Single-Cell Perturbation Modeling

Single-cell perturbation modeling asks how gene edits, drugs, and other interventions change cell states, including how responses differ across cells and conditions. Approaches include conditional flow-matching and diffusion models that generate response distributions, latent-variable models that separate perturbation effects from baseline cell state, and methods using regulatory networks, biological knowledge, or retrieval of similar experiments. Models are tested on settings such as Perturb-seq, drug-response atlases, and the Virtual Cell Challenge, with tasks including unseen perturbations, cell types, doses, and combinations. A central challenge is that strong benchmark scores may not transfer to new contexts or show that models learned target-specific mechanisms rather than shared background signals.