ChemTS: an efficient python library for de novo molecular generation. Issue 1 (31st December 2017)

• Record Type: Journal Article
• Authors: Yang, Xiufeng; Zhang, Jinzhe; Yoshizoe, Kazuki; Terayama, Kei; Tsuda, Koji
• Is Part Of: Science and technology of advanced materials. Volume 18:Issue 1(2017)
• Page Start: 972
• Page End: 976
• Publication Date: 2017-12-31
• Subjects: Molecular design -- Monte Carlo tree search -- recurrent neural network -- python library; 60 New topics/Others -- 404 Materials informatics / Genomics; Materials -- Technological innovations -- Periodicals; 620.112
• DOI: 10.1080/14686996.2017.1401424
• Languages: English
• ISSNs: 1468-6996

Abstract

Abstract: Automatic design of organic materials requires black-box optimization in a vast chemical space. In conventional molecular design algorithms, a molecule is built as a combination of predetermined fragments. Recently, deep neural network models such as variational autoencoders and recurrent neural networks (RNNs) are shown to be effective in de novo design of molecules without any predetermined fragments. This paper presents a novel Python library ChemTS that explores the chemical space by combining Monte Carlo tree search and an RNN. In a benchmarking problem of optimizing the octanol-water partition coefficient and synthesizability, our algorithm showed superior efficiency in finding high-scoring molecules. ChemTS is available athttps://github.com/tsudalab/ChemTS . Graphical Abstract: