Drug combination therapies are well-established strategies for the treatment of cancer with low toxicity and fewer adverse effects. Computational drug synergy prediction approaches can accelerate the discovery of novel combination therapies, but the existing methods do not explicitly consider the key role of important substructures in producing synergistic effects. To this end, we propose a significant substructure-aware anticancer drug synergy prediction method, named SDDSynergy, to adaptively identify critical functional groups in drug synergy. SDDSynergy splits the task of predicting drug synergy into predicting the effect of individual substructures on cancer cell lines and highlights the impact of important substructures through a novel drug–cell line attention mechanism. And a substructure pair attention mechanism is incorporated to capture the information on internal substructure pairs interaction in drug combinations, which aids in predicting synergy. The substructures of different sizes and shapes are directly obtained from the molecular graph of the drugs by multilayer substructure information passing networks. Extensive experiments on three real-world data sets demonstrate that SDDSynergy outperforms other state-of-the-art methods. We also verify that many of the novel drug combinations predicted by SDDSynergy are supported by previous studies or clinical trials through an in-depth literature survey.

中文翻译：

---

SDDSynergy：学习重要的分子子结构以进行可解释的抗癌药物协同预测

药物联合疗法是治疗癌症的成熟策略，具有低毒性和较少的不良反应。计算药物协同预测方法可以加速新型联合疗法的发现，但现有方法没有明确考虑重要子结构在产生协同效应中的关键作用。为此，我们提出了一种重要的子结构感知抗癌药物协同预测方法，称为SDDSynergy，以自适应地识别药物协同中的关键功能基团。 SDDSynergy 将预测药物协同作用的任务分解为预测单个子结构对癌细胞系的影响，并通过新型药物细胞系注意机制突出重要子结构的影响。并且采用了子结构对注意机制来捕获药物组合中内部子结构对相互作用的信息，这有助于预测协同作用。通过多层子结构信息传递网络直接从药物的分子图获得不同大小和形状的子结构。对三个真实世界数据集的大量实验表明，SDDSynergy 优于其他最先进的方法。我们还通过深入的文献调查验证了SDDSynergy预测的许多新型药物组合均得到了先前研究或临床试验的支持。