Abstract
Recently, in antibody drug discovery, AI and simulation have become essential for improving the efficiency of protein engineering, designing lead antibodies, and assessing and improving developability and immunogenicity. This presentation will provide an overview of these applications, incorporating our recent research to outline the current landscape, challenges, and future perspectives. This includes developing a methodology to assess "human-likeness" of antibody structures from two-dimensional images using a Variational Autoencoder as an anomaly detection problem, suggesting the potential to assess protein stability through ultra-short molecular dynamics simulations, and examples where point mutations have successfully stabilized proteins based on changes in free energy due to amino acid mutations.
Short BioDr. Shirai led the Bioinformatics Group at Astellas Pharma Inc., where he achieved notable results at the global antibody structure prediction competition (AMAII; Los Angeles) and spearheaded international industry-academic collaboration on antibody informatics under the EBI industry programme based in the UK. He has served as the Vice Representative for Japan with the Asia Pacific Protein Association, as Vice President of the Protein Science Society of Japan, and Visiting Professor at the University of Tsukuba.
Dr. Shirai has also contributed to committees responsible for the development of the supercomputer "Fugaku." Currently, he serves as a Coordinator at the RIKEN Center for Computational Science, where he is responsible for promoting the use of high-performance computing in life sciences and actively working to develop a platform for antibody drug discovery by leveraging RIKEN's comprehensive capabilities.