def test_classify_manual_svtype_from_file():
bedpe1 = viola.read_bedpe(StringIO(data))
bedpe2 = viola.read_bedpe(StringIO(data))
ls_conditions = [
small_del, large_del, small_dup, large_dup, small_inv, tra
]
ls_names = [
'small_del', 'large_del', 'small_dup', 'large_dup', 'small_inv', 'tra'
]
multibedpe = viola.MultiBedpe([bedpe1, bedpe2], ['bedpe1', 'bedpe2'])
path = os.path.join(HERE, '../bedpe/data/example_definition.txt')
result = multibedpe.classify_manual_svtype(definitions=path)
manual_sv_type = multibedpe.manual_sv_type
manual_sv_type.set_index('id', inplace=True)
manual_sv_type_expected = pd.read_csv(StringIO(data_expected),
sep='\t',
names=('id', 'value_idx',
'manual_sv_type'))
manual_sv_type_expected.set_index('id', inplace=True)
pd.testing.assert_frame_equal(manual_sv_type,
manual_sv_type_expected,
check_like=True)
result_expected = pd.DataFrame([[2, 3, 1, 0, 2, 2, 2],
[2, 3, 1, 0, 2, 2, 2]])
result_expected.columns = ls_names + ['others']
result_expected.columns.name = 'manual_sv_type'
result_expected.index = ['bedpe1', 'bedpe2']
result_expected.index.name = 'patients'
pd.testing.assert_frame_equal(result, result_expected)
def test_classify_manual_svtype_exclude_empty():
bedpe1 = viola.read_bedpe(StringIO(data))
bedpe2 = viola.read_bedpe(StringIO(data))
empty1 = viola.read_bedpe(StringIO(data_empty))
empty2 = viola.read_bedpe(StringIO(data_empty))
ls_conditions = [
small_del, large_del, small_dup, large_dup, small_inv, tra
]
ls_names = [
'small_del', 'large_del', 'small_dup', 'large_dup', 'small_inv', 'tra'
]
multibedpe = viola.MultiBedpe([bedpe1, empty1, bedpe2, empty2],
['bedpe1', 'empty1', 'bedpe2', 'empty2'])
result = multibedpe.classify_manual_svtype(ls_conditions=ls_conditions,
ls_names=ls_names,
exclude_empty_cases=True)
manual_sv_type = multibedpe.manual_sv_type
manual_sv_type.set_index('id', inplace=True)
manual_sv_type_expected = pd.read_csv(StringIO(data_expected),
sep='\t',
names=('id', 'value_idx',
'manual_sv_type'))
manual_sv_type_expected.set_index('id', inplace=True)
pd.testing.assert_frame_equal(manual_sv_type,
manual_sv_type_expected,
check_like=True)
result_expected = pd.DataFrame([[2, 3, 1, 0, 2, 2, 2],
[2, 3, 1, 0, 2, 2, 2]])
result_expected.columns = ls_names + ['others']
result_expected.columns.name = 'manual_sv_type'
result_expected.index = ['bedpe1', 'bedpe2']
result_expected.index.name = 'patients'
pd.testing.assert_frame_equal(result, result_expected)
class TestReadBedpe:
data = """chrom1\tstart1\tend1\tchrom2\tstart2\tend2\tname\tscore\tstrand1\tstrand2
chr1\t10\t13\tchr2\t20\t30\ttest1\t10\t+\t+
chr3\t100\t130\tchr3\t210\t230\ttest2\t30\t-\t+
"""
b = StringIO(data)
obj = viola.read_bedpe(b)
def test_read_bedpe(self):
b = StringIO(self.data)
viola.read_bedpe(b)
def test_svpos(self):
expected_data = """id\tchrom1\tpos1\tchrom2\tpos2\tstrand1\tstrand2\tqual\tsvtype\tref\talt
test1\tchr1\t12\tchr2\t26\t+\t+\t10\tBND\tN\tN]chr2:26]
test2\tchr3\t116\tchr3\t221\t-\t+\t30\tDUP\tN\t<DUP>
"""
df_svpos = self.obj.get_table('positions')
df_expected = pd.read_csv(StringIO(expected_data), sep="\t")
pd.testing.assert_frame_equal(df_svpos, df_expected)
def test_create_alt_field_from_position(self):
test_data = """id\tchrom1\tpos1\tchrom2\tpos2\tstrand1\tstrand2\tsvtype\tref
test1\tchr1\t10\tchr2\t10\t+\t-\tBND\tN
test2\tchr1\t10\tchr1\t10\t+\t-\tDEL\tN
"""
b = StringIO(test_data)
df_svpos = pd.read_csv(b, sep="\t")
result = viola.io.parser.create_alt_field_from_position(df_svpos)
def test_classify_manual_svtype():
bedpe = viola.read_bedpe(StringIO(data))
ls_conditions = [
small_del, large_del, small_dup, large_dup, small_inv, tra
]
ls_names = [
'small_del', 'large_del', 'small_dup', 'large_dup', 'small_inv', 'tra'
]
result = bedpe.classify_manual_svtype(ls_conditions=ls_conditions,
ls_names=ls_names)
manual_sv_type = bedpe.manual_sv_type
manual_sv_type.set_index('id', inplace=True)
manual_sv_type_expected = pd.read_csv(StringIO(data_expected),
sep='\t',
names=('id', 'value_idx',
'manual_sv_type'))
manual_sv_type_expected.set_index('id', inplace=True)
pd.testing.assert_frame_equal(manual_sv_type,
manual_sv_type_expected,
check_like=True)
result_expected = pd.Series([2, 3, 1, 0, 2, 2, 2])
result_expected.index = ls_names + ['others']
result_expected.name = 'manual_sv_type'
pd.testing.assert_series_equal(result, result_expected)
def test_remove_info():
bedpe = viola.read_bedpe(StringIO(data))
bedpe_copy = bedpe.copy()
test_info = pd.DataFrame({'id': ['test1', 'test2'], 'value_idx': [0, 0], 'test': ['t', 'u']})
bedpe.add_info_table('test', test_info)
bedpe.remove_info_table('test')
viola.testing.assert_bedpe_equal(bedpe, bedpe_copy)
def test_to_bedpe():
bedpe = viola.read_bedpe(StringIO(data))
bedpe.to_bedpe(os.path.join(HERE, 'data/output.bedpe'))
bedpe.to_bedpe(os.path.join(HERE, 'data/output.svlen.bedpe'),
custom_infonames=['svlen'])
assert filecmp.cmp(os.path.join(HERE, 'data/output.bedpe'),
os.path.join(HERE, 'data/bedpe_expected.bedpe'))
assert filecmp.cmp(os.path.join(HERE, 'data/output.svlen.bedpe'),
os.path.join(HERE, 'data/output.svlen.expected.bedpe'))
def generate_feature_matrix(input_dir, input_files, input_files_id, format_,
caller, svtype_col_name, as_breakpoint,
definitions, output):
"""
Generate feature matrix from VCF or BEDPE files.
"""
if format_ == 'bedpe':
if (input_dir is None) & (input_files is None):
return
elif (input_files is None):
data = viola.read_bedpe_multi(input_dir,
svtype_col_name=svtype_col_name)
elif (input_dir is None):
ls_input = input_files.split(',')
ls_bedpe = [
viola.read_bedpe(path, svtype_col_name=svtype_col_name)
for path in ls_input
]
if input_files_id is None:
ls_names = range(len(ls_bedpe))
else:
ls_names = input_files_id.split(',')
data = viola.MultiBedpe(ls_bedpe, ls_names)
else:
return
else:
if (input_dir is None) & (input_files is None):
return
elif (input_files is None):
data = viola.read_vcf_multi(input_dir,
variant_caller=caller,
as_breakpoint=as_breakpoint)
elif (input_dir is None):
ls_input = input_files.split(',')
if as_breakpoint:
ls_vcf = [
viola.read_vcf(
path, variant_caller=caller).breakend2breakpoint()
for path in ls_input
]
else:
ls_vcf = [
viola.read_vcf(path, variant_caller=caller)
for path in ls_input
]
if input_files_id is None:
ls_names = range(len(ls_vcf))
else:
ls_names = input_files_id.split(',')
data = viola.MultiBedpe(ls_vcf, ls_names)
else:
return
result = data.classify_manual_svtype(definitions=definitions)
result.to_csv(output, sep='\t')
def test_append_info():
bedpe = viola.read_bedpe(StringIO(data))
test_info = pd.DataFrame({
'id': ['test1', 'test2'],
'value_idx': [0, 0],
'test': ['t', 'u']
})
bedpe.add_info_table('test', test_info)
pd.testing.assert_frame_equal(bedpe._odict_alltables['test'], test_info)
pd.testing.assert_frame_equal(bedpe._odict_df_info['test'], test_info)
assert 'test' in bedpe._ls_infokeys
def test_classify_manual_svtype_from_file():
bedpe = viola.read_bedpe(StringIO(data))
path = os.path.join(HERE, 'data/example_definition.txt')
result = bedpe.classify_manual_svtype(definitions=path)
manual_sv_type = bedpe.manual_sv_type
manual_sv_type.set_index('id', inplace=True)
manual_sv_type_expected = pd.read_csv(StringIO(data_expected),
sep='\t',
names=('id', 'value_idx',
'manual_sv_type'))
manual_sv_type_expected.set_index('id', inplace=True)
pd.testing.assert_frame_equal(manual_sv_type,
manual_sv_type_expected,
check_like=True)
result_expected = pd.Series([2, 3, 1, 0, 2, 2, 2])
ls_names = [
'small_del', 'large_del', 'small_dup', 'large_dup', 'small_inv', 'tra'
]
result_expected.index = ls_names + ['others']
result_expected.name = 'manual_sv_type'
pd.testing.assert_series_equal(result, result_expected)
def test_copy():
bedpe = viola.read_bedpe(StringIO(data))
bedpe_copy = bedpe.copy()
viola.testing.assert_bedpe_equal(bedpe, bedpe_copy)
def test_read_bedpe(self):
b = StringIO(self.data)
viola.read_bedpe(b)
def test_classify_manual_svtype_from_article():
bedpe = viola.read_bedpe(StringIO(data))
try:
result = bedpe.classify_manual_svtype(definitions="article")
except TypeError:
pass
def test_read_bedpe_with_empty():
bedpe1 = viola.read_bedpe(StringIO(data))
bedpe2 = viola.read_bedpe(StringIO(data))
bedpe_empty = viola.read_bedpe(StringIO(data_empty))
multibedpe = viola.MultiBedpe([bedpe1, bedpe2, bedpe_empty], ['bedpe1', 'bedpe2', 'empty'])
