def testSmallRna(self):
if is_test_enabled(
TestLevel.EXHAUSTIVE, _LOG, module_name=".".join([self.__class__.__name__, sys._getframe().f_code.co_name])
):
cmd = [
"-i",
self.small_rna,
"-t",
self.small_tree,
"-d",
"rna",
"-o",
self.ts.top_level_temp,
"--temporaries=%s" % self.ts.top_level_temp,
"-j",
self.job_name,
"--keeptemp",
"--iter-limit=1",
]
self._exe(cmd)
self.assert_is_nuc(self.small_rna, "RNA")
self.assert_is_nuc(self.small_aln_path, "RNA")
self.assertSameInputOutputSequenceData([self.small_rna], [self.small_aln_path])
self.assertNoGapColumns([self.small_aln_path, self.iter_aln_path])
self.assert_is_nuc(self.iter_aln_path, "DNA")
self.assertSameSequences(
[self.small_rna, self.small_aln_path, self.convert_rna_to_dna(self.iter_aln_path, reverse=True)]
)
cfg = get_configuration(self.cfg_path)
self.assertEqual(cfg.commandline.datatype.upper(), "RNA")
def testProteinAmbiguousCharactersMafftFasttreeTrusted(self):
if is_test_enabled(TestLevel.EXHAUSTIVE,
_LOG,
module_name=".".join([
self.__class__.__name__,
sys._getframe().f_code.co_name
])):
arg_list = [
'-d',
'protein',
'--temporaries=%s' % self.ts.top_level_temp,
'--iter-limit=1',
'-j',
self.job_name,
'-o',
self.ts.top_level_temp,
'-i',
self.ambig_aa,
'-t',
self.ambig_aa_tree,
'--aligner=mafft',
'--merger=muscle',
'--tree-estimator=fasttree',
]
self._exe_run_sate(arg_list, rc=0)
self.assertSameInputOutputSequenceData([self.ambig_aa], [
os.path.join(
self.ts.top_level_temp, self.job_name +
'.marker001.caenophidia_mos.ambiguities.aln')
])
self.assertNoGapColumns([
os.path.join(
self.ts.top_level_temp, self.job_name +
'.marker001.caenophidia_mos.ambiguities.aln')
])
def testSingleAminoAcidLocusRun(self):
if is_test_enabled(TestLevel.EXHAUSTIVE,
_LOG,
module_name=".".join([
self.__class__.__name__,
sys._getframe().f_code.co_name
])):
arg_list = [
'-d',
'protein',
'--temporaries=%s' % self.ts.top_level_temp,
'--iter-limit=1',
'-j',
self.job_name,
'-o',
self.ts.top_level_temp,
'-i',
self.caenophidia_file,
]
self._exe_run_sate(arg_list, rc=0)
self.assertSameInputOutputSequenceData([self.caenophidia_file], [
os.path.join(self.ts.top_level_temp,
self.job_name + '.marker001.caenophidia_mos.aln')
])
self.assertNoGapColumns([
os.path.join(self.ts.top_level_temp,
self.job_name + '.marker001.caenophidia_mos.aln')
])
def testSmallRna(self):
if is_test_enabled(TestLevel.EXHAUSTIVE,
_LOG,
module_name=".".join([
self.__class__.__name__,
sys._getframe().f_code.co_name
])):
cmd = [
'-i', self.small_rna, '-t', self.small_tree, '-d', 'rna', '-o',
self.ts.top_level_temp,
'--temporaries=%s' % self.ts.top_level_temp, '-j',
self.job_name, '--keeptemp', '--iter-limit=1'
]
self._exe(cmd)
self.assert_is_nuc(self.small_rna, 'RNA')
self.assert_is_nuc(self.small_aln_path, 'RNA')
self.assertSameInputOutputSequenceData([self.small_rna],
[self.small_aln_path])
self.assertNoGapColumns([self.small_aln_path, self.iter_aln_path])
self.assert_is_nuc(self.iter_aln_path, 'DNA')
self.assertSameSequences([
self.small_rna, self.small_aln_path,
self.convert_rna_to_dna(self.iter_aln_path, reverse=True)
])
cfg = get_configuration(self.cfg_path)
self.assertEqual(cfg.commandline.datatype.upper(), 'RNA')
def testMultiDnaLocusRun(self):
if is_test_enabled(TestLevel.EXHAUSTIVE, _LOG,
module_name=".".join([self.__class__.__name__,
sys._getframe().f_code.co_name])):
arg_list = ['-d', 'dna',
'--temporaries=%s' % self.ts.top_level_temp,
'--iter-limit=1',
'-m',
'-j', self.job_name,
'-o', self.ts.top_level_temp,
'-i', self.multi_dir,]
self._exe_run_sate(arg_list, rc=0)
seqs_in1_path = os.path.join(self.multi_dir, '1.fasta')
seqs_in2_path = os.path.join(self.multi_dir, '2.fasta')
seqs_out1_path = os.path.join(self.ts.top_level_temp,
self.job_name + '.marker001.1.aln')
seqs_out2_path = os.path.join(self.ts.top_level_temp,
self.job_name + '.marker002.2.aln')
self.assertSameInputOutputSequenceData(
[seqs_in1_path, seqs_in2_path],
[seqs_out1_path, seqs_out2_path])
concat_out = os.path.join(self.ts.top_level_temp,
self.job_name + '_temp_iteration_0_seq_alignment.txt')
self.assertSameConcatenatedSequences(
concatenated_data=concat_out,
seq_data_list=[seqs_in1_path, seqs_in2_path])
self.assertNoGapColumns([seqs_out1_path, seqs_out2_path,
concat_out])
def testRnaDnaIdentity(self):
if is_test_enabled(
TestLevel.EXHAUSTIVE, _LOG, module_name=".".join([self.__class__.__name__, sys._getframe().f_code.co_name])
):
dna_cmd = [
"-i",
self.dna,
"-d",
"dna",
"-t",
self.tree,
"-o",
self.dna_tmp,
"--temporaries=%s" % self.dna_tmp,
"-j",
self.job_name,
"--aligner=mafft",
"--merger=muscle",
"--tree-estimator=fasttree",
"--start-tree-search-from-current",
"--tree-estimator-model=-gtr -gamma -seed 1111",
"--iter-limit=1",
]
self._exe_run_sate(dna_cmd)
rna_cmd = [
"-i",
self.rna,
"-d",
"rna",
"-t",
self.tree,
"-o",
self.rna_tmp,
"--temporaries=%s" % self.rna_tmp,
"-j",
self.job_name,
"--aligner=mafft",
"--merger=muscle",
"--tree-estimator=fasttree",
"--start-tree-search-from-current",
"--tree-estimator-model=-gtr -gamma -seed 1111",
"--iter-limit=1",
]
self._exe_run_sate(rna_cmd)
self.assert_is_nuc(self.dna_aln, "DNA")
self.assert_is_nuc(self.rna_aln, "RNA")
self.assertNoGapColumns([self.dna_aln, self.rna_aln])
self.assertSameDataSet(
[
self.rna,
self.rna_aln,
self.convert_rna_to_dna(self.dna, reverse=True),
self.convert_rna_to_dna(self.dna_aln, reverse=True),
]
)
# self.assertSameScores([self.dna_score, self.rna_score])
# self.assertSameTrees([self.dna_tree, self.rna_tree])
self.assertSameFiles([self.dna_tmp_aln, self.rna_tmp_aln])
def testHummingBirdDataRun(self):
if is_test_enabled(TestLevel.EXHAUSTIVE,
_LOG,
module_name=".".join([
self.__class__.__name__,
sys._getframe().f_code.co_name
])):
arg_list = [
'-d',
'dna',
'--temporaries=%s' % self.ts.top_level_temp,
'--iter-limit=1',
'--start-tree-search-from-current',
'--treefile=%s' %
os.path.join(self.hummingbird_dir, 'starting.tre'),
'--merger=muscle',
'--tree-estimator=fasttree',
'-m',
'-j',
self.job_name,
'-o',
self.ts.top_level_temp,
'-i',
self.hummingbird_dir,
]
self._exe_run_sate(arg_list, rc=0)
seqs_in1_path = os.path.join(self.hummingbird_dir, 'AK1.fasta')
seqs_in2_path = os.path.join(self.hummingbird_dir, 'bfib.fasta')
seqs_in3_path = os.path.join(self.hummingbird_dir, 'nd2.fasta')
seqs_in4_path = os.path.join(self.hummingbird_dir, 'nd4.fasta')
seqs_out1_path = os.path.join(self.ts.top_level_temp,
self.job_name + '.marker001.AK1.aln')
seqs_out2_path = os.path.join(
self.ts.top_level_temp, self.job_name + '.marker002.bfib.aln')
seqs_out3_path = os.path.join(self.ts.top_level_temp,
self.job_name + '.marker003.nd2.aln')
seqs_out4_path = os.path.join(self.ts.top_level_temp,
self.job_name + '.marker004.nd4.aln')
self.assertSameInputOutputSequenceData(
[seqs_in1_path, seqs_in2_path, seqs_in3_path, seqs_in4_path], [
seqs_out1_path, seqs_out2_path, seqs_out3_path,
seqs_out4_path
])
concat_out = os.path.join(
self.ts.top_level_temp,
self.job_name + '_temp_iteration_0_seq_alignment.txt')
self.assertSameConcatenatedSequences(concatenated_data=concat_out,
seq_data_list=[
seqs_in1_path,
seqs_in2_path,
seqs_in3_path,
seqs_in4_path
])
self.assertNoGapColumns([
seqs_out1_path, seqs_out2_path, seqs_out3_path, seqs_out4_path,
concat_out
])
def testMulti(self):
if is_test_enabled(TestLevel.EXHAUSTIVE,
_LOG,
module_name=".".join([
self.__class__.__name__,
sys._getframe().f_code.co_name
])):
self._main_execution([
'-m', '-i',
data_source_path('testmulti'), '-o', self.ts.top_level_temp,
'--temporaries=%s' % self.ts.top_level_temp, '-j',
self.job_name, '--iter-limit=1'
])
def testHummingBirdDataRun(self):
if is_test_enabled(TestLevel.EXHAUSTIVE, _LOG,
module_name=".".join([self.__class__.__name__,
sys._getframe().f_code.co_name])):
arg_list = ['-d', 'dna',
'--temporaries=%s' % self.ts.top_level_temp,
'--iter-limit=1',
'--start-tree-search-from-current',
'--treefile=%s' % os.path.join(
self.hummingbird_dir,
'starting.tre'),
'--merger=muscle',
'--tree-estimator=fasttree',
'-m',
'-j', self.job_name,
'-o', self.ts.top_level_temp,
'-i', self.hummingbird_dir,]
self._exe_run_sate(arg_list, rc=0)
seqs_in1_path = os.path.join(self.hummingbird_dir,
'AK1.fasta')
seqs_in2_path = os.path.join(self.hummingbird_dir,
'bfib.fasta')
seqs_in3_path = os.path.join(self.hummingbird_dir,
'nd2.fasta')
seqs_in4_path = os.path.join(self.hummingbird_dir,
'nd4.fasta')
seqs_out1_path = os.path.join(self.ts.top_level_temp,
self.job_name + '.marker001.AK1.aln')
seqs_out2_path = os.path.join(self.ts.top_level_temp,
self.job_name + '.marker002.bfib.aln')
seqs_out3_path = os.path.join(self.ts.top_level_temp,
self.job_name + '.marker003.nd2.aln')
seqs_out4_path = os.path.join(self.ts.top_level_temp,
self.job_name + '.marker004.nd4.aln')
self.assertSameInputOutputSequenceData(
[seqs_in1_path, seqs_in2_path,
seqs_in3_path, seqs_in4_path],
[seqs_out1_path, seqs_out2_path,
seqs_out3_path, seqs_out4_path])
concat_out = os.path.join(self.ts.top_level_temp,
self.job_name + '_temp_iteration_0_seq_alignment.txt')
self.assertSameConcatenatedSequences(
concatenated_data=concat_out,
seq_data_list=[seqs_in1_path, seqs_in2_path,
seqs_in3_path, seqs_in4_path])
self.assertNoGapColumns([seqs_out1_path, seqs_out2_path,
seqs_out3_path, seqs_out4_path, concat_out])
def testMulti(self):
if is_test_enabled(
TestLevel.EXHAUSTIVE, _LOG, module_name=".".join([self.__class__.__name__, sys._getframe().f_code.co_name])
):
self._main_execution(
[
"-m",
"-i",
data_source_path("testmulti"),
"-o",
self.ts.top_level_temp,
"--temporaries=%s" % self.ts.top_level_temp,
"-j",
self.job_name,
"--iter-limit=1",
]
)
def testSingleAminoAcidLocusRun(self):
if is_test_enabled(TestLevel.EXHAUSTIVE, _LOG,
module_name=".".join([self.__class__.__name__,
sys._getframe().f_code.co_name])):
arg_list = ['-d', 'protein',
'--temporaries=%s' % self.ts.top_level_temp,
'--iter-limit=1',
'-j', self.job_name,
'-o', self.ts.top_level_temp,
'-i', self.caenophidia_file,]
self._exe_run_sate(arg_list, rc=0)
self.assertSameInputOutputSequenceData(
[self.caenophidia_file],
[os.path.join(self.ts.top_level_temp,
self.job_name + '.marker001.caenophidia_mos.aln')])
self.assertNoGapColumns([os.path.join(self.ts.top_level_temp,
self.job_name + '.marker001.caenophidia_mos.aln')])
def testMultiAminoAcidLocusRun(self):
if is_test_enabled(TestLevel.EXHAUSTIVE,
_LOG,
module_name=".".join([
self.__class__.__name__,
sys._getframe().f_code.co_name
])):
arg_list = [
'-d',
'protein',
'--temporaries=%s' % self.ts.top_level_temp,
'--iter-limit=1',
'-m',
'-j',
self.job_name,
'-o',
self.ts.top_level_temp,
'-i',
self.multi_aa_dir,
]
self._exe_run_sate(arg_list, rc=0)
seqs_in1_path = os.path.join(self.multi_aa_dir,
'caenophidia_mos.fasta')
seqs_in2_path = os.path.join(self.multi_aa_dir,
'caenophidia_mos2.fasta')
seqs_out1_path = os.path.join(
self.ts.top_level_temp,
self.job_name + '.marker001.caenophidia_mos.aln')
seqs_out2_path = os.path.join(
self.ts.top_level_temp,
self.job_name + '.marker002.caenophidia_mos2.aln')
self.assertSameInputOutputSequenceData(
[seqs_in1_path, seqs_in2_path],
[seqs_out1_path, seqs_out2_path])
concat_out = os.path.join(
self.ts.top_level_temp,
self.job_name + '_temp_iteration_0_seq_alignment.txt')
self.assertSameConcatenatedSequences(
concatenated_data=concat_out,
seq_data_list=[seqs_in1_path, seqs_in2_path])
self.assertNoGapColumns(
[seqs_out1_path, seqs_out2_path, concat_out])
def testProteinAmbiguousCharactersMafftFasttreeTrusted(self):
if is_test_enabled(TestLevel.EXHAUSTIVE, _LOG,
module_name=".".join([self.__class__.__name__,
sys._getframe().f_code.co_name])):
arg_list = ['-d', 'protein',
'--temporaries=%s' % self.ts.top_level_temp,
'--iter-limit=1',
'-j', self.job_name,
'-o', self.ts.top_level_temp,
'-i', self.ambig_aa,
'-t', self.ambig_aa_tree,
'--aligner=mafft',
'--merger=muscle',
'--tree-estimator=fasttree',]
self._exe_run_sate(arg_list, rc=0)
self.assertSameInputOutputSequenceData(
[self.ambig_aa],
[os.path.join(self.ts.top_level_temp,
self.job_name + '.marker001.caenophidia_mos.ambiguities.aln')])
self.assertNoGapColumns([os.path.join(self.ts.top_level_temp,
self.job_name + '.marker001.caenophidia_mos.ambiguities.aln')])
def testRnaDnaIdentity(self):
if is_test_enabled(TestLevel.EXHAUSTIVE,
_LOG,
module_name=".".join([
self.__class__.__name__,
sys._getframe().f_code.co_name
])):
dna_cmd = [
'-i', self.dna, '-d', 'dna', '-t', self.tree, '-o',
self.dna_tmp,
'--temporaries=%s' % self.dna_tmp, '-j', self.job_name,
'--aligner=mafft', '--merger=muscle',
'--tree-estimator=fasttree',
'--start-tree-search-from-current',
'--tree-estimator-model=-gtr -gamma -seed 1111',
'--iter-limit=1'
]
self._exe_run_sate(dna_cmd)
rna_cmd = [
'-i', self.rna, '-d', 'rna', '-t', self.tree, '-o',
self.rna_tmp,
'--temporaries=%s' % self.rna_tmp, '-j', self.job_name,
'--aligner=mafft', '--merger=muscle',
'--tree-estimator=fasttree',
'--start-tree-search-from-current',
'--tree-estimator-model=-gtr -gamma -seed 1111',
'--iter-limit=1'
]
self._exe_run_sate(rna_cmd)
self.assert_is_nuc(self.dna_aln, 'DNA')
self.assert_is_nuc(self.rna_aln, 'RNA')
self.assertNoGapColumns([self.dna_aln, self.rna_aln])
self.assertSameDataSet([
self.rna, self.rna_aln,
self.convert_rna_to_dna(self.dna, reverse=True),
self.convert_rna_to_dna(self.dna_aln, reverse=True)
])
# self.assertSameScores([self.dna_score, self.rna_score])
# self.assertSameTrees([self.dna_tree, self.rna_tree])
self.assertSameFiles([self.dna_tmp_aln, self.rna_tmp_aln])
def testDnaAmbiguousCharactersClustalRaxmlUntrusted(self):
if is_test_enabled(TestLevel.EXHAUSTIVE, _LOG,
module_name=".".join([self.__class__.__name__,
sys._getframe().f_code.co_name])):
arg_list = ['-d', 'dna',
'--temporaries=%s' % self.ts.top_level_temp,
'--iter-limit=1',
'-j', self.job_name,
'-o', self.ts.top_level_temp,
'-i', self.ambig_dna,
'-t', self.ambig_dna_tree,
'--aligner=clustalw2',
'--merger=muscle',
'--tree-estimator=raxml',
'--untrusted',]
self._exe_run_sate(arg_list, rc=0)
self.assertSameInputOutputSequenceData(
[self.ambig_dna],
[os.path.join(self.ts.top_level_temp,
self.job_name + '.marker001.small.ambiguities.aln')])
self.assertNoGapColumns([os.path.join(self.ts.top_level_temp,
self.job_name + '.marker001.small.ambiguities.aln')])
def testDnaAmbiguousCharactersClustalRaxmlUntrusted(self):
if is_test_enabled(TestLevel.EXHAUSTIVE,
_LOG,
module_name=".".join([
self.__class__.__name__,
sys._getframe().f_code.co_name
])):
arg_list = [
'-d',
'dna',
'--temporaries=%s' % self.ts.top_level_temp,
'--iter-limit=1',
'-j',
self.job_name,
'-o',
self.ts.top_level_temp,
'-i',
self.ambig_dna,
'-t',
self.ambig_dna_tree,
'--aligner=clustalw2',
'--merger=muscle',
'--tree-estimator=raxml',
'--untrusted',
]
self._exe_run_sate(arg_list, rc=0)
self.assertSameInputOutputSequenceData([self.ambig_dna], [
os.path.join(
self.ts.top_level_temp,
self.job_name + '.marker001.small.ambiguities.aln')
])
self.assertNoGapColumns([
os.path.join(
self.ts.top_level_temp,
self.job_name + '.marker001.small.ambiguities.aln')
])
def testOpal(self):
if is_test_enabled(TestLevel.SLOW, _LOG):
self._impl_test_merger('opal')
def testOpal(self):
if is_test_enabled(TestLevel.SLOW, _LOG):
self._impl_test_merger('opal')
def testMuscle(self):
if is_test_enabled(TestLevel.SLOW, _LOG):
self._impl_test_merger('muscle')
def testMafft(self):
if is_test_enabled(TestLevel.EXHAUSTIVE, _LOG):
self._impl_test_aligner('mafft', 'anolis.fasta')
def testOpal(self):
if is_test_enabled(TestLevel.EXHAUSTIVE, _LOG):
self._impl_test_aligner('opal', 'anolis.fasta')
def testClustalW2(self):
if is_test_enabled(TestLevel.EXHAUSTIVE, _LOG):
self._impl_test_aligner('clustalw2', 'anolis.fasta')
def testClustalW2(self):
if is_test_enabled(TestLevel.EXHAUSTIVE, _LOG):
self._impl_test_aligner('clustalw2', 'anolis.fasta')
def testOpal(self):
if is_test_enabled(TestLevel.EXHAUSTIVE, _LOG):
self._impl_test_aligner('opal', 'anolis.fasta')
def testMafft(self):
if is_test_enabled(TestLevel.EXHAUSTIVE, _LOG):
self._impl_test_aligner('mafft', 'anolis.fasta')
def testMuscle(self):
if is_test_enabled(TestLevel.SLOW, _LOG):
self._impl_test_merger('muscle')
