アブストラクト
| Date | 15:00-16:00 Jan 09, 2024 |
| Speaker | Yayoi Natsume-Kitatani Leader of the Bioinformatics group, AI Center for Health and Biomedical Research, National Institutes of Biomedical Innovation, Health and Nutrition |
| Title | Hurdles in Drug Discovery and Expected Role of AI/ML: Drug Target Discovery and Prediction of Activity/Safety of Candidate Substances |
| Abstract |
In the field of drug discovery, although only promising candidates
advance to clinical trials after a multifaceted evaluation process,
the failure rate in clinical trials is still not low. In particular,
the rate of failure in Phase II clinical trials in which efficacy in
humans is not confirmed is as high as approximately 70%. This means
that the efficacy confirmed in experimental animals was not confirmed
in humans, and that there is a limit to the search for drug targets
using experimental animals. Against this background, the "Development
of Artificial Intelligence to Accelerate New Drug Development" project
aims to answer the question, "is it possible to search for drug
targets based on human information from the initial stage of new drug
development?” In this presentation, I will introduce the achievements
of the project to date and the possibility of a new approach to
present drug target candidates in a data-driven manner.
On another note, high standards of both efficacy and safety are required in the development of vaccines to be administered to healthy humans. However, since these are trade-offs, there is a need for efficient development of adjuvants that can be added to vaccines to enhance efficacy. For a long time, adjuvant development has been found through trial and error, relying on the experience of researchers. However, naturally, the adjuvant itself must be highly safe, and further evidence is needed to demonstrate the efficacy and safety of the adjuvant itself as well as the vaccine in order to prove the effect brought about by its addition. Against this background, a new trend has emerged that aims to achieve efficient and highly accurate adjuvant development based on evidence-based and data-driven approaches. To realize this, the "Next Generation Adjuvant Research Group" was established in 2010, and the "Adjuvant Database Project" was launched in 2012. Furthermore, from 2017, the AMED "Development of Effective and Safe Next-Generation Adjuvants Backed by Innovative Technology" included research aimed at establishing a system to evaluate the efficacy and safety of adjuvants. I will introduce a data-driven approach to next-generation adjuvant development that utilizes the adjuvant database established through these projects.
|