Few-shot drug synergy prediction via rapid cross-tier adaptation meta-optimization.

Abstract

Drug combination therapy offers key advantages over monotherapy in personalized oncology by reducing drug resistance and toxicity. However, predicting synergistic effects for rare cell lines remains challenging, as existing methods suffer from poor generalizability in data-scarce scenarios owing to their reliance on large training datasets and inability to effectively transfer knowledge across distinct cellular contexts. Here, we present MetaSynergy, a Rapid Cross-tier Adaptation Meta-Optimization (R-CAMO)-based framework for few-shot drug synergy prediction through cross-domain knowledge transfer and meta-optimized adaptation. We first designed a multimodal feature learning architecture integrating drug molecular graphs with cell line omics profiles, then implemented a stage-wise training strategy based on R-CAMO for few-shot drug synergy prediction: (i) cross-domain pretraining establishes meta-initialized representations by transferring knowledge from data-rich cell lines to scarce target domains, enhancing feature representation capability in data-scarce scenarios. (ii) Cross-tier meta-optimization enables rapid adaptation to data-scarce scenarios: the inner-tier refines task-specific parameters of the prediction network on the target domain, while the outer-tier meta-learns task-shared, generalizable parameters by minimizing the cross-cell line prediction loss. (iii) Fine-tuning further refines task-specific parameters, improving generalizability to novel drug combinations within the same cellular context. Experimental results demonstrate that MetaSynergy achieves excellent performance in few-shot, zero-shot and low-similarity tasks, surpassing most baseline methods and highlighting its robustness and generalizability. Ablation studies confirmed the pivotal role of R-CAMO strategy in data-scarce cell lines. Furthermore, MetaSynergy successfully identified novel synergistic drug combinations in several understudied malignancies, underscoring its potential in precision oncology.