Generalizable single-cell perturbation response prediction using energy-guided flow matching

2026-09-26

AI Summary

This study addresses the limitations of existing single-cell perturbation models in adapting to distribution shifts and novel perturbation conditions by proposing scEGFlow. This framework integrates conditional flow matching with energy-guided mechanisms, dynamically connecting control and perturbed cells through energy gradients to enable flexible regulation without retraining, thereby establishing a new generative flow paradigm grounded in biological landscapes. Experimental results demonstrate that scEGFlow achieves superior reconstruction of response distributions under both seen and unseen perturbations, effectively preserves the geometric structure of cellular manifolds, and significantly enhances predictive accuracy in few-shot scenarios. Ultimately, this work provides a modular, generalizable, and controllable solution for single-cell perturbation modeling.

Abstract

Predicting phenotypic and transcriptional responses to perturbations at single-cell resolution provides a powerful tool for probing biological systems. However, existing methods typically rely on fixed mappings learned during training, making it challenging to calibrate distribution shifts or adapt to novel perturbation conditions during inference. Here, we present scEGFlow, an energy-guided flow matching framework that dynamically bridges control and perturbed cellular states. scEGFlow models continuous transitions from control cell populations to perturbed states using conditional flow matching. It then applies condition-specific energy gradients to correct and steer these predictions, enabling flexible adjustments without retraining the flow model. Evaluations across benchmarks spanning imaging phenotypes and transcriptomic profiles show that scEGFlow outperforms existing methods in reconstructing response distributions under both seen and unseen perturbation conditions, faithfully preserving cellular manifold geometry and population heterogeneity. This advantage is notable when adapting to new conditions with only a few measured cells, consistently improving prediction accuracy. Furthermore, scEGFlow accurately recapitulates perturbation-induced up- and down-regulation patterns across consensus gene expression signatures, where energy guidance improves the agreement between predicted and observed regulatory directions. Ultimately, these findings demonstrate that scEGFlow provides a modular, generalizable, and steerable solution for single-cell perturbation modeling. By grounding generative flows in learned biological landscapes, this architecture establishes a new computational paradigm for navigating and manipulating cellular behavior in silico.

Problem

• single-cell perturbation response prediction
• distribution shift
• generalizability
• novel perturbation conditions

Innovation

• Energy-guided flow matching
• Single-cell perturbation prediction
• Conditional flow matching
• Generalizability
• Distribution shift adaptation