Few-Shot Generalization to Novel Compounds in Single-Cell Drug Response via Graph-Infused Meta-Pretraining.

Understanding drug responses at the single-cell level is crucial for identifying biomarkers and uncovering resistance mechanisms. However, existing models predominantly rely on genomic profiles, while overlooking drug structure-function relationships and showing limited generalization to novel drugs with distinct structures. To address this limitation, we propose a novel framework that integrates drug structural information with genomic data. Specifically, we develop a graph-aware Transformer to capture interatomic relations and generate joint representations linking atomic features to genomic profiles. To overcome the scarcity of single-cell drug response data, we propose a novel predictive framework that leverages prior knowledge from bulk RNA datasets through meta-pretraining and few-shot transfer learning. Furthermore, we introduce a position-based feature extraction network and a gene gradient attribution algorithm to identify key resistance genes and drug action pathways. Pre-trained on 223 drugs across 14 tissues and tested on seven single-cell datasets, our model achieves an approximate 5% improvement in accuracy for known drugs and about 20% increase in generalization to unseen drugs. This approach provides an effective method for studying drug resistance mechanisms at single-cell level, particularly for novel compounds.