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 write(self, bioseqs_file):
"""
Save all sequences stored at the BioSeqs object in the 'bioseqs_file'
(in GENBANK format). A file with a detailed report of the sequences will
be created replacing the extension of 'bioseqs_file' by ".rep". If
'bioseqs_file' contains a relative path, the current working directory
will be used to get the absolute path. If any file already exists, it
will be overwritten without warning.
Arguments :
bioseqs_file ( string )
New BioSeqs sequence file.
Raises :
IOError
If the path provided doesn't exist.
"""
data_filepath = get_abspath(bioseqs_file)
report_filepath = os.path.splitext(data_filepath)[0] + ".rep"
# Generate a single string with all the report content
str_report = "\n".join([" ".join(x) for x in self._report])
# Write all the information in the BioSeqs files
try:
SeqIO.write(viewvalues(self.data), data_filepath, "genbank")
with open(report_filepath, "w") as report_file:
report_file.write("Num. sequences: {:d}\nHistory:\n" "{:s}".format(len(self), str_report))
except IOError:
raise
except:
if os.path.lexists(data_filepath):
os.remove(data_filepath)
if os.path.lexists(report_filepath):
os.remove(report_filepath)
raise
def write(self, bioseqs_file):
"""
Save all sequences stored at the BioSeqs object in the 'bioseqs_file'
(in GENBANK format). A file with a detailed report of the sequences will
be created replacing the extension of 'bioseqs_file' by ".rep". If
'bioseqs_file' contains a relative path, the current working directory
will be used to get the absolute path. If any file already exists, it
will be overwritten without warning.
Arguments:
bioseqs_file (string)
New BioSeqs sequence file.
Raises:
IOError
If the path provided doesn't exist.
"""
data_filepath = get_abspath(bioseqs_file)
report_filepath = os.path.splitext(data_filepath)[0] + '.rep'
# Generate a single string with all the report content
str_report = '\n'.join([' '.join(x) for x in self._report])
# Write all the information in the BioSeqs files
try:
SeqIO.write(viewvalues(self.data), data_filepath, 'genbank')
with open(report_filepath, 'w') as report_file:
report_file.write('Num. sequences: {:d}\nHistory:\n' \
'{:s}'.format(len(self), str_report))
except IOError:
raise
except:
if (os.path.lexists(data_filepath)):
os.remove(data_filepath)
if (os.path.lexists(report_filepath)):
os.remove(report_filepath)
raise
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_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_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)
