scCBGM: Interpretable Single-Cell Counterfactual Editing
For computational biologists studying cellular responses to perturbations, scCBGM provides an interpretable method to predict counterfactual cell states, though it is an incremental extension of concept bottleneck architectures to single-cell data.
scCBGM introduces a concept bottleneck framework for interpretable counterfactual editing of single-cell RNA-seq data, achieving superior combinatorial generalization and counterfactual prediction across multiple real datasets with cell-level validation on synthetic benchmarks.
Understanding cellular phenotypes and how they respond to perturbations is critical for disease biology and therapeutic design. Single-cell RNA sequencing enables characterization at cellular resolution, yet the combinatorial space of conditions makes exhaustive experimental mapping infeasible. We introduce single-cell Concept Bottleneck Generative Models (scCBGM), a framework for interpretable and precise counterfactual editing of individual cells. scCBGM adapts concept bottleneck architectures for single-cell data through decoder skip connections and a cross-covariance penalty that promotes disentanglement without dimensional constraints. We extend the framework to flow matching models, enabling concept-guided editing in both encoding-decoding and generation regimes. To enable rigorous evaluation, we develop a synthetic benchmark with ground-truth counterfactuals. Across multiple real datasets, scCBGM demonstrates superior performance in combinatorial generalization and counterfactual prediction, supported by cell-level validation on synthetic data and population-level benchmarks on real datasets.