期刊
JOURNAL OF BIOINFORMATICS AND COMPUTATIONAL BIOLOGY
卷 20, 期 5, 页码 -出版社
WORLD SCIENTIFIC PUBL CO PTE LTD
DOI: 10.1142/S0219720022500238
关键词
Drug-target interaction; matrix completion; graph convolutional network; graph auto-encoder
类别
资金
- National Key Research and Development Program of China [2018AAA0100100]
This study proposes a novel model called GCMCDTI for predicting drug-target interactions using graph convolutional network based on matrix completion, achieving high AUC values on four benchmark datasets.
Identification of potential drug-target interactions (DTIs) plays a pivotal role in the development of drug and target discovery in the public healthcare sector. However, biological experiments for predicting interactions between drugs and targets are still expensive, complicated, and time-consuming. Thus, computational methods are widely applied for aiding drug-target interaction prediction. In this paper, we propose a novel model, named GCMCDTI, for DTIs prediction which adopts a graph convolutional network based on matrix completion. We regard the association prediction between drugs and targets as link prediction and treat the process as matrix completion, and then a graph convolutional auto-encoder framework is employed to construct the drug and target embeddings. Then, a bilinear decoder is applied to reconstruct the DTI matrix. We conduct our experiments on four benchmark datasets consisting of enzymes, G protein-coupled receptors (GPCRs), ion channels, and nuclear receptors. The five-fold cross-validation results achieve the high average AUC values of 95.78%, 95.31%, 93.90%, and 91.77%, respectively. To further evaluate our method, we compare our proposed method with other state-of-the-art approaches. The comparison results illustrate that our proposed method obtains improvement in performance on DTI prediction. The proposed method will be a good choice in the field of DTI prediction.
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