Predicting cellular transcriptional responses to genetic perturbations is a central issue in single-cell biology, particularly in zero-shot scenarios where the perturbed gene or gene combination is unseen during training. The primary challenge is that perturbation effects are not solely determined by expression state; they depend on how the perturbed gene product influences other genes and proteins, how those downstream factors act on cis-regulatory elements, and which regulatory programs are active in the current cell state. To capture this biological complexity more effectively, we propose CisTransCell, a cell-conditioned multi-modal framework for single-cell perturbation prediction that augments each gene with two complementary priors: a regulatory-sequence prior that captures how the gene is controlled, and a coding-sequence prior that captures what the gene product does. By integrating these priors with cellular expression state, CisTransCell models the perturbation response as a cascade from gene function to regulatory control to downstream transcriptional change. Experiments on benchmark single-cell perturbation datasets show that CisTransCell achieves strong performance in zero-shot perturbation prediction.
Blogger's Review: The CisTransCell framework effectively integrates gene regulation and functional information, overcoming traditional limitations and providing a fresh perspective on single-cell perturbation prediction. Future research could explore the influence of additional biological factors to enhance prediction accuracy.