Multitype drug interaction prediction based on the deep fusion of drug features and topological relationships.

Autor: Kang LP; School of Computer and Information Engineering, Xiamen University of Technology, Xiamen, China., Lin KB; School of Computer and Information Engineering, Xiamen University of Technology, Xiamen, China.; Engineering Research Center of Big Data Application in Private Health Medicine, Fujian Provincial University, Putian, China., Lu P; School of Economics and Management, Xiamen University of Technology, Xiamen, China., Yang F; Department of Automation, Xiamen University, Xiamen, China., Chen JP; School of Computer and Information Engineering, Xiamen University of Technology, Xiamen, China.
Jazyk: angličtina
Zdroj: PloS one [PLoS One] 2022 Aug 29; Vol. 17 (8), pp. e0273764. Date of Electronic Publication: 2022 Aug 29 (Print Publication: 2022).
DOI: 10.1371/journal.pone.0273764
Abstrakt: Drug-drug interaction (DDI) prediction has received considerable attention from industry and academia. Most existing methods predict DDIs from drug attributes or relationships with neighbors, which does not guarantee that informative drug embeddings for prediction will be obtained. To address this limitation, we propose a multitype drug interaction prediction method based on the deep fusion of drug features and topological relationships, abbreviated DM-DDI. The proposed method adopts a deep fusion strategy to combine drug features and topologies to learn representative drug embeddings for DDI prediction. Specifically, a deep neural network model is first used on the drug feature matrix to extract feature information, while a graph convolutional network model is employed to capture structural information from the adjacency matrix. Then, we adopt delivery operations that allow the two models to exchange information between layers, as well as an attention mechanism for a weighted fusion of the two learned embeddings before the output layer. Finally, the unified drug embeddings for the downstream task are obtained. We conducted extensive experiments on real-world datasets, the experimental results demonstrated that DM-DDI achieved more accurate prediction results than state-of-the-art baselines. Furthermore, in two tasks that are more similar to real-world scenarios, DM-DDI outperformed other prediction methods for unknown drugs.
Competing Interests: The authors have declared that no competing interests exist.
Databáze: MEDLINE
Externí odkaz:
Nepřihlášeným uživatelům se plný text nezobrazuje