Selective exploration of anti-inflammatory substances using chemical big data

2020 Fiscal Year Final Research Report

• Project/Area Number: 19K23813
• Research Category: Grant-in-Aid for Research Activity Start-up
• Allocation Type: Multi-year Fund
• Review Section: 0801:Pharmaceutical sciences and related fields
• Research Institution: Ritsumeikan University
• Principal Investigator: Ogawa Keiko 立命館大学, 薬学部, 助教 (20844278)
• Project Period (FY): 2019-08-30 – 2021-03-31
• Keywords: 活性予測 / トリテルペン / 機械学習 / 天然物化学 / ケモインフォマティクス / 生物活性 / ビッグデータ

Outline of Final Research Achievements

The purpose of this study is to develop a new approach to identify the active compounds from the data in previous studies by using information processing technology.
As a result of this research, we constructed a prediction model that discriminates the active or inactive of triterpenes by using machine learning methods. In addition, the activity assay of triterpenes were measured and several active compounds were found . The results of the activity tests were compared with the prediction results, and it was verified that the accuracy of the predictive model was approximately 80%.

Free Research Field

天然物化学、データサイエンス

Academic Significance and Societal Importance of the Research Achievements

本研究により、高い判別能を持つ抗HSV-1活性予測モデルの構築ができた。この予測モデルは種々のトリテルペン及びその配糖体についても適用が可能である。本予測モデルを用いることによって、抗HSV-1活性を持つトリテルペンを事前に想定して成分探索研究や構造誘導化を行うことができ、より効率的な活性物質開拓に繋げられることが期待される。