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

2023 Fiscal Year Final Research Report

Evolutionary Molecular Engineering Guided by Machine Learning: Smart Maturation Process for Cancer Therapeutic Antibodies

Research Project

  • PDF
Project/Area Number 20H00315
Research Category

Grant-in-Aid for Scientific Research (A)

Allocation TypeSingle-year Grants
Section一般
Review Section Medium-sized Section 27:Chemical engineering and related fields
Research InstitutionTohoku University

Principal Investigator

Umetsu Mitsuo  東北大学, 工学研究科, 教授 (70333846)

Co-Investigator(Kenkyū-buntansha) 亀田 倫史  国立研究開発法人産業技術総合研究所, 情報・人間工学領域, 上級主任研究員 (40415774)
齋藤 裕  国立研究開発法人産業技術総合研究所, 情報・人間工学領域, 主任研究員 (60721496)
津田 宏治  東京大学, 大学院新領域創成科学研究科, 教授 (90357517)
伊藤 智之  東北大学, 工学研究科, 助教 (40987880)
Project Period (FY) 2020-04-01 – 2024-03-31
Keywords進化分子工学 / 機械学習 / タンパク質 / 抗体
Outline of Final Research Achievements

In this study, we have developed a technology that can predict amino acid sequences with optimized multiple functions and properties by advancing evolutionary molecular engineering, which can indicate the direction of evolution from information on small variants using machine learning. We developed a process to accelerate the development of antibody drugs that can simultaneously optimize the properties of antibody by creating a predictor for camelid heavy-chain antibody variable region fragment using machine learning with the expression level, target binding, structural stability, humaneness, and other properties of about 100 variants as training data.

Free Research Field

タンパク質工学

Academic Significance and Societal Importance of the Research Achievements

バイオ医薬品などを中心に50兆円の市場規模をもつ機能タンパク質の機能と物性は反相関することが多い。特に抗体へのアミノ酸配列の改変では、標的結合性と構造安定性の反相関性は社会実装において課題なることが多い。本研究の成果は、タンパク質の複数の機能・物性を同時に最適化できる機械学習の潜在性を示すと共に、機能タンパク質の開発課題である開発時間・労力・コストの問題解決への可能性も示すことができた。

URL: 

Published: 2025-01-30  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi