Drug candidate discovery by development of a context-sensitive target network similarity metric

2016 Fiscal Year Final Research Report

• Project/Area Number: 25870336
• Research Category: Grant-in-Aid for Young Scientists (B)
• Allocation Type: Multi-year Fund
• Research Field: Life / Health / Medical informatics; System genome science
• Research Institution: Kyoto University
• Principal Investigator: Brown John 京都大学, 医学研究科, 講師 (90583188)
• Research Collaborator: SCHNEIDER Gisbert ETH Zurich ; REKER Daniel Massachusetts Institute of Technology
• Project Period (FY): 2013-04-01 – 2017-03-31
• Keywords: chemogenomics / comput. drug discovery / pattern recognition / life science informatics / ケモジェノミクス / 計算創薬 / 統計パターン認識 / 生命情報科学

Outline of Final Research Achievements

In this project, we executed research for computational drug discovery. The fundamental principle of most drugs is that a compound works to inhibit the function of a particular protein. To know in advance which compounds will inhibit which proteins is difficult, but in recent years computational methods have become developed which are expected to bring down drug development costs.
In this research we developed a new method for the prediction of compound-protein interactions. Among its many features, ours is special in that it requires neither big data nor complex artificial intelligence (AI), yet can still build a highly predictive model. We disproved the current trend of "big data drug discovery" by developing a reproducible method and reported multiple scientific papers. We are planning with pharmaceutical companies to apply the technology to joint research projects.

Free Research Field

計算創薬