Multi-batch single-cell comparative atlas construction by deep learning disentanglement

• Published in: Nature communications 2023-07, Vol.14 (1), p.4126-4126, Article 4126
• Main Authors: Lynch, Allen W., Brown, Myles, Meyer, Clifford A.
• Format: Article
• Language: English
• Subjects: 45/91; 631/114/1305; 631/114/2401; 631/114/2415; 631/114/794; 631/1647/48; Ascomycota; Biological Assay; Biological effects; Biological variation; Cancer; Cells; Chromatin; Chromatin Immunoprecipitation Sequencing; Comparative analysis; Data mining; Datasets; Deep Learning; Embryogenesis; Embryonic Development; Embryonic growth stage; Gene expression; Humanities and Social Sciences; Mathematical models; Medical research; Methods; multidisciplinary; Perturbation; Quorum sensing; Regularization; Ribonucleic acid; RNA; Science; Science (multidisciplinary); Statistical models
• ISSN: 2041-1723; 2041-1723
• DOI: 10.1038/s41467-023-39494-2

Cell state atlases constructed through single-cell RNA-seq and ATAC-seq analysis are powerful tools for analyzing the effects of genetic and drug treatment-induced perturbations on complex cell systems. Comparative analysis of such atlases can yield new insights into cell state and trajectory alterations. Perturbation experiments often require that single-cell assays be carried out in multiple batches, which can introduce technical distortions that confound the comparison of biological quantities between different batches. Here we propose CODAL, a variational autoencoder-based statistical model which uses a mutual information regularization technique to explicitly disentangle factors related to technical and biological effects. We demonstrate CODAL’s capacity for batch-confounded cell type discovery when applied to simulated datasets and embryonic development atlases with gene knockouts. CODAL improves the representation of RNA-seq and ATAC-seq modalities, yields interpretable modules of biological variation, and enables the generalization of other count-based generative models to multi-batched data. Comparing single-cell RNA-seq and ATAC-seq data from multiple batches is challenging due to technical artifacts. Here, the authors propose a method that disentangles technical and biological effects, facilitating batch-confounded chromatin and gene expression state discovery and enhancing the analysis of perturbation effects on cell populations.