Skip to content
Open access

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

Oct 2026 · bioRxiv · 3 citations · ⚡ 1 influential · 54 references
Biology

TL;DR

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.

Abstract

Predicting cellular response to perturbations is key to understanding biological mechanisms and selecting therapeutic targets. However, generalizing across cellular contexts, perturbations, and experimental datasets remains challenging due to incomplete representations of the system being perturbed and the difficulty of measuring true perturbation effects within that system. We introduce PIE, a model that addresses these limitations by reformulating the learning task around population-level perturbation effects and incorporating auxiliary inputs that better characterize the biological system. PIE directly predicts differentially expressed genes and changes in gene expression for each (context, perturbation) pair, using external biological knowledge, baseline gene expression, and observed perturbation responses. Its architecture accommodates input sources with variable feature sets and predicts effects on genes seen and unseen during training. On the Replogle–Nadig dataset, PIE achieves state-of-the-art performance on most metrics across all tested generalization settings, including the most challenging setting where both the context and perturbation are unseen during training. For predicting differentially expressed genes, PIE achieves 1.2–3.2 times the AUPRC of the strongest baseline in each setting: across unseen contexts, perturbations, experimental datasets, and jointly unseen contexts and perturbations. Overall, PIE provides a framework for generalizing perturbation effects across diverse experimental conditions.

Read PDF

Similar papers

Open access Nov 2026

RELAY: Relational In-Context Learning for Cellular Perturbation Prediction

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...

Yu-Ze Sun, Jing-Hao Feng, Yan-Feng Wang et al. · 0 citations
Open access Oct 2026

EMBER: Contextualized gene representations enable compositional prediction across cellular perturbations

Predicting the effects of individual and combined perturbations is central to identifying context-specific vulnerabilities and designing targeted interventions. Yet learning gene representations that integrate functional relationships with cellular state and transfer across perturbation tasks remains challenging. Here,...

Nicholas Ho, E. Xing, Jian Ma · 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 Nov 2026

ExPert infers causal perturbations from cell states across biological and clinical contexts

Pooled single-cell CRISPR screens have driven substantial effort toward models predicting the response to a perturbation. We posed the inverse question: which perturbation produced an observed cell state? Here we developed ExPert (Extracting Perturbations), which learns one prototype per perturbation in a latent space...

Leon Schwartz, Jacob L. Schlamowitz, Benjamin Kuznets-Speck et al. · 0 citations
Open access Sep 2026

SHERLOCK: Structured representation learning and causal inference of downstream perturbation effects

SHERLOCK is presented, an interpretable deep generative framework for single-cell perturbation analysis that represents perturbation effects as structured interventions on a latent baseline cellular state and enables counterfactual estimation of their downstream transcriptional effects under explicit identifiability as...

Ming-Xuan Zhang, Joshua D. Myers, Ling-Ting Shi et al. · 0 citations
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

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