def filter_by_mac(variations,
max_alleles,
max_allowable_mac=None,
min_allowable_mac=None,
filter_id='filter_by_mac',
min_num_genotypes=MIN_NUM_GENOTYPES_FOR_POP_STAT,
calc_histogram=False,
n_bins=DEF_NUM_BINS,
limits=None):
macs = calc_mac(variations,
max_alleles=max_alleles,
min_num_genotypes=min_num_genotypes)
# print(compute(macs))
result = _select_vars(variations, macs, min_allowable_mac,
max_allowable_mac)
if calc_histogram:
if limits is None:
limits = (0, variations.num_samples)
counts, bin_edges = va.histogram(macs, n_bins=n_bins, limits=limits)
result[FLT_STATS][COUNT] = counts
result[FLT_STATS][BIN_EDGES] = bin_edges
limits = []
if min_allowable_mac is not None:
limits.append(min_allowable_mac)
if max_allowable_mac is not None:
limits.append(max_allowable_mac)
result[FLT_STATS]['limits'] = limits
return {
FLT_VARS: result[FLT_VARS],
FLT_ID: filter_id,
FLT_STATS: result[FLT_STATS]
}
def test_calc_mac2(self):
gts = np.array([[[0], [0], [0], [0]], [[0], [0], [1], [1]],
[[0], [0], [0], [1]], [[-1], [-1], [-1], [-1]]])
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)
# with this step we create a variation wi
result = calc_mac(variations, max_alleles=3, min_num_genotypes=1)
macs = compute(result)
assert np.allclose(macs, np.array([4, 2, 3, np.NaN]), equal_nan=True)
def test_calc_mac_in_memory(self):
variations = Variations(samples=np.array(['aa', 'bb']))
gts = np.array([[[0, 0], [0, 0]], [[0, 2], [1, -1]], [[0, 0], [1, 1]],
[[-1, -1], [-1, -1]]])
variations[GT_FIELD] = gts
macs = calc_mac(variations, max_alleles=3, min_num_genotypes=0)
expected = [2, 1, 1, math.nan]
for a, b in zip(macs, expected):
if math.isnan(a):
self.assertTrue(math.isnan(b))
continue
self.assertAlmostEqual(a, b, places=2)
def test_calc_mac(self):
variations = Variations(samples=da.array(['aa', 'bb']))
gts = np.array([[[0, 0], [0, 0]], [[0, 2], [1, -1]], [[0, 0], [1, 1]],
[[-1, -1], [-1, -1]]])
variations[GT_FIELD] = da.from_array(gts)
# with this step we create a variation with dask arrays of unknown
# shapes
variations = remove_low_call_rate_vars(variations, 0)[FLT_VARS]
macs = calc_mac(variations, max_alleles=3, min_num_genotypes=0)
result = compute(macs)
expected = [2, 1, 1, math.nan]
for a, b in zip(result, expected):
if math.isnan(a):
self.assertTrue(math.isnan(b))
continue
self.assertAlmostEqual(a, b, places=2)