cs.CVNov 16, 2026

PerturbJEPA: Joint-Embedding Predictive Learning of Cellular Perturbation Responses

Authors: Jiangshuan Pang, Youzhe He, Yiting Deng, Wangyang Tang, Huinan Xu, Qi Lu, Shiping Liu, Zhenkun Zhuang

Organizations: School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing 100049, China · Key Laboratory of Brain Cell Mapping of Zhejiang Province, BGI Research, Hangzhou 310030, China. · Center for Excellence in Brain Science and Intelligence Technology (Institute of Neuroscience), Chinese Academy of Sciences

Abstract

Identifying the drug and dose that produced a cellular response requires preserving treatment effects within each cellular background. A joint-embedding predictor can match its targets while ignoring the intervention if its encoder preserves differences across backgrounds but erases differences between treated and control populations within each one. We call this failure interventional contrast collapse. PerturbJEPA encodes the difference in mean gene expression between treated and control populations as an effect vector. It aligns the displacement between their latent centroids with this vector and regularizes the vectors to preserve variation across population pairs. We show that the measured displacements cannot all coincide within a batch when effect-vector variation exceeds the root-mean-square alignment error. Trained with separate drug and dose ranking objectives, the model predicts candidate responses from a common control population and matches them to the observed response without cell pairing or expression reconstruction. We evaluate 3,592 Tahoe-100M queries on held-out combinations of known interventions and cellular backgrounds, each with over 700 drug-dose candidates in a fixed, background-specific catalog. PerturbJEPA achieves 91.46% macro joint drug-dose Recall@1, exceeding STATE by 3.40 percentage points (95% drug-cluster bootstrap interval of 1.72 to 5.07 points). Controlled diagnostics show that treatment-control differences can shrink even when representations remain globally dispersed. With the drug ranking objective fixed, adding effect-vector regularization to alignment raises joint Recall@1 from 18.57% to 87.47%.

Figures & tables

Appendix figures & tables11 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. LLM-Guided Retrieval for Prediction of Molecular Perturbation Responses

    Aug 3, 2026Betty Xiong, Jan-Christian Huetter, Gabriele Scalia +2Single-Cell Perturbation ModelingDrug Discovery

  2. Differentiable Retrieval-Augmented Generation for Predicting Cellular Responses to Gene Perturbation

    Mar 7, 2026Andrea Giuseppe Di Francesco, Andrea Rubbi, Rishabh Jain +1Single-Cell Perturbation ModelingRetrieval-Augmented Generation