MUFFIN: multi-scale feature fusion for drug-drug interaction prediction

被引:137
作者
Chen, Yujie [1 ]
Ma, Tengfei [1 ]
Yang, Xixi [1 ]
Wang, Jianmin [1 ]
Song, Bosheng [1 ]
Zeng, Xiangxiang [1 ]
机构
[1] Hunan Univ, Sch Comp Sci & Engn, Changsha 410012, Peoples R China
基金
中国国家自然科学基金;
关键词
D O I
10.1093/bioinformatics/btab169
中图分类号
Q5 [生物化学];
学科分类号
071010 ; 081704 ;
摘要
Motivation: Adverse drug-drug interactions (DDIs) are crucial for drug research and mainly cause morbidity and mortality. Thus, the identification of potential DDIs is essential for doctors, patients and the society. Existing traditional machine learning models rely heavily on handcraft features and lack generalization. Recently, the deep learning approaches that can automatically learn drug features from the molecular graph or drug-related network have improved the ability of computational models to predict unknown DDIs. However, previous works utilized large labeled data and merely considered the structure or sequence information of drugs without considering the relations or topological information between drug and other biomedical objects (e.g. gene, disease and pathway), or considered knowledge graph (KG) without considering the information from the drug molecular structure. Results: Accordingly, to effectively explore the joint effect of drug molecular structure and semantic information of drugs in knowledge graph for DDI prediction, we propose a multi-scale feature fusion deep learning model named MUFFIN. MUFFIN can jointly learn the drug representation based on both the drug-self structure information and the KG with rich bio-medical information. In MUFFIN, we designed a bi-level cross strategy that includes cross- and scalar-level components to fuse multi-modal features well. MUFFIN can alleviate the restriction of limited labeled data on deep learning models by crossing the features learned from large-scale KG and drug molecular graph. We evaluated our approach on three datasets and three different tasks including binary-class, multi-class and multi-label DDI prediction tasks. The results showed that MUFFIN outperformed other state-of-the-art baselines.
引用
收藏
页码:2651 / 2658
页数:8
相关论文
共 38 条
[1]   Bio2RDF: Towards a mashup to build bioinformatics knowledge systems [J].
Belleau, Francois ;
Nolin, Marc-Alexandre ;
Tourigny, Nicole ;
Rigault, Philippe ;
Morissette, Jean .
JOURNAL OF BIOMEDICAL INFORMATICS, 2008, 41 (05) :706-716
[2]  
Bordes Antoine, 2013, Advances in neural information processing systems
[3]   Machine learning-based prediction of drug-drug interactions by integrating drug phenotypic, therapeutic, chemical, and genomic properties [J].
Cheng, Feixiong ;
Zhao, Zhongming .
JOURNAL OF THE AMERICAN MEDICAL INFORMATICS ASSOCIATION, 2014, 21 (E2) :E278-E286
[4]  
Deac Andreea., 2019, Drug-drug adverse effect prediction with graph co-attention
[5]   When good drugs go bad [J].
Giacomini, Kathleen M. ;
Krauss, Ronald M. ;
Roden, Dan M. ;
Eichelbaum, Michel ;
Hayden, Michael R. .
NATURE, 2007, 446 (7139) :975-977
[6]  
Gilmer J, 2017, PR MACH LEARN RES, V70
[7]   INDI: a computational framework for inferring drug interactions and their associated recommendations [J].
Gottlieb, Assaf ;
Stein, Gideon Y. ;
Oron, Yoram ;
Ruppin, Eytan ;
Sharan, Roded .
MOLECULAR SYSTEMS BIOLOGY, 2012, 8
[8]  
Hu W., 2019, INT C LEARNING REPRE
[9]  
Huang KX, 2020, AAAI CONF ARTIF INTE, V34, P702
[10]  
Ioannidis V., 2020, DRKG-Drug Repurposing Knowledge Graph for Covid-19