arXiv:2610.13966v1 Announce Type: cross Abstract: Predicting cellular responses to chemical and genetic perturbations is a central test for AI virtual cells, yet many single-cell models reduce each c...
Generative modeling has shown increasing promise for predicting cellular perturbation effects under chemical compound treatments. Existing approaches either model perturbation as a distribution-to-dis...
The paper introduces scEGFlow, an energy‑guided flow matching framework that predicts how single cells respond to perturbations by modeling continuous transitions from control to perturbed states. It uses conditional flow matching and condition‑specific energy gradients to dynamically adjust predictions without retraining, achieving superior performance on imaging and transcriptomic benchmarks, even for unseen perturbations or limited data. The method preserves cellular manifold geometry, heterogeneity, and accurately recapitulates gene‑expression regulatory patterns.
The paper introduces Distribution‑Conditioned Transport (DCT), a framework that learns transport maps conditioned on embeddings of source and target distributions, allowing generalization to unseen distribution pairs. DCT supports semi‑supervised learning for distributional forecasting by leveraging distributions observed at only one condition. It is agnostic to the transport mechanism and is demonstrated on synthetic benchmarks and four biological applications, including batch effect transfer in single‑cell genomics and modeling T‑cell receptor sequence evolution.
arXiv:2608. 06824v1 Announce Type: cross Abstract: A central task in virtual cell modeling is predicting single-cell transcriptional responses to unseen genetic perturbations and drug combinations, and biological networks provide valuable priors on gene relationships.
arXiv:2509. 26405v2 Announce Type: replace Abstract: We introduce InVirtuoGen, a discrete flow generative model for fragmented SMILES for de novo and fragment-constrained generation, and target-property/lead optimization of small molecules.
arXiv:2606.27752v2 Announce Type: replace Abstract: Single-cell perturbation models can reduce costly wet-lab screening by predicting how cells respond transcriptionally to interventions. Recent adva...
arXiv:2607. 19426v1 Announce Type: cross Abstract: Single-cell datasets are increasingly costly to store, audit, and reuse for model training.
The paper introduces SUDO, a simulation‑free framework for unbalanced dynamic optimal transport (UDOT) that supports general convex growth penalties beyond the quadratic Wasserstein‑Fisher‑Rao case. By showing that concave penalties lead to degenerate solutions, the authors focus on convex penalties, learning conditional paths and transport costs to solve a semi‑coupling problem and then applying unbalanced flow matching. On benchmark datasets, SUDO matches the accuracy of analytical WFR solvers while being faster than simulation‑based methods, and it also handles asymmetric penalties that better reflect proliferation‑dominant biological priors.
arXiv:2606. 11286v1 Announce Type: cross Abstract: High-content imaging assays quantify cellular responses to chemical and genetic perturbations, yet continuous trajectories of individual cells are unobservable because cells are chemically fixed at acquisition.
arXiv:2601. 22495v2 Announce Type: replace Abstract: Fine-tuning flow matching models is a central challenge in settings with limited data, evolving distributions, or computational constraints.
The paper investigates how to transport the full distribution of treatment effects from a source site to a target site in a cross‑site, one‑armed design where only control units are observed in the target. It proposes learning a transformation between sites via optimal transport on control samples, then applying this transformation to the source treated sample to generate a synthetic target treated distribution. The authors prove convergence of this synthetic distribution to the true target distribution and validate the method with simulations and a patient‑derived xenograft data application.