EDDINet: Enhancing drug–drug interaction prediction via information flow and consensus constrained multi-graph contrastive learningVisa övriga samt affilieringar
2025 (Engelska)Ingår i: Artificial Intelligence in Medicine, ISSN 0933-3657, E-ISSN 1873-2860, Vol. 159, s. 1-13, artikel-id 103029Artikel i tidskrift (Refereegranskat) Published
Abstract [en]
Predicting drug–drug interactions (DDIs) is crucial for understanding and preventing adverse drug reactions (ADRs). However, most existing methods inadequately explore the interactive information between drugs in a self-supervised manner, limiting our comprehension of drug–drug associations. This paper introduces EDDINet: Enhancing Drug-Drug Interaction Prediction via Information Flow and Consensus-Constrained Multi-Graph Contrastive Learning for precise DDI prediction. We first present a cross-modal information-flow mechanism to integrate diverse drug features, enriching the structural insights conveyed by the drug feature vector. Next, we employ contrastive learning to filter various biological networks, enhancing the model's robustness. Additionally, we propose a consensus regularization framework that collaboratively trains multi-view models, producing high-quality drug representations. To unify drug representations derived from different biological information, we utilize an attention mechanism for DDI prediction. Extensive experiments demonstrate that EDDINet surpasses state-of-the-art unsupervised models and outperforms some supervised baseline models in DDI prediction tasks. Our approach shows significant advantages and holds promising potential for advancing DDI research and improving drug safety assessments. Our codes are available at: https://github.com/95LY/EDDINet_code. © 2024 The Authors
Ort, förlag, år, upplaga, sidor
Amsterdam: Elsevier, 2025. Vol. 159, s. 1-13, artikel-id 103029
Nyckelord [en]
Consensus regularization, Contrastive learning, DDI prediction, Information flow, Multi-graph
Nationell ämneskategori
Data- och informationsvetenskap
Identifikatorer
URN: urn:nbn:se:hh:diva-55055DOI: 10.1016/j.artmed.2024.103029Scopus ID: 2-s2.0-85210116931OAI: oai:DiVA.org:hh-55055DiVA, id: diva2:1920083
Anmärkning
This work is supported by the National Natural Science Foundation of China (No. 62072290 , 61672329 , 62172076 ), Natural Science Foundation of Shandong Province (No. ZR2021MF118 , ZR2022QF022 ), Postgraduate Quality Education and Teaching Resources Project of Shandong Province (No. SDYKC2022053 , SDYAL2022060 ), Jinan \u201C20 new colleges and universities\u201D Funded Project (No. 202228110 ), the Zhejiang Provincial Natural Science Foundation of China (Grant No. LY23F020003 ), and the Municipal Government of Quzhou ( 2022D006 ).
2024-12-102024-12-102025-10-01Bibliografiskt granskad