arXiv:2601.21092 · v4

MapPFN: Learning Causal Perturbation Maps in Context

首次提交 2026-01-29 06:28

版本更新 2026-10-27 06:50

雷达观测 2026-10-29 00:35

摘要

Planning effective interventions in biological systems requires treatment-effect models that adapt to unseen biological contexts by identifying their specific underlying mechanisms. Yet single-cell perturbation datasets span only a handful of biological contexts, and existing methods cannot leverage new interventional evidence at inference time to adapt beyond their training data. To meta-learn a perturbation effect estimator, we present MapPFN, a prior-data fitted network (PFN) pre-trained on a synthetic biological prior with causal interventions, decoupling pre-training from limited wet-lab data. Unlike existing methods, MapPFN uses in-context learning to map a sequence of experiments to a post-perturbation distribution, enabling a single pre-trained model to adapt to new datasets and gene sets. Our results show that combining synthetic pre-training with fine-tuning on real single-cell data improves perturbation predictions across biological contexts. The code, model and data are available at https://marvinsxtr.github.io/MapPFN.

作者备注：Accepted at NeurIPS 2026