def test_calc_obs_het_in_memory(self):
variations = Variations(samples=np.array(['a', 'b', 'c', 'd']))
gts = np.array([[[0, 0], [0, 1], [0, -1], [-1, -1]],
[[0, 0], [0, 0], [0, -1], [-1, -1]]])
dps = np.array([[5, 12, 10, 10], [10, 10, 10, 10]])
variations[GT_FIELD] = gts
variations[DP_FIELD] = dps
het = calc_obs_het(variations, min_num_genotypes=0)
self.assertTrue(np.allclose(het, [0.5, 0]))
# het = calc_obs_het(variations, min_num_genotypes=10)
# assert np.allclose(het, [np.NaN, np.NaN], equal_nan=True)
het = calc_obs_het(variations,
min_num_genotypes=0,
min_call_dp_for_het_call=10)
self.assertTrue(np.allclose(het, [1, 0]))
het = calc_obs_het(variations,
min_num_genotypes=0,
max_call_dp_for_het_call=11)
self.assertTrue(np.allclose(het, [0, 0]))
het = calc_obs_het(variations,
min_num_genotypes=0,
min_call_dp_for_het_call=5)
self.assertTrue(np.allclose(het, [0.5, 0]))
def test_calc_obs_het2(self):
gts = np.array([[[0, 0], [0, 1], [0, -1], [-1, -1]],
[[0, 0], [0, 0], [0, -1], [-1, -1]]])
dps = np.array([[5, 12, 10, 10], [10, 10, 10, 10]])
samples = np.array([str(i) for i in range(gts.shape[1])])
variations = Variations(samples=da.array(samples))
variations[GT_FIELD] = da.from_array(gts)
variations[DP_FIELD] = da.from_array(dps)
het = calc_obs_het(variations, min_num_genotypes=0)
het = compute(het)
assert np.allclose(het, [0.5, 0])
het = calc_obs_het(variations, min_num_genotypes=10)
het = compute(het)
assert np.allclose(het, [np.NaN, np.NaN], equal_nan=True)
het = calc_obs_het(variations,
min_num_genotypes=0,
min_call_dp_for_het_call=10)
het = compute(het)
assert np.allclose(het, [1, 0])
het = calc_obs_het(variations,
min_num_genotypes=0,
max_call_dp_for_het_call=11)
het = compute(het)
assert np.allclose(het, [0, 0])
het = calc_obs_het(variations,
min_num_genotypes=0,
min_call_dp_for_het_call=5)
het = compute(het)
assert np.allclose(het, [0.5, 0])
def test_calc_obs_het(self):
variations = Variations(samples=da.array(['a', 'b', 'c', 'd']))
gts = np.array([[[0, 0], [0, 1], [0, -1], [-1, -1]],
[[0, 0], [0, 0], [0, -1], [-1, -1]]])
dps = np.array([[5, 12, 10, 10], [10, 10, 10, 10]])
variations[GT_FIELD] = da.from_array(gts)
variations[DP_FIELD] = da.from_array(dps)
# with this step we create a variation with dask arrays of unknown shapes
variations = remove_low_call_rate_vars(variations, 0)[FLT_VARS]
het = calc_obs_het(variations, min_num_genotypes=0)
self.assertTrue(np.allclose(het.compute(), [0.5, 0]))
# het = calc_obs_het(variations, min_num_genotypes=10)
# assert np.allclose(het, [np.NaN, np.NaN], equal_nan=True)
het = calc_obs_het(variations,
min_num_genotypes=0,
min_call_dp_for_het_call=10)
self.assertTrue(np.allclose(het.compute(), [1, 0]))
het = calc_obs_het(variations,
min_num_genotypes=0,
max_call_dp_for_het_call=11)
self.assertTrue(np.allclose(het.compute(), [0, 0]))
het = calc_obs_het(variations,
min_num_genotypes=0,
min_call_dp_for_het_call=5)
self.assertTrue(np.allclose(het.compute(), [0.5, 0]))
def filter_by_obs_heterocigosis(
variations,
max_allowable_het=None,
min_allowable_het=None,
min_call_dp_for_het_call=None,
max_call_dp_for_het_call=None,
filter_id='obs_het',
min_num_genotypes=MIN_NUM_GENOTYPES_FOR_POP_STAT,
calc_histogram=False,
n_bins=DEF_NUM_BINS,
limits=None):
obs_het = calc_obs_het(variations,
min_num_genotypes=min_num_genotypes,
min_call_dp_for_het_call=min_call_dp_for_het_call,
max_call_dp_for_het_call=max_call_dp_for_het_call)
result = _select_vars(variations,
obs_het,
min_allowable=min_allowable_het,
max_allowable=max_allowable_het)
if calc_histogram:
if limits is None:
limits = (0, 1)
counts, bin_edges = va.histogram(obs_het, n_bins=n_bins, limits=limits)
result[FLT_STATS][COUNT] = counts
result[FLT_STATS][BIN_EDGES] = bin_edges
limits = []
if min_allowable_het is not None:
limits.append(min_allowable_het)
if max_allowable_het is not None:
limits.append(max_allowable_het)
result[FLT_STATS]['limits'] = limits
return {
FLT_VARS: result[FLT_VARS],
FLT_ID: filter_id,
FLT_STATS: result[FLT_STATS]
}