Skip to content
Open access

RELAY: Relational In-Context Learning for Cellular Perturbation Prediction

Nov 2026 · bioRxiv · 0 citations · 40 references
Biology

Abstract

Cellular responses to perturbations vary across multiple experimental variables, such as perturbation identity, cell type, donor, and dose, defining a multidimensional condition space in which each measured population occupies one coordinate. Existing methods predict unmeasured conditions using explicit representations of these variable values, generalizing unseen values therefore depends on the availability and quality of such representations. We present RELAY, a relational in-context model that predicts unmeasured coordinates from measured responses at related coordinates. For each target, RELAY uses measured control–perturbed pairs from conditions that share one or more experimental variables with the target, such as the same perturbation in another cell type. The model receives only which variables are shared, not their values, and uses these demonstrations to predict the target response. We evaluate RELAY on chemical, genetic, and cytokine perturbation datasets under two settings: unseen combinations, where test values are individually observed during training but not in their target combinations, and unseen variable values, where test values are introduced only through context at inference. RELAY outperforms existing in-context methods on unseen variable values and supervised perturbation-prediction methods on unseen combinations. All resources will be open sourced1 2, including code and data.

Read PDF

Similar papers

Open access Oct 2026

PIE: Generalizing perturbation effects across unseen perturbations, contexts and datasets

A model that addresses limitations of the learning task around population-level perturbation effects and incorporating auxiliary inputs that better characterize the biological system is introduced, providing a framework for generalizing perturbation effects across diverse experimental conditions.

Rishi Verma, Abhinav K. Adduri, Beatrice Bevilacqua et al. · 3 citations · ⚡1
Oct 2026

InDyVAE: An interaction and dependency-aware variational autoencoder for single-cell perturbation response generation.

InDyVAE, an interaction- and dependency-aware variational autoencoder that models response generation as a connected sequence of transformations, is evaluated on four Perturb-seq datasets using treatment-effect agreement, top-gene overlap, and quality-control compliance under three thresholds.

Qi Yu, Ren-Yu Yang, Chun-Xue Shao et al. · 0 citations
#artificial intelligence Preprint Oct 2026

Learning Perturbation-Specific Representations through Conditional Energy Prior for Cellular Response Prediction

AI-based cellular perturbation prediction is essential to accelerate drug discovery and therapeutic identification. However, perturbation-specific signals are generally obscured by cellular complexity, making it difficult for existing methods to correctly capture perturbation effects. To address this problem, we propos...

Yu-Chen Yan, Ya-Tao Bian · 0 citations
Open access Oct 2026

How Much Can AI Virtual Cells Gain from Unified Perturbational Modeling?

This work introduces three unification modules into a variational autoencoder (VAE)-based AIVC predictor to address these sources of heterogeneity: gene-channel alignment, shared perturbation encoding, and joint embedding of gene expression and identity.

Zong-Ting Wei, Yue-Dian Ye, Shu-Guang Cui et al. · 0 citations
Open access Sep 2026

Regulon-informed cellular representations reveal task-dependent generalization in drug combination prediction

A symmetric three-class predictor of DrugComb ZIP interactions was developed and compared all seven combinations of landmark expression, Hallmark pathway scores and CollecTRI regulon activities, demonstrating that the predictive value of functional context representations depends on both the type of domain shift and th...

Elizaveta Ignatova, M. Likhter · 0 citations

AmbiModBench: Benchmarking Gene Perturbation Prediction Beyond Shared Responses

Predicting cellular responses to genetic perturbations helps prioritize experiments in single-cell genomics, where exhaustive measurement is infeasible. While computational models increasingly predict these responses, three evaluation deficiencies obscure what their scores demonstrate. First, absolute metrics cannot se...

Si-Kai Huang, Zhi-Wen Yang, Kai Yu et al. · 1 citation

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