def test_families_instance_type_assertion():
error_message = "families must be an instance of FamiliesData!"
with pytest.raises(AssertionError) as excinfo:
DenovoLoader.flexible_denovo_load(
None,
None,
denovo_location="foo",
denovo_variant="bar",
denovo_person_id="baz",
families="bla",
)
assert str(excinfo.value) == error_message
def test_read_variants_genome_assertion(fixture_dirname, fake_families):
filename = fixture_dirname("denovo_import/variants_DAE_style.tsv")
with pytest.raises(AssertionError) as excinfo:
DenovoLoader.flexible_denovo_load(
filename,
None,
families=fake_families,
denovo_location="location",
denovo_variant="variant",
denovo_family_id="familyId",
denovo_best_state="bestState",
)
assert str(excinfo.value) == "You must provide a genome object!"
def test_read_variants_DAE_style(genome_2013, fixture_dirname, fake_families):
filename = fixture_dirname("denovo_import/variants_DAE_style.tsv")
res_df = DenovoLoader.flexible_denovo_load(
filename,
genome_2013,
families=fake_families,
denovo_location="location",
denovo_variant="variant",
denovo_family_id="familyId",
denovo_best_state="bestState",
)
expected_df = pd.DataFrame({
"chrom": ["1", "2", "2", "3", "4"],
"position": [123, 234, 234, 345, 456],
"reference": ["A", "T", "G", "G", "G"],
"alternative": ["G", "A", "A", "A", "A"],
"family_id": ["f1", "f1", "f2", "f3", "f4"],
"genotype": [None, None, None, None, None],
"best_state": [
np.array([[2, 2, 1, 2, 1], [0, 0, 1, 0, 1]]),
np.array([[2, 2, 1, 2, 2], [0, 0, 1, 0, 0]]),
np.array([[2, 2, 2, 1], [0, 0, 0, 1]]),
np.array([[1], [1]]),
np.array([[1, 1], [1, 1]]),
],
})
assert compare_variant_dfs(res_df, expected_df)
def test_read_variants_person_ids(genome_2013, filename, fake_families,
fixture_dirname):
filename = fixture_dirname(filename)
res_df = DenovoLoader.flexible_denovo_load(
filename,
genome_2013,
families=fake_families,
denovo_chrom="chrom",
denovo_pos="pos",
denovo_ref="ref",
denovo_alt="alt",
denovo_person_id="personId",
)
expected_df = pd.DataFrame({
"chrom": ["1", "2", "2", "3", "4"],
"position": [123, 234, 235, 345, 456],
"reference": ["A", "T", "G", "G", "G"],
"alternative": ["G", "A", "A", "A", "A"],
"family_id": ["f1", "f1", "f2", "f3", "f4"],
"genotype": [
np.array([[0, 0, 0, 0, 0], [0, 0, 1, 0, 1]]),
np.array([[0, 0, 0, 0, 0], [0, 0, 1, 0, 0]]),
np.array([[0, 0, 0, 0], [0, 0, 0, 1]]),
np.array([[0], [1]]),
np.array([[0, 0], [1, 1]]),
],
"best_state": [None, None, None, None, None],
})
print(res_df)
print(expected_df)
res_df = res_df.sort_values(["chrom", "position", "reference"])
res_df = res_df.reset_index(drop=True)
expected_df = expected_df.sort_values(["chrom", "position", "reference"])
expected_df = expected_df.reset_index(drop=True)
print(res_df)
print(expected_df)
assert compare_variant_dfs(res_df, expected_df)