Sep 2026· Computers and artificial intelligence· 0 citations· 58 references
TL;DR
A claim-centered framework is introduced that clarifies which claims current DDI benchmarks can support and what additional evidence is needed before predictions can guide prescribing or monitoring and shows that useful explanations require evidence alignment and actionability in addition to visual plausibility.
Abstract
Drug–drug interactions (DDIs) are a major source of preventable medication-related harm, but the evidence used to anticipate them spans molecular structure, pharmacology, biomedical text, knowledge graphs, and longitudinal clinical records. Computational studies often treat distinct targets as a single benchmark, even though binary interaction screening, event prediction, relation extraction, and patient-specific risk require different evidence and validation. This critical review introduces a claim-centered framework that aligns the clinical question, evidence source, prediction unit, model inductive bias, validation design, and intended use. Representative methods are compared by what they encode, the assumptions they impose, and their characteristic failure modes rather than by incomparable leaderboard scores. The analysis covers similarity and factorization methods, molecular and relational graph learning, pair-conditioned substructure models, contrastive and pretrained learning, multimodal fusion, and language-based systems. A validation-to-translation ladder then connects leakage-aware splitting, calibration, uncertainty, external testing, mechanistic corroboration, and prospective workflow evaluation. The synthesis indicates that architecture-level gains are conditional on label construction and distribution shift. It also shows that useful explanations require evidence alignment and actionability in addition to visual plausibility. This framework clarifies which claims current DDI benchmarks can support and what additional evidence is needed before predictions can guide prescribing or monitoring.
This review systematically analyzes key challenges in DDI prediction: balancing model performance with interpretability, integrating heterogeneous features, ensuring sample set reliability, and optimizing algorithmic architectures, and outlines promising directions for future innovation.
Yun Zuo, Jia-Yi Ji, Yuwen Li et al.· Current Bioinformatics· 0 citations
A systematic reference for future algorithm design, mechanism exploration, and real-world drug discovery applications for AI-driven DTI prediction methodologies, covering binding theories, task formulations, data representation, model design, translational applications, and unresolved challenges.
Jia-Xuan Hu, Lianlian Wu, Song He et al.· Journal of Chemical Informat...· 0 citations
Drug-drug interactions (DDIs) represent a critical challenge in drug development and clinical practice, as they can lead to severe adverse effects, including toxicity and reduced therapeutic efficacy. Deep learning methods have shown promise in large-scale, rapid DDI prediction; however, current approaches suffer from...
The proposed approach demonstrates that the PoSMNA descriptors of drug pairs can be used for preliminary prediction of DDI-associated ADR severity, and can help to filter out potentially dangerous drug combinations at an early stage and are implemented in the AdverDDIPred web-application.
Владислав Сергеевич Сухачёв, S. M. Ivanov, D. Filimonov et al.· Pharmaceuticals· 0 citations
A structure-agnostic framework that combines semantic representations derived from Medical Subject Headings with graph-derived topology from a Drug–Target–Protein knowledge graph constructed from DrugBank and UniProt is presented and it is found that graph-derived topology is particularly beneficial when ontology annot...
Results show that closed-loop perturbation validation recovers literature-supported molecular regions more accurately than existing alternatives while producing cross-drug interaction scores that better reflect predictor behavior.