Home >

news ヘルプ

論文・著書情報


タイトル
和文: 
英文:Molecular activity prediction using graph convolutional deep neural network considering distance on a molecular graph 
著者
和文: 大上 雅史, 伊井 良太, 柳澤 渓甫, 秋山 泰.  
英文: Ohue M, Ii R, Yanagisawa K, Akiyama Y..  
言語 English 
掲載誌/書名
和文:研究報告数理モデル化と問題解決(MPS) 
英文:IPSJ SIG Technical Report 
巻, 号, ページ Vol. 2019-MPS-124    No. 3    pp. 1-4
出版年月 2019年7月22日 
出版者
和文: 
英文: 
会議名称
和文: 
英文: 
開催地
和文: 
英文: 
公式リンク https://ipsj.ixsq.nii.ac.jp/ej/?action=pages_view_main&active_action=repository_view_main_item_detail&item_id=198416&item_no=1&page_id=13&block_id=8
 
アブストラクト Machine learning is often used in virtual screening to find compounds that are pharmacologically active on a target protein. The weave module is a type of graph convolutional deep neural network that uses not only features focusing on atoms alone (atom features) but also features focusing on atom pairs (pair features); thus, it can consider information of nonadjacent atoms. However, the correlation between the distance on the graph and the 3-D coordinate distance is uncertain. In this paper, we propose three improvements for modifying the weave module. First, the distances between ring atoms on the graph were modified to bring the distances on the graph closer to the coordinate distance. Second, different weight matrices were used depending on the distance on the graph in the convolution layers of the pair features. Finally, a weighted sum, by distance, was used when converting pair features to atom features. The experimental results show that the performance of the proposed method is slightly better than that of the weave module, and the improvement in the distance representation might be useful for compound activity prediction.

©2007 Institute of Science Tokyo All rights reserved.