Analysis of multi-condition single-cell data with latent embedding multivariate regression

2025/01/03 by Constantin Ahlmann-Eltze, Wolfgang Huber · 3 voices · 4 citations
Biochemistry, Genetics and Molecular Biology · Mathematics · #Single-cell and spatial transcriptomics #Gene expression and cancer classification #Statistical Methods and Inference

paper · pdf · doi:10.1038/s41588-024-01996-0

Abstract

Identifying gene expression differences in heterogeneous tissues across conditions is a fundamental biological task, enabled by multi-condition single-cell RNA sequencing (RNA-seq). Current data analysis approaches divide the constituent cells into clusters meant to represent cell types, but such discrete categorization tends to be an unsatisfactory model of the underlying biology. Here, we introduce latent embedding multivariate regression (LEMUR), a model that operates without, or before, commitment to discrete categorization. LEMUR (1) integrates data from different conditions, (2) predicts each cell's gene expression changes as a function of the conditions and its position in latent space and (3) for each gene, identifies a compact neighborhood of cells with consistent differential expression. We apply LEMUR to cancer, zebrafish development and spatial gradients in Alzheimer's disease, demonstrating its broad applicability.

Citations

• A single-cell molecular map of mouse gastrulation and early organogenesis

Cited by

• Reconstructing and comparing signal transduction networks from single-cell protein quantification data
• VDW-GNNs: Vector diffusion wavelets for geometric graph neural networks
• Interpretation, extrapolation and perturbation of single cells
• Generalized promotion time cure model: A new modeling framework to identify cell-type-specific genes and improve survival prognosis

Discussions

• How to do differential expression with scRNAseq data? State of the art is "pseudo-bulk" analysis with RNA-seq methods like edgeR or DESeq2, where "cell type" is encoded as discrete categories. Biologi [bsky, 246 points, 7 comments]
• 🦎 Differential expression analysis relies on cluster identities, unless you perform a regression along continuous representation in latent space. LEMUR from @const-ae.bsky.social & @wkhuber.bsky.soci [bsky, 13 points, 0 comments]
• New single-cell analysis framework, LEMUR, disentangles covariates and latent cell states from multi-condition data to predict counterfactual gene expression and identify cell neighborhoods with simil [bsky, 0 points, 1 comments]

Related

• Analysis of multi-condition single-cell data with latent embedding multivariate regression
• Partition Decoupling for Multi-gene Analysis of Gene Expression Profiling Data
• Contrastive latent variable modeling with application to case-control sequencing experiments
• Regression-Based Analysis of Multimodal Single-Cell Data Integration Strategies
• Structured factorization for single-cell gene expression data