def test_masked_windowed_divergence(self):
h = HaplotypeArray([[0, 0, 0, 0], [0, 0, 0, 1], [0, 0, 1, 1],
[0, 1, 1, 1], [1, 1, 1, 1], [0, 0, 1, 2],
[0, 1, 1, 2], [0, 1, -1, -1], [-1, -1, -1, -1]])
h1 = h.take([0, 1], axis=1)
h2 = h.take([2, 3], axis=1)
ac1 = h1.count_alleles()
ac2 = h2.count_alleles()
pos = SortedIndex([2, 4, 7, 14, 15, 18, 19, 25, 27])
mask = np.tile(np.repeat(np.array([True, False]), 5), 3)
expect, _, _, _ = allel.windowed_divergence(pos,
ac1,
ac2,
size=5,
start=1,
stop=31)
expect = expect[::2]
actual, _, _, _ = allel.windowed_divergence(pos,
ac1,
ac2,
size=10,
start=1,
stop=31,
is_accessible=mask)
assert_array_almost_equal(expect, actual)
def test_patterson_d(self):
aca = [[0, 2],
[2, 0],
[2, 0],
[1, 1],
[0, 0]]
acb = [[0, 2],
[0, 2],
[0, 2],
[1, 1],
[0, 2]]
acc = [[2, 0],
[2, 0],
[0, 2],
[1, 1],
[0, 2]]
acd = [[2, 0],
[0, 2],
[2, 0],
[1, 1],
[0, 2]]
num, den = allel.patterson_d(aca, acb, acc, acd)
expect_num = [0., 1., -1., 0., np.nan]
expect_den = [0., 1., 1., 0.25, np.nan]
assert_array_almost_equal(expect_num, num)
assert_array_almost_equal(expect_den, den)
def test_masked_windowed_diversity(self):
# four haplotypes, 6 pairwise comparison
h = allel.HaplotypeArray([[0, 0, 0, 0], [0, 0, 0, 1], [0, 0, 1, 1],
[0, 1, 1, 1], [1, 1, 1, 1], [0, 0, 1, 2],
[0, 1, 1, 2], [0, 1, -1, -1],
[-1, -1, -1, -1]])
ac = h.count_alleles()
# mean pairwise diversity
# expect = [0, 3/6, 4/6, 3/6, 0, 5/6, 5/6, 1, -1]
pos = SortedIndex([2, 4, 7, 14, 15, 18, 19, 25, 27])
mask = np.tile(np.repeat(np.array([True, False]), 5), 3)
# expected is every other window with size 5
expect, _, _, _ = allel.windowed_diversity(pos,
ac,
size=5,
start=1,
stop=31)
# only getting every other element
expect = expect[::2]
# actual is window of size 10 with the last half masked out
actual, _, _, _ = allel.windowed_diversity(pos,
ac,
size=10,
start=1,
stop=31,
is_accessible=mask)
assert_array_almost_equal(expect, actual)
def test_windowed_tajima_d(self):
from allel import windowed_tajima_d
pos = np.array([1, 11, 21, 31, 41])
# example with calculable value
ac = AlleleCountsArray([[1, 3], [2, 2], [3, 1], [1, 3], [2, 2]])
expect = np.array([0.168] * 3)
actual, _, _ = windowed_tajima_d(pos, ac, size=25, step=10)
assert_array_almost_equal(expect, actual, decimal=3)
# too few sites
actual, _, _ = windowed_tajima_d(pos, ac, size=15, step=10)
assert 4 == len(actual)
assert np.all(np.isnan(actual))
# too few segregating sites
ac = AlleleCountsArray([[4, 0], [2, 2], [3, 1], [4, 0], [2, 2]])
actual, _, _ = windowed_tajima_d(pos, ac, size=25, step=10)
assert 3 == len(actual)
assert np.all(np.isnan(actual))
# allow people to override if they really want to
expect = np.array([0.592] * 3)
actual, _, _ = windowed_tajima_d(pos,
ac,
size=25,
step=10,
min_sites=2)
assert_array_almost_equal(expect, actual, decimal=3)
def test_moving_tajima_d(self):
from allel import moving_tajima_d
# example with calculable value
ac = AlleleCountsArray([[1, 3],
[2, 2],
[3, 1],
[1, 3],
[2, 2]])
expect = np.array([0.168] * 3)
actual = moving_tajima_d(ac, size=3, step=1)
assert_array_almost_equal(expect, actual, decimal=3)
# too few sites
actual = moving_tajima_d(ac, size=2, step=1)
assert 4 == len(actual)
assert np.all(np.isnan(actual))
# too few segregating sites
ac = AlleleCountsArray([[4, 0],
[2, 2],
[3, 1],
[4, 0],
[2, 2]])
actual = moving_tajima_d(ac, size=3, step=1)
assert 3 == len(actual)
assert np.all(np.isnan(actual))
# allow people to override if they really want to
expect = np.array([0.592] * 3)
actual = moving_tajima_d(ac, size=3, step=1, min_sites=2)
assert_array_almost_equal(expect, actual, decimal=3)
def test_mean_pairwise_diversity(self):
# start with simplest case, two haplotypes, one pairwise comparison
h = HaplotypeArray([[0, 0],
[1, 1],
[0, 1],
[1, 2],
[0, -1],
[-1, -1]])
ac = h.count_alleles()
expect = [0, 0, 1, 1, -1, -1]
actual = allel.mean_pairwise_difference(ac, fill=-1)
aeq(expect, actual)
# four haplotypes, 6 pairwise comparison
h = HaplotypeArray([[0, 0, 0, 0],
[0, 0, 0, 1],
[0, 0, 1, 1],
[0, 1, 1, 1],
[1, 1, 1, 1],
[0, 0, 1, 2],
[0, 1, 1, 2],
[0, 1, -1, -1],
[-1, -1, -1, -1]])
ac = h.count_alleles()
expect = [0, 3/6, 4/6, 3/6, 0, 5/6, 5/6, 1, -1]
actual = allel.mean_pairwise_difference(ac, fill=-1)
assert_array_almost_equal(expect, actual)
def test_nsl01_scan_b():
h = np.array([[0, 0, 0, 1], [0, 0, 1, 0], [0, 1, 0, 0], [1, 0, 0, 0]])
nsl0, nsl1 = nsl01_scan(h)
expect_nsl0 = [1, 4 / 3, 4 / 3, 4 / 3]
assert_array_almost_equal(expect_nsl0, nsl0)
expect_nsl1 = [np.nan, np.nan, np.nan, np.nan]
assert_array_almost_equal(expect_nsl1, nsl1)
def test_nsl01_scan_a():
h = np.array([[0, 0, 0, 1, 1, 1], [0, 0, 0, 1, 1, 1], [0, 0, 0, 1, 1, 1],
[0, 0, 0, 1, 1, 1]])
nsl0, nsl1 = nsl01_scan(h)
expect_nsl0 = [1, 2, 3, 4]
assert_array_almost_equal(expect_nsl0, nsl0)
expect_nsl1 = [1, 2, 3, 4]
assert_array_almost_equal(expect_nsl1, nsl1)
def test_patterson_f3(self):
aca = [[0, 2], [2, 0], [0, 2], [0, 2], [0, 0]]
acb = [[2, 0], [0, 2], [0, 2], [0, 2], [0, 2]]
acc = [[1, 1], [1, 1], [0, 2], [2, 0], [1, 1]]
expect_f3 = [-.5, -.5, 0., 1., np.nan]
actual_f3, actual_hzc = allel.patterson_f3(acc, aca, acb)
assert_array_almost_equal(expect_f3, actual_f3)
expect_hzc = [1., 1., 0., 0., 1.]
assert_array_almost_equal(expect_hzc, actual_hzc)
def test_patterson_f2(self):
aca = [[0, 2],
[2, 0],
[1, 1],
[0, 0]]
acb = [[0, 2],
[0, 2],
[0, 2],
[0, 2]]
expect = [0., 1., 0., np.nan]
actual = allel.patterson_f2(aca, acb)
assert_array_almost_equal(expect, actual)
def test_ihh_scan_d():
# edge case: start from 0 haplotype homozygosity
gaps = np.array([10], dtype='f8')
h = np.array([[0, 1], [1, 0]])
expect = [0, 0]
actual = ihh_scan(h, gaps, min_ehh=0, include_edges=False)
assert_array_almost_equal(expect, actual)
expect = [0, 0]
actual = ihh_scan(h, gaps, min_ehh=0, include_edges=True)
assert_array_almost_equal(expect, actual)
def test_ihh_scan_a():
# simple case: 1 haplotype pair, haplotype homozygosity over all variants
gaps = np.array([10, 10], dtype='f8')
h = np.array([[0, 0], [0, 0], [0, 0]])
# do not include edges
expect = [np.nan, np.nan, np.nan]
actual = ihh_scan(h, gaps, min_ehh=0, include_edges=False)
assert_array_almost_equal(expect, actual)
# include edges
expect = [0, 10, 20]
actual = ihh_scan(h, gaps, min_ehh=0, include_edges=True)
assert_array_almost_equal(expect, actual)
def test_ihh_scan_c():
# simple case: 1 haplotype pair, haplotype homozygosity decays
gaps = np.array([10, 10], dtype='f8')
h = np.array([[0, 1], [0, 0], [0, 0]])
# do not include edges
expect = [0, 5, 15]
actual = ihh_scan(h, gaps, min_ehh=0, include_edges=False)
assert_array_almost_equal(expect, actual)
# include edges
expect = [0, 5, 15]
actual = ihh_scan(h, gaps, min_ehh=0, include_edges=True)
assert_array_almost_equal(expect, actual)
def test_ihh_scan_b():
# 1 haplotype pair, haplotype homozygosity over all variants
# handling of large gap (encoded as -1)
gaps = np.array([10, -1], dtype='f8')
h = np.array([[0, 0], [0, 0], [0, 0]])
# do not include edges
expect = [np.nan, np.nan, np.nan]
actual = ihh_scan(h, gaps, min_ehh=0, include_edges=False)
assert_array_almost_equal(expect, actual)
# include edges
expect = [0, 10, np.nan]
actual = ihh_scan(h, gaps, min_ehh=0, include_edges=True)
assert_array_almost_equal(expect, actual)
def test_pbs():
# minimal input data, sanity check for output existence and type
ac1 = [[2, 0], [0, 2], [1, 1], [2, 0], [0, 2]]
ac2 = [[1, 1], [2, 0], [0, 2], [2, 0], [0, 2]]
ac3 = [[0, 2], [1, 1], [2, 0], [2, 0], [0, 2]]
ret = pbs(ac1, ac2, ac3, window_size=2, window_step=1)
assert isinstance(ret, np.ndarray)
assert 1 == ret.ndim
assert 4 == ret.shape[0]
assert 'f' == ret.dtype.kind
# regression check
expect = [0.52349464, 0., -0.85199356, np.nan]
assert_array_almost_equal(expect, ret)
# final value is nan because variants in final window are non-segregating
assert np.isnan(ret[3])
def test_heterozygosity_expected(self):
def refimpl(f, ploidy, fill=0):
"""Limited reference implementation for testing purposes."""
# check allele frequencies sum to 1
af_sum = np.sum(f, axis=1)
# assume three alleles
p = f[:, 0]
q = f[:, 1]
r = f[:, 2]
out = 1 - p**ploidy - q**ploidy - r**ploidy
with ignore_invalid():
out[(af_sum < 1) | np.isnan(af_sum)] = fill
return out
# diploid
g = GenotypeArray([[[0, 0], [0, 0]],
[[1, 1], [1, 1]],
[[1, 1], [2, 2]],
[[0, 0], [0, 1]],
[[0, 0], [0, 2]],
[[1, 1], [1, 2]],
[[0, 1], [0, 1]],
[[0, 1], [1, 2]],
[[0, 0], [-1, -1]],
[[0, 1], [-1, -1]],
[[-1, -1], [-1, -1]]], dtype='i1')
expect1 = [0, 0, 0.5, .375, .375, .375, .5, .625, 0, .5, -1]
af = g.count_alleles().to_frequencies()
expect2 = refimpl(af, ploidy=g.ploidy, fill=-1)
actual = allel.heterozygosity_expected(af, ploidy=g.ploidy, fill=-1)
assert_array_almost_equal(expect1, actual)
assert_array_almost_equal(expect2, actual)
expect3 = [0, 0, 0.5, .375, .375, .375, .5, .625, 0, .5, 0]
actual = allel.heterozygosity_expected(af, ploidy=g.ploidy, fill=0)
assert_array_almost_equal(expect3, actual)
# polyploid
g = GenotypeArray([[[0, 0, 0], [0, 0, 0]],
[[1, 1, 1], [1, 1, 1]],
[[1, 1, 1], [2, 2, 2]],
[[0, 0, 0], [0, 0, 1]],
[[0, 0, 0], [0, 0, 2]],
[[1, 1, 1], [0, 1, 2]],
[[0, 0, 1], [0, 1, 1]],
[[0, 1, 1], [0, 1, 2]],
[[0, 0, 0], [-1, -1, -1]],
[[0, 0, 1], [-1, -1, -1]],
[[-1, -1, -1], [-1, -1, -1]]], dtype='i1')
af = g.count_alleles().to_frequencies()
expect = refimpl(af, ploidy=g.ploidy, fill=-1)
actual = allel.heterozygosity_expected(af, ploidy=g.ploidy, fill=-1)
assert_array_almost_equal(expect, actual)
def test_windowed_diversity(self):
# four haplotypes, 6 pairwise comparison
h = HaplotypeArray([[0, 0, 0, 0], [0, 0, 0, 1], [0, 0, 1, 1],
[0, 1, 1, 1], [1, 1, 1, 1], [0, 0, 1, 2],
[0, 1, 1, 2], [0, 1, -1, -1], [-1, -1, -1, -1]])
ac = h.count_alleles()
# mean pairwise diversity
# expect = [0, 3/6, 4/6, 3/6, 0, 5/6, 5/6, 1, -1]
pos = SortedIndex([2, 4, 7, 14, 15, 18, 19, 25, 27])
expect = [(7 / 6) / 10, (13 / 6) / 10, 1 / 11]
actual, _, _, _ = allel.windowed_diversity(pos,
ac,
size=10,
start=1,
stop=31)
assert_array_almost_equal(expect, actual)
def test_inbreeding_coefficient(self):
# diploid
g = GenotypeArray(
[[[0, 0], [0, 0]], [[1, 1], [1, 1]], [[1, 1], [2, 2]],
[[0, 0], [0, 1]], [[0, 0], [0, 2]], [[1, 1], [1, 2]],
[[0, 1], [0, 1]], [[0, 1], [1, 2]], [[0, 0], [-1, -1]],
[[0, 1], [-1, -1]], [[-1, -1], [-1, -1]]],
dtype='i1')
# ho = np.array([0, 0, 0, .5, .5, .5, 1, 1, 0, 1, -1])
# he = np.array([0, 0, 0.5, .375, .375, .375, .5, .625, 0, .5, -1])
# expect = 1 - (ho/he)
expect = [
-1, -1, 1 - 0, 1 - (.5 / .375), 1 - (.5 / .375), 1 - (.5 / .375),
1 - (1 / .5), 1 - (1 / .625), -1, 1 - (1 / .5), -1
]
actual = allel.inbreeding_coefficient(g, fill=-1)
assert_array_almost_equal(expect, actual)
def test_windowed_divergence(self):
# simplest case, two haplotypes in each population
h = HaplotypeArray([[0, 0, 0, 0], [0, 0, 0, 1], [0, 0, 1, 1],
[0, 1, 1, 1], [1, 1, 1, 1], [0, 0, 1, 2],
[0, 1, 1, 2], [0, 1, -1, -1], [-1, -1, -1, -1]])
h1 = h.take([0, 1], axis=1)
h2 = h.take([2, 3], axis=1)
ac1 = h1.count_alleles()
ac2 = h2.count_alleles()
# mean pairwise divergence
# expect = [0/4, 2/4, 4/4, 2/4, 0/4, 4/4, 3/4, -1, -1]
pos = SortedIndex([2, 4, 7, 14, 15, 18, 19, 25, 27])
expect = [(6 / 4) / 10, (9 / 4) / 10, 0 / 11]
actual, _, _, _ = allel.windowed_divergence(pos,
ac1,
ac2,
size=10,
start=1,
stop=31)
assert_array_almost_equal(expect, actual)
def test_ihh01_scan_a():
gaps = np.array([10, 10, 10], dtype='f8')
h = np.array([[0, 0, 1], [0, 1, 1], [1, 1, 0], [1, 0, 0]])
ihh0, ihh1 = ihh01_scan(h, gaps, min_ehh=0.05, include_edges=False)
expect_ihh0 = [np.nan, np.nan, np.nan, 5]
assert_array_almost_equal(expect_ihh0, ihh0)
expect_ihh1 = [np.nan, 5, 5, np.nan]
assert_array_almost_equal(expect_ihh1, ihh1)
ihh0, ihh1 = ihh01_scan(h, gaps, min_ehh=0, include_edges=True)
expect_ihh0 = [0, np.nan, np.nan, 5]
assert_array_almost_equal(expect_ihh0, ihh0)
expect_ihh1 = [np.nan, 5, 5, np.nan]
assert_array_almost_equal(expect_ihh1, ihh1)
def test_ihh01_scan_e():
# min_maf
gaps = np.array([10, 10], dtype='f8')
h = np.array([[0, 0, 1],
[0, 0, 1],
[0, 0, 1]])
expect_ihh0 = [0, 10, 20]
expect_ihh1 = [np.nan, np.nan, np.nan]
ihh0, ihh1 = ihh01_scan(h, gaps, min_ehh=0, min_maf=0, include_edges=True)
assert_array_almost_equal(expect_ihh0, ihh0)
assert_array_almost_equal(expect_ihh1, ihh1)
expect_ihh0 = [np.nan, np.nan, np.nan]
expect_ihh1 = [np.nan, np.nan, np.nan]
ihh0, ihh1 = ihh01_scan(h, gaps, min_ehh=0, min_maf=0.4, include_edges=True)
assert_array_almost_equal(expect_ihh0, ihh0)
assert_array_almost_equal(expect_ihh1, ihh1)
def test_rogers_huff_r(self):
gn = [[0, 1, 2], [0, 1, 2]]
expect = 1.
actual = allel.rogers_huff_r(gn)
assert expect == actual
gn = [[0, 1, 2], [2, 1, 0]]
expect = -1.
actual = allel.rogers_huff_r(gn)
assert expect == actual
gn = [[0, 0, 0], [0, 0, 0]]
actual = allel.rogers_huff_r(gn)
assert np.isnan(actual)
gn = [[0, 0, 0], [1, 1, 1]]
actual = allel.rogers_huff_r(gn)
assert np.isnan(actual)
gn = [[1, 1, 1], [1, 1, 1]]
actual = allel.rogers_huff_r(gn)
assert np.isnan(actual)
gn = [[0, -1, 0], [-1, 1, -1]]
actual = allel.rogers_huff_r(gn)
assert np.isnan(actual)
gn = [[0, 1, 0], [-1, -1, -1]]
actual = allel.rogers_huff_r(gn)
assert np.isnan(actual)
gn = [[0, 1, 0, 1], [0, 1, 1, 0]]
expect = 0
actual = allel.rogers_huff_r(gn)
assert expect == actual
gn = [[0, 1, 2, -1], [0, 1, 2, 2]]
expect = 1.
actual = allel.rogers_huff_r(gn)
assert expect == actual
gn = [[0, 1, 2, 2], [0, 1, 2, -1]]
expect = 1.
actual = allel.rogers_huff_r(gn)
assert expect == actual
gn = [[0, 1, 2], [0, 1, -1]]
expect = 1.
actual = allel.rogers_huff_r(gn)
assert expect == actual
gn = [[0, 2], [2, 0], [0, 1]]
expect = [-1, 1, -1]
actual = allel.rogers_huff_r(gn)
assert_array_almost_equal(expect, actual)
gn = [[0, 2, 0], [0, 2, 0], [2, 0, 2], [0, 2, -1]]
expect = [1, -1, 1, -1, 1, -1]
actual = allel.rogers_huff_r(gn)
assert_array_almost_equal(expect, actual)
def test_ihh01_scan_d():
gaps = np.array([10, 10, 10], dtype='f8')
h = np.array([[0, 0, 1, 1, 1, 0], [0, 1, 0, 1, 0, 1], [1, 0, 0, 0, 1, 1],
[0, 0, 0, 1, 1, 1]])
ihh0, ihh1 = ihh01_scan(h, gaps, min_ehh=0.05)
x = (10 * (1 + 1 / 3) / 2) + (10 * (1 / 3 + 0) / 2)
expect_ihh0 = [np.nan, np.nan, x, x]
assert_array_almost_equal(expect_ihh0, ihh0)
expect_ihh1 = [np.nan, np.nan, x, x]
assert_array_almost_equal(expect_ihh1, ihh1)
ihh0, ihh1 = ihh01_scan(h, gaps, min_ehh=0)
expect_ihh0 = [np.nan, np.nan, x, x]
assert_array_almost_equal(expect_ihh0, ihh0)
expect_ihh1 = [np.nan, np.nan, x, x]
assert_array_almost_equal(expect_ihh1, ihh1)
ihh0, ihh1 = ihh01_scan(h, gaps, min_ehh=0, include_edges=True)
expect_ihh0 = [0, 10 * 2 / 3, x, x]
assert_array_almost_equal(expect_ihh0, ihh0)
expect_ihh1 = [0, 10 * 2 / 3, x, x]
assert_array_almost_equal(expect_ihh1, ihh1)
