def windowed_weir_cockerham_fst(pos, g, subpops, size=None, start=None,
stop=None, step=None, windows=None,
fill=np.nan, max_allele=None):
"""Estimate average Fst in windows over a single chromosome/contig,
following the method of Weir and Cockerham (1984).
Parameters
----------
pos : array_like, int, shape (n_items,)
Variant positions, using 1-based coordinates, in ascending order.
g : array_like, int, shape (n_variants, n_samples, ploidy)
Genotype array.
subpops : sequence of sequences of ints
Sample indices for each subpopulation.
size : int
The window size (number of bases).
start : int, optional
The position at which to start (1-based).
stop : int, optional
The position at which to stop (1-based).
step : int, optional
The distance between start positions of windows. If not given,
defaults to the window size, i.e., non-overlapping windows.
windows : array_like, int, shape (n_windows, 2), optional
Manually specify the windows to use as a sequence of (window_start,
window_stop) positions, using 1-based coordinates. Overrides the
size/start/stop/step parameters.
fill : object, optional
The value to use where there are no variants within a window.
max_allele : int, optional
The highest allele index to consider.
Returns
-------
fst : ndarray, float, shape (n_windows,)
Average Fst in each window.
windows : ndarray, int, shape (n_windows, 2)
The windows used, as an array of (window_start, window_stop) positions,
using 1-based coordinates.
counts : ndarray, int, shape (n_windows,)
Number of variants in each window.
"""
# compute values per-variant
a, b, c = weir_cockerham_fst(g, subpops, max_allele=max_allele)
# define the statistic to compute within each window
def average_fst(wa, wb, wc):
return np.nansum(wa) / (np.nansum(wa) + np.nansum(wb) + np.nansum(wc))
# calculate average Fst in windows
fst, windows, counts = windowed_statistic(pos, values=(a, b, c),
statistic=average_fst,
size=size, start=start,
stop=stop, step=step,
windows=windows, fill=fill)
return fst, windows, counts
def windowed_patterson_fst(pos, ac1, ac2, size=None, start=None, stop=None,
step=None, windows=None, fill=np.nan):
"""Estimate average Fst in windows over a single chromosome/contig,
following the method of Patterson (2012).
Parameters
----------
pos : array_like, int, shape (n_items,)
Variant positions, using 1-based coordinates, in ascending order.
ac1 : array_like, int, shape (n_variants, n_alleles)
Allele counts array from the first population.
ac2 : array_like, int, shape (n_variants, n_alleles)
Allele counts array from the second population.
size : int, optional
The window size (number of bases).
start : int, optional
The position at which to start (1-based).
stop : int, optional
The position at which to stop (1-based).
step : int, optional
The distance between start positions of windows. If not given,
defaults to the window size, i.e., non-overlapping windows.
windows : array_like, int, shape (n_windows, 2), optional
Manually specify the windows to use as a sequence of (window_start,
window_stop) positions, using 1-based coordinates. Overrides the
size/start/stop/step parameters.
fill : object, optional
The value to use where there are no variants within a window.
Returns
-------
fst : ndarray, float, shape (n_windows,)
Average Fst in each window.
windows : ndarray, int, shape (n_windows, 2)
The windows used, as an array of (window_start, window_stop) positions,
using 1-based coordinates.
counts : ndarray, int, shape (n_windows,)
Number of variants in each window.
"""
# compute values per-variants
num, den = patterson_fst(ac1, ac2)
# define the statistic to compute within each window
def average_fst(wn, wd):
return np.nansum(wn) / np.nansum(wd)
# calculate average Fst in windows
fst, windows, counts = windowed_statistic(pos, values=(num, den),
statistic=average_fst,
size=size, start=start,
stop=stop, step=step,
windows=windows, fill=fill)
return fst, windows, counts
def windowed_r_squared(pos,
gn,
size=None,
start=None,
stop=None,
step=None,
windows=None,
fill=np.nan,
percentile=50):
"""Summarise linkage disequilibrium in windows over a single
chromosome/contig.
Parameters
----------
pos : array_like, int, shape (n_items,)
The item positions in ascending order, using 1-based coordinates..
gn : array_like, int8, shape (n_variants, n_samples)
Diploid genotypes at biallelic variants, coded as the number of
alternate alleles per call (i.e., 0 = hom ref, 1 = het, 2 = hom alt).
size : int, optional
The window size (number of bases).
start : int, optional
The position at which to start (1-based).
stop : int, optional
The position at which to stop (1-based).
step : int, optional
The distance between start positions of windows. If not given,
defaults to the window size, i.e., non-overlapping windows.
windows : array_like, int, shape (n_windows, 2), optional
Manually specify the windows to use as a sequence of (window_start,
window_stop) positions, using 1-based coordinates. Overrides the
size/start/stop/step parameters.
fill : object, optional
The value to use where a window is empty, i.e., contains no items.
percentile : int or sequence of ints, optional
The percentile or percentiles to calculate within each window.
Returns
-------
out : ndarray, shape (n_windows,)
The value of the statistic for each window.
windows : ndarray, int, shape (n_windows, 2)
The windows used, as an array of (window_start, window_stop) positions,
using 1-based coordinates.
counts : ndarray, int, shape (n_windows,)
The number of items in each window.
Notes
-----
Linkage disequilibrium (r**2) is calculated using the method of Rogers
and Huff (2008).
See Also
--------
allel.stats.window.windowed_statistic
"""
# define the statistic function
if isinstance(percentile, (list, tuple)):
fill = [fill for _ in percentile]
def statistic(gnw):
r_squared = rogers_huff_r(gnw)**2
return [np.percentile(r_squared, p) for p in percentile]
else:
def statistic(gnw):
r_squared = rogers_huff_r(gnw)**2
return np.percentile(r_squared, percentile)
return windowed_statistic(pos,
gn,
statistic,
size,
start=start,
stop=stop,
step=step,
windows=windows,
fill=fill)
def roh_poissonhmm(gv,
pos,
phet_roh=0.001,
phet_nonroh=(0.0025, 0.01),
transition=1e-3,
window_size=1000,
min_roh=0,
is_accessible=None,
contig_size=None):
"""Call ROH (runs of homozygosity) in a single individual given a genotype vector.
This function computes the likely ROH using a Poisson HMM model. The chromosome is divided into
equally accessible windows of specified size, then the number of hets observed in each is used
to fit a Poisson HMM. Note this is much faster than `roh_mhmm`, but at the cost of some
resolution.
The model is provided with a probability of observing a het in a ROH (`phet_roh`) and one
or more probabilities of observing a het in a non-ROH, as this probability may not be
constant across the genome (`phet_nonroh`).
Parameters
----------
gv : array_like, int, shape (n_variants, ploidy)
Genotype vector.
pos: array_like, int, shape (n_variants,)
Positions of variants, same 0th dimension as `gv`.
phet_roh: float, optional
Probability of observing a heterozygote in a ROH. Appropriate values
will depend on de novo mutation rate and genotype error rate.
phet_nonroh: tuple of floats, optional
One or more probabilites of observing a heterozygote outside of ROH.
Appropriate values will depend primarily on nucleotide diversity within
the population, but also on mutation rate and genotype error rate.
transition: float, optional
Probability of moving between states. This is based on windows, so a larger window size may
call for a larger transitional probability
window_size: integer, optional
Window size (equally accessible bases) to consider as a potential ROH. Setting this window
too small may result in spurious ROH calls, while too large will result in a lack of
resolution.
min_roh: integer, optional
Minimum size (bp) to condsider as a ROH. Will depend on contig size and recombination rate.
is_accessible: array_like, bool, shape (`contig_size`,), optional
Boolean array for each position in contig describing whether accessible
or not. Although optional, highly recommended so invariant sites are distinguishable from
sites where variation is inaccessible
contig_size: integer, optional
If is_accessible is not available, use this to specify the size of the contig, and assume
all sites are accessible.
Returns
-------
df_roh: DataFrame
Data frame where each row describes a run of homozygosity. Columns are 'start',
'stop', 'length' and 'is_marginal'. Start and stop are 1-based, stop-inclusive.
froh: float
Proportion of genome in a ROH.
Notes
-----
This function requires `pomegranate` (>= 0.9.0) to be installed.
"""
from pomegranate import HiddenMarkovModel, PoissonDistribution
# equally accessbile windows
if is_accessible is None:
if contig_size is None:
raise ValueError(
"If is_accessibile argument is not provided, you must provide contig_size"
)
is_accessible = np.ones((contig_size, ), dtype="bool")
else:
contig_size = is_accessible.size
eqw = equally_accessible_windows(is_accessible, window_size)
ishet = GenotypeVector(gv).is_het()
counts, wins, records = windowed_statistic(pos, ishet, np.sum, windows=eqw)
# heterozygote probabilities
het_px = np.concatenate([(phet_roh, ), phet_nonroh])
# start probabilities (all equal)
start_prob = np.repeat(1 / het_px.size, het_px.size)
# transition between underlying states
transition_mx = _hmm_derive_transition_matrix(transition, het_px.size)
dists = [PoissonDistribution(x * window_size) for x in het_px]
model = HiddenMarkovModel.from_matrix(
transition_probabilities=transition_mx,
distributions=dists,
starts=start_prob)
prediction = np.array(model.predict(counts[:, None]))
df_blocks = tabulate_state_blocks(prediction,
states=list(range(len(het_px))))
df_roh = df_blocks[(df_blocks.state == 0)].reset_index(drop=True)
# adapt the dataframe for ROH
df_roh["start"] = df_roh.start_ridx.apply(lambda y: eqw[y, 0])
df_roh["stop"] = df_roh.stop_lidx.apply(lambda y: eqw[y, 1])
df_roh["length"] = df_roh.stop - df_roh.start
# filter by ROH size
if min_roh > 0:
df_roh = df_roh[df_roh.length >= min_roh]
# compute FROH
froh = df_roh.length.sum() / contig_size
return df_roh[["start", "stop", "length", "is_marginal"]], froh
def windowed_tajima_d(pos, ac, size=None, start=None, stop=None, step=None, windows=None, fill=np.nan):
"""Calculate the value of Tajima's D in windows over a single
chromosome/contig.
Parameters
----------
pos : array_like, int, shape (n_items,)
Variant positions, using 1-based coordinates, in ascending order.
ac : array_like, int, shape (n_variants, n_alleles)
Allele counts array.
size : int, optional
The window size (number of bases).
start : int, optional
The position at which to start (1-based).
stop : int, optional
The position at which to stop (1-based).
step : int, optional
The distance between start positions of windows. If not given,
defaults to the window size, i.e., non-overlapping windows.
windows : array_like, int, shape (n_windows, 2), optional
Manually specify the windows to use as a sequence of (window_start,
window_stop) positions, using 1-based coordinates. Overrides the
size/start/stop/step parameters.
fill : object, optional
The value to use where a window is completely inaccessible.
Returns
-------
D : ndarray, float, shape (n_windows,)
Tajima's D.
windows : ndarray, int, shape (n_windows, 2)
The windows used, as an array of (window_start, window_stop) positions,
using 1-based coordinates.
counts : ndarray, int, shape (n_windows,)
Number of variants in each window.
Examples
--------
>>> import allel
>>> g = allel.GenotypeArray([[[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 = g.count_alleles()
>>> pos = [2, 4, 7, 14, 15, 18, 19, 25, 27]
>>> D, windows, counts = allel.stats.windowed_tajima_d(
... pos, ac, size=10, start=1, stop=31
... )
>>> D
array([ 0.59158014, 2.93397641, 6.12372436])
>>> windows
array([[ 1, 10],
[11, 20],
[21, 31]])
>>> counts
array([3, 4, 2])
"""
# check inputs
if not isinstance(pos, SortedIndex):
pos = SortedIndex(pos, copy=False)
if not hasattr(ac, "count_segregating"):
ac = AlleleCountsArray(ac, copy=False)
# assume number of chromosomes sampled is constant for all variants
n = ac.sum(axis=1).max()
# calculate constants
a1 = np.sum(1 / np.arange(1, n))
a2 = np.sum(1 / (np.arange(1, n) ** 2))
b1 = (n + 1) / (3 * (n - 1))
b2 = 2 * (n ** 2 + n + 3) / (9 * n * (n - 1))
c1 = b1 - (1 / a1)
c2 = b2 - ((n + 2) / (a1 * n)) + (a2 / (a1 ** 2))
e1 = c1 / a1
e2 = c2 / (a1 ** 2 + a2)
# locate segregating variants
is_seg = ac.is_segregating()
# calculate mean pairwise difference
mpd = mean_pairwise_difference(ac, fill=0)
# define statistic to compute for each window
# noinspection PyPep8Naming
def statistic(w_is_seg, w_mpd):
S = np.count_nonzero(w_is_seg)
pi = np.sum(w_mpd)
d = pi - (S / a1)
d_stdev = np.sqrt((e1 * S) + (e2 * S * (S - 1)))
wD = d / d_stdev
return wD
D, windows, counts = windowed_statistic(
pos,
values=(is_seg, mpd),
statistic=statistic,
size=size,
start=start,
stop=stop,
step=step,
windows=windows,
fill=fill,
)
return D, windows, counts
def windowed_watterson_theta(
pos, ac, size=None, start=None, stop=None, step=None, windows=None, is_accessible=None, fill=np.nan
):
"""Calculate the value of Watterson's estimator in windows over a single
chromosome/contig.
Parameters
----------
pos : array_like, int, shape (n_items,)
Variant positions, using 1-based coordinates, in ascending order.
ac : array_like, int, shape (n_variants, n_alleles)
Allele counts array.
size : int, optional
The window size (number of bases).
start : int, optional
The position at which to start (1-based).
stop : int, optional
The position at which to stop (1-based).
step : int, optional
The distance between start positions of windows. If not given,
defaults to the window size, i.e., non-overlapping windows.
windows : array_like, int, shape (n_windows, 2), optional
Manually specify the windows to use as a sequence of (window_start,
window_stop) positions, using 1-based coordinates. Overrides the
size/start/stop/step parameters.
is_accessible : array_like, bool, shape (len(contig),), optional
Boolean array indicating accessibility status for all positions in the
chromosome/contig.
fill : object, optional
The value to use where a window is completely inaccessible.
Returns
-------
theta_hat_w : ndarray, float, shape (n_windows,)
Watterson's estimator (theta hat per base).
windows : ndarray, int, shape (n_windows, 2)
The windows used, as an array of (window_start, window_stop) positions,
using 1-based coordinates.
n_bases : ndarray, int, shape (n_windows,)
Number of (accessible) bases in each window.
counts : ndarray, int, shape (n_windows,)
Number of variants in each window.
Examples
--------
>>> import allel
>>> g = allel.GenotypeArray([[[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 = g.count_alleles()
>>> pos = [2, 4, 7, 14, 15, 18, 19, 25, 27]
>>> theta_hat_w, windows, n_bases, counts = allel.stats.windowed_watterson_theta(
... pos, ac, size=10, start=1, stop=31
... )
>>> theta_hat_w
array([ 0.10909091, 0.16363636, 0.04958678])
>>> windows
array([[ 1, 10],
[11, 20],
[21, 31]])
>>> n_bases
array([10, 10, 11])
>>> counts
array([3, 4, 2])
""" # flake8: noqa
# check inputs
if not isinstance(pos, SortedIndex):
pos = SortedIndex(pos, copy=False)
is_accessible = asarray_ndim(is_accessible, 1, allow_none=True)
if not hasattr(ac, "count_segregating"):
ac = AlleleCountsArray(ac, copy=False)
# locate segregating variants
is_seg = ac.is_segregating()
# count segregating variants in windows
S, windows, counts = windowed_statistic(
pos, is_seg, statistic=np.count_nonzero, size=size, start=start, stop=stop, step=step, windows=windows, fill=0
)
# assume number of chromosomes sampled is constant for all variants
n = ac.sum(axis=1).max()
# (n-1)th harmonic number
a1 = np.sum(1 / np.arange(1, n))
# absolute value of Watterson's theta
theta_hat_w_abs = S / a1
# theta per base
theta_hat_w, n_bases = per_base(theta_hat_w_abs, windows=windows, is_accessible=is_accessible, fill=fill)
return theta_hat_w, windows, n_bases, counts
def windowed_df(
pos, ac1, ac2, size=None, start=None, stop=None, step=None, windows=None, is_accessible=None, fill=np.nan
):
"""Calculate the density of fixed differences between two populations in
windows over a single chromosome/contig.
Parameters
----------
pos : array_like, int, shape (n_items,)
Variant positions, using 1-based coordinates, in ascending order.
ac1 : array_like, int, shape (n_variants, n_alleles)
Allele counts array for the first population.
ac2 : array_like, int, shape (n_variants, n_alleles)
Allele counts array for the second population.
size : int, optional
The window size (number of bases).
start : int, optional
The position at which to start (1-based).
stop : int, optional
The position at which to stop (1-based).
step : int, optional
The distance between start positions of windows. If not given,
defaults to the window size, i.e., non-overlapping windows.
windows : array_like, int, shape (n_windows, 2), optional
Manually specify the windows to use as a sequence of (window_start,
window_stop) positions, using 1-based coordinates. Overrides the
size/start/stop/step parameters.
is_accessible : array_like, bool, shape (len(contig),), optional
Boolean array indicating accessibility status for all positions in the
chromosome/contig.
fill : object, optional
The value to use where a window is completely inaccessible.
Returns
-------
df : ndarray, float, shape (n_windows,)
Per-base density of fixed differences in each window.
windows : ndarray, int, shape (n_windows, 2)
The windows used, as an array of (window_start, window_stop) positions,
using 1-based coordinates.
n_bases : ndarray, int, shape (n_windows,)
Number of (accessible) bases in each window.
counts : ndarray, int, shape (n_windows,)
Number of variants in each window.
See Also
--------
allel.model.locate_fixed_differences
"""
# check inputs
pos = SortedIndex(pos, copy=False)
is_accessible = asarray_ndim(is_accessible, 1, allow_none=True)
# locate fixed differences
loc_df = locate_fixed_differences(ac1, ac2)
# count number of fixed differences in windows
n_df, windows, counts = windowed_statistic(
pos,
values=loc_df,
statistic=np.count_nonzero,
size=size,
start=start,
stop=stop,
step=step,
windows=windows,
fill=0,
)
# calculate value per base
df, n_bases = per_base(n_df, windows, is_accessible=is_accessible, fill=fill)
return df, windows, n_bases, counts
def windowed_divergence(
pos, ac1, ac2, size=None, start=None, stop=None, step=None, windows=None, is_accessible=None, fill=np.nan
):
"""Estimate nucleotide divergence between two populations in windows
over a single chromosome/contig.
Parameters
----------
pos : array_like, int, shape (n_items,)
Variant positions, using 1-based coordinates, in ascending order.
ac1 : array_like, int, shape (n_variants, n_alleles)
Allele counts array for the first population.
ac2 : array_like, int, shape (n_variants, n_alleles)
Allele counts array for the second population.
size : int, optional
The window size (number of bases).
start : int, optional
The position at which to start (1-based).
stop : int, optional
The position at which to stop (1-based).
step : int, optional
The distance between start positions of windows. If not given,
defaults to the window size, i.e., non-overlapping windows.
windows : array_like, int, shape (n_windows, 2), optional
Manually specify the windows to use as a sequence of (window_start,
window_stop) positions, using 1-based coordinates. Overrides the
size/start/stop/step parameters.
is_accessible : array_like, bool, shape (len(contig),), optional
Boolean array indicating accessibility status for all positions in the
chromosome/contig.
fill : object, optional
The value to use where a window is completely inaccessible.
Returns
-------
Dxy : ndarray, float, shape (n_windows,)
Nucleotide divergence in each window.
windows : ndarray, int, shape (n_windows, 2)
The windows used, as an array of (window_start, window_stop) positions,
using 1-based coordinates.
n_bases : ndarray, int, shape (n_windows,)
Number of (accessible) bases in each window.
counts : ndarray, int, shape (n_windows,)
Number of variants in each window.
Examples
--------
Simplest case, two haplotypes in each population::
>>> import allel
>>> 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]])
>>> ac1 = h.count_alleles(subpop=[0, 1])
>>> ac2 = h.count_alleles(subpop=[2, 3])
>>> pos = [2, 4, 7, 14, 15, 18, 19, 25, 27]
>>> dxy, windows, n_bases, counts = windowed_divergence(
... pos, ac1, ac2, size=10, start=1, stop=31
... )
>>> dxy
array([ 0.15 , 0.225, 0. ])
>>> windows
array([[ 1, 10],
[11, 20],
[21, 31]])
>>> n_bases
array([10, 10, 11])
>>> counts
array([3, 4, 2])
"""
# check inputs
pos = SortedIndex(pos, copy=False)
is_accessible = asarray_ndim(is_accessible, 1, allow_none=True)
# calculate mean pairwise divergence
mpd = mean_pairwise_difference_between(ac1, ac2, fill=0)
# sum in windows
mpd_sum, windows, counts = windowed_statistic(
pos, values=mpd, statistic=np.sum, size=size, start=start, stop=stop, step=step, windows=windows, fill=0
)
# calculate value per base
dxy, n_bases = per_base(mpd_sum, windows, is_accessible=is_accessible, fill=fill)
return dxy, windows, n_bases, counts
def windowed_r_squared(pos, gn, size=None, start=None, stop=None, step=None,
windows=None, fill=np.nan, percentile=50):
"""Summarise linkage disequilibrium in windows over a single
chromosome/contig.
Parameters
----------
pos : array_like, int, shape (n_items,)
The item positions in ascending order, using 1-based coordinates..
gn : array_like, int8, shape (n_variants, n_samples)
Diploid genotypes at biallelic variants, coded as the number of
alternate alleles per call (i.e., 0 = hom ref, 1 = het, 2 = hom alt).
size : int, optional
The window size (number of bases).
start : int, optional
The position at which to start (1-based).
stop : int, optional
The position at which to stop (1-based).
step : int, optional
The distance between start positions of windows. If not given,
defaults to the window size, i.e., non-overlapping windows.
windows : array_like, int, shape (n_windows, 2), optional
Manually specify the windows to use as a sequence of (window_start,
window_stop) positions, using 1-based coordinates. Overrides the
size/start/stop/step parameters.
fill : object, optional
The value to use where a window is empty, i.e., contains no items.
percentile : int or sequence of ints, optional
The percentile or percentiles to calculate within each window.
Returns
-------
out : ndarray, shape (n_windows,)
The value of the statistic for each window.
windows : ndarray, int, shape (n_windows, 2)
The windows used, as an array of (window_start, window_stop) positions,
using 1-based coordinates.
counts : ndarray, int, shape (n_windows,)
The number of items in each window.
Notes
-----
Linkage disequilibrium (r**2) is calculated using the method of Rogers
and Huff (2008).
See Also
--------
allel.stats.window.windowed_statistic
"""
# define the statistic function
if isinstance(percentile, (list, tuple)):
fill = [fill for _ in percentile]
def statistic(gnw):
r_squared = rogers_huff_r(gnw) ** 2
return [np.percentile(r_squared, p) for p in percentile]
else:
def statistic(gnw):
r_squared = rogers_huff_r(gnw) ** 2
return np.percentile(r_squared, percentile)
return windowed_statistic(pos, gn, statistic, size, start=start,
stop=stop, step=step, windows=windows, fill=fill)
def windowed_watterson_theta(pos,
ac,
size=None,
start=None,
stop=None,
step=None,
windows=None,
is_accessible=None,
fill=np.nan):
"""Calculate the value of Watterson's estimator in windows over a single
chromosome/contig.
Parameters
----------
pos : array_like, int, shape (n_items,)
Variant positions, using 1-based coordinates, in ascending order.
ac : array_like, int, shape (n_variants, n_alleles)
Allele counts array.
size : int, optional
The window size (number of bases).
start : int, optional
The position at which to start (1-based).
stop : int, optional
The position at which to stop (1-based).
step : int, optional
The distance between start positions of windows. If not given,
defaults to the window size, i.e., non-overlapping windows.
windows : array_like, int, shape (n_windows, 2), optional
Manually specify the windows to use as a sequence of (window_start,
window_stop) positions, using 1-based coordinates. Overrides the
size/start/stop/step parameters.
is_accessible : array_like, bool, shape (len(contig),), optional
Boolean array indicating accessibility status for all positions in the
chromosome/contig.
fill : object, optional
The value to use where a window is completely inaccessible.
Returns
-------
theta_hat_w : ndarray, float, shape (n_windows,)
Watterson's estimator (theta hat per base).
windows : ndarray, int, shape (n_windows, 2)
The windows used, as an array of (window_start, window_stop) positions,
using 1-based coordinates.
n_bases : ndarray, int, shape (n_windows,)
Number of (accessible) bases in each window.
counts : ndarray, int, shape (n_windows,)
Number of variants in each window.
Examples
--------
>>> import allel
>>> g = allel.GenotypeArray([[[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 = g.count_alleles()
>>> pos = [2, 4, 7, 14, 15, 18, 19, 25, 27]
>>> theta_hat_w, windows, n_bases, counts = allel.windowed_watterson_theta(
... pos, ac, size=10, start=1, stop=31
... )
>>> theta_hat_w
array([0.10909091, 0.16363636, 0.04958678])
>>> windows
array([[ 1, 10],
[11, 20],
[21, 31]])
>>> n_bases
array([10, 10, 11])
>>> counts
array([3, 4, 2])
""" # flake8: noqa
# check inputs
if not isinstance(pos, SortedIndex):
pos = SortedIndex(pos, copy=False)
is_accessible = asarray_ndim(is_accessible, 1, allow_none=True)
if not hasattr(ac, 'count_segregating'):
ac = AlleleCountsArray(ac, copy=False)
# locate segregating variants
is_seg = ac.is_segregating()
# count segregating variants in windows
S, windows, counts = windowed_statistic(pos,
is_seg,
statistic=np.count_nonzero,
size=size,
start=start,
stop=stop,
step=step,
windows=windows,
fill=0)
# assume number of chromosomes sampled is constant for all variants
n = ac.sum(axis=1).max()
# (n-1)th harmonic number
a1 = np.sum(1 / np.arange(1, n))
# absolute value of Watterson's theta
theta_hat_w_abs = S / a1
# theta per base
theta_hat_w, n_bases = per_base(theta_hat_w_abs,
windows=windows,
is_accessible=is_accessible,
fill=fill)
return theta_hat_w, windows, n_bases, counts
def windowed_df(pos,
ac1,
ac2,
size=None,
start=None,
stop=None,
step=None,
windows=None,
is_accessible=None,
fill=np.nan):
"""Calculate the density of fixed differences between two populations in
windows over a single chromosome/contig.
Parameters
----------
pos : array_like, int, shape (n_items,)
Variant positions, using 1-based coordinates, in ascending order.
ac1 : array_like, int, shape (n_variants, n_alleles)
Allele counts array for the first population.
ac2 : array_like, int, shape (n_variants, n_alleles)
Allele counts array for the second population.
size : int, optional
The window size (number of bases).
start : int, optional
The position at which to start (1-based).
stop : int, optional
The position at which to stop (1-based).
step : int, optional
The distance between start positions of windows. If not given,
defaults to the window size, i.e., non-overlapping windows.
windows : array_like, int, shape (n_windows, 2), optional
Manually specify the windows to use as a sequence of (window_start,
window_stop) positions, using 1-based coordinates. Overrides the
size/start/stop/step parameters.
is_accessible : array_like, bool, shape (len(contig),), optional
Boolean array indicating accessibility status for all positions in the
chromosome/contig.
fill : object, optional
The value to use where a window is completely inaccessible.
Returns
-------
df : ndarray, float, shape (n_windows,)
Per-base density of fixed differences in each window.
windows : ndarray, int, shape (n_windows, 2)
The windows used, as an array of (window_start, window_stop) positions,
using 1-based coordinates.
n_bases : ndarray, int, shape (n_windows,)
Number of (accessible) bases in each window.
counts : ndarray, int, shape (n_windows,)
Number of variants in each window.
See Also
--------
allel.model.locate_fixed_differences
"""
# check inputs
pos = SortedIndex(pos, copy=False)
is_accessible = asarray_ndim(is_accessible, 1, allow_none=True)
# locate fixed differences
loc_df = locate_fixed_differences(ac1, ac2)
# count number of fixed differences in windows
n_df, windows, counts = windowed_statistic(pos,
values=loc_df,
statistic=np.count_nonzero,
size=size,
start=start,
stop=stop,
step=step,
windows=windows,
fill=0)
# calculate value per base
df, n_bases = per_base(n_df,
windows,
is_accessible=is_accessible,
fill=fill)
return df, windows, n_bases, counts
def windowed_divergence(pos,
ac1,
ac2,
size=None,
start=None,
stop=None,
step=None,
windows=None,
is_accessible=None,
fill=np.nan):
"""Estimate nucleotide divergence between two populations in windows
over a single chromosome/contig.
Parameters
----------
pos : array_like, int, shape (n_items,)
Variant positions, using 1-based coordinates, in ascending order.
ac1 : array_like, int, shape (n_variants, n_alleles)
Allele counts array for the first population.
ac2 : array_like, int, shape (n_variants, n_alleles)
Allele counts array for the second population.
size : int, optional
The window size (number of bases).
start : int, optional
The position at which to start (1-based).
stop : int, optional
The position at which to stop (1-based).
step : int, optional
The distance between start positions of windows. If not given,
defaults to the window size, i.e., non-overlapping windows.
windows : array_like, int, shape (n_windows, 2), optional
Manually specify the windows to use as a sequence of (window_start,
window_stop) positions, using 1-based coordinates. Overrides the
size/start/stop/step parameters.
is_accessible : array_like, bool, shape (len(contig),), optional
Boolean array indicating accessibility status for all positions in the
chromosome/contig.
fill : object, optional
The value to use where a window is completely inaccessible.
Returns
-------
Dxy : ndarray, float, shape (n_windows,)
Nucleotide divergence in each window.
windows : ndarray, int, shape (n_windows, 2)
The windows used, as an array of (window_start, window_stop) positions,
using 1-based coordinates.
n_bases : ndarray, int, shape (n_windows,)
Number of (accessible) bases in each window.
counts : ndarray, int, shape (n_windows,)
Number of variants in each window.
Examples
--------
Simplest case, two haplotypes in each population::
>>> import allel
>>> 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]])
>>> ac1 = h.count_alleles(subpop=[0, 1])
>>> ac2 = h.count_alleles(subpop=[2, 3])
>>> pos = [2, 4, 7, 14, 15, 18, 19, 25, 27]
>>> dxy, windows, n_bases, counts = windowed_divergence(
... pos, ac1, ac2, size=10, start=1, stop=31
... )
>>> dxy
array([0.15 , 0.225, 0. ])
>>> windows
array([[ 1, 10],
[11, 20],
[21, 31]])
>>> n_bases
array([10, 10, 11])
>>> counts
array([3, 4, 2])
"""
# check inputs
pos = SortedIndex(pos, copy=False)
is_accessible = asarray_ndim(is_accessible, 1, allow_none=True)
# calculate mean pairwise divergence
mpd = mean_pairwise_difference_between(ac1, ac2, fill=0)
# sum in windows
mpd_sum, windows, counts = windowed_statistic(pos,
values=mpd,
statistic=np.sum,
size=size,
start=start,
stop=stop,
step=step,
windows=windows,
fill=0)
# calculate value per base
dxy, n_bases = per_base(mpd_sum,
windows,
is_accessible=is_accessible,
fill=fill)
return dxy, windows, n_bases, counts
def windowed_tajima_d(pos,
ac,
size=None,
start=None,
stop=None,
step=None,
windows=None,
min_sites=3):
"""Calculate the value of Tajima's D in windows over a single
chromosome/contig.
Parameters
----------
pos : array_like, int, shape (n_items,)
Variant positions, using 1-based coordinates, in ascending order.
ac : array_like, int, shape (n_variants, n_alleles)
Allele counts array.
size : int, optional
The window size (number of bases).
start : int, optional
The position at which to start (1-based).
stop : int, optional
The position at which to stop (1-based).
step : int, optional
The distance between start positions of windows. If not given,
defaults to the window size, i.e., non-overlapping windows.
windows : array_like, int, shape (n_windows, 2), optional
Manually specify the windows to use as a sequence of (window_start,
window_stop) positions, using 1-based coordinates. Overrides the
size/start/stop/step parameters.
min_sites : int, optional
Minimum number of segregating sites for which to calculate a value. If
there are fewer, np.nan is returned. Defaults to 3.
Returns
-------
D : ndarray, float, shape (n_windows,)
Tajima's D.
windows : ndarray, int, shape (n_windows, 2)
The windows used, as an array of (window_start, window_stop) positions,
using 1-based coordinates.
counts : ndarray, int, shape (n_windows,)
Number of variants in each window.
Examples
--------
>>> import allel
>>> g = allel.GenotypeArray([[[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 = g.count_alleles()
>>> pos = [2, 4, 7, 14, 15, 20, 22, 25, 27]
>>> D, windows, counts = allel.windowed_tajima_d(pos, ac, size=20, step=10, start=1, stop=31)
>>> D
array([1.36521524, 4.22566622])
>>> windows
array([[ 1, 20],
[11, 31]])
>>> counts
array([6, 6])
"""
# check inputs
if not isinstance(pos, SortedIndex):
pos = SortedIndex(pos, copy=False)
if not hasattr(ac, 'count_segregating'):
ac = AlleleCountsArray(ac, copy=False)
# assume number of chromosomes sampled is constant for all variants
n = ac.sum(axis=1).max()
# calculate constants
a1 = np.sum(1 / np.arange(1, n))
a2 = np.sum(1 / (np.arange(1, n)**2))
b1 = (n + 1) / (3 * (n - 1))
b2 = 2 * (n**2 + n + 3) / (9 * n * (n - 1))
c1 = b1 - (1 / a1)
c2 = b2 - ((n + 2) / (a1 * n)) + (a2 / (a1**2))
e1 = c1 / a1
e2 = c2 / (a1**2 + a2)
# locate segregating variants
is_seg = ac.is_segregating()
# calculate mean pairwise difference
mpd = mean_pairwise_difference(ac, fill=0)
# define statistic to compute for each window
# noinspection PyPep8Naming
def statistic(w_is_seg, w_mpd):
S = np.count_nonzero(w_is_seg)
if S < min_sites:
return np.nan
pi = np.sum(w_mpd)
d = pi - (S / a1)
d_stdev = np.sqrt((e1 * S) + (e2 * S * (S - 1)))
wD = d / d_stdev
return wD
D, windows, counts = windowed_statistic(pos,
values=(is_seg, mpd),
statistic=statistic,
size=size,
start=start,
stop=stop,
step=step,
windows=windows,
fill=np.nan)
return D, windows, counts
def windowed_diversity(pos, ac, size=None, start=None, stop=None, step=None,
windows=None, is_accessible=None, fill=np.nan):
"""Estimate nucleotide diversity in windows over a single
chromosome/contig.
Parameters
----------
pos : array_like, int, shape (n_items,)
Variant positions, using 1-based coordinates, in ascending order.
ac : array_like, int, shape (n_variants, n_alleles)
Allele counts array.
size : int, optional
The window size (number of bases).
start : int, optional
The position at which to start (1-based).
stop : int, optional
The position at which to stop (1-based).
step : int, optional
The distance between start positions of windows. If not given,
defaults to the window size, i.e., non-overlapping windows.
windows : array_like, int, shape (n_windows, 2), optional
Manually specify the windows to use as a sequence of (window_start,
window_stop) positions, using 1-based coordinates. Overrides the
size/start/stop/step parameters.
is_accessible : array_like, bool, shape (len(contig),), optional
Boolean array indicating accessibility status for all positions in the
chromosome/contig.
fill : object, optional
The value to use where a window is completely inaccessible.
Returns
-------
pi : ndarray, float, shape (n_windows,)
Nucleotide diversity in each window.
windows : ndarray, int, shape (n_windows, 2)
The windows used, as an array of (window_start, window_stop) positions,
using 1-based coordinates.
n_bases : ndarray, int, shape (n_windows,)
Number of (accessible) bases in each window.
counts : ndarray, int, shape (n_windows,)
Number of variants in each window.
Examples
--------
>>> import allel
>>> g = allel.GenotypeArray([[[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 = g.count_alleles()
>>> pos = [2, 4, 7, 14, 15, 18, 19, 25, 27]
>>> pi, windows, n_bases, counts = allel.windowed_diversity(
... pos, ac, size=10, start=1, stop=31
... )
>>> pi
array([0.11666667, 0.21666667, 0.09090909])
>>> windows
array([[ 1, 10],
[11, 20],
[21, 31]])
>>> n_bases
array([10, 10, 11])
>>> counts
array([3, 4, 2])
"""
# check inputs
if not isinstance(pos, SortedIndex):
pos = SortedIndex(pos, copy=False)
is_accessible = asarray_ndim(is_accessible, 1, allow_none=True)
# masking inaccessible sites from pos and ac
pos, ac = mask_inaccessible(is_accessible, pos, ac)
# calculate mean pairwise difference
mpd = mean_pairwise_difference(ac, fill=0)
# sum differences in windows
mpd_sum, windows, counts = windowed_statistic(
pos, values=mpd, statistic=np.sum, size=size, start=start, stop=stop,
step=step, windows=windows, fill=0
)
# calculate value per base
pi, n_bases = per_base(mpd_sum, windows, is_accessible=is_accessible,
fill=fill)
return pi, windows, n_bases, counts
