Explainable modeling of single-cell perturbation data using attention and sparse dictionary learning

2025/04/01 by Yang Xu, Stephen M. Fleming, Matthew Tegtmeyer +2 · 1 voice · 1 citation
Biochemistry, Genetics and Molecular Biology · #Cell Image Analysis Techniques #Gene Regulatory Network Analysis #Single-cell and spatial transcriptomics

paper · doi:10.1016/j.cels.2025.101245

openalex publication_date 2025/04/01 · openalex created_date 2025/10/10 · openalex updated_date 2026/06/26

Abstract

Single-cell transcriptomics, in conjunction with genetic and compound perturbations, offers a robust approach for exploring cellular behaviors in diverse contexts. Such experiments allow uncovering cell-state-specific responses to perturbations and unraveling the intricate molecular mechanisms governing cellular behavior. However, prevailing computational methods predominantly focus on predicting average cellular responses, disregarding inherent response heterogeneity associated with cell state diversity and model explainability. In this study, we present CellCap, a deep generative model designed for the end-to-end analysis of single-cell perturbation experiments. CellCap employs sparse dictionary learning in a latent space to deconstruct cell-state-specific perturbation responses into a set of transcriptional response programs and utilizes an attention mechanism to capture correspondence between cell state and perturbation response. We thoroughly evaluate CellCap's interpretability using multiple simulated scenarios as well as two real single-cell perturbation datasets. Our results demonstrate that CellCap successfully uncovers the relationship between cell state and perturbation response, unveiling insights overlooked in previous analyses.

Citations

• Unsupervised Domain Adaptation by Backpropagation
• Auto-Encoding Variational Bayes
• Adversarial Variational Bayes: Unifying Variational Autoencoders and Generative Adversarial Networks
• PANTHER version 16: a revised family classification, tree-based classification tool, enhancer regions and extensive API
• Exploiting Generative AI to Scale up Intelligent Tutoring Systems

Cited by

• Interpretation, extrapolation and perturbation of single cells

Discussions

• 🧠 Expect to see more of this in the future: Explainable modelling of single-cell perturbations by attention and sparse dictionary learning 📄 Read the full paper by Mehrtash Babadi and colleagues in [bsky, 0 points, 0 comments]

Related

• Causal machine learning for single-cell genomics
• Interpretable Modeling of Single-cell perturbation Responses to Novel Drugs Using Cycle Consistence Learning
• PerturBench: Benchmarking Machine Learning Models for Cellular Perturbation Analysis
• A Systematic Comparison of Single-Cell Perturbation Response Prediction Models
• CisTransCell: Single-Cell Perturbation Prediction via Gene Function, Regulatory Control, and Cellular Context