| Project/Area Number |
17K20043
|
|---|
| Research Category |
Grant-in-Aid for Challenging Research (Exploratory)
|
| Allocation Type | Multi-year Fund |
|---|
| Research Field |
Environmental analyses and evaluation and related fields
|
|---|
| Research Institution | Kyoto University |
|---|
Principal Investigator |
Brown John 京都大学, 医学研究科, 講師 (90583188)
|
|---|
| Project Period (FY) |
2017-06-30 – 2019-03-31
|
| Project Status |
Completed (Fiscal Year 2018)
|
| Budget Amount *help |
¥6,500,000 (Direct Cost: ¥5,000,000、Indirect Cost: ¥1,500,000)
Fiscal Year 2018: ¥1,950,000 (Direct Cost: ¥1,500,000、Indirect Cost: ¥450,000)
Fiscal Year 2017: ¥4,550,000 (Direct Cost: ¥3,500,000、Indirect Cost: ¥1,050,000)
|
|---|
| Keywords | 核内受容体 / 化学物質 / 人工知能 / 能動的学習 / 分子設計 / 安全評価 / 可視化 / AI / 評価統計選択 / 画像化 / 相互作用 / 受容体 / 計算創薬 / 安全性 / 化審法 / ケモジェノミクス |
|---|
| Outline of Final Research Achievements |
Many side effects of drugs and inflammation reactions are the result of drugs and other chemicals interacting with multiple receptors. An ideal safety policy would be to test all chemicals against all receptors, but this is unrealistic due to expenses and limited resources. As a result, there is a societal need to apply machine learning (AI) techniques which can reduce the number of experimental validations required. In this research, we explored the challenge of developing machine learning models for protein families involved in cellular regulation, namely nuclear hormone receptors and metabolic CYP450 enzymes. Our results proved the ability to build highly predictive models for these protein families. The methods developed in the research can be used by regulatory agencies, and can contribute to reduction of risk on the human population.
|
| Academic Significance and Societal Importance of the Research Achievements |
工場などで排出される空気に複数の化学物質が含まれている。人体に対する安全性を確認するため、化学物質の分子的な作用機序を明確にする必要がある。本研究は細胞制御と代謝に関連するタンパク質に対する化学物質の結合性を予測する手法を開発でき、次世代安全対策に貢献する技術を成立できた。
また、開発した手法は、活用が期待される人工知能(AI)をどのように評価と解釈をすれば良いかという課題に大きく貢献し、学術的にも社会的にも意義がある。
|
