BioERP A biomedical heterogeneous network-based self-supervised representation learning approach for entity relationship predictions
Introduction
BioERP is a biomedical heterogeneous network-based self-supervised representation learning approach for entity relationship predictions. A self-supervised meta path detection mechanism is proposed to train a deep Transformer encoder model that can capture the global structure and semantic feature in BioHNs. Meanwhile, a biomedical entity mask learning strategy is designed to reflect local associations of vertices. Finally, the representations from different task models are concatenated to generate two-level representation vectors for predicting relationship among entities. The results on eight datasets show BioERP outperforms 30 state-of-the-art methods. In particular, BioERP reveals great performance with results close to 1 in terms of AUC and AUPR on the drug-target interaction predictions. In summary, BioERP is a promising bio-entity relationship prediction approach.
Publications
Credits
- Xiaoqi Wang xqw@hnu.edu.cn InvestigatorDeveloper
College of Computer Science and Electronic Engineering, Hunan University, China
- Shaoliang Peng slpeng@hnu.edu.cn InvestigatorDeveloper
College of Computer Science and Electronic Engineering, Hunan University, China
- Fei Li pittacus@gmail.com InvestigatorDeveloper
Computer Network Information Center, Chinese Academy of Sciences, Beijing, China
Community Ratings
Usability | Efficiency | Reliability | Rated By |
---|---|---|---|
0 user | |||
Sign in to rate |
Accession | BT007163 |
---|---|
Tool Type | Application |
Category | Data integration, Biological network reconstruction, Network analysis, Drug targets, Drug repositioning |
Platforms | Linux/Unix |
Technologies | Python3 |
User Interface | Terminal Command Line |
Latest Release | 1.0 (May 31, 2021) |
Download Count | 765 |
Country/Region | China |
Submitted By | Shaoliang Peng |
2018YFC0910400