def test_heterozygosity_observed(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')
expect = [0, 0, 0, .5, .5, .5, 1, 1, 0, 1, -1]
actual = allel.heterozygosity_observed(g, fill=-1)
aeq(expect, 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')
expect = [0, 0, 0, .5, .5, .5, 1, 1, 0, 1, -1]
actual = allel.heterozygosity_observed(g, fill=-1)
aeq(expect, actual)
def test_observed_heterozygosity__scikit_allel_comparison(
n_variant, n_sample, missing_pct, window_size, seed):
ds = simulate_genotype_call_dataset(
n_variant=n_variant,
n_sample=n_sample,
n_ploidy=2,
missing_pct=missing_pct,
seed=seed,
)
ds["sample_cohort"] = (
["samples"],
np.zeros(n_sample, int),
)
ds = window(ds, size=window_size)
ho_sg = observed_heterozygosity(ds)["stat_observed_heterozygosity"].values
if n_sample % window_size:
# scikit-allel will drop the ragged end
ho_sg = ho_sg[0:-1]
# calculate with scikit-allel
ho_sa = allel.moving_statistic(
allel.heterozygosity_observed(ds["call_genotype"]),
np.sum,
size=window_size,
)
# add cohort dimension to scikit-allel result
np.testing.assert_almost_equal(ho_sg, ho_sa[..., None])
haps = np.array(ts1.genotype_matrix())
positions = np.array([s.position for s in ts1.sites()])
genotypes = allel.HaplotypeArray(haps).to_genotypes(ploidy=2)
allele_counts = genotypes.count_alleles()
subpop_allele_counts = genotypes.count_alleles_subpops(subpops=pops)
genotype_allele_counts = genotypes.to_allele_counts()
##SNP stats
segsites = np.shape(genotypes)[0]
pi = allel.sequence_diversity(positions, allele_counts, start=1, stop=1e7)
tajD = allel.tajima_d(ac=allele_counts, start=1, stop=1e7)
thetaW = allel.watterson_theta(pos=positions,
ac=allele_counts,
start=1,
stop=1e7)
het_o = np.mean(allel.heterozygosity_observed(genotypes))
fst = allel.stats.fst.average_weir_cockerham_fst(
genotypes,
[[0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19],
[
20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36,
37, 38, 39
]], 100)[0]
dxy = allel.stats.diversity.sequence_divergence(positions,
subpop_allele_counts['0'],
subpop_allele_counts['1'])
##Identical-by-state haplotype block length stats (i.e. LD-type stats)
#between population comparisons
bw_pairs = list(itertools.product(pops['0'], pops['1']))
ibs_bw = []
def traditional_stats(data):
"""
Caclulates lots of (mostly) traditional statistics,
that are summaries of the site frequency spectrum.
Arguments
---------
data: Named tuple of results (made by collate_results function)
Returns
---------
Nested dictionary of statistics
"""
pop_names = ["domestic", "wild", "captive", "all_pops"]
stats = {
"sfs_mean": {},
"diversity": {},
"wattersons_theta": {},
"tajimas_d": {},
"observed_heterozygosity": {},
"expected_heterozygosity": {},
"segregating_sites": {},
"monomorphic_sites": {},
"roh_mean": {},
"roh_iqr": {},
"r2": {},
"f3": {},
"divergence": {},
"fst": {},
"f2": {},
}
for pop in pop_names:
# One way statistics
stats["sfs_mean"][pop] = binned_sfs_mean(data.allele_counts[pop])
stats["diversity"][pop] = allel.sequence_diversity(
data.positions, data.allele_counts[pop])
stats["wattersons_theta"][pop] = allel.watterson_theta(
data.positions, data.allele_counts[pop])
stats["tajimas_d"][pop] = allel.tajima_d(data.allele_counts[pop],
data.positions)
stats["observed_heterozygosity"][pop] = allel.heterozygosity_observed(
data.genotypes[pop]).mean()
stats["expected_heterozygosity"][pop] = allel.heterozygosity_expected(
data.allele_counts[pop].to_frequencies(), ploidy=2).mean()
stats["segregating_sites"] = data.allele_counts[pop].count_segregating(
)
if pop != "all_pops": # all_pops has no monomorphic sites
stats["monomorphic_sites"][pop] = data.allele_counts[
pop].count_non_segregating()
# Three way statistics
other_pops = [
pop_name for pop_name in pop_names
if pop_name not in ["all_pops", pop]
]
t, b = allel.patterson_f3(data.allele_counts[pop],
data.allele_counts[other_pops[0]],
data.allele_counts[other_pops[1]])
stats["f3"][pop] = np.sum(t) / np.sum(b)
# Two way statistics
for comparison in ["domestic_wild", "domestic_captive", "wild_captive"]:
p = comparison.split("_")
stats["divergence"][comparison] = allel.sequence_divergence(
data.positions, data.allele_counts[p[0]], data.allele_counts[p[1]])
num, den = allel.hudson_fst(data.allele_counts[p[0]],
data.allele_counts[p[1]])
stats["fst"][comparison] = np.sum(num) / np.sum(den)
stats["f2"][comparison] = allel.patterson_f2(
data.allele_counts[p[0]], data.allele_counts[p[1]]).mean()
return stats
