def test_same_as_the_reference_implementation() -> None:
"""
This test validates that our implementation gets exactly
the same results as the reference R implementation.
"""
d = Path(__file__).parent
ds = read_plink(path="hapmap_JPT_CHB_r23a_filtered")
pcs = da.from_array(
pd.read_csv(d.joinpath("pcs.csv").as_posix(), usecols=[1, 2]).to_numpy()
)
ds[sample_pca_projection] = (("samples", "components"), pcs)
phi = pc_relate(ds).pc_relate_phi.compute()
n_samples = 90
assert isinstance(phi, xr.DataArray)
assert phi.shape == (n_samples, n_samples)
# Get genesis/reference results:
genesis_phi = pd.read_csv(d.joinpath("kinbtwe.csv"))
genesis_phi = genesis_phi[["kin"]].to_numpy()
phi_s = phi.data[np.triu_indices_from(phi.data, 1)] # type: ignore[no-untyped-call]
assert phi_s.size == genesis_phi.size
assert np.allclose(phi_s, genesis_phi.T)
def test_pc_relate__genotype_inputs_checks() -> None:
g_wrong_ploidy = simulate_genotype_call_dataset(100, 10, n_ploidy=3)
with pytest.raises(ValueError, match="PC Relate only works for diploid genotypes"):
pc_relate(g_wrong_ploidy)
g_non_biallelic = simulate_genotype_call_dataset(100, 10, n_allele=3)
with pytest.raises(
ValueError, match="PC Relate only works for biallelic genotypes"
):
pc_relate(g_non_biallelic)
g_no_pcs = simulate_genotype_call_dataset(100, 10)
with pytest.raises(ValueError, match="sample_pca_projection not present"):
pc_relate(g_no_pcs)
with pytest.raises(ValueError, match="call_genotype not present"):
pc_relate(g_no_pcs.drop_vars("call_genotype"))
with pytest.raises(ValueError, match="call_genotype_mask not present"):
pc_relate(g_no_pcs.drop_vars("call_genotype_mask"))
def test_pc_relate__maf_inputs_checks() -> None:
g = simulate_genotype_call_dataset(100, 10)
with pytest.raises(ValueError, match=r"MAF must be between \(0.0, 1.0\)"):
pc_relate(g, maf=-1)
with pytest.raises(ValueError, match=r"MAF must be between \(0.0, 1.0\)"):
pc_relate(g, maf=1.0)
with pytest.raises(ValueError, match=r"MAF must be between \(0.0, 1.0\)"):
pc_relate(g, maf=0.0)