📖 API reference

Preprocessing

pseudobulk(adata[, sample_key, group_key, ...])

Create pseudobulk samples from single-cell RNA-seq data.

size_factors(adata[, method, layer, ...])

Compute size factors for (single-cell) RNA-seq normalization.

Differential Expression

nb_fit(adata[, condition_key, formula, ...])

Fit Gamma-Poisson (negative binomial) GLMs to count data.

nb_test(adata, fit[, contrast, ...])

Test for differential expression using quasi-likelihood F-test.

nb_de(adata[, condition_key, formula, ...])

One-shot negative binomial DE: fit model and test in one call.

NBFitResult(beta, overdispersions, mu, ...)

Result container for nb_fit.

de(adata[, condition_key, formula, ...])

Differential expression testing for non-count data.

rank_de(adata, condition_key[, layer, ...])

Perform rank-based differential expression analysis using AUROC statistics.

grouped(func, adata, group_key[, ...])

Run a DE function separately for each group and combine results.

Effect Sizes

log2fc(adata, condition_key[, reference, ...])

Calculate log2 fold changes between condition levels.

auroc(adata, condition_key[, reference, ...])

Calculate Area Under the Receiver Operating Characteristic (AUROC) between condition levels.

Utilities

build_design(obs[, formula, condition_key, ...])

Build a design matrix from a formula or condition_key.

gsea(genes[, background, gene_sets, ...])

Run enrichment analysis for a single gene list using Enrichr.

Models

LinearRegression([maxiter, tol, optimizer, ...])

Linear regression with Ordinary Least Squares estimation.

LogisticRegression([maxiter, tol, ...])

Logistic regression in JAX.

NegativeBinomialRegression([maxiter, tol, ...])

Negative Binomial regression in JAX.

Plotting

dotplot(adata, markers, groupby[, save])

Create a dot plot showing mean expression and fraction of cells expressing markers per group.

heatmap(adata, markers, groupby[, save])

Create a dot plot showing mean expression and fraction of cells expressing markers per group.

matrixplot(adata, markers, groupby[, save])

Create a matrix plot showing mean expression of markers per group.

violinplot(adata, genes, groupby[, splitby, ...])

Create a violin plot for gene expression across groups and splits.

volcanoplot(df[, x, y, effect_key, ...])

Create a volcano plot using matplotlib.