PharmaIndustrial India Magazine September-October 2023

contributing to the speedup and efficiency of the drug discov - ery process for pharmaceutical companies. Details of each technology are as follows: 1. Generative AI technology that accurately estimates the vari- ous forms of protein conformation and their proportions Accurate prediction of conformational changes of a target pro- tein in a wide range requires the possible forms of the confor- mation and their accurate proportions. In this study, Fujitsu and RIKEN reconstructed a 3D density map of each conformation from a large number of projection images and the correspond- ing angles at a given moment. At the same time, the two par- ties estimated the proportion based on the frequency of the reconstructed conformation as a clue. 2. Technology for predicting conformational change based on low dimensional feature of protein conformation Since the conformation of the target protein is usually ex- pressed by high-dimensional data, it is difficult to directly pre - dict the conformational changes. However, in the process of reconstructing the conformation by the generative AI technolo- gy of the preceding paragraph, Fujitsu and RIKEN extracted a low-dimensional feature of the conformation. Using generative AI technology, Fujitsu and RIKEN analyzed the low-dimension- al data and predicted the conformational changes by restoring 3D density maps. PHARMA INDUSTRIALINDIA · SEP-OCT 23 23 TECH TALK Image: Outline of the newly developed technology Encoder and decoder are trained on images that have been taken in large enough quantities by a microscope. After train- ing, it is possible to obtain an analyzable low-dimensional dis- tribution 1) in the latent space that is equivalent to the structural distribution 2), which is difficult to analyze. At the same time, the decoder can recover various 3D density maps correspond- ing to low-dimensional features. Future Plans Moving forward, Fujitsu and RIKEN will leverage the newly de- veloped AI drug discovery technology as one of the core tech- nologies for analyzing complexes between target proteins and antibodies and for predicting structural changes in molecules with high accuracy and speed. To contribute to the realization of Society5.0 in the field of med - icine, RIKEN is promoting the construction of a drug discovery DX platform on supercomputer Fugaku, aiming to innovate the drug discovery process by using it as one of the new technolo- gies to estimate the various structural states of target proteins. RIKEN is further promoting various initiatives including TRIP aimed at creating innovative research platforms that effectively generate new fields of knowledge across research fields. Fujitsu also plans to start offering of its prediction technology for protein structural changes as an AI innovation core compo- nent module of Fujitsu Kozuchi (code name) - Fujitsu AI Plat- form. Under Fujitsu Uvance, which aims to realize a sustainable world, Fujitsu is promoting Healthy Living, which maximizes the life experience of everyone. Fujitsu will continue to contribute to solving social problems in the medical field by developing technologies that combine its strengths in AI and HPC.