• Search Research Projects
  • Search Researchers
  • How to Use
  1. Back to previous page

A theoretical study for the improvement of solvation model by machine learning

Research Project

Project/Area Number 19K05381
Research Category

Grant-in-Aid for Scientific Research (C)

Allocation TypeMulti-year Fund
Section一般
Review Section Basic Section 32010:Fundamental physical chemistry-related
Research InstitutionUniversity of Tsukuba

Principal Investigator

Matsui Toru  筑波大学, 数理物質系, 准教授 (70716076)

Project Period (FY) 2019-04-01 – 2023-03-31
Project Status Completed (Fiscal Year 2022)
Budget Amount *help
¥4,160,000 (Direct Cost: ¥3,200,000、Indirect Cost: ¥960,000)
Fiscal Year 2021: ¥390,000 (Direct Cost: ¥300,000、Indirect Cost: ¥90,000)
Fiscal Year 2020: ¥520,000 (Direct Cost: ¥400,000、Indirect Cost: ¥120,000)
Fiscal Year 2019: ¥3,250,000 (Direct Cost: ¥2,500,000、Indirect Cost: ¥750,000)
Keywords溶媒和モデル / 機械学習 / 酸解離定数 / 酸化還元電位 / 密度汎関数理論 / 金属錯体 / 分配係数 / logP / 量子化学計算
Outline of Research at the Start

量子化学計算において、溶媒和モデルを用いて様々な化合物の物理量を算出できるようになったが、まだ十分な精度が得られない場合が多い。これまではモデル化・定式化することで改善策を得てきているが、人為的な補正項や線形近似にとどまっているケースが多く十分なエビデンスがない。そこで、本研究では新しい試みとして「機械学習」を取り入れて、分子から与えられた情報から溶媒和モデルで得られる溶媒和自由エネルギーで生じる誤差を評価する関数を作成して、精度を向上させる補正の手段・スキームを考察する。

Outline of Final Research Achievements

In this study, we improved the following three aspects by combining quantum chemical calculations with a solvation model:
(1) We obtained more accurate partition coefficients (logP) by using machine learning to correct solvation energy. (2) We analyzed oxidation potentials and identified significant error factors using Lasso regression. We compared experimental and calculated values for 114 organic compounds and performed an analysis using machine learning. (3) In the calculation of acid dissociation constants, conventional methods involved linear approximations based on calculations for compounds with the same functional groups. However, there were unnatural aspects in the reasoning and compound selection. Therefore, we proposed the derivation of acid dissociation constants using multiple regression to obtain more accurate results.

Academic Significance and Societal Importance of the Research Achievements

本研究を通して、量子化学と情報科学・データサイエンスとが融合する形態が第3ステージの量子化学になると考えて「量子化学3.0の時代」という造語を提唱するに至る段階になったと考えている。 「機械学習」や「人工知能」「自動化」など情報科学分野の進展は目覚ましい。それに付随して、機械学習・深層学習が多くの分野で普及が進んでいる昨今ではデータベース化がより進行している。したがって、今後の量子化学ではコンピュータによる自動的なデータ収集などが主流になると予測できるが、アウトプットとゴール(大抵の場合は実験値)との「差」をどう解釈するかは今後も課題であり続けるだろう。

Report

(5 results)
  • 2022 Annual Research Report   Final Research Report ( PDF )
  • 2021 Research-status Report
  • 2020 Research-status Report
  • 2019 Research-status Report
  • Research Products

    (16 results)

All 2023 2022 2021 2020 2019

All Journal Article (6 results) (of which Peer Reviewed: 6 results,  Open Access: 2 results) Presentation (10 results) (of which Int'l Joint Research: 2 results,  Invited: 1 results)

  • [Journal Article] A Theoretical Study on Rate Constants of Excited State Proton Transfer Reaction in Anthracene-Urea Derivatives2023

    • Author(s)
      Onozawa Shu、Nishimura Yoshinobu、Matsui Toru
    • Journal Title

      Bulletin of the Chemical Society of Japan

      Volume: 96 Issue: 3 Pages: 215-222

    • DOI

      10.1246/bcsj.20220332

    • Related Report
      2022 Annual Research Report
    • Peer Reviewed
  • [Journal Article] Factor analysis of error in oxidation potential calculation: A machine learning study2022

    • Author(s)
      Kanamaru Yuki、Matsui Toru
    • Journal Title

      Journal of Computational Chemistry

      Volume: 43 Issue: 22 Pages: 1504-1512

    • DOI

      10.1002/jcc.26953

    • Related Report
      2022 Annual Research Report
    • Peer Reviewed
  • [Journal Article] A Practical Prediction of LogPo/w through Semiempirical Electronic Structure Calculations with Dielectric Continuum Model2021

    • Author(s)
      Takahashi Teruyuki、Matsui Toru、Hengphasatporn Kowit、Shigeta Yasuteru
    • Journal Title

      Bulletin of the Chemical Society of Japan

      Volume: 94 Issue: 7 Pages: 1807-1814

    • DOI

      10.1246/bcsj.20210035

    • NAID

      130008076923

    • Related Report
      2021 Research-status Report 2020 Research-status Report
    • Peer Reviewed
  • [Journal Article] Recent Developments of Computational Methods for pKa Prediction Based on Electronic Structure Theory with Solvation Models2021

    • Author(s)
      Fujiki Ryo、Matsui Toru、Shigeta Yasuteru、Nakano Haruyuki、Yoshida Norio
    • Journal Title

      J

      Volume: 4 Issue: 4 Pages: 849-864

    • DOI

      10.3390/j4040058

    • Related Report
      2021 Research-status Report
    • Peer Reviewed / Open Access
  • [Journal Article] Unique photophysical properties of 1,8-naphthalimide derivatives: generation of semi-stable radical anion species by photo-induced electron transfer from a carboxy group2021

    • Author(s)
      H. Izawa, F. Yasufuku, T. Nokami, S. Ifuku, H. Saimoto, T. Matsui, K. Morihashi, M. Sumita
    • Journal Title

      ACS Omega

      Volume: 6 Issue: 20 Pages: 13456-13465

    • DOI

      10.1021/acsomega.1c01685

    • Related Report
      2021 Research-status Report
    • Peer Reviewed / Open Access
  • [Journal Article] Estimation of Acid Dissociation Constants (pKa) of N-Containing Heterocycles in DMSO and Transferability of Gibbs Free Energy in Different Solvent Conditions2020

    • Author(s)
      Hengphasatporn Kowit、Matsui Toru、Shigeta Yasuteru
    • Journal Title

      Chemistry Letters

      Volume: 49 Issue: 3 Pages: 307-310

    • DOI

      10.1246/cl.190946

    • NAID

      130007805919

    • Related Report
      2019 Research-status Report
    • Peer Reviewed
  • [Presentation] Machine Learning Assisted DFT Calculation Using Solvation Model2023

    • Author(s)
      Toru Matsui
    • Organizer
      The 10th meeting of the Asia Pacific Association of Theoretical and Computational Chemists
    • Related Report
      2022 Annual Research Report
    • Int'l Joint Research / Invited
  • [Presentation] Interaction analysis of FIV protease and HIV-1 protease inhibitors using the FMO method2023

    • Author(s)
      Shohei Osaki, Toru Matsui
    • Organizer
      The 10th meeting of the Asia Pacific Association of Theoretical and Computational Chemists
    • Related Report
      2022 Annual Research Report
    • Int'l Joint Research
  • [Presentation] 荷電系において溶媒和モデルが記述する溶媒静電ポテンシャルの解析2023

    • Author(s)
      金丸 雄基, 松井 亨
    • Organizer
      日本化学会第103春季年会
    • Related Report
      2022 Annual Research Report
  • [Presentation] 原田 秦冴, 松井 亨2023

    • Author(s)
      長距離補正密度汎関数理論を用いた有機薄膜太陽電池材料となる高分子の軌道準位の計算
    • Organizer
      日本化学会第103春季年会
    • Related Report
      2022 Annual Research Report
  • [Presentation] 酸化電位算出における誤差の機械学習を用いた要因解析2022

    • Author(s)
      金丸 雄基, 松井 亨
    • Organizer
      第15回分子科学討論会
    • Related Report
      2022 Annual Research Report
  • [Presentation] 酸化還元電位算出における誤差の機械学習を用いた要因解析2022

    • Author(s)
      金丸雄基, 松井亨
    • Organizer
      日本化学会第102春季年会
    • Related Report
      2021 Research-status Report
  • [Presentation] FIVプロテアーゼとHIV-1プロテアーゼ阻害剤の相互作用解析2022

    • Author(s)
      大﨑象平, 松井亨
    • Organizer
      日本化学会第102春季年会
    • Related Report
      2021 Research-status Report
  • [Presentation] 酸化還元電位算出における誤差の機械学習を用いた要因解析2021

    • Author(s)
      金丸雄基, 松井亨
    • Organizer
      第15回分子科学討論会
    • Related Report
      2021 Research-status Report
  • [Presentation] 機械学習による溶媒和モデルの半経験的改善法2020

    • Author(s)
      登坂 夏名、尾﨑 大和、松井 亨
    • Organizer
      日本化学会第100春季年会
    • Related Report
      2019 Research-status Report
  • [Presentation] 長距離補正密度汎関数による領域分割パラメータの簡便な決定法2019

    • Author(s)
      尾﨑 大和、藤田 健宏、松井 亨、寺山 慧、隅田 真人、守橋 健二
    • Organizer
      第13回分子科学討論会
    • Related Report
      2019 Research-status Report

URL: 

Published: 2019-04-18   Modified: 2024-01-30  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi