Skip to content
Open access

Single-cell perturbation prediction near experimental reproducibility with GENESIS

Nov 2026 · bioRxiv · 1 citation · 42 references
Medicine Biology

TL;DR

Generative ENErgy-based Single-cell Intervention Simulator is presented, a generative framework that predicts single-cell response distributions directly from the covariates defining an experimental condition and augments sparsely sampled populations and predicts responses in unmeasured conditions.

Abstract

Single-cell perturbation atlases now measure cellular responses across millions of cells, but the number of possible combinations of biological contexts, perturbations, doses and other experimental variables make exhaustive measurements infeasible. Here, we present GENESIS (Generative ENErgy-based Single-cell Intervention Simulator), a generative framework that predicts single-cell response distributions directly from the covariates defining an experimental condition. GENESIS uses a lightweight neural network trained with the energy score, a strictly proper scoring rule for distributions. We introduce an experiment-calibrated evaluation framework in which prediction error is interpreted relative to the reproducibility of repeated measurements of the same condition. Across the Tahoe-100M small-molecule atlas and a large PBMC cytokine atlas, GENESIS significantly outperforms existing generative models and statistical baselines and approaches experimental reproducibility on independently repeated conditions. Importantly, GENESIS remains accurate when trained on only a fraction of the available experimental conditions or cells, and generated profiles recover experimentally observed context-dependent transcriptional programs. At comparable training-cell budgets, GENESIS achieves more accurate predictions when measurements span more experimental conditions rather than profiling fewer conditions more deeply. Together, these findings suggest a complementary strategy for perturbation studies: broader, lower-depth measurements can expand experimental coverage, while GENESIS augments sparsely sampled populations and predicts responses in unmeasured conditions.

Read PDF

Similar papers

Open access Nov 2026

scDisentangle: sequential disentanglement for single-cell perturbation response prediction

Predicting the transcriptional response of single cells to perturbation is a central goal of single-cell modeling, with broad application to analysis and experimental design. Existing methods often fail to beat simple baselines and offer little insight into how biological variation is organized. We present scDisentangl...

Salim El Mejjad, Salwa Enezari, A. Bedraoui et al. · 0 citations
Open access Oct 2026

The recoverable resolution of cellular perturbation-response prediction

Virtual cell models aim to predict how cells respond to perturbations, yet accurate prediction of post-perturbation gene expression can conceal failures to recover context-specific responses. Here we identify context geometry compression (CGC), in which models preserve cellular identity and shared perturbation effects...

Yong-Qi Huang, Han-Zhi Wang, Chen-Yu Li et al. · 1 citation
Open access Sep 2026

PerturbBridge: Conditional Latent Schrödinger Bridge for Single-Cell Perturbation Response Prediction

PerturbBridge is proposed, a conditional latent Schrödinger Bridge framework that reformulates stochastic population transport over high-dimensional, sparse geneexpression profiles as bridge learning in a compact cell latent space, and achieves state-of-the-art performance in differential-expression recovery on both be...

Zhi-Hao Liu, Chang-Zhi Jiang, Can Yang et al. · 0 citations
Preprint Nov 2026

CytoWave: Perturbation-Centric Pretraining for Single-Cell Response Prediction

Predicting gene expression under perturbations from single-cell data is a fundamental task for modeling cellular responses, with applications in discovering gene function and designing therapeutics. However, existing methods often struggle to generalize across datasets due to differences in experimental protocols, biol...

Yu-Wei Miao, Jing-Quan Yan, Hehuan Ma et al. · 0 citations
Open access Oct 2026

Building virtual cell dynamics that evolve with biological measurements

Virtual cell models built from single-cell measurements need to predict how cells change over time, but new biological measurements often reveal dynamical relationships that existing models cannot express. Translating such measurements into dynamics therefore requires deciding what biological relation should be modeled...

Zhenyi Zhang, Zi-Han Wang, Qi Tian et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.