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

Development of a prediction method for cofactors binding to uncharacterized enzymes using feedback from experimental validations

Research Project

Project/Area Number 19K12211
Research Category

Grant-in-Aid for Scientific Research (C)

Allocation TypeMulti-year Fund
Section一般
Review Section Basic Section 62010:Life, health and medical informatics-related
Research InstitutionNagahama Institute of Bio-Science and Technology

Principal Investigator

Shionyu Masafumi  長浜バイオ大学, バイオサイエンス学部, 准教授 (30345847)

Co-Investigator(Kenkyū-buntansha) 土方 敦司  長浜バイオ大学, バイオサイエンス学部, プロジェクト特任講師 (80415273)
向 由起夫  長浜バイオ大学, バイオサイエンス学部, 教授 (60252615)
Project Period (FY) 2019-04-01 – 2022-03-31
Project Status Completed (Fiscal Year 2021)
Budget Amount *help
¥4,420,000 (Direct Cost: ¥3,400,000、Indirect Cost: ¥1,020,000)
Fiscal Year 2021: ¥1,430,000 (Direct Cost: ¥1,100,000、Indirect Cost: ¥330,000)
Fiscal Year 2020: ¥1,430,000 (Direct Cost: ¥1,100,000、Indirect Cost: ¥330,000)
Fiscal Year 2019: ¥1,560,000 (Direct Cost: ¥1,200,000、Indirect Cost: ¥360,000)
Keywords機能予測 / 酵素 / 機械学習 / 出芽酵母 / ピリドキサールリン酸 / 低分子結合予測
Outline of Research at the Start

研究代表者が開発したタンパク質に結合する低分子を予測する手法を、補酵素の1種であるピリドキサールリン酸と結合する酵素をモデルとしてより高精度となるように改良する。その際、構造パターン抽出に有用な深層学習を予測法に取り入れる。また、結合予測の実験的な検証を行い、その結果を予測法改良にフィードバックする。その後、他の補酵素の結合についても予測できるように拡張する。この研究成果をゲノム中に存在する機能が不明なタンパク質に適用することで、新規の酵素発見に資することが期待できる。

Outline of Final Research Achievements

We developed ProLMS-GNN, which built prediction models for binding small-molecule ligands to proteins by learning the structural features of the ligand-binding sites using a graph neural network. We also studied the experimental methods for verifying the binding of pyridoxal 5'-phosphate (PLP), an important coenzyme in organisms, to proteins and confirmed that a microbiological assay for vitamin B6 could verify the ability of PLP-binding to proteins. We comprehensively estimated the PLP-binding ability of budding yeast proteins using the prediction model built by ProLMS-GNN and verified that experimentally. As a result, at least two uncharacterized proteins were confirmed to bind PLP.

Academic Significance and Societal Importance of the Research Achievements

ゲノムにコードされるタンパク質のうちの約2割は機能の手がかりのない機能未知タンパク質である。本研究で開発したProLMS-GNNは、既存の予測法と比較して同等程度以上の精度でPLPやFADとの結合を予測できることが確認できている。また、PLPと結合することが予測された機能未知タンパク質において、実験的にPLPとの結合が確認できたことから、ProLMS-GNNをさらに多くの補酵素についても結合を予測できるよう発展させることで、機能未知タンパク質の中からそれらの補酵素と関連の深い機能を持つ新奇の酵素を見つけられる可能性が示された。

Report

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

    (13 results)

All 2022 2021 2020 2019 Other

All Journal Article (4 results) (of which Int'l Joint Research: 1 results,  Peer Reviewed: 4 results,  Open Access: 4 results) Presentation (6 results) Remarks (3 results)

  • [Journal Article] Intermolecular Interactions between a Membrane Protein and a Glycolipid Essential for Membrane Protein Integration2022

    • Author(s)
      Mori Shoko、Nomura Kaoru、Fujikawa Kohki、Osawa Tsukiho、Shionyu Masafumi、Yoda Takao、Shirai Tsuyoshi、Tsuda Shugo、Yoshizawa-Kumagaye Kumiko、Masuda Shun、Nishio Hideki、Yoshiya Taku、Suzuki Sonomi、Muramoto Maki、Nishiyama Ken-ichi、Shimamoto Keiko
    • Journal Title

      ACS Chemical Biology

      Volume: 17 Issue: 3 Pages: 609-618

    • DOI

      10.1021/acschembio.1c00882

    • Related Report
      2021 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] Current status of structure-based drug repurposing against COVID-19 by targeting SARS-CoV-2 proteins2021

    • Author(s)
      Hijikata Atsushi、Shionyu Clara、Nakae Setsu、Shionyu Masafumi、Ota Motonori、Kanaya Shigehiko、Shirai Tsuyoshi
    • Journal Title

      Biophysics and Physicobiology

      Volume: 18 Issue: 0 Pages: 226-240

    • DOI

      10.2142/biophysico.bppb-v18.025

    • NAID

      130008106407

    • ISSN
      2189-4779
    • Related Report
      2021 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] Evaluating cepharanthine analogues as natural drugs against SARS‐CoV‐22021

    • Author(s)
      Hijikata Atsushi、Shionyu‐Mitsuyama Clara、Nakae Setsu、Shionyu Masafumi、Ota Motonori、Kanaya Shigehiko、Hirokawa Takatsugu、Nakajima Shogo、Watashi Koichi、Shirai Tsuyoshi
    • Journal Title

      FEBS Open Bio

      Volume: 12 Issue: 1 Pages: 285-294

    • DOI

      10.1002/2211-5463.13337

    • Related Report
      2021 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] Curcumin Derivatives Verify the Essentiality of ROS Upregulation in Tumor Suppression2019

    • Author(s)
      Nakamae Ikuko、Morimoto Tsumoru、Shima Hiroki、Shionyu Masafumi、Fujiki Hisayo、Yoneda-Kato Noriko、Yokoyama Takashi、Kanaya Shigehiko、Kakiuchi Kiyomi、Shirai Tsuyoshi、Meiyanto Edy、Kato Jun-ya
    • Journal Title

      Molecules

      Volume: 24 Issue: 22 Pages: 4067-4067

    • DOI

      10.3390/molecules24224067

    • Related Report
      2019 Research-status Report
    • Peer Reviewed / Open Access / Int'l Joint Research
  • [Presentation] Protein-cofactor binding prediction with graph neural networks2021

    • Author(s)
      Masafumi Shionyu, Atsushi Hijikata
    • Organizer
      第59回日本生物物理学会年会
    • Related Report
      2021 Annual Research Report
  • [Presentation] グラフニューラルネットワークを用いたタンパク質の低分子リガンド結合予測2021

    • Author(s)
      塩生真史, 土方敦司
    • Organizer
      第21回日本蛋白質科学会年会
    • Related Report
      2021 Annual Research Report
  • [Presentation] Prediction of PLP-binding proteins by using machine learning-based methods2020

    • Author(s)
      Masafumi Shionyu, Tomohiro Hatta, Atsushi Hijikata
    • Organizer
      第58回日本生物物理学会年会
    • Related Report
      2020 Research-status Report
  • [Presentation] Machine learning models for predicting ligand-binding sites using residue-wise features2019

    • Author(s)
      Masafumi Shionyu, Atsushi Hijikata
    • Organizer
      第57回日本生物物理学会年会
    • Related Report
      2019 Research-status Report
  • [Presentation] A local structural environment descriptor towards evaluating impact of rare variants in humans on protein structures and functions.2019

    • Author(s)
      Atsushi Hijikata, Masafumi Shionyu, Tsuyoshi Shirai
    • Organizer
      第57回日本生物物理学会年会
    • Related Report
      2019 Research-status Report
  • [Presentation] 結合傾向値を特徴量とした機械学習による低分子リガンド結合残基予測2019

    • Author(s)
      塩生真史, 山崎まど香, 土方敦司
    • Organizer
      第19回日本蛋白質科学会年会 第71回日本細胞生物学会大会 合同年次大会
    • Related Report
      2019 Research-status Report
  • [Remarks] Het-PDB Navi.

    • URL

      https://hetpdbnavi.nagahama-i-bio.ac.jp

    • Related Report
      2021 Annual Research Report
  • [Remarks] Het-PDB Navi2

    • URL

      https://hetpdbnavi.nagahama-i-bio.ac.jp

    • Related Report
      2020 Research-status Report
  • [Remarks] Het-PDB Navi2

    • URL

      http://hetpdbnavi.nagahama-i-bio.ac.jp

    • Related Report
      2019 Research-status Report

URL: 

Published: 2019-04-18   Modified: 2023-01-30  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi