期刊
BRIEFINGS IN BIOINFORMATICS
卷 22, 期 2, 页码 2141-2150出版社
OXFORD UNIV PRESS
DOI: 10.1093/bib/bbaa044
关键词
drug-target interaction prediction; graph convolutional network; deep neural network; biological networks
资金
- National Natural Science Foundation of China [61702421, U1811262, 61772426]
- China Postdoctoral Science Foundation [2017M610651]
- National Key Research and Development Program of China [2016YFC0901605]
- National Science and Technology Major Project [2016YFC 1202302]
- [20180029]
In order to improve the identification of DTIs, a DPP network was established and a novel learning framework GCN-DTI was proposed. The method utilizes graph convolutional networks to learn DPP features and deep neural networks to predict final DTI labels, outperforming existing approaches significantly.
Identification of new drug-target interactions (DTIs) is an important but a time-consuming and costly step in drug discovery. In recent years, to mitigate these drawbacks, researchers have sought to identify DTIs using computational approaches. However, most existing methods construct drug networks and target networks separately, and then predict novel DTIs based on known associations between the drugs and targets without accounting for associations between drug-protein pairs (DPPs). To incorporate the associations between DPPs into DTI modeling, we built a DPP network based on multiple drugs and proteins in which DPPs are the nodes and the associations between DPPs are the edges of the network. We then propose a novel learning-based framework, 'graph convolutional network (GCN)-DTI', for DTI identification. The model first uses a graph convolutional network to learn the features for each DPP. Second, using the feature representation as an input, it uses a deep neural network to predict the final label. The results of our analysis show that the proposed framework outperforms some state-of-the-art approaches by a large margin.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据