def test_ihs_data():
h = np.hstack([hap1, hap2])
pos = np.arange(1, h.shape[0] + 1)
expect = np.log(5.5/1.5)
for use_threads in True, False:
for include_edges in True, False:
score = ihs(h, pos, include_edges=include_edges,
use_threads=use_threads)
actual = score[9]
assert expect == actual
def test_ihs():
n_variants = 1000
n_haplotypes = 20
h = np.random.randint(0, 2, size=(n_variants, n_haplotypes)).astype('i1')
pos = np.arange(0, n_variants * 10, 10)
for use_threads in True, False:
for min_ehh in 0, 0.05, 0.5:
for include_edges in True, False:
score = ihs(h, pos, min_ehh=min_ehh,
include_edges=include_edges,
use_threads=use_threads)
assert isinstance(score, np.ndarray)
assert (n_variants,) == score.shape
assert np.dtype('f8') == score.dtype
with pytest.raises(ValueError):
ihs(h, pos[1:])
with pytest.raises(ValueError):
ihs(h, pos, map_pos=pos[1:])
def ihs(haplotype, pos_vec, window=None):
"""Compute the standardize integrated haplotype score"""
ihs = allel.ihs(haplotype, pos_vec, min_maf=0.01, include_edges=True)
ihs_stand, bins = allel.standardize_by_allele_count(
ihs, haplotype.count_alleles().T[1], diagnostics=False)
if window:
di = pd.DataFrame(ihs_stand, columns=["iHS"])
di["pos_cat"] = pd.cut(pos_vec, window, labels=range(1, window + 1))
dig = di.groupby("pos_cat").iHS.mean()
return dig
else:
return ihs_stand
import seaborn as sns
import pandas as pd
chromlist = ["Wb_Chr1_0", "Wb_Chr1_1", "Wb_Chr2_0", "Wb_Chr2_1", "Wb_Chr2_2",
"Wb_Chr2_3", "Wb_Chr3_0", "Wb_Chr3_1", "Wb_Chr4_0", "Wb_Chr4_1",
"Wb_Chr4_2"]
seldict = {}
for c in chromlist:
callset = h5py.File("PNG.phased.autosomal.recode.{}.h5".format(c), mode='r')
samples = callset['samples'][:]
sample_name = [sid.decode() for sid in samples.tolist()]
g = allel.GenotypeChunkedArray(callset["calldata/GT"])
h = g.to_haplotypes()
pos = allel.SortedIndex(callset["variants/POS"][:])
acc = h.count_alleles()[:, 1]
# ihs
ihs = allel.ihs(h, pos, include_edges=True)
ihs_std = allel.standardize_by_allele_count(ihs, acc)
plt.plot(pos, -np.log10(ihs_std[0]))
nan = ~np.isnan(ihs)
ihs_real = ihs[nan]
pos_ihs = pos[nan]
# nsl
nsl = allel.nsl(h)
nsl_std = allel.standardize_by_allele_count(nsl, acc)
plt.plot(pos, -np.log10(nsl_std[0]))
nan = ~np.isnan(ihs)
nsl_real = ihs[nan]
pos_nsl = pos[nan]
seldict[c] = (ihs_std[0], nsl_std[0])
## ehh is site dependent site dependent
#ehh = allel.ehh_decay(h)
"Wb_Chr1_0", "Wb_Chr1_1", "Wb_Chr2_0", "Wb_Chr2_1", "Wb_Chr2_2",
"Wb_Chr2_3", "Wb_Chr3_0", "Wb_Chr3_1", "Wb_Chr4_0", "Wb_Chr4_1",
"Wb_Chr4_2"
]
seldict = {}
for c in chromlist:
callset = h5py.File("PNG.phased.autosomal.recode.{}.h5".format(c),
mode='r')
samples = callset['samples'][:]
sample_name = [sid.decode() for sid in samples.tolist()]
g = allel.GenotypeChunkedArray(callset["calldata/GT"])
h = g.to_haplotypes()
pos = allel.SortedIndex(callset["variants/POS"][:])
acc = h.count_alleles()[:, 1]
# ihs
ihs = allel.ihs(h, pos, include_edges=True)
ihs_std = allel.standardize_by_allele_count(ihs, acc)
plt.plot(pos, -np.log10(ihs_std[0]))
nan = ~np.isnan(ihs)
ihs_real = ihs[nan]
pos_ihs = pos[nan]
# nsl
nsl = allel.nsl(h)
nsl_std = allel.standardize_by_allele_count(nsl, acc)
plt.plot(pos, -np.log10(nsl_std[0]))
nan = ~np.isnan(ihs)
nsl_real = ihs[nan]
pos_nsl = pos[nan]
seldict[c] = (ihs_std[0], nsl_std[0])
## ehh is site dependent site dependent
#ehh = allel.ehh_decay(h)