def test_nexus_header(self):
dataset = Dataset(self.seq_records,
format='NEXUS',
partitioning='by gene')
expected = '10'
result = dataset.number_taxa
self.assertEqual(expected, result)
def test_dataset(self):
dataset = Dataset(self.test_data,
format='FASTA',
partitioning='by gene')
result = dataset.dataset_str
expected = open(os.path.join(FASTA_DATA_PATH, 'dataset.fas')).read()
self.assertEqual(expected, result)
def test_generation_of_errors(self):
self.seq_records[0].seq = 'TTTN--CAGTAG'
with self.assertRaises(TranslationErrorMixedGappedSeq):
Dataset(self.seq_records,
format='NEXUS',
partitioning='by gene',
aminoacids=True)
def test_dataset_as_aminoacids(self):
dataset = Dataset(test_data,
format='MEGA',
partitioning='by gene',
aminoacids=True)
result = dataset.dataset_str
expected = open(os.path.join(MEGA_DATA_PATH, 'dataset_aa.meg')).read()
self.assertEqual(expected, result)
def test_generation_of_warnings(self):
self.seq_records[0].seq = 'TTTCAGTAG'
dataset = Dataset(self.seq_records,
format='NEXUS',
partitioning='by gene',
aminoacids=True)
expected = "Gene ArgKin, sequence CP100_10 contains stop codons '*'"
self.assertEqual(expected, dataset.warnings[0])
def test_dataset_all_codon_positions_partitioned_by_gene(self):
dataset = Dataset(self.seq_records,
format='NEXUS',
codon_positions='ALL',
partitioning='by gene')
test_data_file = os.path.join(NEXUS_DATA_PATH, 'dataset.nex')
expected = open(test_data_file, 'r').read()
result = dataset.dataset_str
self.assertEqual(expected.strip(), result)
def test_dataset_as_degenerate(self):
dataset = Dataset(test_data,
format='MEGA',
partitioning='by gene',
degenerate='S')
result = dataset.dataset_str
expected = open(os.path.join(MEGA_DATA_PATH,
'dataset_degenerate.meg')).read()
self.assertEqual(expected, result)
def test_codon_positions_parameter(self):
dataset = Dataset(self.seq_records,
format='NEXUS',
partitioning='by gene')
self.assertRaises(AttributeError,
DatasetFooter,
data=dataset.data,
codon_positions='1st-2nd, 3rd',
partitioning='by gene')
def test_aminoacid_dataset(self):
dataset = Dataset(self.seq_records,
format='NEXUS',
partitioning='by gene',
aminoacids=True)
result = dataset.dataset_str
with open(os.path.join(NEXUS_DATA_PATH, 'dataset_aa.nex'),
'r') as handle:
expected = handle.read()
self.assertEqual(expected.strip(), result)
def test_partitioned_by_1st2nd_3rd_only_3rd_codon_position(self):
test_data = get_test_data("sample_data_numbers.txt")
dataset = Dataset(test_data,
format='FASTA',
partitioning='1st-2nd, 3rd',
codon_positions='3rd')
result = dataset.dataset_str
expected = open(
os.path.join(FASTA_DATA_PATH, 'dataset_3rd_numbers.fas')).read()
self.assertEqual(expected, result)
def test_dataset_1st_2nd_codon_positions_partitioned_by_gene(self):
seq_records = get_test_data("seq_records", "sample_data_numbers.txt")
dataset = Dataset(seq_records,
format='NEXUS',
codon_positions='1st-2nd',
partitioning='by gene')
test_data_file = os.path.join(NEXUS_DATA_PATH,
'dataset_1st2nd_codons_numbers.nex')
expected = open(test_data_file, 'r').read()
result = dataset.dataset_str
self.assertEqual(expected, result)
def test_dataset__with_long_name(self):
"""Test that we can output fasta files with long names
Test taht we don't truncate to 54 characters
"""
dataset = Dataset(self.test_data,
format='FASTA',
partitioning='by gene')
result = dataset.dataset_str
expected = open(os.path.join(FASTA_DATA_PATH, 'dataset.fas')).read()
self.assertEqual(expected, result)
def test_make_partition_line(self):
dataset = Dataset(test_data, format='NEXUS', partitioning='by gene')
footer = DatasetFooter(data=dataset.data,
codon_positions='ALL',
partitioning='by gene')
expected = """
partition GENES = 7: ArgKin, COI-begin, COI_end, ef1a, RpS2, RpS5, wingless;
set partition = GENES;
"""
result = footer.make_partition_line()
self.assertEqual(expected.strip(), result)
def test_dataset_with_gaps(self):
seq = self.test_data[0].seq
seq = list(seq)
seq[:3] = "---"
self.test_data[0].seq = "".join(seq)
dataset = Dataset(self.test_data,
format='FASTA',
partitioning='by gene')
result = dataset.dataset_str
expected = open(os.path.join(FASTA_DATA_PATH,
'dataset_with_gaps.fas')).read()
self.assertEqual(expected, result)
def test_dataset_when_seqrecord_taxonomy_is_none(self):
raw_data = get_test_data('raw_data')
raw_data[0]['taxonomy'] = None
seq_records = []
for i in raw_data:
seq_record = SeqRecordExpanded(i['seq'],
voucher_code=i['voucher_code'],
taxonomy=i['taxonomy'],
gene_code=i['gene_code'],
reading_frame=i['reading_frame'],
table=i['table'])
seq_records.append(seq_record)
dataset = Dataset(seq_records, format='NEXUS', partitioning='by gene')
self.assertTrue('CP100_10 ' in dataset.dataset_str)
def test_make_charset_block(self):
dataset = Dataset(self.seq_records,
format='NEXUS',
partitioning='by gene')
footer = DatasetFooter(data=dataset.data,
codon_positions='ALL',
partitioning='by gene')
expected = """
begin mrbayes;
charset ArgKin = 1-596;
charset COI-begin = 597-1265;
charset COI_end = 1266-2071;
charset ef1a = 2072-3311;
charset RpS2 = 3312-3722;
charset RpS5 = 3723-4339;
charset wingless = 4340-4739;
"""
result = footer.charset_block
self.assertEqual(expected.strip(), result)
def test_dataset_when_seqrecord_taxonomy_is_has_family(self):
raw_data = get_test_data('raw_data')
raw_data[0]['taxonomy'] = {
'family': 'Aussidae',
'genus': 'Aus',
'species': 'aus'
}
seq_records = []
for i in raw_data:
seq_record = SeqRecordExpanded(i['seq'],
voucher_code=i['voucher_code'],
taxonomy=i['taxonomy'],
gene_code=i['gene_code'],
reading_frame=i['reading_frame'],
table=i['table'])
seq_records.append(seq_record)
dataset = Dataset(seq_records, format='NEXUS', partitioning='by gene')
self.assertTrue('CP100_10_Aussidae_Aus_aus ' in dataset.dataset_str)
def test_charset_file(self):
dataset = Dataset(self.test_data, format='PHYLIP', partitioning='by gene')
result = dataset.extra_dataset_str
with open(os.path.join(PHYLIP_DATA_PATH, 'charset_block_file.txt'), 'r') as handle:
expected = handle.read()
self.assertEqual(expected.strip(), result)
def test_dataset(self):
dataset = Dataset(self.test_data, format='PHYLIP', partitioning='by gene')
result = dataset.dataset_str
with open(os.path.join(PHYLIP_DATA_PATH, 'dataset.phy'), 'r') as handle:
expected = handle.read()
self.assertEqual(expected.strip(), result.strip())
def test_dataset_with_degenerate(self):
dataset = Dataset(self.data, format='TNT', partitioning='by gene',
degenerate='S')
result = dataset.dataset_str
expected = open(os.path.join(TNT_DATA_PATH, 'dataset_degenerate.tnt')).read()
self.assertEqual(expected.rstrip(), result)
def test_aa_dataset_with_outgroup(self):
with open(os.path.join(TNT_DATA_PATH, 'dataset_aa_with_outgroup.tnt'), "r") as handle:
expected = handle.read()
dataset = Dataset(self.data, format='TNT', partitioning='by gene',
outgroup='CP100-15', aminoacids=True)
self.assertEqual(expected.rstrip(), dataset.dataset_str)