aiqbench analysis
scCBGM introduces a novel framework for interpretable counterfactual editing in single-cell data by adapting concept bottleneck models with decoder skip connections and flow matching. The approach achieves superior combinatorial generalization and precise prediction across multiple real datasets, validated against a new synthetic benchmark with ground-truth labels. This method addresses the infeasibility of exhaustive experimental mapping in disease biology by enabling precise, concept-guided manipulation of cellular phenotypes.
scCBGM: Interpretable Single-Cell Counterfactual Editing
arXiv:2606.07760v1 Announce Type: new Abstract: 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.
Abstract: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.
Machine Learning (cs.LG)
arXiv:2606.07760 [cs.LG]
(or arXiv:2606.07760v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2606.07760 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 227 words
Related coverage
Class-Aware Reinforcement Learning for Counterfactual Explanation Generation
arXiv · Jul 31, 2026
Don't Judge an LLM Only by Its Activations: Discovering Suppressed Safety Features via Counterfactual Activation Potential
arXiv · Oct 7, 2026
Graph-Regularized Synthetic Control for Stable Counterfactual Estimation under Donor Redundancy
arXiv · Oct 21, 2026
How Faithful Is Attribution for Sales Forecasting? A Counterfactual Study
arXiv · Sep 7, 2026