Home >

news Help

Publication Information


Title
Japanese:タンパク質-化合物相互作用ネットワークのリンクマイニング 
English: 
Author
Japanese: 山崎卓朗, 大上雅史, 秋山泰.  
English: Takuro Yamazaki, Masahito Ohue, Yutaka Akiyama.  
Language Japanese 
Journal/Book name
Japanese:研究報告バイオ情報学（BIO） 
English:IPSJ SIG Technical Report 
Volume, Number, Page 2016-BIO-45    9    1-7
Published date Mar. 11, 2016 
Publisher
Japanese:情報処理学会 
English: 
Conference name
Japanese:情報処理学会 第45回バイオ情報学研究会 
English: 
Conference site
Japanese:石川県能美市 
English: 
Official URL https://ipsj.ixsq.nii.ac.jp/ej/?action=pages_view_main&active_action=repository_view_main_item_detail&item_id=158087&item_no=1&page_id=13&block_id=8
 
Abstract Virtual screening (VS) is widely used in the process of a computational drug discovery for reducing a large amount of cost. Chemical genomics-based virtual screening (CGBVS) which is a kind of VS predicts new protein-compound interactions (PCIs) from known PCIs data using several methods of machine learning or data mining. Although CGBVS provides highly efficient and accurate PCIs prediction, CGBVS has poor performance on prediction for new compound for which PCIs are unknown. Pairwise kernel method (PKM) is one of the state-of-the-art methods of CGBVS, that showed highest accuracy on prediction for new compounds. In this study, from the viewpoint of link mining we improved PKM by combining link indicator and chemical similarity, and evaluated their accuracy. The proposed method obtained AUPR value of 0.562 which is higher than that achieved by using normal PKM (0.468).

©2007 Tokyo Institute of Technology All rights reserved.