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

Study on machine learning approaches for heterogeneous biological data based on mixing regularization models

Research Project

Project/Area Number 17K00407
Research Category

Grant-in-Aid for Scientific Research (C)

Allocation TypeMulti-year Fund
Section一般
Research Field Life / Health / Medical informatics
Research InstitutionKyushu University

Principal Investigator

Maruyama Osamu  九州大学, 芸術工学研究院, 准教授 (20282519)

Project Period (FY) 2017-04-01 – 2021-03-31
Project Status Completed (Fiscal Year 2020)
Budget Amount *help
¥4,420,000 (Direct Cost: ¥3,400,000、Indirect Cost: ¥1,020,000)
Fiscal Year 2019: ¥1,170,000 (Direct Cost: ¥900,000、Indirect Cost: ¥270,000)
Fiscal Year 2018: ¥1,820,000 (Direct Cost: ¥1,400,000、Indirect Cost: ¥420,000)
Fiscal Year 2017: ¥1,430,000 (Direct Cost: ¥1,100,000、Indirect Cost: ¥330,000)
Keywordsモチーフ / ギブス・サンプリング / 結合部位 / E3ユビキチン / タンパク質disorder / 混合正則化 / バイオインフォマティクス / デグロン / 崩壊型ギブス・サンプリング / E3ユビキチン・ライゲース / 依存関係モデル / E3ユビキチン・ライゲース / たんぱく質disorder / モデリング / 機械学習 / マルコフ連鎖モンテカルロ法 / タンパク質複合体 / タンパク質間相互作用ネットワーク / ボルツマン分布 / ヘテロ生物データ
Outline of Final Research Achievements

For the problem of protein complex prediction and that of E3 ubiquitin ligase binding site prediction, I got successful results to some extent, by modeling target data, designing evaluation functions, and constructing optimization algorithms based on the Gibbs sampling algorithm. Particularly, for the problem of E3 ubiquitin ligase binding site prediction, I designed complicated likelihood functions, the multiple prior distributions based on biological knowledge, and collapsed Gibbs sampling algorithm for the posterior probability distribution derived from the likelihood functions and the prior probability distributions. I showed that the proposed method is superior to existing methods in prediction accuracy on our target datasets.

Academic Significance and Societal Importance of the Research Achievements

本研究では,データ・ドリブンな研究手法として,データに基づくモデリングを行い評価関数を設計するスキームを確立することが出来た.とくに,事後確率によるモデリングの柔軟性の高さとギブス・サンプリングをベースとした最適化の汎用性の組み合わせの利点を示すことが出来た.また,取り組んだ生物学的個別課題「E3ユビキチン・ライゲース結合部位予測問題」に関しては,タンパク質配列上の結合部位の予測情報は新規薬剤の設計などに応用できる可能性がある.

Report

(5 results)
  • 2020 Annual Research Report   Final Research Report ( PDF )
  • 2019 Research-status Report
  • 2018 Research-status Report
  • 2017 Research-status Report
  • Research Products

    (10 results)

All 2020 2019 2018 2017

All Journal Article (5 results) (of which Int'l Joint Research: 1 results,  Peer Reviewed: 5 results,  Open Access: 2 results) Presentation (5 results) (of which Int'l Joint Research: 1 results)

  • [Journal Article] DegSampler3: Pairwise Dependency Model in Degradation Motif Site Prediction of Substrate Protein Sequences2019

    • Author(s)
      Maruyama Osamu、Matsuzaki Fumiko
    • Journal Title

      Proceedings - 2019 IEEE 19th International Conference on Bioinformatics and Bioengineering, BIBE 2019

      Volume: NA Pages: 11-17

    • DOI

      10.1109/bibe.2019.00012

    • Related Report
      2019 Research-status Report
    • Peer Reviewed
  • [Journal Article] Determining the minimum number of protein-protein interactions required to support known protein complexes2018

    • Author(s)
      Natsu Nakajima, Morihiro Hayashida, Jesper Jansson, Osamu Maruyama, Tatsuya Akutsu
    • Journal Title

      PLOS ONE

      Volume: 13 Issue: 4 Pages: e0195545-e0195545

    • DOI

      10.1371/journal.pone.0195545

    • Related Report
      2018 Research-status Report
    • Peer Reviewed / Open Access / Int'l Joint Research
  • [Journal Article] [Regular Paper] DegSampler: Collapsed Gibbs Sampler for Detecting E3 Binding Sites2018

    • Author(s)
      Maruyama Osamu、Matsuzaki Fumiko
    • Journal Title

      Proc. of 2018 IEEE 18th International Conference on Bioinformatics and Bioengineering (BIBE)

      Volume: 1 Pages: 1-9

    • DOI

      10.1109/bibe.2018.00009

    • Related Report
      2018 Research-status Report
    • Peer Reviewed
  • [Journal Article] Two Challenging Difficulties of Protein Complex Prediction2018

    • Author(s)
      Maruyama Osamu
    • Journal Title

      Agriculture as a Metaphor for Creativity in All Human Endeavors. FMfI 2016. Mathematics for Industry

      Volume: 28 Pages: 139-145

    • DOI

      10.1007/978-981-10-7811-8_14

    • ISBN
      9789811078101, 9789811078118
    • Related Report
      2017 Research-status Report
    • Peer Reviewed
  • [Journal Article] RocSampler: regularizing overlapping protein complexes in protein-protein interaction networks2017

    • Author(s)
      Maruyama Osamu、Kuwahara Yuki
    • Journal Title

      BMC Bioinformatics

      Volume: 18 Issue: S15 Pages: 491-491

    • DOI

      10.1186/s12859-017-1920-5

    • Related Report
      2017 Research-status Report
    • Peer Reviewed / Open Access
  • [Presentation] Predicting Discriminative Motifs for DNA Methylation in Mammalian Development2020

    • Author(s)
      Ryo Shimizu, Wan Kin Au Yeung, Hidehiro Toh, Hiroyuki Sasaki and Osamu Maruyama
    • Organizer
      2020年日本バイオインフォマティクス学会年会 第9回生命医薬情報学連合大会IIBMP2020
    • Related Report
      2020 Annual Research Report
  • [Presentation] DegSampler3: Pairwise dependency model in degradation motif site prediction of substrate protein sequences2019

    • Author(s)
      Osamu Maruyama
    • Organizer
      2019 IEEE 19th International Conference on Bioinformatics and Bioengineering, BIBE 2019
    • Related Report
      2019 Research-status Report
    • Int'l Joint Research
  • [Presentation] E3結合部位予測のための崩壊型ギブス・サンプラーDegSampler2019

    • Author(s)
      丸山 修
    • Organizer
      分子生物情報研究会 (SIG-MBI)
    • Related Report
      2018 Research-status Report
  • [Presentation] 正負例配列集合のためのコンセンサス・モチーフによるクラスタリング・アルゴリズム2017

    • Author(s)
      丸山 修
    • Organizer
      日本バイオインフォマティクス学会(JSBi)九州地域部会セミナー宮崎開催
    • Related Report
      2017 Research-status Report
  • [Presentation] Regularizing protein complexes by mutually exclusive protein-protein interactions2017

    • Author(s)
      丸山 修
    • Organizer
      第6回生命医薬情報学連合大会(IIBMP 2017)
    • Related Report
      2017 Research-status Report

URL: 

Published: 2017-04-28   Modified: 2022-01-27  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi