def test_ssl01_scan_int8(self):
from allel.opt.stats import nsl01_scan_int8
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')
nsl0, nsl1 = nsl01_scan_int8(h)
expect_nsl0 = [1, 2, 3, 4]
assert_array_nanclose(expect_nsl0, nsl0)
expect_nsl1 = [1, 2, 3, 4]
assert_array_nanclose(expect_nsl1, nsl1)
h = np.array([[0, 0, 0, 1],
[0, 0, 1, 0],
[0, 1, 0, 0],
[1, 0, 0, 0]], dtype='i1')
nsl0, nsl1 = nsl01_scan_int8(h)
expect_nsl0 = [1, 4/3, 4/3, 4/3]
assert_array_nanclose(expect_nsl0, nsl0)
expect_nsl1 = [np.nan, np.nan, np.nan, np.nan]
assert_array_nanclose(expect_nsl1, nsl1)
h = np.array([[0, 0, 1],
[0, 1, 1],
[1, 1, 0],
[1, 0, 0]], dtype='i1')
nsl0, nsl1 = nsl01_scan_int8(h)
expect_nsl0 = [1, np.nan, np.nan, 1]
assert_array_nanclose(expect_nsl0, nsl0)
expect_nsl1 = [np.nan, 1, 1, np.nan]
assert_array_nanclose(expect_nsl1, nsl1)
def nsl(h):
"""Compute the unstandardized number of segregating sites by length (nSl)
for each variant, comparing the reference and alternate alleles,
after Ferrer-Admetlla et al. (2014).
Parameters
----------
h : array_like, int, shape (n_variants, n_haplotypes)
Haplotype array.
Returns
-------
score : ndarray, float, shape (n_variants,)
Notes
-----
This function will calculate nSl for all variants. To exclude variants
below a given minor allele frequency, filter the input haplotype array
before passing to this function.
The function only expects segregating sites, so ensure any
non-segregating sites are removed before passing in the haplotype array.
This function computes nSl by 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 does nothing about nSl calculations where haplotype
homozygosity extends up to the first or last variant. There will be edge
effects.
This function currently does nothing to account for large gaps between
variants. There will be edge effects near any large gaps.
This function returns unstandardised scores. Typically nSl scores are
are normalised by subtracting the mean and dividing by the standard
deviation.
"""
from allel.opt.stats import nsl01_scan_int8
# check there are no invariant sites
ac = h.count_alleles()
assert np.all(ac.is_segregating()), 'please remove non-segregating sites'
# scan forward
nsl0_fwd, nsl1_fwd = nsl01_scan_int8(h)
# scan backward
nsl0_rev, nsl1_rev = nsl01_scan_int8(h[::-1])
nsl0_rev = nsl0_rev[::-1]
nsl1_rev = nsl1_rev[::-1]
# compute unstandardized score
nsl0 = nsl0_fwd + nsl0_rev
nsl1 = nsl1_fwd + nsl1_rev
score = np.log(nsl1 / nsl0)
return score
def test_nsl01_scan_int8_c():
h = np.array([[0, 0, 1], [0, 1, 1], [1, 1, 0], [1, 0, 0]], dtype='i1')
nsl0, nsl1 = nsl01_scan_int8(h)
expect_nsl0 = [1, np.nan, np.nan, 1]
assert_array_nanclose(expect_nsl0, nsl0)
expect_nsl1 = [np.nan, 1, 1, np.nan]
assert_array_nanclose(expect_nsl1, nsl1)
def test_nsl01_scan_int8_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]],
dtype='i1')
nsl0, nsl1 = nsl01_scan_int8(h)
expect_nsl0 = [1, 2, 3, 4]
assert_array_nanclose(expect_nsl0, nsl0)
expect_nsl1 = [1, 2, 3, 4]
assert_array_nanclose(expect_nsl1, nsl1)
def test_nsl01_scan_int8_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]], dtype='i1')
nsl0, nsl1 = nsl01_scan_int8(h)
expect_nsl0 = [1, 2, 3, 4]
assert_array_nanclose(expect_nsl0, nsl0)
expect_nsl1 = [1, 2, 3, 4]
assert_array_nanclose(expect_nsl1, nsl1)
def test_nsl01_scan_int8_c():
h = np.array([[0, 0, 1],
[0, 1, 1],
[1, 1, 0],
[1, 0, 0]], dtype='i1')
nsl0, nsl1 = nsl01_scan_int8(h)
expect_nsl0 = [1, np.nan, np.nan, 1]
assert_array_nanclose(expect_nsl0, nsl0)
expect_nsl1 = [np.nan, 1, 1, np.nan]
assert_array_nanclose(expect_nsl1, nsl1)
def nsl(h, use_threads=True):
"""Compute the unstandardized number of segregating sites by length (nSl)
for each variant, comparing the reference and alternate alleles,
after Ferrer-Admetlla et al. (2014).
Parameters
----------
h : array_like, int, shape (n_variants, n_haplotypes)
Haplotype array.
use_threads : bool, optional
If True use multiple threads to compute.
Returns
-------
score : ndarray, float, shape (n_variants,)
Notes
-----
This function will calculate nSl 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 nSl by 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 does nothing about nSl calculations where haplotype
homozygosity extends up to the first or last variant. There may be edge
effects.
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 nsl01_scan_int8
# check inputs
h = HaplotypeArray(np.asarray(h, dtype="i1"))
# # check there are no invariant sites
# ac = h.count_alleles()
# assert np.all(ac.is_segregating()), 'please remove non-segregating sites'
if use_threads and multiprocessing.cpu_count() > 1:
# create pool
pool = ThreadPool(2)
# scan forward
result_fwd = pool.apply_async(nsl01_scan_int8, args=(h,))
# scan backward
result_rev = pool.apply_async(nsl01_scan_int8, args=(h[::-1],))
# wait for both to finish
pool.close()
pool.join()
# obtain results
nsl0_fwd, nsl1_fwd = result_fwd.get()
nsl0_rev, nsl1_rev = result_rev.get()
else:
# scan forward
nsl0_fwd, nsl1_fwd = nsl01_scan_int8(h)
# scan backward
nsl0_rev, nsl1_rev = nsl01_scan_int8(h[::-1])
# handle backwards
nsl0_rev = nsl0_rev[::-1]
nsl1_rev = nsl1_rev[::-1]
# compute unstandardized score
nsl0 = nsl0_fwd + nsl0_rev
nsl1 = nsl1_fwd + nsl1_rev
score = np.log(nsl1 / nsl0)
return score