PIE: Generalizing perturbation effects across unseen perturbations, contexts and datasets
Preprint
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.Keywords
This publication has 43 references indexed in Scilit:
- Predicting cellular responses to perturbation across diverse contexts with StateCell, 2026
- Universal cell embedding provides a foundation model for cell biologyNature, 2026
- Virtual Cell Challenge: Toward a Turing test for the virtual cellCell, 2025
- Systematic reconstruction of molecular pathway signatures using scalable single-cell perturbation screensNature Cell Biology, 2025
- Simple and effective embedding model for single-cell biology built from ChatGPTNature Biomedical Engineering, 2024
- Transfer learning enables predictions in network biologyNature, 2023
- Mapping information-rich genotype-phenotype landscapes with genome-scale Perturb-seqCell, 2022
- A Next Generation Connectivity Map: L1000 Platform and the First 1,000,000 ProfilesCell, 2017
- Gene Ontology: tool for the unification of biologyNature Genetics, 2000
- Support-vector networksMachine Learning, 1995