Discovery of a lead compound for a therapeutic drug against COVID-19 Kyoto Pharmaceutical University
A methodology for drug designs using the latest AI technology was developed through joint research with Preferred Networks, Inc.
September 6, 2021- The research group lead by Professor Kenichi Akaji, Kyoto Pharmaceutical University, in collaboration with Preferred Networks, Inc. (PFN), developed a methodology for drug design using the latest artificial intelligence (AI) technology, and discovered a lead compound for a therapeutic drug against coronavirus disease 2019 (COVID-19).
This technique is not restricted to the development of a therapeutic drug against COVID-19, and can be applied to accelerate the development of any kind of drug.
Basic research to develop a therapeutic drug against severe acute respiratory syndrome (SARS), which is one of the emerging infectious diseases, has been continuously ongoing at Kyoto Pharmaceutical University. Till date, there have been reports of the successful synthesis of both peptide and non-peptide cyclic compounds that are capable of inhibiting an enzymatic function required for the propagation of SARS-CoV-2, the virus causing SARS. Combining this basic research with AI technology for drug development developed by PFN, based on deep learning, has created a promising lead compound for inhibiting the main protease that is essential for the propagation of SARS-CoV-2.
Example of a pharmaceutical agent (in yellow) binding to the main protease
of SARS-CoV-2 (in purple) to inhibit viral replication
Note: To protect intellectual properties, the agent shown in the figure above represents
a different compound from what PFN and KPU discovered in the joint research.
This research collaboration that brings together the results from the research conducted at Kyoto Pharmaceutical University and the use of AI in drug development, has produced a lead compound with a novel structure in record time. This shows that the results from basic research conducted at a university has the scope of becoming a “hit” for drug design using AI. It also shows that, a compound designed by a computer can be used for evaluation of its drug rationality.
In the present study, 13 compounds were produced from the calculations using the AI drug development strategy by PFN and its private supercomputer, MN-2. These compounds were then synthesized at Kyoto Pharmaceutical University. Out of these 13 compounds, it was found that 7 compounds exhibited an inhibitory effect on the activity of the main protease for SARS-CoV-2. This clearly shows that bringing together results from effective basic research and the latest AI drug development technology is a promising strategy for drug development.
At Kyoto Pharmaceutical University, research on drug development will continue to contribute to the field and research collaborations will be accelerated for finding applications for such research.
■About Kyoto Pharmaceutical University
Kyoto Pharmaceutical University is one of the oldest educational institutions in Japan, with a 137-year-long history. The university trains its students to become “pharmacist scientists”, with strong research skills. More than 22,000 graduates are pursuing their careers in the pharmaceutical industry, hospitals, pharmacies, universities, and government agencies. Kyoto Pharmaceutical University will continuously strive to produce graduates who can contribute to society even beyond the discipline of pharmacy.
Kyoto Pharmaceutical University
Office for Planning & Public Relations