Chemical structure mining for adverse reactions and early stage signal detection

2016 Fiscal Year Final Research Report

• Project/Area Number: 24240025
• Research Category: Grant-in-Aid for Scientific Research (A)
• Allocation Type: Single-year Grants
• Section: 一般
• Research Field: Intelligent informatics
• Research Institution: Kwansei Gakuin University
• Principal Investigator: Okada Takashi 関西学院大学, 理工学部, 理工学部研究員 (00103135)
• Co-Investigator(Kenkyū-buntansha): 猪口 明博 関西学院大学, 理工学部, 准教授 (70452456) ; 鷲尾 隆 大阪大学, 産業科学研究所, 教授 (00192815)
• Project Period (FY): 2012-04-01 – 2016-03-31
• Keywords: 医薬品副作用 / データマイニング / ATCコード / 分類樹説明変数 / 構造アラート

Outline of Final Research Achievements

Effective components of drugs are accumulated in PharmCompo database. Each entry in the database has ATC codes. A new algorithm has been proposed to detect classification nodes and component nodes characteristically related to an adverse reaction by drugs. We have applied this algorithm to adverse event reports in JADER using anaphylaxis and other 6 reactions. Drug classifications and component drugs were detected causing frequent reactions. Browsing the structures of these drugs led to several substructures, and the succeeding structure refinement process enabled the proposal of structural alerts to these adverse reactions.

Free Research Field

データマイニング