API reference

I/O module

limix.io.bgen.read(filepath[, …])

Read a given BGEN file.

limix.io.bimbam.read_phenotype(filepath[, …])

Read a BIMBAM phenotype file.

limix.io.csv.read(filename[, sep, header, …])

Read a CSV file.

limix.io.gen.read(prefix[, verbose])

Read GEN files into Pandas data frames.


Read the HDF5 limix file format.

limix.io.npy.read(filepath[, verbose])

Read NumPy arrays saved in a file.

limix.io.plink.read(prefix[, verbose])

Read PLINK files into Pandas data frames.

Quality control


Box-Cox transformation for normality conformance.


Compute minor allele frequencies.


Count the number of missing values per column.

limix.qc.indep_pairwise(X, window_size, …)

Determine pair-wise independent variants.

limix.qc.mean_impute(X[, axis, inplace])

Impute NaN values.

limix.qc.mean_standardize(X[, axis, inplace])

Zero-mean and one-deviation normalisation.

limix.qc.normalise_covariance(K[, out])

Variance rescaling of covariance matrix 𝙺.

limix.qc.quantile_gaussianize(X[, axis, inplace])

Normalize a sequence of values via rank and Normal c.d.f.

limix.qc.remove_dependent_cols(X[, tol])

Remove dependent columns.


Filters out variants with the same genetic profile.


limix.stats.Chi2Mixture([scale_min, …])

Mixture of 𝜒² distributions.

limix.stats.allele_expectation(p, nalleles, …)

Allele expectation.


Compute allele frequency from its expectation.

limix.stats.compute_dosage(X[, alt])

Compute dosage from allele expectation.

limix.stats.confusion_matrix(df[, wsize])

Provide a couple of scores based on the idea of windows around genetic markers.

limix.stats.empirical_pvalues(xt, x0)

Function to compute empirical p-values.

limix.stats.linear_kinship(G[, out, verbose])

Estimate Kinship matrix via linear kernel.

limix.stats.lrt_pvalues(null_lml, alt_lmls)

Compute p-values from likelihood ratios.

limix.stats.multipletests(pvals[, alpha, …])

Test results and p-value correction for multiple tests.

limix.stats.multivariate_normal(random, …)

Draw random samples from a multivariate normal distribution.

limix.stats.pca(X, ncomp)

Principal component analysis.

Heritability estimation

limix.her.estimate(y, lik, K[, M, verbose])

Estimate the so-called narrow-sense heritability.

Variance decomposition

limix.vardec.VarDec(y[, lik, M])

Variance decompositon through GLMMs.

Quantitative trait loci

limix.qtl.scan(G, Y[, lik, K, M, idx, A, …])

Multi-trait association and interaction testing via linear mixed models.

limix.qtl.iscan(G, y[, lik, K, M, idx, E0, …])

Single-trait association with interaction test via generalized linear mixed models.


Plotting & Graphics


Change to box aspect considering the plotted points.


Consolidate multiple curves in a single one.

limix.plot.image(file[, ax])

Show an image.

limix.plot.kinship(K[, nclusters, img_kws, ax])

Plot heatmap of a kinship matrix.


Example datasets.

limix.plot.manhattan(data[, colora, colorb, …])

Produce a manhattan plot.

limix.plot.normal(x[, bins, nstd, ax])

Plot a fit of a normal distribution to the data in x.

limix.plot.pca(X[, pts_kws, ax])

Plot the first two principal components of a design matrix.

limix.plot.power(pv[, label, alphas, …])

Plot number of hits across significance levels.

limix.plot.qqplot(a[, label, alpha, cutoff, …])

Quantile-Quantile plot of observed p-values versus theoretical ones.

limix.plot.image(file[, ax])

Show an image.


Get matplotlib.pyplot.


Shell utilities


Compute sha256 from a given file.

limix.sh.download(url[, dest, verbose])

Download file.

limix.sh.extract(filepath[, verbose])

Extract a compressed file.


Remove file.