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

Development and Implementation of Small-Scale, High-Efficiency Genomic Selection Method Using Reinforcement Learning-Based "Lookahead"

Research Project

Project/Area Number 23K23572
Project/Area Number (Other) 22H02306 (2022-2023)
Research Category

Grant-in-Aid for Scientific Research (B)

Allocation TypeMulti-year Fund (2024)
Single-year Grants (2022-2023)
Section一般
Review Section Basic Section 39010:Science in plant genetics and breeding-related
Research InstitutionThe University of Tokyo

Principal Investigator

Iwata Hiroyoshi  東京大学, 大学院農学生命科学研究科(農学部), 教授 (00355489)

Co-Investigator(Kenkyū-buntansha) 加賀 秋人  国立研究開発法人農業・食品産業技術総合研究機構, 作物研究部門, 主席研究員 (30391551)
辻本 壽  鳥取大学, 国際乾燥地研究教育機構, 特任教授 (50183075)
Project Period (FY) 2024-04-01 – 2025-03-31
Project Status Completed (Fiscal Year 2024)
Budget Amount *help
¥17,420,000 (Direct Cost: ¥13,400,000、Indirect Cost: ¥4,020,000)
Fiscal Year 2024: ¥5,720,000 (Direct Cost: ¥4,400,000、Indirect Cost: ¥1,320,000)
Fiscal Year 2023: ¥5,590,000 (Direct Cost: ¥4,300,000、Indirect Cost: ¥1,290,000)
Fiscal Year 2022: ¥6,110,000 (Direct Cost: ¥4,700,000、Indirect Cost: ¥1,410,000)
Keywordsゲノミック選抜 / 交配組合せ最適化 / 育種計画最適化 / 動的計画法 / ベイズ最適化 / 育種計画 / 強化学習 / 最適化 / 交配・育種計画最適化
Outline of Research at the Start

従来の表現型選抜では、表現型の望ましい個体や系統を選抜して交雑するため、表現型が秀でていない個体・系統がもつ有用対立遺伝子が選抜の過程で失われてしまう。ゲノミック選抜(GS)も、基本的には同じ問題を抱えている。本問題を解決するには、GSの予測モデルに基づき有用なゲノム領域が集積されるように選抜・交雑を繰り返すことが考えられるが、そのためには数世代先の状態の「先読み」に基づく選抜・交配が必要となる。本研究では、先読みを行いながら、有用なゲノム領域が集団から失われないように集積していく育種システムを開発する。

Outline of Final Research Achievements

This study aimed to implement and accelerate genomic selection (GS) in small-scale breeding programs by developing a method to design crosses that “anticipate” the genetic gain of future generations. The method was validated through both simulations and real populations. Crosses were optimized to maximize the genetic gain in the final generation using stochastic tree search and integer programming. Breeding populations derived from recombinant inbred lines of soybean were used to design a crossing strategy that jointly considers expected breeding values and progeny variance. The prediction accuracy and genetic improvement were evaluated through an outdoor drought trial conducted at Tottori University. Furthermore, phenotypic data obtained from different environments revealed shared structures of drought response and demonstrated the predictability of these responses using genomic information. In addition, trait estimation methods utilizing UAVs and deep learning were also developed.

Academic Significance and Societal Importance of the Research Achievements

本研究は、情報科学的手法による選抜と交配の同時最適化を通じて、次世代育種戦略に向けた新たな理論・技術基盤を提供した。将来世代の遺伝的獲得量を「先読み」するため、遺伝的分離を予測し、それを最大化する数理最適化に基づく交配設計手法を開発し、実集団とシミュレーションで有効性を検証した点は、GS実装に向けた重要な前進である。さらに、正準相関分析により干ばつ応答に共通する表現型構造とそのゲノム予測可能性を明らかにし、UAVと深層学習による新たな表現型情報取得手法も開発した。これらの成果は、小規模育種にも適用可能な技術として、気候変動下の作物安定生産と持続可能な農業の実現に資する社会的意義を有する。

Report

(4 results)
  • 2024 Annual Research Report   Final Research Report ( PDF )
  • 2023 Annual Research Report
  • 2022 Annual Research Report
  • Research Products

    (20 results)

All 2025 2024 2023 2022 Other

All Int'l Joint Research (3 results) Journal Article (7 results) (of which Int'l Joint Research: 1 results,  Peer Reviewed: 5 results,  Open Access: 4 results) Presentation (10 results) (of which Int'l Joint Research: 3 results,  Invited: 4 results)

  • [Int'l Joint Research] INRAE/Paris-Saclay University(フランス)

    • Related Report
      2024 Annual Research Report
  • [Int'l Joint Research] INRAE/Paris-Saclay University(フランス)

    • Related Report
      2023 Annual Research Report
  • [Int'l Joint Research] INRAE/Paris-Saclay University(フランス)

    • Related Report
      2022 Annual Research Report
  • [Journal Article] High-Throughput Phenotyping of Soybean Biomass: Conventional Trait Estimation and Novel Latent Feature Extraction Using UAV Remote Sensing and Deep Learning Models2024

    • Author(s)
      Okada Mashiro、Barras Cl?ment、Toda Yusuke、Hamazaki Kosuke、Ohmori Yoshihiro、Yamasaki Yuji、Takahashi Hirokazu、Takanashi Hideki、Tsuda Mai、Hirai Masami Yokota、Tsujimoto Hisashi、Kaga Akito、Nakazono Mikio、Fujiwara Toru、Iwata Hiroyoshi
    • Journal Title

      Plant Phenomics

      Volume: 6 Pages: 0244-0244

    • DOI

      10.34133/plantphenomics.0244

    • Related Report
      2024 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] Modeling soybean growth: A mixed model approach2024

    • Author(s)
      Delattre Maud、Toda Yusuke、Tressou Jessica、Iwata Hiroyoshi
    • Journal Title

      PLOS Computational Biology

      Volume: 20 Issue: 7 Pages: e1011258-e1011258

    • DOI

      10.1371/journal.pcbi.1011258

    • Related Report
      2024 Annual Research Report
    • Int'l Joint Research
  • [Journal Article] Cross potential selection: a proposal for optimizing crossing combinations in recurrent selection using the usefulness criterion of future inbred lines2024

    • Author(s)
      Sakurai Kengo、Hamazaki Kosuke、Inamori Minoru、Kaga Akito、Iwata Hiroyoshi
    • Journal Title

      G3: Genes, Genomes, Genetics

      Volume: 14 Issue: 11

    • DOI

      10.1093/g3journal/jkae224

    • Related Report
      2024 Annual Research Report
  • [Journal Article] Reaction norm for genomic prediction of plant growth: modeling drought stress response in soybean2024

    • Author(s)
      Toda, Y., Sasaki, G., Ohmori, Y. et al.
    • Journal Title

      Theretical and Applied Genetics

      Volume: 137 Issue: 4 Pages: 77-77

    • DOI

      10.1007/s00122-024-04565-5

    • Related Report
      2023 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] AI-assisted selection of mating pairs through simulation-based optimized progeny allocation strategies in plant breeding2024

    • Author(s)
      Hamazaki K, Iwata H
    • Journal Title

      Frontiers in Plant Science

      Volume: 15 Pages: 1361894-1361894

    • DOI

      10.3389/fpls.2024.1361894

    • Related Report
      2023 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] Bayesian optimisation for breeding schemes2023

    • Author(s)
      Diot Julien、Iwata Hiroyoshi
    • Journal Title

      Frontiers in Plant Science

      Volume: 13 Pages: 1050198-1050198

    • DOI

      10.3389/fpls.2022.1050198

    • Related Report
      2022 Annual Research Report
    • Peer Reviewed
  • [Journal Article] Time‐series multispectral imaging in soybean for improving biomass and genomic prediction accuracy2022

    • Author(s)
      Sakurai Kengo、Toda Yusuke、Kajiya‐Kanegae Hiromi、Ohmori Yoshihiro、Yamasaki Yuji、Takahashi Hirokazu、Takanashi Hideki、Tsuda Mai、Tsujimoto Hisashi、Kaga Akito、Nakazono Mikio、Fujiwara Toru、Iwata Hiroyoshi
    • Journal Title

      The Plant Genome

      Volume: 15 Issue: 4

    • DOI

      10.1002/tpg2.20244

    • Related Report
      2022 Annual Research Report
    • Peer Reviewed / Open Access
  • [Presentation] ダイズ RILs および交配後代集団を用いた地上部表現型の分離予測精度の検証2025

    • Author(s)
      櫻井 建吾, 戸田 悠介, 辻本 壽, 加賀 秋人, 岩田 洋佳
    • Organizer
      日本育種学会第147回講演会
    • Related Report
      2024 Annual Research Report
  • [Presentation] 気候変動に応えるデータ駆動型育種:品種改良の新たな可能性2025

    • Author(s)
      岩田洋佳
    • Organizer
      公益財団法人農学会 公開シンポジウム「気候変動下の食料生産の確保に向けた研究最前線」
    • Related Report
      2024 Annual Research Report
    • Invited
  • [Presentation] ベイズ最適化様 Random Forest: イネの遺伝子型と環境の最適組合せの探索2025

    • Author(s)
      望月 秀斗, 濱崎 甲資, 佐藤 睦志, 阿部 陽, 金 天海, 下野 裕之, 岩田 洋佳
    • Organizer
      日本育種学会第147回講演会
    • Related Report
      2024 Annual Research Report
  • [Presentation] 期待される近交系の能力分布をもとに複数形質を考慮した交配戦略2024

    • Author(s)
      櫻井 建吾, Moreau Laurence, MaryHuard Tristan, 岩田 洋佳
    • Organizer
      日本育種学会第146回講演会
    • Related Report
      2024 Annual Research Report
  • [Presentation] 「育種の民主化を目指して:匠の技から合理的な技術 へ」 Democratizing Breeding: From Artisanal Skills to Rational Technologies2024

    • Author(s)
      岩田 洋佳, 本多 潔
    • Organizer
      日本育種学会第146回講演会
    • Related Report
      2024 Annual Research Report
    • Invited
  • [Presentation] 非線形成長モデルに基づくUAVリモートセンシングデータと手計測データの融合2023

    • Author(s)
      福本勇太、Chen T, 戸田悠介、大森良弘、山崎裕司、高橋宏和、高梨秀樹、津田麻衣、平井優美、辻本壽、加賀秋人、中園幹生、藤原徹、岩田洋佳
    • Organizer
      日本育種学会第144回講演会
    • Related Report
      2023 Annual Research Report
  • [Presentation] データ駆動型で育種を最適化する2023

    • Author(s)
      岩田洋佳
    • Organizer
      令和5年度野菜花き課題別研究会「野菜の品種開発・生産におけるAI・データ活用の現状と展望」
    • Related Report
      2023 Annual Research Report
    • Invited
  • [Presentation] Bayesian optimization of genotype and environment interaction2023

    • Author(s)
      Iwata H, Chen T, Sato C, Yamasaki M, Kim CH, Abe A, Shimono H
    • Organizer
      6th International Conference on Econometrics and Statistics (EcoSta 2023)
    • Related Report
      2023 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Growth model-based fusion of satellite and drone remote sensing data2023

    • Author(s)
      Chen T, Okada M, Fukumoto Y, Fukumoto S, Okada M, Guo W, Iwata H
    • Organizer
      5th International Workshop on Machine Learning for Cyber-Agricultural System (MLCAS2023)
    • Related Report
      2023 Annual Research Report
    • Int'l Joint Research / Invited
  • [Presentation] Data-Driven Breeding Accelerates Improvements in Genetic Ability of Crop Plants2023

    • Author(s)
      Hiroyoshi Iwata
    • Organizer
      International Symposium on Data Driven Breeding
    • Related Report
      2022 Annual Research Report
    • Int'l Joint Research

URL: 

Published: 2022-04-19   Modified: 2026-01-16  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi