def test_ihh01_scan_int8_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]], dtype='i1')
ihh0, ihh1 = ihh01_scan_int8(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_nanclose(expect_ihh0, ihh0)
expect_ihh1 = [np.nan, np.nan, x, x]
assert_array_nanclose(expect_ihh1, ihh1)
ihh0, ihh1 = ihh01_scan_int8(h, gaps, min_ehh=0)
expect_ihh0 = [np.nan, np.nan, x, x]
assert_array_nanclose(expect_ihh0, ihh0)
expect_ihh1 = [np.nan, np.nan, x, x]
assert_array_nanclose(expect_ihh1, ihh1)
ihh0, ihh1 = ihh01_scan_int8(h, gaps, min_ehh=0, include_edges=True)
expect_ihh0 = [0, 10 * 2 / 3, x, x]
assert_array_nanclose(expect_ihh0, ihh0)
expect_ihh1 = [0, 10 * 2 / 3, x, x]
assert_array_nanclose(expect_ihh1, ihh1)
def ihs(h, pos, min_ehh=0.05):
"""Compute the unstandardized integrated haplotype score (IHS) for each
variant, comparing integrated haplotype homozygosity between the
reference and alternate alleles.
Parameters
----------
h : array_like, int, shape (n_variants, n_haplotypes)
Haplotype array.
pos : array_like, int, shape (n_variants,)
Variant positions on physical or genetic map.
min_ehh: float, optional
Minimum EHH beyond which to truncate integrated haplotype
homozygosity calculation.
Returns
-------
score : ndarray, float, shape (n_variants,)
Unstandardized IHS scores.
Notes
-----
This function will calculate IHS for all variants. To exclude variants
below a given minor allele frequency, filter the input haplotype array
before passing to this function.
This function computes IHS comparing the reference and alternate alleles.
These can be polarised by switching the sign for any variant where the
reference allele is derived.
This function returns NaN for any IHS calculations where haplotype
homozygosity does not decay below `min_ehh` before reaching the first or
last variant. To disable this behaviour, set `min_ehh` to None.
This function currently does nothing to account for large gaps between
variants. There will be edge effects near any large gaps.
Note that the unstandardized score is returned. Usually these scores are
then normalised in different allele frequency bins.
"""
from allel.opt.stats import ihh01_scan_int8
# scan forward
ihh0_fwd, ihh1_fwd = ihh01_scan_int8(h, pos, min_ehh=min_ehh)
# scan backward
ihh0_rev, ihh1_rev = ihh01_scan_int8(h[::-1], pos[::-1], min_ehh=min_ehh)
ihh0_rev = ihh0_rev[::-1]
ihh1_rev = ihh1_rev[::-1]
# compute unstandardized score
ihh0 = ihh0_fwd + ihh0_rev
ihh1 = ihh1_fwd + ihh1_rev
score = np.log(ihh1 / ihh0)
return score
def test_ihh01_scan_int8_a():
gaps = np.array([10, 10, 10], dtype='f8')
h = np.array([[0, 0, 1], [0, 1, 1], [1, 1, 0], [1, 0, 0]], dtype='i1')
ihh0, ihh1 = ihh01_scan_int8(h, gaps, min_ehh=0.05, include_edges=False)
expect_ihh0 = [np.nan, np.nan, np.nan, 5]
assert_array_nanclose(expect_ihh0, ihh0)
expect_ihh1 = [np.nan, 5, 5, np.nan]
assert_array_nanclose(expect_ihh1, ihh1)
ihh0, ihh1 = ihh01_scan_int8(h, gaps, min_ehh=0, include_edges=True)
expect_ihh0 = [0, np.nan, np.nan, 5]
assert_array_nanclose(expect_ihh0, ihh0)
expect_ihh1 = [np.nan, 5, 5, np.nan]
assert_array_nanclose(expect_ihh1, ihh1)
def test_ihh01_scan_int8_c():
gaps = np.array([10, 10, 10], dtype='f8')
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]], dtype='i1')
ihh0, ihh1 = ihh01_scan_int8(h, gaps, min_ehh=0.05)
expect_ihh0 = [np.nan, np.nan, np.nan, np.nan]
assert_array_nanclose(expect_ihh0, ihh0)
expect_ihh1 = [np.nan, np.nan, np.nan, np.nan]
assert_array_nanclose(expect_ihh1, ihh1)
ihh0, ihh1 = ihh01_scan_int8(h, gaps, min_ehh=0, include_edges=True)
expect_ihh0 = [0, 10, 20, 30]
assert_array_nanclose(expect_ihh0, ihh0)
expect_ihh1 = [0, 10, 20, 30]
assert_array_nanclose(expect_ihh1, ihh1)
def test_ihh01_scan_int8_e():
# min_maf
gaps = np.array([10, 10], dtype='f8')
h = np.array([[0, 0, 1],
[0, 0, 1],
[0, 0, 1]], dtype='i1')
expect_ihh0 = [0, 10, 20]
expect_ihh1 = [np.nan, np.nan, np.nan]
ihh0, ihh1 = ihh01_scan_int8(h, gaps, min_ehh=0,
min_maf=0, include_edges=True)
assert_array_nanclose(expect_ihh0, ihh0)
assert_array_nanclose(expect_ihh1, ihh1)
expect_ihh0 = [np.nan, np.nan, np.nan]
expect_ihh1 = [np.nan, np.nan, np.nan]
ihh0, ihh1 = ihh01_scan_int8(h, gaps, min_ehh=0,
min_maf=0.4, include_edges=True)
assert_array_nanclose(expect_ihh0, ihh0)
assert_array_nanclose(expect_ihh1, ihh1)
def test_ihh01_scan_int8_b():
gaps = np.array([10, 10, 10], dtype='f8')
h = np.array([[0, 0, 0, 1], [0, 0, 1, 0], [0, 1, 0, 0], [1, 0, 0, 0]],
dtype='i1')
ihh0, ihh1 = ihh01_scan_int8(h, gaps, min_ehh=0.05, include_edges=False)
x = (10 * (1 + 1 / 3) / 2) + (10 * (1 / 3 + 0) / 2)
expect_ihh0 = [np.nan, np.nan, x, x]
assert_array_nanclose(expect_ihh0, ihh0)
expect_ihh1 = [np.nan, np.nan, np.nan, np.nan]
assert_array_nanclose(expect_ihh1, ihh1)
ihh0, ihh1 = ihh01_scan_int8(h, gaps, min_ehh=0, include_edges=False)
expect_ihh0 = [np.nan, np.nan, x, x]
assert_array_nanclose(expect_ihh0, ihh0)
expect_ihh1 = [np.nan, np.nan, np.nan, np.nan]
assert_array_nanclose(expect_ihh1, ihh1)
ihh0, ihh1 = ihh01_scan_int8(h, gaps, min_ehh=0, include_edges=True)
expect_ihh0 = [0, 10 * (1 + 1 / 3) / 2, x, x]
assert_array_nanclose(expect_ihh0, ihh0)
expect_ihh1 = [np.nan, np.nan, np.nan, np.nan]
assert_array_nanclose(expect_ihh1, ihh1)
def test_ihh01_scan_int8_e():
# min_maf
gaps = np.array([10, 10], dtype='f8')
h = np.array([[0, 0, 1], [0, 0, 1], [0, 0, 1]], dtype='i1')
expect_ihh0 = [0, 10, 20]
expect_ihh1 = [np.nan, np.nan, np.nan]
ihh0, ihh1 = ihh01_scan_int8(h,
gaps,
min_ehh=0,
min_maf=0,
include_edges=True)
assert_array_nanclose(expect_ihh0, ihh0)
assert_array_nanclose(expect_ihh1, ihh1)
expect_ihh0 = [np.nan, np.nan, np.nan]
expect_ihh1 = [np.nan, np.nan, np.nan]
ihh0, ihh1 = ihh01_scan_int8(h,
gaps,
min_ehh=0,
min_maf=0.4,
include_edges=True)
assert_array_nanclose(expect_ihh0, ihh0)
assert_array_nanclose(expect_ihh1, ihh1)
def test_ihh01_scan_int8(self):
from allel.opt.stats import ihh01_scan_int8
pos = [10, 20, 30, 40]
# case 1
h = np.array([[0, 0, 1],
[0, 1, 1],
[1, 1, 0],
[1, 0, 0]], dtype='i1')
ihh0, ihh1 = ihh01_scan_int8(h, pos, min_ehh=0.05)
expect_ihh0 = [np.nan, np.nan, np.nan, 0]
assert_array_nanclose(expect_ihh0, ihh0)
expect_ihh1 = [np.nan, np.nan, 0, np.nan]
assert_array_nanclose(expect_ihh1, ihh1)
ihh0, ihh1 = ihh01_scan_int8(h, pos, min_ehh=None)
expect_ihh0 = [0, np.nan, np.nan, 0]
assert_array_nanclose(expect_ihh0, ihh0)
expect_ihh1 = [np.nan, 0, 0, np.nan]
assert_array_nanclose(expect_ihh1, ihh1)
# case 2
h = np.array([[0, 0, 0, 1],
[0, 0, 1, 0],
[0, 1, 0, 0],
[1, 0, 0, 0]], dtype='i1')
ihh0, ihh1 = ihh01_scan_int8(h, pos, min_ehh=0.05)
expect_ihh0 = [np.nan, np.nan, np.nan, 10*2/3]
assert_array_nanclose(expect_ihh0, ihh0)
expect_ihh1 = [np.nan, np.nan, np.nan, np.nan]
assert_array_nanclose(expect_ihh1, ihh1)
ihh0, ihh1 = ihh01_scan_int8(h, pos, min_ehh=None)
expect_ihh0 = [0, 10*2/3, 10*2/3, 10*2/3]
assert_array_nanclose(expect_ihh0, ihh0)
expect_ihh1 = [np.nan, np.nan, np.nan, np.nan]
assert_array_nanclose(expect_ihh1, ihh1)
# case 3
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]], dtype='i1')
ihh0, ihh1 = ihh01_scan_int8(h, pos, min_ehh=0.05)
expect_ihh0 = [np.nan, np.nan, np.nan, np.nan]
assert_array_nanclose(expect_ihh0, ihh0)
expect_ihh1 = [np.nan, np.nan, np.nan, np.nan]
assert_array_nanclose(expect_ihh1, ihh1)
ihh0, ihh1 = ihh01_scan_int8(h, pos, min_ehh=None)
expect_ihh0 = [0, 10, 20, 30]
assert_array_nanclose(expect_ihh0, ihh0)
expect_ihh1 = [0, 10, 20, 30]
assert_array_nanclose(expect_ihh1, ihh1)
# case 4
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]], dtype='i1')
ihh0, ihh1 = ihh01_scan_int8(h, pos, min_ehh=0.05)
expect_ihh0 = [np.nan, np.nan, np.nan, 10*2/3]
assert_array_nanclose(expect_ihh0, ihh0)
expect_ihh1 = [np.nan, np.nan, np.nan, 10*2/3]
assert_array_nanclose(expect_ihh1, ihh1)
ihh0, ihh1 = ihh01_scan_int8(h, pos, min_ehh=None)
expect_ihh0 = [0, 10*2/3, 10*2/3, 10*2/3]
assert_array_nanclose(expect_ihh0, ihh0)
expect_ihh1 = [0, 10*2/3, 10*2/3, 10*2/3]
assert_array_nanclose(expect_ihh1, ihh1)
def ihs(
h,
pos,
map_pos=None,
min_ehh=0.05,
min_maf=0.05,
include_edges=False,
gap_scale=20000,
max_gap=200000,
is_accessible=None,
use_threads=True,
):
"""Compute the unstandardized integrated haplotype score (IHS) for each
variant, comparing integrated haplotype homozygosity between the
reference (0) and alternate (1) alleles.
Parameters
----------
h : array_like, int, shape (n_variants, n_haplotypes)
Haplotype array.
pos : array_like, int, shape (n_variants,)
Variant positions (physical distance).
map_pos : array_like, float, shape (n_variants,)
Variant positions (genetic map distance).
min_ehh: float, optional
Minimum EHH beyond which to truncate integrated haplotype
homozygosity calculation.
min_maf : float, optional
Do not compute integrated haplotype homozogysity for variants with
minor allele frequency below this value.
include_edges : bool, optional
If True, report scores even if EHH does not decay below `min_ehh`
before reaching the edge of the data.
gap_scale : int, optional
Rescale distance between variants if gap is larger than this value.
max_gap : int, optional
Do not report scores if EHH spans a gap larger than this number of
base pairs.
is_accessible : array_like, bool, optional
Genome accessibility array. If provided, distance between variants
will be computed as the number of accessible bases between them.
use_threads : bool, optional
If True use multiple threads to compute.
Returns
-------
score : ndarray, float, shape (n_variants,)
Unstandardized IHS scores.
Notes
-----
This function will calculate IHS for all variants. To exclude variants
below a given minor allele frequency, filter the input haplotype array
before passing to this function.
This function computes IHS comparing the reference and alternate alleles.
These can be polarised by switching the sign for any variant where the
reference allele is derived.
This function returns NaN for any IHS calculations where haplotype
homozygosity does not decay below `min_ehh` before reaching the first or
last variant. To disable this behaviour, set `include_edges` to True.
Note that the unstandardized score is returned. Usually these scores are
then standardized in different allele frequency bins.
See Also
--------
standardize_by_allele_count
"""
from allel.opt.stats import ihh01_scan_int8
# check inputs
h = HaplotypeArray(np.asarray(h, dtype="i1"))
pos = asarray_ndim(pos, 1)
check_dim0_aligned(h, pos)
# compute gaps between variants for integration
gaps = compute_ihh_gaps(pos, map_pos, gap_scale, max_gap, is_accessible)
# setup kwargs
kwargs = dict(min_ehh=min_ehh, min_maf=min_maf, include_edges=include_edges)
if use_threads and multiprocessing.cpu_count() > 1:
# run with threads
# create pool
pool = ThreadPool(2)
# scan forward
result_fwd = pool.apply_async(ihh01_scan_int8, (h, gaps), kwargs)
# scan backward
result_rev = pool.apply_async(ihh01_scan_int8, (h[::-1], gaps[::-1]), kwargs)
# wait for both to finish
pool.close()
pool.join()
# obtain results
ihh0_fwd, ihh1_fwd = result_fwd.get()
ihh0_rev, ihh1_rev = result_rev.get()
# cleanup
pool.terminate()
else:
# run without threads
# scan forward
ihh0_fwd, ihh1_fwd = ihh01_scan_int8(h, gaps, **kwargs)
# scan backward
ihh0_rev, ihh1_rev = ihh01_scan_int8(h[::-1], gaps[::-1], **kwargs)
# handle reverse scan
ihh0_rev = ihh0_rev[::-1]
ihh1_rev = ihh1_rev[::-1]
# compute unstandardized score
ihh0 = ihh0_fwd + ihh0_rev
ihh1 = ihh1_fwd + ihh1_rev
score = np.log(ihh1 / ihh0)
return score
