Building foundation of polymer informatics: ensemble of generators and virtual libraries of diverse functional polymers

2023 Fiscal Year Annual Research Report

• Project/Area Number: 21K14675
• Research Institution: The Institute of Statistical Mathematics
• Principal Investigator: Wu Stephen 統計数理研究所, 先端データサイエンス研究系, 准教授 (70804186)
• Project Period (FY): 2021-04-01 – 2024-03-31
• Keywords: polymer informatics / generative models / open source software

Outline of Annual Research Achievements

In 2023, we continued the validation of the virtual libraries, as originally planned. We also successfully refined the ensemble of polymer generators within the XenonPy platform, our open source software developed in this project, based on the new measurement results for the synthesized polyimides last fiscal year. Candidates in the virtual library are further filtered using state-of-the-art clustering algorithm and a new model for solubility estimation of polymers in different solvents in order to help the polymer scientists ranking the order for synthesis trials. Our analyses demonstrated that the data-driven polymer design approach based on our generative models is effective on discovery of new functional polymers with desired properties. A total of six new polyimides that were confirmed to exhibit liquid crystalline structure through X-ray diffraction measurement. Our models also continue to contribute to the RadonPy project, which is a collaborative national project between academia and industry to form the largest open calculation database for polymers. This project is just a starting point and we will continue to expand the capacity of our generative models and predictive models for different polymer type and polymer properties to set the groundwork for future innovations in polymer design and materials science.

Research Products

• [Journal Article] A Bayesian method for concurrently designing molecules and synthetic reaction networks (2023)
  • Author(s): Zhang Qi、Liu Chang、Wu Stephen、Hayashi Yoshihiro、Yoshida Ryo
  • Journal Title: Science and Technology of Advanced Materials: Methods Volume: 3 Pages: 2204994
  • DOI: 10.1080/27660400.2023.2204994
  • Peer Reviewed / Open Access / Int'l Joint Research
• [Journal Article] Multitask Machine Learning to Predict Polymer-Solvent Miscibility Using Flory-Huggins Interaction Parameters (2023)
  • Author(s): Aoki Yuta、Wu Stephen、Tsurimoto Teruki、Hayashi Yoshihiro、Minami Shunya、Tadamichi Okubo、Shiratori Kazuya、Yoshida Ryo
  • Journal Title: Macromolecules Volume: 56 Pages: 5446～5456
  • DOI: 10.1021/acs.macromol.2c02600
  • Peer Reviewed / Open Access / Int'l Joint Research
• [Presentation] Polymer Design by Interplay of Machine Learning, Computer Simulation and Expert Knowledge (2023)
  • Author(s): Stephen Wu
  • Organizer: 64th World Statistics Congress
  • Int'l Joint Research
• [Presentation] マルチタスク学習を用いたポリマー・溶媒系における Flory-Huggins χ パラメータの予測 (2023)
  • Author(s): 白鳥 和矢, 青木 裕太, Stephen Wu, 釣本 輝希, 林 慶浩, 南 俊匠, 大久保 忠利, 吉田 亮
  • Organizer: 日本高分子討論会
• [Presentation] 集積センサーアレイとフォトサーマルロックイン法によるポリイミド薄膜の面内熱拡散率測定と高速熱分析 (2023)
  • Author(s): 中川栞, Felix Jiang, 前田颯, Stephen Wu, 林慶浩, 劉芽久哉, Xuan Thang Vu, Sven Ingebrandt, 吉田亮, 早川晃鏡, 森川淳子
  • Organizer: 第59回熱測定討論会
• [Remarks] XenonPy
  • URL: https://xenonpy.readthedocs.io/en/latest/