PertAdapt: Unlocking Single-Cell Foundation Models for Genetic Perturbation Prediction via Condition-Sensitive Adaptation

Single-cell foundation models (FMs) pretrained on massive unlabeled scRNA-seq data show strong potential in predicting transcriptional responses to unseen genetic perturbations. However, existing approaches insufficiently transfer pretrained knowledge and overlook the imbalance between perturbation-sensitive and insensitive genes, yielding only marginal improvements over nonpretrained baselines. To address these limitations, we introduce PertAdapt, a framework that unlocks FMs to accurately predict genetic perturbation effects via integrating a plug-in perturbation adapter and an adaptive loss. The adapter employs a gene-similarity-masked attention mechanism to jointly encode perturbation conditions and contextualized representations of unperturbed cells, enabling more effective knowledge transfer. To better capture differential expression patterns, the adaptive loss dynamically reweights perturbation-sensitive genes relative to global transcriptomic signals. Extensive experiments across seven perturbation datasets, including both single- and double-gene settings, demonstrate that PertAdapt consistently outperforms non-pretrained and FM baselines. Moreover, PertAdapt demonstrates strong capacity for modeling multiplexed gene interactions, generalizing in limited-data regimes, and maintaining robustness across backbone sizes.