scMEDAL: interpretable single-cell transcriptomics analysis with batch effect visualization via deep mixed-effects autoencoder

Single-cell RNA sequencing enables high-resolution analysis of cellular heterogeneity, yet disentangling biological signal from batch effects remains challenging. Existing batch-correction algorithms suppress or discard batch-related variation rather than modeling it. We propose scMEDAL—single-cell Mixed Effects Deep Autoencoder Learning—a framework that separately and independently models batch-invariant and batch-specific effects. The principal innovation, scMEDAL-RE, is a random-effects Bayesian autoencoder that learns batch-specific representations while preserving biologically meaningful information confounded with batch effects, signal often lost under standard correction. Across diverse conditions (autism, leukemia, cardiovascular), cell types, and technical and biological effects, scMEDAL-RE produces interpretable, batch-specific embeddings that complement multiple batch correction methods, improving prediction of disease status, donor group, and tissue. scMEDAL also provides generative visualizations—including counterfactual reconstructions of a cell’s expression as if acquired in another batch. Overall, scMEDAL is a versatile, interpretable framework that complements existing correction, providing insight into cellular heterogeneity and data acquisition. Batch effects in single-cell RNA-seq can obscure biology and limit interpretation. Here, authors present a deep learning framework that separates batch-specific and batch-invariant signals, preserves biological information confounded with batch effects, and enables interpretable visualisations.