot_file, self.tmp_dir, cfg)
for suffix in ('_intI.res', '_intI_table.res', '_phage_int.res',
'_phage_int_table.res'):
res = os.path.join(self.tmp_dir, replicon.id + suffix)
self.assertTrue(os.path.exists(res))
def test_find_integrase_no_gembase_no_protfile(self):
try:
cfg = Config(self.args)
self.args.gembase = False
cfg._prefix_data = os.path.join(os.path.dirname(__file__), 'data')
replicon_name = 'acba.007.p01.13'
replicon_path = self.find_data(
os.path.join('Replicons', replicon_name + '.fst'))
topologies = Topology('lin')
with FastaIterator(replicon_path) as sequences_db:
sequences_db.topologies = topologies
replicon = next(sequences_db)
len_ori = replicon.__class__.__len__
replicon.__class__.__len__ = lambda x: 500000
prot_file = os.path.join(self.tmp_dir, "foo.prt")
open(prot_file, 'w').close()
with self.catch_log():
with self.assertRaises(EmptyFileError) as ctx:
integrase.find_integrase(replicon.id, prot_file,
self.tmp_dir, cfg)
finally:
replicon.__class__.__len__ = len_ori
def test_find_integrase_no_gembase_no_protfile_no_prodigal(self):
try:
self.args.hmmsearch = 'foo'
self.args.gembase = False
cfg = Config(self.args)
cfg._prefix_data = os.path.join(os.path.dirname(__file__), 'data')
replicon_name = 'acba.007.p01.13'
replicon_path = self.find_data(
os.path.join('Replicons', replicon_name + '.fst'))
topologies = Topology('lin')
with FastaIterator(replicon_path) as sequences_db:
sequences_db.topologies = topologies
replicon = next(sequences_db)
len_ori = replicon.__class__.__len__
replicon.__class__.__len__ = lambda x: 500000
prot_file = os.path.join(self.tmp_dir, replicon.id + ".prt")
shutil.copyfile(
self.find_data(os.path.join('Proteins', replicon.id + ".prt")),
prot_file)
with self.assertRaises(RuntimeError) as ctx:
integrase.find_integrase(replicon.id, prot_file, self.tmp_dir,
cfg)
self.assertTrue(
re.search(
"failed : \[Errno 2\] No such file or directory: 'foo'",
str(ctx.exception)))
finally:
replicon.__class__.__len__ = len_ori
def test_find_integrase_no_gembase_no_protfile_short_seq(self):
try:
cfg = Config(self.args)
self.args.gembase = False
cfg._prefix_data = os.path.join(os.path.dirname(__file__), 'data')
replicon_name = 'acba.007.p01.13'
replicon_path = self.find_data(
os.path.join('Replicons', replicon_name + '.fst'))
prot_name = 'ACBA.007.P01_13'
prot_path = self.find_data(
os.path.join('Proteins', prot_name + '.prt'))
topologies = Topology('lin')
with FastaIterator(replicon_path) as sequences_db:
sequences_db.topologies = topologies
replicon = next(sequences_db)
len_ori = replicon.__class__.__len__
replicon.__class__.__len__ = lambda x: 200
prot_file = os.path.join(self.tmp_dir, replicon.id + ".prt")
shutil.copyfile(prot_path, prot_file)
integrase.find_integrase(replicon.id, prot_file, self.tmp_dir, cfg)
for suffix in ('_intI.res', '_intI_table.res', '_phage_int.res',
'_phage_int_table.res'):
res = os.path.join(self.tmp_dir, replicon.id + suffix)
self.assertTrue(os.path.exists(res))
finally:
replicon.__class__.__len__ = len_ori
def test_find_integrase_no_gembase_with_protfile_empty(self):
try:
cfg = Config(self.args)
self.args.gembase = False
cfg._prefix_data = os.path.join(os.path.dirname(__file__), 'data')
replicon_name = 'acba.007.p01.13'
replicon_path = self.find_data(
os.path.join('Replicons', replicon_name + '.fst'))
topologies = Topology('lin')
with FastaIterator(replicon_path) as sequences_db:
sequences_db.topologies = topologies
replicon = next(sequences_db)
len_ori = replicon.__class__.__len__
replicon.__class__.__len__ = lambda x: 200
prot_file = os.path.join(self.tmp_dir, replicon.id + ".prt")
open(prot_file, 'w').close()
with self.assertRaises(EmptyFileError) as ctx:
with self.catch_log():
integrase.find_integrase(replicon.id, prot_file,
self.tmp_dir, cfg)
self.assertTrue(
re.match(
"^The protein file: '.*' is empty cannot perform hmmsearch on it.$",
str(ctx.exception)))
finally:
replicon.__class__.__len__ = len_ori
def test_find_integron_calin_threshold(self):
replicon_name = 'ESCO001.B.00018.P002'
replicon_path = self.find_data(os.path.join('Replicons', replicon_name + '.fst'))
prot_file = self.find_data(os.path.join('Proteins', replicon_name + '.prt'))
topologies = Topology('circ')
with FastaIterator(replicon_path) as sequences_db:
sequences_db.topologies = topologies
replicon = next(sequences_db)
replicon_results_path = self.find_data(os.path.join('Results_Integron_Finder_{}'.format(replicon_name),
'tmp_{}'.format(replicon.id)))
attc_file = os.path.join(replicon_results_path, '{}_attc_table.res'.format(replicon.id))
intI_file = os.path.join(replicon_results_path, '{}_intI.res'.format(replicon.id))
phageI_file = os.path.join(replicon_results_path, '{}_phage_int.res'.format(replicon.id))
args = argparse.Namespace()
args.no_proteins = False
args.keep_palindromes = True
args.distance_threshold = 4000
args.attc_model = 'attc_4.cm'
args.evalue_attc = 1.0
args.max_attc_size = 200
args.min_attc_size = 40
args.local_max = False
args.gembase = False
args.union_integrases = False
args.calin_threshold = 2
cfg = Config(args)
cfg._prefix_data = os.path.join(os.path.dirname(__file__), 'data')
prot_db = ProdigalDB(replicon, cfg, prot_file=prot_file)
with self.catch_log() as log:
integrons = find_integron(replicon, prot_db, attc_file, intI_file, phageI_file, cfg)
self.assertEqual(len(integrons), 2)
args.calin_threshold = 3
cfg = Config(args)
cfg._prefix_data = os.path.join(os.path.dirname(__file__), 'data')
with self.catch_log() as log:
integrons = find_integron(replicon, prot_db, attc_file, intI_file, phageI_file, cfg)
self.assertEqual(len(integrons), 1)
def test_find_integrase_gembase_hmmer_error(self):
self.args.gembase = True
self.args.cpu = 'foo'
cfg = Config(self.args)
cfg._prefix_data = os.path.join(os.path.dirname(__file__), 'data')
replicon_name = 'acba.007.p01.13'
replicon_path = os.path.join(self._data_dir, 'Replicons',
replicon_name + '.fst')
topologies = Topology('lin')
with FastaIterator(replicon_path) as sequences_db:
sequences_db.topologies = topologies
replicon = next(sequences_db)
prot_file = os.path.join(self.tmp_dir, replicon.id + ".prt")
shutil.copyfile(
os.path.join(self._data_dir, 'Proteins', replicon.id + ".prt"),
prot_file)
with self.assertRaises(RuntimeError) as ctx:
integrase.find_integrase(replicon.id, prot_file, self.tmp_dir, cfg)
self.assertTrue(str(ctx.exception).endswith('failed return code = 1'))
def test_find_integrase_gembase_no_hmmer_no_replicon(self):
self.args.gembase = True
self.args.hmmsearch = 'foo'
cfg = Config(self.args)
cfg._prefix_data = os.path.join(os.path.dirname(__file__), 'data')
replicon_name = 'acba.007.p01.13'
replicon_path = os.path.join(self._data_dir, 'Replicons',
replicon_name + '.fst')
topologies = Topology('lin')
with FastaIterator(replicon_path) as sequences_db:
sequences_db.topologies = topologies
replicon = next(sequences_db)
prot_file = os.path.join(self.tmp_dir, replicon.id + ".prt")
with self.catch_log():
with self.assertRaises(RuntimeError) as ctx:
integrase.find_integrase(replicon.id, prot_file, self.tmp_dir,
cfg)
self.assertEqual(
"The protein file: '{}' does not exists cannot perform hmmsearch on it."
.format(prot_file), str(ctx.exception))
def test_find_integron_proteins_n_union_integrase(self):
replicon_name = 'OBAL001.B.00005.C001'
replicon_id = 'OBAL001.B.00005.C001'
replicon_path = self.find_data(
os.path.join('Replicons', replicon_name + '.fst'))
prot_file = self.find_data(
os.path.join('Proteins', replicon_name + '.prt'))
topologies = Topology('lin')
with FastaIterator(replicon_path) as sequences_db:
sequences_db.topologies = topologies
replicon = next(sequences_db)
result_dir = 'Results_Integron_Finder_{}.union'.format(replicon_name)
attc_file = self.find_data(
os.path.join(result_dir, 'tmp_{}'.format(replicon.id),
'{}_attc_table.res'.format(replicon.id)))
intI_file = self.find_data(
os.path.join(result_dir, 'tmp_{}'.format(replicon.id),
'{}_intI.res'.format(replicon.id)))
phageI_file = self.find_data(
os.path.join(result_dir, 'tmp_{}'.format(replicon.id),
'{}_phage_int.res'.format(replicon.id)))
args = argparse.Namespace()
args.evalue_attc = 1.
args.max_attc_size = 200
args.min_attc_size = 40
args.distance_threshold = 4000 # (4kb at least between 2 different arrays)
args.calin_threshold = 2
args.attc_model = 'attc_4.cm'
args.no_proteins = False
args.keep_palindromes = True
args.union_integrases = True
args.gembase = False # needed by read_hmm which is called when no_proteins == False
args.local_max = False
cfg = Config(args)
cfg._prefix_data = os.path.join(os.path.dirname(__file__), 'data')
prot_db = ProdigalDB(replicon, cfg, prot_file=prot_file)
exp_msg = """In replicon {}, there are:
- 3 complete integron(s) found with a total 4 attC site(s)
- 0 CALIN element(s) found with a total of 0 attC site(s)
- 2 In0 element(s) found with a total of 0 attC site""".format(replicon.id)
with self.catch_log() as log:
integrons = find_integron(replicon, prot_db, attc_file, intI_file,
phageI_file, cfg)
catch_msg = log.get_value().strip()
self.assertEqual(catch_msg, exp_msg)
self.assertEqual(len(integrons), 5)
integron = integrons[0]
self.assertEqual(integron.replicon.name, replicon_id)
empty = pd.DataFrame(columns=self.columns).astype(dtype=self.dtype)
exp_int = []
exp_int.append(
pd.DataFrame([[
418072, 419283, 1, 5.400000e-25, 'protein', 'Phage_integrase',
np.nan, 'intI'
]],
columns=self.columns,
index=['OBAL001.B.00005.C001_388'
]).astype(dtype=self.dtype))
exp_int.append(
pd.DataFrame([[
434671, 440118, -1, 0.085, 'protein', 'Phage_integrase',
np.nan, 'intI'
]],
columns=self.columns,
index=['OBAL001.B.00005.C001_399'
]).astype(dtype=self.dtype))
exp_int.append(
pd.DataFrame([[
516941, 517834, -1, 1.200000e-54, 'protein', 'Phage_integrase',
np.nan, 'intI'
]],
columns=self.columns,
index=['OBAL001.B.00005.C001_472'
]).astype(dtype=self.dtype))
exp_int.append(
pd.DataFrame([[
1940269, 1941171, 1, 4.200000e-43, 'protein',
'Phage_integrase', np.nan, 'intI'
]],
columns=self.columns,
index=['OBAL001.B.00005.C001_1793'
]).astype(dtype=self.dtype))
exp_int.append(
pd.DataFrame([[
1545830, 1546807, -1, 1.100000e-21, 'protein',
'intersection_tyr_intI', np.nan, 'intI'
]],
columns=self.columns,
index=['OBAL001.B.00005.C001_1416'
]).astype(dtype=self.dtype))
exp_attC = []
exp_attC.append(
pd.DataFrame(
[[421689, 421764, 1, 0.13, 'attC', 'attc_4', np.nan, 'attC']],
columns=self.columns,
index=['attc_001']).astype(dtype=self.dtype))
exp_attC.append(
pd.DataFrame([[
442458, 442514, -1, 7.000000e-07, 'attC', 'attc_4', np.nan,
'attC'
]],
columns=self.columns,
index=['attc_001']).astype(dtype=self.dtype))
exp_attC.append(empty)
exp_attC.append(empty)
exp_attC.append(
pd.DataFrame([[
1547800, 1547859, 1, 0.00049, 'attC', 'attc_4', np.nan, 'attC'
], [1548775, 1548834, 1, 0.00009, 'attC', 'attc_4', 916.0, 'attC']
],
columns=self.columns,
index=['attc_001',
'attc_002']).astype(dtype=self.dtype))
for i, integron in enumerate(integrons):
self.assertEqual(integron.replicon.name, replicon_id)
pdt.assert_frame_equal(integron.integrase, exp_int[i])
pdt.assert_frame_equal(integron.attC, exp_attC[i])
pdt.assert_frame_equal(integron.promoter, empty)
pdt.assert_frame_equal(integron.attI, empty)
pdt.assert_frame_equal(integron.proteins, empty)
def test_find_integron_proteins_circ_replicon(self):
replicon_name = 'acba.007.p01.13'
replicon_id = 'ACBA.007.P01_13'
replicon_path = self.find_data(
os.path.join('Replicons', replicon_name + '.fst'))
prot_file = self.find_data(
os.path.join('Proteins', replicon_id + '.prt'))
topologies = Topology('circ')
with FastaIterator(replicon_path) as sequences_db:
sequences_db.topologies = topologies
replicon = next(sequences_db)
exp_result_dir = 'Results_Integron_Finder_acba.007.p01.13.circular'
attc_file = self.find_data(
os.path.join(exp_result_dir, 'tmp_{}'.format(replicon.id),
'{}_attc_table.res'.format(replicon.id)))
intI_file = self.find_data(
os.path.join(exp_result_dir, 'tmp_{}'.format(replicon.id),
'{}_intI.res'.format(replicon.id)))
phageI_file = self.find_data(
os.path.join(exp_result_dir, 'tmp_{}'.format(replicon.id),
'{}_phage_int.res'.format(replicon.id)))
args = argparse.Namespace()
args.no_proteins = False
args.keep_palindromes = True
args.union_integrases = False
args.gembase = False # needed by read_hmm which is called when no_proteins == False
args = argparse.Namespace()
args.evalue_attc = 1.
args.max_attc_size = 200
args.min_attc_size = 40
args.distance_threshold = 4000 # (4kb at least between 2 different arrays)
args.attc_model = 'attc_4.cm'
args.no_proteins = False
args.gembase = False # needed by read_hmm which is called when no_proteins == False
args.union_integrases = False
args.keep_palindromes = True
args.calin_threshold = 2
args.local_max = False
cfg = Config(args)
cfg._prefix_data = os.path.join(os.path.dirname(__file__), 'data')
prot_db = ProdigalDB(replicon, cfg, prot_file=prot_file)
exp_msg = """In replicon {}, there are:
- 1 complete integron(s) found with a total 3 attC site(s)
- 0 CALIN element(s) found with a total of 0 attC site(s)
- 0 In0 element(s) found with a total of 0 attC site""".format(replicon.id)
with self.catch_log() as log:
integrons = find_integron(replicon, prot_db, attc_file, intI_file,
phageI_file, cfg)
catch_msg = log.get_value().strip()
self.assertEqual(catch_msg, exp_msg)
self.assertEqual(len(integrons), 1)
integron = integrons[0]
self.assertEqual(integron.replicon.name, replicon_id)
exp = pd.DataFrame(
{
'annotation': 'intI',
'distance_2attC': np.nan,
'evalue': 1.900000e-25,
'model': 'intersection_tyr_intI',
'pos_beg': 55,
'pos_end': 1014,
'strand': 1,
'type_elt': 'protein'
},
columns=self.columns,
index=['ACBA.007.P01_13_1'])
exp = exp.astype(dtype=self.dtype)
pdt.assert_frame_equal(integron.integrase, exp)
exp = pd.DataFrame(
{
'annotation': ['attC'] * 3,
'distance_2attC': [np.nan, 1196.0, 469.0],
'evalue': [1.000000e-09, 1.000000e-04, 1.100000e-07],
'model': ['attc_4'] * 3,
'pos_beg': [17825, 19080, 19618],
'pos_end': [17884, 19149, 19726],
'strand': [-1, -1, -1],
'type_elt': 'attC'
},
columns=self.columns,
index=['attc_001', 'attc_002', 'attc_003'])
exp = exp.astype(dtype=self.dtype)
pdt.assert_frame_equal(integron.attC, exp)
exp = pd.DataFrame(columns=self.columns)
exp = exp.astype(dtype=self.dtype)
pdt.assert_frame_equal(integron.promoter, exp)
pdt.assert_frame_equal(integron.attI, exp)
pdt.assert_frame_equal(integron.proteins, exp)
def test_find_integron_attC_is_df(self):
replicon_name = 'acba.007.p01.13'
replicon_id = 'ACBA.007.P01_13'
replicon_path = self.find_data(
os.path.join('Replicons', replicon_name + '.fst'))
prot_file = self.find_data(
os.path.join('Proteins', replicon_id + '.prt'))
topologies = Topology('lin')
with FastaIterator(replicon_path) as sequences_db:
sequences_db.topologies = topologies
replicon = next(sequences_db)
attc_file = self.find_data(
os.path.join('Results_Integron_Finder_{}'.format(replicon_name),
'tmp_{}'.format(replicon.id),
'{}_attc_table.res'.format(replicon.id)))
intI_file = self.find_data(
os.path.join('Results_Integron_Finder_{}'.format(replicon_name),
'tmp_{}'.format(replicon.id),
'{}_intI.res'.format(replicon.id)))
phageI_file = self.find_data(
os.path.join('Results_Integron_Finder_{}'.format(replicon_name),
'tmp_{}'.format(replicon.id),
'{}_phage_int.res'.format(replicon.id)))
args = argparse.Namespace()
args.no_proteins = True
args.keep_palindromes = True
args.attc_model = 'attc_4.cm'
args.evalue_attc = 1.0
args.max_attc_size = 200
args.min_attc_size = 40
args.distance_threshold = 4000
args.calin_threshold = 2
args.local_max = False
cfg = Config(args)
cfg._prefix_data = os.path.join(os.path.dirname(__file__), 'data')
len_model_attc = 47 # length in 'CLEN' (value for model attc_4.cm)
attc_file = read_infernal(attc_file,
replicon_name,
len_model_attc,
evalue=cfg.evalue_attc,
size_max_attc=cfg.max_attc_size,
size_min_attc=cfg.min_attc_size)
prot_db = ProdigalDB(replicon, cfg, prot_file=prot_file)
exp_msg = """In replicon {}, there are:
- 0 complete integron(s) found with a total 0 attC site(s)
- 1 CALIN element(s) found with a total of 3 attC site(s)
- 0 In0 element(s) found with a total of 0 attC site""".format(replicon.id)
with self.catch_log() as log:
integrons = find_integron(replicon, prot_db, attc_file, intI_file,
phageI_file, cfg)
catch_msg = log.get_value().strip()
self.assertEqual(catch_msg, exp_msg)
self.assertEqual(len(integrons), 1)
integron = integrons[0]
self.assertEqual(integron.replicon.name, replicon_id)
exp = pd.DataFrame(
{
'annotation': ['attC'] * 3,
'distance_2attC': [np.nan, 1196.0, 469.0],
'evalue': [1.000000e-09, 1.000000e-04, 1.100000e-07],
'model': ['attc_4'] * 3,
'pos_beg': [17825, 19080, 19618],
'pos_end': [17884, 19149, 19726],
'strand': [-1, -1, -1],
'type_elt': 'attC'
},
columns=self.columns,
index=['attc_001', 'attc_002', 'attc_003'])
pdt.assert_frame_equal(integron.attC, exp)
exp = pd.DataFrame(columns=self.columns)
exp = exp.astype(dtype=self.dtype)
pdt.assert_frame_equal(integron.integrase, exp)
pdt.assert_frame_equal(integron.promoter, exp)
pdt.assert_frame_equal(integron.attI, exp)
pdt.assert_frame_equal(integron.proteins, exp)
def test_find_integron(self):
replicon_name = 'acba.007.p01.13'
prot_name = 'ACBA.007.P01_13'
replicon_path = self.find_data(os.path.join('Replicons', replicon_name + '.fst'))
prot_file = self.find_data(os.path.join('Proteins', prot_name + '.prt'))
topologies = Topology('lin')
with FastaIterator(replicon_path) as sequences_db:
sequences_db.topologies = topologies
replicon = next(sequences_db)
replicon_results_path = self.find_data(os.path.join('Results_Integron_Finder_{}'.format(replicon_name),
'tmp_{}'.format(replicon.id)))
attc_file = os.path.join(replicon_results_path, '{}_attc_table.res'.format(replicon.id))
intI_file = os.path.join(replicon_results_path, '{}_intI.res'.format(replicon.id))
phageI_file = os.path.join(replicon_results_path, '{}_phage_int.res'.format(replicon.id))
args = argparse.Namespace()
args.no_proteins = True
args.keep_palindromes = True
args.distance_threshold = 4000
args.attc_model = 'attc_4.cm'
args.evalue_attc = 1.0
args.max_attc_size = 200
args.min_attc_size = 40
args.calin_threshold = 2
args.local_max = False
cfg = Config(args)
cfg._prefix_data = os.path.join(os.path.dirname(__file__), 'data')
prot_db = ProdigalDB(replicon, cfg, prot_file=prot_file)
exp_msg = """In replicon {}, there are:
- 0 complete integron(s) found with a total 0 attC site(s)
- 1 CALIN element(s) found with a total of 3 attC site(s)
- 0 In0 element(s) found with a total of 0 attC site""".format(replicon.id)
with self.catch_log() as log:
integrons = find_integron(replicon, prot_db, attc_file, intI_file, phageI_file, cfg)
catch_msg = log.get_value().strip()
self.assertEqual(catch_msg, exp_msg)
self.assertEqual(len(integrons), 1)
integron = integrons[0]
self.assertEqual(integron.replicon.id, replicon.id)
exp = pd.DataFrame({'annotation': ['attC'] * 3,
'distance_2attC': [np.nan, 1196.0, 469.0],
'evalue': [1.000000e-09, 1.000000e-04, 1.100000e-07],
'model': ['attc_4'] * 3,
'pos_beg': [17825, 19080, 19618],
'pos_end': [17884, 19149, 19726],
'strand': [-1, -1, -1],
'type_elt': 'attC'},
columns=self.columns,
index=['attc_001', 'attc_002', 'attc_003'])
pdt.assert_frame_equal(integron.attC, exp)
exp = pd.DataFrame(columns=self.columns,)
exp = exp.astype(dtype=self.dtype)
pdt.assert_frame_equal(integron.integrase, exp)
pdt.assert_frame_equal(integron.promoter, exp)
pdt.assert_frame_equal(integron.attI, exp)
pdt.assert_frame_equal(integron.proteins, exp)
def test_find_integron_proteins_n_union_integrase(self):
replicon_name = 'OBAL001.B.00005.C001'
replicon_id = 'OBAL001.B.00005.C001'
replicon_path = self.find_data(os.path.join('Replicons', replicon_name + '.fst'))
prot_file = self.find_data(os.path.join('Proteins', replicon_name + '.prt'))
topologies = Topology('lin')
with FastaIterator(replicon_path) as sequences_db:
sequences_db.topologies = topologies
replicon = next(sequences_db)
result_dir = 'Results_Integron_Finder_{}.union'.format(replicon_name)
attc_file = self.find_data(os.path.join(result_dir,
'tmp_{}'.format(replicon.id),
'{}_attc_table.res'.format(replicon.id)))
intI_file = self.find_data(os.path.join(result_dir,
'tmp_{}'.format(replicon.id),
'{}_intI.res'.format(replicon.id)))
phageI_file = self.find_data(os.path.join(result_dir,
'tmp_{}'.format(replicon.id),
'{}_phage_int.res'.format(replicon.id)))
args = argparse.Namespace()
args.evalue_attc = 1.
args.max_attc_size = 200
args.min_attc_size = 40
args.distance_threshold = 4000 # (4kb at least between 2 different arrays)
args.calin_threshold = 2
args.attc_model = 'attc_4.cm'
args.no_proteins = False
args.keep_palindromes = True
args.union_integrases = True
args.gembase = False # needed by read_hmm which is called when no_proteins == False
args.local_max = False
cfg = Config(args)
cfg._prefix_data = os.path.join(os.path.dirname(__file__), 'data')
prot_db = ProdigalDB(replicon, cfg, prot_file=prot_file)
exp_msg = """In replicon {}, there are:
- 3 complete integron(s) found with a total 4 attC site(s)
- 0 CALIN element(s) found with a total of 0 attC site(s)
- 2 In0 element(s) found with a total of 0 attC site""".format(replicon.id)
with self.catch_log() as log:
integrons = find_integron(replicon,
prot_db,
attc_file,
intI_file,
phageI_file,
cfg)
catch_msg = log.get_value().strip()
self.assertEqual(catch_msg, exp_msg)
self.assertEqual(len(integrons), 5)
integron = integrons[0]
self.assertEqual(integron.replicon.name, replicon_id)
empty = pd.DataFrame(columns=self.columns).astype(dtype=self.dtype)
exp_int = []
exp_int.append(pd.DataFrame(
[[418072, 419283, 1, 5.400000e-25, 'protein', 'Phage_integrase', np.nan, 'intI']],
columns=self.columns,
index=['OBAL001.B.00005.C001_388']).astype(dtype=self.dtype))
exp_int.append(pd.DataFrame(
[[434671, 440118, -1, 0.085, 'protein', 'Phage_integrase', np.nan, 'intI']],
columns=self.columns,
index=['OBAL001.B.00005.C001_399']).astype(dtype=self.dtype))
exp_int.append(pd.DataFrame(
[[516941, 517834, -1, 1.200000e-54, 'protein', 'Phage_integrase', np.nan, 'intI']],
columns=self.columns,
index=['OBAL001.B.00005.C001_472']).astype(dtype=self.dtype))
exp_int.append(pd.DataFrame(
[[1940269, 1941171, 1, 4.200000e-43, 'protein', 'Phage_integrase', np.nan, 'intI']],
columns=self.columns,
index=['OBAL001.B.00005.C001_1793']).astype(dtype=self.dtype))
exp_int.append(pd.DataFrame(
[[1545830, 1546807, -1, 1.100000e-21, 'protein', 'intersection_tyr_intI', np.nan, 'intI']],
columns=self.columns,
index=['OBAL001.B.00005.C001_1416']).astype(dtype=self.dtype))
exp_attC = []
exp_attC.append(pd.DataFrame(
[[421689, 421764, 1, 0.13, 'attC', 'attc_4', np.nan, 'attC']],
columns=self.columns,
index=['attc_001']).astype(dtype=self.dtype))
exp_attC.append(pd.DataFrame(
[[442458, 442514, -1, 7.000000e-07, 'attC', 'attc_4', np.nan, 'attC']],
columns=self.columns,
index=['attc_001']).astype(dtype=self.dtype))
exp_attC.append(empty)
exp_attC.append(empty)
exp_attC.append(pd.DataFrame(
[[1547800, 1547859, 1, 0.00049, 'attC', 'attc_4', np.nan, 'attC'],
[1548775, 1548834, 1, 0.00009, 'attC', 'attc_4', 916.0, 'attC']],
columns=self.columns,
index=['attc_001', 'attc_002']).astype(dtype=self.dtype))
for i, integron in enumerate(integrons):
self.assertEqual(integron.replicon.name, replicon_id)
pdt.assert_frame_equal(integron.integrase, exp_int[i])
pdt.assert_frame_equal(integron.attC, exp_attC[i])
pdt.assert_frame_equal(integron.promoter, empty)
pdt.assert_frame_equal(integron.attI, empty)
pdt.assert_frame_equal(integron.proteins, empty)
def test_find_integron_proteins_lin_replicon(self):
replicon_name = 'acba.007.p01.13'
replicon_id = 'ACBA.007.P01_13'
replicon_path = self.find_data(os.path.join('Replicons', replicon_name + '.fst'))
prot_file = self.find_data(os.path.join('Proteins', replicon_id + '.prt'))
topologies = Topology('lin')
with FastaIterator(replicon_path) as sequences_db:
sequences_db.topologies = topologies
replicon = next(sequences_db)
exp_result_dir = 'Results_Integron_Finder_acba.007.p01.13.linear'
attc_file = self.find_data(os.path.join(exp_result_dir,
'tmp_{}'.format(replicon.id),
'{}_attc_table.res'.format(replicon.id)))
intI_file = self.find_data(os.path.join(exp_result_dir,
'tmp_{}'.format(replicon.id),
'{}_intI.res'.format(replicon.id)))
phageI_file = self.find_data(os.path.join(exp_result_dir,
'tmp_{}'.format(replicon.id),
'{}_phage_int.res'.format(replicon.id)))
args = argparse.Namespace()
args.no_proteins = False
args.keep_palindromes = True
args.union_integrases = False
args.gembase = False # needed by read_hmm which is called when no_proteins == False
args = argparse.Namespace()
args.evalue_attc = 1.
args.max_attc_size = 200
args.min_attc_size = 40
args.distance_threshold = 4000 # (4kb at least between 2 different arrays)
args.attc_model = 'attc_4.cm'
args.no_proteins = False
args.gembase = False # needed by read_hmm which is called when no_proteins == False
args.union_integrases = False
args.keep_palindromes = True
args.calin_threshold = 2
args.local_max = False
cfg = Config(args)
cfg._prefix_data = os.path.join(os.path.dirname(__file__), 'data')
prot_db = ProdigalDB(replicon, cfg, prot_file=prot_file)
exp_msg = """In replicon {}, there are:
- 0 complete integron(s) found with a total 0 attC site(s)
- 1 CALIN element(s) found with a total of 3 attC site(s)
- 1 In0 element(s) found with a total of 0 attC site""".format(replicon.id)
with self.catch_log() as log:
integrons = find_integron(replicon,
prot_db,
attc_file,
intI_file,
phageI_file,
cfg)
catch_msg = log.get_value().strip()
self.assertEqual(catch_msg, exp_msg)
self.assertEqual(len(integrons), 2)
exp_int = []
exp = pd.DataFrame({'annotation': 'intI',
'distance_2attC': np.nan,
'evalue': 1.900000e-25,
'model': 'intersection_tyr_intI',
'pos_beg': 55,
'pos_end': 1014,
'strand': 1,
'type_elt': 'protein'},
columns=self.columns,
index=['ACBA.007.P01_13_1'])
exp = exp.astype(dtype=self.dtype)
exp_int.append(exp)
exp_int.append(pd.DataFrame(columns=self.columns).astype(dtype=self.dtype))
exp_attC = [pd.DataFrame(columns=self.columns).astype(dtype=self.dtype)]
exp = pd.DataFrame({'annotation': ['attC'] * 3,
'distance_2attC': [np.nan, 1196.0, 469.0],
'evalue': [1.000000e-09, 1.000000e-04, 1.100000e-07],
'model': ['attc_4'] * 3,
'pos_beg': [17825, 19080, 19618],
'pos_end': [17884, 19149, 19726],
'strand': [-1, -1, -1],
'type_elt': 'attC'},
columns=self.columns,
index=['attc_001', 'attc_002', 'attc_003'])
exp = exp.astype(dtype=self.dtype)
exp_attC.append(exp)
empty = pd.DataFrame(columns=self.columns).astype(dtype=self.dtype)
for i, integron in enumerate(integrons):
self.assertEqual(integron.replicon.name, replicon_id)
pdt.assert_frame_equal(integron.integrase, exp_int[i])
pdt.assert_frame_equal(integron.attC, exp_attC[i])
pdt.assert_frame_equal(integron.promoter, empty)
pdt.assert_frame_equal(integron.attI, empty)
pdt.assert_frame_equal(integron.proteins, empty)