def test_ehh_decay():
h = [[0, 0, 1, 1], [0, 0, 1, 1], [0, 0, 0, 1], [0, 0, 0, 0], [0, 1, 0, 0]]
e = [2 / 6, 2 / 6, 1 / 6, 1 / 6, 0]
a = ehh_decay(h)
assert_array_equal(e, a)
# with multiallelics
h = [[0, 0, 2, 2], [0, 0, 1, 1], [0, 0, 0, 3], [0, 0, 0, 0], [0, 4, 0, 0]]
e = [2 / 6, 2 / 6, 1 / 6, 1 / 6, 0]
a = ehh_decay(h)
assert_array_equal(e, a)
def get_ehh_decay(haparray, haplotype_pos, core_left, core_right, core_haps,
flank):
# Get the haplotype arrays
pos_left, haps_left, pos_right, haps_right = extract_haplotype_array(
haparray, haplotype_pos, core_left, core_right, flank)
# Get the positions of interest
all_pos = np.concatenate((pos_left, pos_right), axis=0)
# Calculate the EHH
all_ehh = pd.DataFrame(columns=all_pos)
for (l, s) in core_haps:
haps_left_core = haps_left.take(sorted(s), axis=1)
haps_right_core = haps_right.take(sorted(s), axis=1)
ehh_decay_left = allel.ehh_decay(haps_left_core[::-1])
ehh_decay_right = allel.ehh_decay(haps_right_core)
all_ehh.loc[l, :] = np.concatenate(
(ehh_decay_left[::-1], ehh_decay_right), axis=0)
return all_ehh.transpose()
def test_ehh_decay():
h = [[0, 0, 1, 1], [0, 0, 1, 1], [0, 0, 0, 1], [0, 0, 0, 0], [0, 1, 0, 0]]
e = [2 / 6, 2 / 6, 1 / 6, 1 / 6, 0]
a = ehh_decay(h)
assert_array_equal(e, a)
# plot
pdf = PdfPages("%s/%s_%s.sel_EHHdecay.pdf" % (outdir,outcode,l_nom))
fig = plt.figure(figsize=(8,8))
ax3 = plt.subplot(2, 1, 1)
for i,clui in enumerate(np.append(clu_list_ids_fil,np.append("no_wt","no_alt"))):
clu_key = "cluster_"+str(clui)
print("EHH %s" % clu_key)
# which variants include in the cluster-wise analysis of selection?
clu_sambool = np.isin(range(0,oc_haploty_hap_seg.n_haplotypes),test_elements=popdich_clu[clu_key])
clu_sambool = np.logical_and(clu_sambool,rmv_miss_bool)
# calculate actual EHH
clu_ehh_up_i = allel.ehh_decay(h=oc_haploty_hap_seg.subset(sel0=clu_varbool_up,sel1=clu_sambool))
clu_ehh_do_i = allel.ehh_decay(h=oc_haploty_hap_seg.subset(sel0=clu_varbool_do,sel1=clu_sambool))
clu_ehh_i = np.concatenate((clu_ehh_up_i[::-1],clu_ehh_do_i))
clu_ehh_i_ar = np.trapz(clu_ehh_i)
ehh_above_start = clu_ehh_pos.compress(clu_ehh_i > ehh_above_thr)[0]
ehh_above_end = clu_ehh_pos.compress(clu_ehh_i > ehh_above_thr)[-1]
ehh_below_start = clu_ehh_pos.compress(clu_ehh_i < ehh_below_thr)[0]
ehh_below_end = clu_ehh_pos.compress(clu_ehh_i < ehh_below_thr)[-1]
# lab is data
clu_lab = "%s, n=%i, a=%.3f\nEHH>%.2f: %i bp %i-%i\nEHH<%.2f: %i bp %i-%i" % (
clu_key, len(popdich_clu[clu_key]),clu_ehh_i_ar,
ehh_above_thr, ehh_above_end-ehh_above_start, ehh_above_start, ehh_above_end,
ehh_below_thr, ehh_below_end-ehh_below_start, ehh_below_start, ehh_below_end
)