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

2022 Fiscal Year Final Research Report

Constructing a Fusion Framework of AI, Simulation, and Evolutionary Analysis in Bitter Taste Receptor

Research Project

  • PDF
Project/Area Number 20K12063
Research Category

Grant-in-Aid for Scientific Research (C)

Allocation TypeMulti-year Fund
Section一般
Review Section Basic Section 62010:Life, health and medical informatics-related
Research InstitutionKyoto University

Principal Investigator

Iwata Hiroaki  京都大学, 医学研究科, 特定准教授 (40613328)

Project Period (FY) 2020-04-01 – 2023-03-31
Keywords人工知能 / シミュレーション / 進化 / 苦味 / ディープラーニング / 分子動力学シミュレーション
Outline of Final Research Achievements

In situations where data is scarce, there have been widespread efforts to construct AI models while generating training data. We propose a semi-supervised learning framework based on self-training. First, known data is used for training to construct an AI model. Next, pseudo-labels are predicted for unknown compound-protein interaction information, thereby increasing the training data and improving the model parameters. As a result, the imbalance between positive and negative samples in the training data gradually diminishes, and furthermore, the final constructed model has been shown to surpass the original model constructed solely using the known training dataset.

Free Research Field

ケモインフォマティクス

Academic Significance and Societal Importance of the Research Achievements

様々な分野にAI技術が適用されてきており、成果が上がってきている。一方で、データが整備されていないことも多く、少量な学習データでよいモデルを作ることは学術的にも社会的にも求められている。本研究では、学習データを生成することで予測精度を高めることができた。今回は、化合物-タンパク質相互作用解析で手法の有用性を示したが、様々な分野で適用が可能である。学術的、社会的意義のある結果が得られた。

URL: 

Published: 2024-01-30  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi