def test_alignment(self):
"""
Testing default procedure for the genes method with alignment assitance
for sequences without biological information (FASTA input instead of
GENBANK).
"""
infile = "Fasta/f006.fasta"
informat = "fasta"
# Check the input
self.assertTrue(os.path.isfile(infile))
self.assertEqual(len(list(SeqIO.parse(infile, informat))), 5)
# Generate the gene clustering without metadata
subset_dict = Cluster.get_subsets("genes", infile, informat)
# Check the output
self.assertEqual(len(subset_dict), 1)
self.assertEqual(len(subset_dict["unprocessable"]), 5)
# Generate the gene clustering with external metadata (from a reference
# sequence)
subset_dict = Cluster.get_subsets("genes", infile, informat, ref_seq="rCRS", alignment_bin=mafft_exe)
# Check the output
self.assertEqual(len(subset_dict), 98)
self.assertNotIn("unprocessable", subset_dict)
for key, value in viewitems(subset_dict):
self.assertNotEqual(len(value), 0)
self.assertTrue(len(value) % 5 == 0)
def test_alignment(self):
"""
Testing default procedure for the genes method with alignment assitance
for sequences without biological information (FASTA input instead of
GENBANK).
"""
infile = 'Fasta/f006.fasta'
informat = 'fasta'
# Check the input
self.assertTrue(os.path.isfile(infile))
self.assertEqual(len(list(SeqIO.parse(infile, informat))), 5)
# Generate the gene clustering without metadata
subset_dict = Cluster.get_subsets('genes', infile, informat)
# Check the output
self.assertEqual(len(subset_dict), 1)
self.assertEqual(len(subset_dict['unprocessable']), 5)
# Generate the gene clustering with external metadata (from a reference
# sequence)
subset_dict = Cluster.get_subsets('genes',
infile,
informat,
ref_seq='rCRS',
alignment_bin=mafft_exe)
# Check the output
self.assertEqual(len(subset_dict), 98)
self.assertNotIn('unprocessable', subset_dict)
for key, value in viewitems(subset_dict):
self.assertNotEqual(len(value), 0)
self.assertTrue(len(value) % 5 == 0)
def test_clustering(self):
"""
Testing procedure for the PRD method.
"""
infile = "Fasta/f007.fasta"
informat = "fasta"
treefile = "Newick/f007.newick"
treeformat = "newick"
# Check the input
self.assertTrue(os.path.isfile(infile))
self.assertEqual(len(list(SeqIO.parse(infile, informat))), 100)
self.assertTrue(os.path.isfile(treefile))
# Generate the subset division
subset_dict = Cluster.get_subsets(
"prd",
infile,
informat,
tree_file=treefile,
file_format=treeformat,
subset_size=25,
overlapping=4,
binary=dcm3_exe,
)
# Check the output
self.assertEqual(len(subset_dict), 17)
result = [len(value) for value in viewvalues(subset_dict)]
result.sort()
self.assertEqual(result, [16, 17, 17, 18, 18, 19, 19, 19, 20, 20, 20, 20, 22, 22, 23, 24, 25])
def test_log_file(self):
"""
Testing the genes method with the generation of a log file in a given
path.
"""
infile = "Genbank/f006.genbank"
informat = "genbank"
logfile = "tmp_test.log"
# Check the input
self.assertTrue(os.path.isfile(infile))
self.assertEqual(len(list(SeqIO.parse(infile, informat))), 5)
self.assertFalse(os.path.isfile(logfile))
self.add_file_to_clean("tmp_test.log")
# Generate the gene clustering
subset_dict = Cluster.get_subsets("genes", infile, informat, log_file=logfile)
# Check the clustering output
self.assertEqual(len(subset_dict), 63)
self.assertIn("unprocessable", subset_dict)
self.assertEqual(len(subset_dict["unprocessable"]), 0)
# Check the content of the log file
self.assertTrue(os.path.isfile(logfile))
with open(logfile, "r") as flog:
content = flog.readlines()
for feature in ["> misc_feature\n", "> D-loop\n", "> rRNA\n", "> tRNA\n", "> CDS\n", "> gene\n"]:
self.assertIn(feature, content)
def test_clustering(self):
"""
Testing procedure for the PRD method.
"""
infile = 'Fasta/f007.fasta'
informat = 'fasta'
treefile = 'Newick/f007.newick'
treeformat = 'newick'
# Check the input
self.assertTrue(os.path.isfile(infile))
self.assertEqual(len(list(SeqIO.parse(infile, informat))), 100)
self.assertTrue(os.path.isfile(treefile))
# Generate the subset division
subset_dict = Cluster.get_subsets('prd',
infile,
informat,
tree_file=treefile,
file_format=treeformat,
subset_size=25,
overlapping=4,
binary=dcm3_exe)
# Check the output
self.assertEqual(len(subset_dict), 17)
result = [len(value) for value in viewvalues(subset_dict)]
result.sort()
self.assertEqual(result, [
16, 17, 17, 18, 18, 19, 19, 19, 20, 20, 20, 20, 22, 22, 23, 24, 25
])
def test_log_file(self):
"""
Testing the genes method with the generation of a log file in a given
path.
"""
infile = 'Genbank/f006.genbank'
informat = 'genbank'
logfile = 'tmp_test.log'
# Check the input
self.assertTrue(os.path.isfile(infile))
self.assertEqual(len(list(SeqIO.parse(infile, informat))), 5)
self.assertFalse(os.path.isfile(logfile))
self.add_file_to_clean('tmp_test.log')
# Generate the gene clustering
subset_dict = Cluster.get_subsets('genes',
infile,
informat,
log_file=logfile)
# Check the clustering output
self.assertEqual(len(subset_dict), 63)
self.assertIn('unprocessable', subset_dict)
self.assertEqual(len(subset_dict['unprocessable']), 0)
# Check the content of the log file
self.assertTrue(os.path.isfile(logfile))
with open(logfile, 'r') as flog:
content = flog.readlines()
for feature in [
'> misc_feature\n', '> D-loop\n', '> rRNA\n', '> tRNA\n',
'> CDS\n', '> gene\n'
]:
self.assertIn(feature, content)
def test_clustering(self):
"""
Testing procedure for the naive rows method.
"""
infile = "Fasta/f001.fasta"
informat = "fasta"
# Check the input
self.assertTrue(os.path.isfile(infile))
self.assertEqual(len(list(SeqIO.parse(infile, informat))), 50)
# Generate the alignment
subset_dict = Cluster.get_subsets("rows", infile, informat, 5)
# Check the output
self.assertEqual(len(subset_dict), 5)
for subset in viewvalues(subset_dict):
self.assertEqual(len(subset), 10)
def test_default(self):
"""
Testing default procedure for the genes method.
"""
infile = "Genbank/f006.genbank"
informat = "genbank"
# Check the input
self.assertTrue(os.path.isfile(infile))
self.assertEqual(len(list(SeqIO.parse(infile, informat))), 5)
# Generate the gene clustering
subset_dict = Cluster.get_subsets("genes", infile, informat)
# Check the output
self.assertEqual(len(subset_dict), 63)
self.assertIn("unprocessable", subset_dict)
self.assertEqual(len(subset_dict["unprocessable"]), 0)
def test_clustering ( self ) :
"""
Testing procedure for the naive rows method.
"""
infile = 'Fasta/f001.fasta'
informat = 'fasta'
# Check the input
self.assertTrue(os.path.isfile(infile))
self.assertEqual(len(list(SeqIO.parse(infile, informat))), 50)
# Generate the alignment
subset_dict = Cluster.get_subsets('rows', infile, informat, 5)
# Check the output
self.assertEqual(len(subset_dict), 5)
for subset in viewvalues(subset_dict) :
self.assertEqual(len(subset), 10)
def test_default(self):
"""
Testing default procedure for the genes method.
"""
infile = 'Genbank/f006.genbank'
informat = 'genbank'
# Check the input
self.assertTrue(os.path.isfile(infile))
self.assertEqual(len(list(SeqIO.parse(infile, informat))), 5)
# Generate the gene clustering
subset_dict = Cluster.get_subsets('genes', infile, informat)
# Check the output
self.assertEqual(len(subset_dict), 63)
self.assertIn('unprocessable', subset_dict)
self.assertEqual(len(subset_dict['unprocessable']), 0)
def test_feature_filter(self):
"""
Testing the genes method with a feature filter.
"""
infile = "Genbank/f006.genbank"
informat = "genbank"
# Check the input
self.assertTrue(os.path.isfile(infile))
self.assertEqual(len(list(SeqIO.parse(infile, informat))), 5)
# Generate the gene clustering
subset_dict = Cluster.get_subsets("genes", infile, informat, feature_filter=["CDS"])
# Check the output
self.assertEqual(len(subset_dict), 14)
for key, subset in viewitems(subset_dict):
if key == "unprocessable":
self.assertEqual(len(subset), 0)
else:
self.assertEqual(len(subset), 5)
def test_feature_filter(self):
"""
Testing the genes method with a feature filter.
"""
infile = 'Genbank/f006.genbank'
informat = 'genbank'
# Check the input
self.assertTrue(os.path.isfile(infile))
self.assertEqual(len(list(SeqIO.parse(infile, informat))), 5)
# Generate the gene clustering
subset_dict = Cluster.get_subsets('genes',
infile,
informat,
feature_filter=['CDS'])
# Check the output
self.assertEqual(len(subset_dict), 14)
for key, subset in viewitems(subset_dict):
if (key == 'unprocessable'):
self.assertEqual(len(subset), 0)
else:
self.assertEqual(len(subset), 5)