def test_pairwise_distance_multidim(self): g = GenotypeArray([[[0, 0], [0, 0]], [[1, 1], [1, 1]], [[1, 1], [2, 2]], [[0, 0], [0, 1]], [[0, 0], [0, 2]], [[1, 1], [1, 2]], [[0, 1], [0, 1]], [[0, 1], [1, 2]], [[0, 0], [-1, -1]], [[0, 1], [-1, -1]], [[-1, -1], [-1, -1]]], dtype='i1') gac = g.to_allele_counts() def metric(ac1, ac2): mpd = allel.stats.mean_pairwise_difference_between(ac1, ac2, fill=0) return mpd.sum() expect = [ allel.stats.mean_pairwise_difference_between(gac[:, 0], gac[:, 1], fill=0).sum()] actual = allel.stats.pairwise_distance(gac, metric) aeq(expect, actual)
def mendel_errors(parent_genotypes, progeny_genotypes): """Locate genotype calls not consistent with Mendelian transmission of alleles. Parameters ---------- parent_genotypes : array_like, int, shape (n_variants, 2, 2) Genotype calls for the two parents. progeny_genotypes : array_like, int, shape (n_variants, n_progeny, 2) Genotype calls for the progeny. Returns ------- me : ndarray, int, shape (n_variants, n_progeny) Count of Mendel errors for each progeny genotype call. Examples -------- The following are all consistent with Mendelian transmission. Note that a value of 0 is returned for missing calls:: >>> import allel >>> import numpy as np >>> genotypes = np.array([ ... # aa x aa -> aa ... [[0, 0], [0, 0], [0, 0], [-1, -1], [-1, -1], [-1, -1]], ... [[1, 1], [1, 1], [1, 1], [-1, -1], [-1, -1], [-1, -1]], ... [[2, 2], [2, 2], [2, 2], [-1, -1], [-1, -1], [-1, -1]], ... # aa x ab -> aa or ab ... [[0, 0], [0, 1], [0, 0], [0, 1], [-1, -1], [-1, -1]], ... [[0, 0], [0, 2], [0, 0], [0, 2], [-1, -1], [-1, -1]], ... [[1, 1], [0, 1], [1, 1], [0, 1], [-1, -1], [-1, -1]], ... # aa x bb -> ab ... [[0, 0], [1, 1], [0, 1], [-1, -1], [-1, -1], [-1, -1]], ... [[0, 0], [2, 2], [0, 2], [-1, -1], [-1, -1], [-1, -1]], ... [[1, 1], [2, 2], [1, 2], [-1, -1], [-1, -1], [-1, -1]], ... # aa x bc -> ab or ac ... [[0, 0], [1, 2], [0, 1], [0, 2], [-1, -1], [-1, -1]], ... [[1, 1], [0, 2], [0, 1], [1, 2], [-1, -1], [-1, -1]], ... # ab x ab -> aa or ab or bb ... [[0, 1], [0, 1], [0, 0], [0, 1], [1, 1], [-1, -1]], ... [[1, 2], [1, 2], [1, 1], [1, 2], [2, 2], [-1, -1]], ... [[0, 2], [0, 2], [0, 0], [0, 2], [2, 2], [-1, -1]], ... # ab x bc -> ab or ac or bb or bc ... [[0, 1], [1, 2], [0, 1], [0, 2], [1, 1], [1, 2]], ... [[0, 1], [0, 2], [0, 0], [0, 1], [0, 1], [1, 2]], ... # ab x cd -> ac or ad or bc or bd ... [[0, 1], [2, 3], [0, 2], [0, 3], [1, 2], [1, 3]], ... ]) >>> me = allel.mendel_errors(genotypes[:, :2], genotypes[:, 2:]) >>> me array([[0, 0, 0, 0], [0, 0, 0, 0], [0, 0, 0, 0], [0, 0, 0, 0], [0, 0, 0, 0], [0, 0, 0, 0], [0, 0, 0, 0], [0, 0, 0, 0], [0, 0, 0, 0], [0, 0, 0, 0], [0, 0, 0, 0], [0, 0, 0, 0], [0, 0, 0, 0], [0, 0, 0, 0], [0, 0, 0, 0], [0, 0, 0, 0], [0, 0, 0, 0]]) The following are cases of 'non-parental' inheritance where one or two alleles are found in the progeny that are not present in either parent. Note that the number of errors may be 1 or 2 depending on the number of non-parental alleles:: >>> genotypes = np.array([ ... # aa x aa -> ab or ac or bb or cc ... [[0, 0], [0, 0], [0, 1], [0, 2], [1, 1], [2, 2]], ... [[1, 1], [1, 1], [0, 1], [1, 2], [0, 0], [2, 2]], ... [[2, 2], [2, 2], [0, 2], [1, 2], [0, 0], [1, 1]], ... # aa x ab -> ac or bc or cc ... [[0, 0], [0, 1], [0, 2], [1, 2], [2, 2], [2, 2]], ... [[0, 0], [0, 2], [0, 1], [1, 2], [1, 1], [1, 1]], ... [[1, 1], [0, 1], [1, 2], [0, 2], [2, 2], [2, 2]], ... # aa x bb -> ac or bc or cc ... [[0, 0], [1, 1], [0, 2], [1, 2], [2, 2], [2, 2]], ... [[0, 0], [2, 2], [0, 1], [1, 2], [1, 1], [1, 1]], ... [[1, 1], [2, 2], [0, 1], [0, 2], [0, 0], [0, 0]], ... # ab x ab -> ac or bc or cc ... [[0, 1], [0, 1], [0, 2], [1, 2], [2, 2], [2, 2]], ... [[0, 2], [0, 2], [0, 1], [1, 2], [1, 1], [1, 1]], ... [[1, 2], [1, 2], [0, 1], [0, 2], [0, 0], [0, 0]], ... # ab x bc -> ad or bd or cd or dd ... [[0, 1], [1, 2], [0, 3], [1, 3], [2, 3], [3, 3]], ... [[0, 1], [0, 2], [0, 3], [1, 3], [2, 3], [3, 3]], ... [[0, 2], [1, 2], [0, 3], [1, 3], [2, 3], [3, 3]], ... # ab x cd -> ae or be or ce or de ... [[0, 1], [2, 3], [0, 4], [1, 4], [2, 4], [3, 4]], ... ]) >>> me = allel.mendel_errors(genotypes[:, :2], genotypes[:, 2:]) >>> me array([[1, 1, 2, 2], [1, 1, 2, 2], [1, 1, 2, 2], [1, 1, 2, 2], [1, 1, 2, 2], [1, 1, 2, 2], [1, 1, 2, 2], [1, 1, 2, 2], [1, 1, 2, 2], [1, 1, 2, 2], [1, 1, 2, 2], [1, 1, 2, 2], [1, 1, 1, 2], [1, 1, 1, 2], [1, 1, 1, 2], [1, 1, 1, 1]]) The following are cases of 'hemi-parental' inheritance, where progeny appear to have inherited two copies of an allele found only once in one of the parents:: >>> genotypes = np.array([ ... # aa x ab -> bb ... [[0, 0], [0, 1], [1, 1], [-1, -1]], ... [[0, 0], [0, 2], [2, 2], [-1, -1]], ... [[1, 1], [0, 1], [0, 0], [-1, -1]], ... # ab x bc -> aa or cc ... [[0, 1], [1, 2], [0, 0], [2, 2]], ... [[0, 1], [0, 2], [1, 1], [2, 2]], ... [[0, 2], [1, 2], [0, 0], [1, 1]], ... # ab x cd -> aa or bb or cc or dd ... [[0, 1], [2, 3], [0, 0], [1, 1]], ... [[0, 1], [2, 3], [2, 2], [3, 3]], ... ]) >>> me = allel.mendel_errors(genotypes[:, :2], genotypes[:, 2:]) >>> me array([[1, 0], [1, 0], [1, 0], [1, 1], [1, 1], [1, 1], [1, 1], [1, 1]]) The following are cases of 'uni-parental' inheritance, where progeny appear to have inherited both alleles from a single parent:: >>> genotypes = np.array([ ... # aa x bb -> aa or bb ... [[0, 0], [1, 1], [0, 0], [1, 1]], ... [[0, 0], [2, 2], [0, 0], [2, 2]], ... [[1, 1], [2, 2], [1, 1], [2, 2]], ... # aa x bc -> aa or bc ... [[0, 0], [1, 2], [0, 0], [1, 2]], ... [[1, 1], [0, 2], [1, 1], [0, 2]], ... # ab x cd -> ab or cd ... [[0, 1], [2, 3], [0, 1], [2, 3]], ... ]) >>> me = allel.mendel_errors(genotypes[:, :2], genotypes[:, 2:]) >>> me array([[1, 1], [1, 1], [1, 1], [1, 1], [1, 1], [1, 1]]) """ # setup parent_genotypes = GenotypeArray(parent_genotypes) progeny_genotypes = GenotypeArray(progeny_genotypes) check_ploidy(parent_genotypes.ploidy, 2) check_ploidy(progeny_genotypes.ploidy, 2) # transform into per-call allele counts max_allele = max(parent_genotypes.max(), progeny_genotypes.max()) parent_gc = parent_genotypes.to_allele_counts(max_allele=max_allele, dtype='i1') progeny_gc = progeny_genotypes.to_allele_counts(max_allele=max_allele, dtype='i1') # detect nonparental and hemiparental inheritance by comparing allele # counts between parents and progeny max_progeny_gc = parent_gc.clip(max=1).sum(axis=1) max_progeny_gc = max_progeny_gc[:, np.newaxis, :] me = (progeny_gc - max_progeny_gc).clip(min=0).sum(axis=2) # detect uniparental inheritance by finding cases where no alleles are # shared between parents, then comparing progeny allele counts to each # parent p1_gc = parent_gc[:, 0, np.newaxis, :] p2_gc = parent_gc[:, 1, np.newaxis, :] # find variants where parents don't share any alleles is_shared_allele = (p1_gc > 0) & (p2_gc > 0) no_shared_alleles = ~np.any(is_shared_allele, axis=2) # find calls where progeny genotype is identical to one or the other parent me[no_shared_alleles & (np.all(progeny_gc == p1_gc, axis=2) | np.all(progeny_gc == p2_gc, axis=2))] = 1 # retrofit where either or both parent has a missing call me[np.any(parent_genotypes.is_missing(), axis=1)] = 0 return me