Molecular Inverse-Design Platform for Material Industries
Abstract
The discovery of new materials has been the essential force which brings a discontinuous improvement to industrial products' performance. However, the extra-vast combinatorial design space of material structures exceeds human experts' capability to explore all, thereby hampering material development. In this paper, we present a material industry-oriented web platform of an AI-driven molecular inverse-design system, which automatically designs brand new molecular structures rapidly and diversely. Different from existing inverse-design solutions, in this system, the combination of substructure-based feature encoding and molecular graph generation algorithms allows a user to gain high-speed, interpretable, and customizable design process. Also, a hierarchical data structure and user-oriented UI provide a flexible and intuitive workflow. The system is deployed on IBM's and our client's cloud servers and has been used by 5 partner companies. To illustrate actual industrial use cases, we exhibit inverse-design of sugar and dye molecules, that were carried out by experimental chemists in those client companies. Compared to general human chemist's standard performance, the molecular design speed was accelerated more than 10 times, and greatly increased variety was observed in the inverse-designed molecules without loss of chemical realism.
Cite
@article{arxiv.2004.11521,
title = {Molecular Inverse-Design Platform for Material Industries},
author = {Seiji Takeda and Toshiyuki Hama and Hsiang-Han Hsu and Victoria A. Piunova and Dmitry Zubarev and Daniel P. Sanders and Jed W. Pitera and Makoto Kogoh and Takumi Hongo and Yenwei Cheng and Wolf Bocanett and Hideaki Nakashika and Akihiro Fujita and Yuta Tsuchiya and Katsuhiko Hino and Kentaro Yano and Shuichi Hirose and Hiroki Toda and Yasumitsu Orii and Daiju Nakano},
journal= {arXiv preprint arXiv:2004.11521},
year = {2020}
}
Comments
9 pages, 7 figures, Accepted to KDD 2020