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

2020 Fiscal Year Final Research Report

Study on statistical methods to integrate high-dimensional and heterogenous biomedical data for predicting and controlling disease progression

Research Project

  • PDF
Project/Area Number 18H03329
Research Category

Grant-in-Aid for Scientific Research (B)

Allocation TypeSingle-year Grants
Section一般
Review Section Basic Section 62010:Life, health and medical informatics-related
Research InstitutionAichi Cancer Center Research Institute (2019-2020)
The University of Tokyo (2018)

Principal Investigator

Yamaguchi Rui  愛知県がんセンター(研究所), システム解析学分野, 分野長 (90380675)

Co-Investigator(Kenkyū-buntansha) 横山 和明  東京大学, 医科学研究所, 助教 (00647498)
Project Period (FY) 2018-04-01 – 2021-03-31
Keywords病態予測 / 情報統合 / 異種多次元データ
Outline of Final Research Achievements

In this research project, we studied computational methodologies to extract useful information from heterogeneous and multi-dimensional biomedical data from each patient in order to predict and control disease progression. We proposed a new method to integrate Bayes Factors from multiple models. Using that, we can build an accurate somatic mutation caller for multiple samples within a single patient. We also devised an explainable AI to extract useful information from the complex biomedical data such as networks. In addition, we monitored circulating tumor DNAs (ctDNAs) to identify minimal residual diseases (MRDs) for blood cancer patients. We showed ctDNA is useful for predicting disease progression of blood cancers. We are continuing to make a method combining ctDNA and other biomedical data for more accurate prediction of disease progression.

Free Research Field

メディカルバイオインフォマティクス

Academic Significance and Societal Importance of the Research Achievements

技術の進展により、患者一人ひとりから多種多様な生体データの情報が得られるようになりつつある。本研究では、それらの異種かつ多要素の膨大なデータを統合的に活用し、個人ごとに異なる病態の経過を、予測しかつ制御するための情報を抽出する数理的方法論を構築することを目標とした。その結果、新たな情報統合および情報抽出のための手法を複数開発した。また実際の臨床データの計測と解析から腫瘍由来循環DNAが血液がんの病態の進展の予測に有用である知見も得た。これらの知見は、今後の更なる精緻な病態遷移予測モデルの開発につながることが期待される。

URL: 

Published: 2022-01-27  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi