def _impl_test_tree_estimator(self, name, datatype, partitions, **kwargs):
num_cpus = kwargs.get('num_cpus', None)
filename = data_source_path('anolis.fasta')
md = MultiLocusDataset()
md.read_files(seq_filename_list=[filename],
datatype=datatype)
md.relabel_for_sate()
# alignment = Alignment()
# alignment.read_filepath(filename, 'FASTA')
te = self.get_tree_estimator(name)
if te is None:
_LOG.warn("test%s skipped" % name)
return
# alignment.datatype = datatype
if num_cpus:
a = te.run(alignment=md,
partitions=partitions,
tmp_dir_par=self.ts.top_level_temp,
delete_temps=True,
num_cpus=num_cpus)
else:
a = te.run(alignment=md,
partitions=partitions,
tmp_dir_par=self.ts.top_level_temp,
delete_temps=True)
def setUp(self):
self.set_up()
self.tmp_sub_dir = self.ts.create_temp_subdir(
parent=self.ts.top_level_temp, prefix='MultiLocusDatasetTest')
self.data_path = os.path.join(self.tmp_sub_dir,
self.job_name + '_test.fasta')
self.mlds = MultiLocusDataset()
class MultiLocusDatasetTest(SateTestCase):
def setUp(self):
self.set_up()
self.tmp_sub_dir = self.ts.create_temp_subdir(
parent=self.ts.top_level_temp,
prefix='MultiLocusDatasetTest')
self.data_path = os.path.join(self.tmp_sub_dir,
self.job_name + '_test.fasta')
self.mlds = MultiLocusDataset()
def tearDown(self):
self.register_files()
self.ts.remove_dir(self.tmp_sub_dir)
self.tear_down()
def _create_seq_file(self, seq_str):
out = open(self.data_path, 'w')
out.write(seq_str)
out.close()
def _parse_seq_dataset(self, sd):
d = {}
for taxon, char_vec in sd.dataset.char_matrices[0].iteritems():
d[taxon.label] = ''.join([i for i in char_vec])
return d
def testRNAConversion(self):
sf = StringIO()
sf.write('>a\nAUGCAUGC\n')
sf.write('>b\nAUGCAUGC\n')
self._create_seq_file(sf.getvalue())
sf.seek(0)
seqs = self.parse_fasta_file(sf)
self.mlds.read_files([self.data_path],
datatype='RNA',
file_format='FASTA')
self.assertEqual(len(self.mlds), 1)
self.assertSameDataSet([seqs, self._parse_seq_dataset(self.mlds[0])])
self.mlds.convert_rna_to_dna()
seqs = self.convert_rna_to_dna(seqs)
for k, v in seqs.iteritems():
self.assertTrue('T' in v)
self.assertSameDataSet([seqs,
self._parse_seq_dataset(self.mlds[0])])
self.mlds.convert_rna_to_dna()
self.assertSameDataSet([seqs,
self._parse_seq_dataset(self.mlds[0])])
self.mlds.convert_dna_to_rna()
seqs = self.convert_rna_to_dna(seqs, reverse=True)
for k, v in seqs.iteritems():
self.assertFalse('T' in v)
self.assertSameDataSet([seqs,
self._parse_seq_dataset(self.mlds[0])])
self.mlds.convert_rna_to_dna()
seqs = self.convert_rna_to_dna(seqs)
for k, v in seqs.iteritems():
self.assertTrue('T' in v)
self.assertSameDataSet([seqs,
self._parse_seq_dataset(self.mlds[0])])
def read_input_sequences(seq_filename_list,
datatype,
missing=None):
md = MultiLocusDataset()
md.read_files(seq_filename_list=seq_filename_list,
datatype=datatype,
missing=missing)
return md
class MultiLocusDatasetTest(SateTestCase):
def setUp(self):
self.set_up()
self.tmp_sub_dir = self.ts.create_temp_subdir(
parent=self.ts.top_level_temp, prefix='MultiLocusDatasetTest')
self.data_path = os.path.join(self.tmp_sub_dir,
self.job_name + '_test.fasta')
self.mlds = MultiLocusDataset()
def tearDown(self):
self.register_files()
self.ts.remove_dir(self.tmp_sub_dir)
self.tear_down()
def _create_seq_file(self, seq_str):
out = open(self.data_path, 'w')
out.write(seq_str)
out.close()
def _parse_seq_dataset(self, sd):
d = {}
for taxon, char_vec in sd.dataset.char_matrices[0].iteritems():
d[taxon.label] = ''.join([i for i in char_vec])
return d
def testRNAConversion(self):
sf = StringIO()
sf.write('>a\nAUGCAUGC\n')
sf.write('>b\nAUGCAUGC\n')
self._create_seq_file(sf.getvalue())
sf.seek(0)
seqs = self.parse_fasta_file(sf)
self.mlds.read_files([self.data_path],
datatype='RNA',
file_format='FASTA')
self.assertEqual(len(self.mlds), 1)
self.assertSameDataSet([seqs, self._parse_seq_dataset(self.mlds[0])])
self.mlds.convert_rna_to_dna()
seqs = self.convert_rna_to_dna(seqs)
for k, v in seqs.iteritems():
self.assertTrue('T' in v)
self.assertSameDataSet([seqs, self._parse_seq_dataset(self.mlds[0])])
self.mlds.convert_rna_to_dna()
self.assertSameDataSet([seqs, self._parse_seq_dataset(self.mlds[0])])
self.mlds.convert_dna_to_rna()
seqs = self.convert_rna_to_dna(seqs, reverse=True)
for k, v in seqs.iteritems():
self.assertFalse('T' in v)
self.assertSameDataSet([seqs, self._parse_seq_dataset(self.mlds[0])])
self.mlds.convert_rna_to_dna()
seqs = self.convert_rna_to_dna(seqs)
for k, v in seqs.iteritems():
self.assertTrue('T' in v)
self.assertSameDataSet([seqs, self._parse_seq_dataset(self.mlds[0])])
def setUp(self):
self.set_up()
self.tmp_sub_dir = self.ts.create_temp_subdir(
parent=self.ts.top_level_temp,
prefix='MultiLocusDatasetTest')
self.data_path = os.path.join(self.tmp_sub_dir,
self.job_name + '_test.fasta')
self.mlds = MultiLocusDataset()
def _impl_test_tree_estimator(self, name, datatype, partitions, **kwargs):
num_cpus = kwargs.get('num_cpus', None)
filename = data_source_path('anolis.fasta')
md = MultiLocusDataset()
md.read_files(seq_filename_list=[filename], datatype=datatype)
md.relabel_for_sate()
# alignment = Alignment()
# alignment.read_filepath(filename, 'FASTA')
te = self.get_tree_estimator(name)
if te is None:
_LOG.warn("test%s skipped" % name)
return
# alignment.datatype = datatype
if num_cpus:
a = te.run(alignment=md,
partitions=partitions,
tmp_dir_par=self.ts.top_level_temp,
delete_temps=True,
num_cpus=num_cpus)
else:
a = te.run(alignment=md,
partitions=partitions,
tmp_dir_par=self.ts.top_level_temp,
delete_temps=True)
def read_input_sequences(seq_filename_list, datatype, missing=None):
md = MultiLocusDataset()
md.read_files(seq_filename_list=seq_filename_list,
datatype=datatype,
missing=missing)
return md