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

2021 Fiscal Year Final Research Report

Optimization for usage of molecular targeted drugs on cancer therapy

Research Project

  • PDF
Project/Area Number 18H04162
Research Category

Grant-in-Aid for Scientific Research (A)

Allocation TypeSingle-year Grants
Section一般
Review Section Medium-sized Section 90:Biomedical engineering and related fields
Research InstitutionThe University of Tokyo

Principal Investigator

Suzuki Hiroshi  東京大学, 医学部附属病院, 教授 (80206523)

Co-Investigator(Kenkyū-buntansha) 本間 雅  東京大学, 医学部附属病院, 講師 (60401072)
苅谷 嘉顕  東京大学, 医学部附属病院, 助教 (20633168)
池淵 祐樹  東京大学, 医学部附属病院, 助教 (20645725)
Project Period (FY) 2018-04-01 – 2022-03-31
Keywords細胞毒性 / 機械学習 / システム薬理学 / 抗がん剤
Outline of Final Research Achievements

In this study, we constructed a machine learning model in which cell survival curves under anti-cancer drugs exposures can be calculated from molecular information in cells by utilizing large-scale public database. The quantitative accuracy of this model is, however, limited since we experimentally observed that the cellular sensitivity was varied by experimental environments. Therefore, a future challenge for this study is to construct a model in which environmental difference can be calibrated. Although there remains such a challenge, we confirmed that our current model could provide qualitative factors related to cellular sensitivity. Thus, our constructed model in this study can be used as a base model to reasonably select anti-cancer drugs by using molecular information about cancer cells.

Free Research Field

システム薬理学

Academic Significance and Societal Importance of the Research Achievements

抗がん剤治療の最適化に関して様々な取り組みが行われているものの、十分な治療効果が得られる割合は必ずしも高くなく、種々の副作用出現により治療を断念せざるを得ない場合も少なくない。本研究では細胞の薬物感受性を予測するモデル構築により、適切な薬物選択を可能とする基盤構築を目指した。モデルの定量的信頼度向上の取り組みは今後の課題であるが、薬剤選択に関連する定性的因子を抽出可能なモデルの構築に成功した。がん細胞および正常細胞への感受性予測を併せることで、薬理効果および一部の副作用発現リスクも考慮した合理的な薬剤選択に寄与しうる研究成果である。

URL: 

Published: 2023-01-30  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi