Joint Learning of Drug-Drug Combination and Drug-Drug Interaction via Coupled Tensor-Tensor Factorization with Side...

Targeted drug therapies offer a promising approach for treating complex diseases, with combinational drug therapies often employed to enhance therapeutic efficacy. However, unintended drug-drug interactions (DDIs) may undermine treatment outcomes or cause adverse side effects. In this work, we propose a novel joint learning framework for the simultaneous prediction of effective drug combinations and DDIs, based on coupled tensor-tensor factorization. Specifically, we model drug combination therapies and DDI by representing drug-drug-disease associations and DDI profiles as coupled three-way tensors. To address the challenges of data incompleteness and sparsity, the proposed model integrates auxiliary drug similarity information, such as chemical structure similarities, drug-specific side effects, drug target profiles, and drug inhibition data on cancer cell lines, within a multiview learning framework. For optimization, we adopt a modified alternating direction method of multipliers (ADMM) algorithm with non-negativity constraints. In addition to standard tensor completion tasks, we further evaluate the proposed method under a more realistic new-drug prediction setting, where all interactions involving a previously unseen drug are withheld. This scenario closely aligns with real-world applications, in which reliable predictions for emerging or under-studied compounds are essential. We evaluate the proposed method (named SI-ADMM for Side Information-ADMM) on a comprehensive dataset compiled from multiple sources, including DrugBank, the Continuous Drug Combination Database (CDCDB), the Side Effect Resource (SIDER), and PubChem. Our experiments show that SI-ADMM maintains robust performance and achieves the best results comparing to other tensor factorization approaches, with or without auxiliary information, particularly in the new-drug prediction setting. The implementation of our method is publicly available at: https://github.com/Xiaoge-Zhang/SI-ADMM.