Title of Paper:Improving neural protein-protein interaction extraction with knowledge selection

Hits:

First Author:Zhou, Huiwei

Correspondence Author:Yao, WH (reprint author), Dalian Univ Technol, Sch Comp Sci & Technol, Dalian 116024, Liaoning, Peoples R China.

Co-author:Li, Xuefei,Yao, Weihong,Liu, Zhuang,Ning, Shixian,Lang, Chengkun,Du, Lei

Date of Publication:2019-12-01

Journal:COMPUTATIONAL BIOLOGY AND CHEMISTRY

Included Journals:PubMed、EI、SCIE

Volume:83

Page Number:107146

ISSN No.:1476-9271

Key Words:PPI extraction; Knowledge selection; Mutual attention; Prior knowledge

Abstract:Protein-protein interaction (PPI) extraction from published scientific literature provides additional support for precision medicine efforts. Meanwhile, knowledge bases (KBs) contain huge amounts of structured information of protein entities and their relations, which can be encoded in entity and relation embeddings to help PPI extraction. However, the prior knowledge of protein-protein pairs must be selectively used so that it is suitable for different contexts. This paper proposes a Knowledge Selection Model (KSM) to fuse the selected prior knowledge and context information for PPI extraction. Firstly, two Transformers encode the context sequence of a protein pair according to each protein embedding, respectively. Then, the two outputs are fed to a mutual attention to capture the important context features towards the protein pair. Next, the context features are used to distill the relation embedding by a knowledge selector. Finally, the selected relation embedding and the context features are concatenated for PPI extraction. Experiments on the BioCreative VI PPI dataset show that KSM achieves a new state-of-the-art performance (38.08 % F1-score) by adding knowledge selection.