With the intention of developing algorithms that use AI for predicting
compound activity, generating compound structures and conducting
Tokyo, Japan [September 1, 2020]
Elix, Inc. (CEO: Shinya Yuki / headquarters in Chiyoda-ku, Tokyo, hereafter as “Elix”) is a research-oriented technology company specializing in deep learning and machine learning. In July 2020, Elix initiated a collaboration with Astellas Pharma Inc. (headquarters in Chuo-ku, Tokyo, hereafter as “Astellas Pharma”) with the objective of developing algorithms that use artificial intelligence (AI) for predicting compound activity, generating compound structures, and conducting retrosynthetic analysis. Elix entered the AI drug discovery field in October 2019 after participating in Blockbuster Tokyo, an acceleration program for pharmaceutical and medical startups.
This collaborative research aims to use AI for predicting the pharmacological activity and properties of compounds (e.g., absorption, distribution, metabolism, and excretion; physical properties; and toxicity), generating compound structures and conducting retrosynthetic analysis.
Recently there has been an increased attention on AI drug discovery, due to its great potential to shorten the long drug discovery timeline, as well as its ability to propose compounds that chemists struggle to devise. While this attention has led to significant improvement in property prediction and compound structure generation, research regarding the retrosynthesis of compounds has to be adequately considered.
While this collaborative research also aims to further improve AI-assisted prediction of properties and compounds structure generation, its core mission will be to drive forward AI-assisted retrosynthetic analysis. This will not only enable AI to generate compounds, but ensure those compounds are significantly easier to synthesize.
Beyond the vital research taken to improve AI-assisted retrosynthetic analysis, this project is strongly aimed at bridging the gap between research and industry. With the assistance of Astellas Pharma’s strong expertise in drug discovery and their drug discovery data accumulated over many years, AI models developed by Elix will have the opportunity to be rigorously assessed for real world validity.
Through this project, Elix and Astellas Pharma will continue their dedication in contributing to the health of people worldwide through improvements in AI drug discovery.
Comments from Elix CEO Shinya Yuki regarding the project
We believe that AI drug discovery is a promising technology for improving efficiency in the drug discovery process and for the search for new chemical compounds. We hope that the collaborative research conducted by Astellas Pharma and Elix will combine our respective strengths and lead to impactful results for society.
About Astellas Pharma, Inc.
Astellas Pharma, Inc. is a pharmaceutical company conducting business in more than 70 countries around the world. We are promoting the Focus Area Approach that is designed to identify opportunities for the continuous creation of new drugs to address diseases with high unmet medical needs by focusing on Biology and Modality. Furthermore, we are also looking beyond our foundational Rx focus to create Rx+® healthcare solutions combine our expertise and knowledge with cutting-edge technology in different fields of external partners. Through these efforts, Astellas Pharma stands on the forefront of healthcare change to turn innovative science into value for patients. For more information, please visit our website at
About Elix, Inc.
Elix, Inc. is a research-oriented technology company specialized in deep learning and machine learning with a focus on AI Drug Discovery / Materials Informatics and Computer Vision. Currently the company offers full assistance, from consulting, model-development and model-licensing to their clients. We are also engaged in research on treatments for COVID-19.
Company name: Elix, Inc.
Head Office: Daini Togo Park Building 3F, 8-34 Yonbancho, Chiyoda-ku, Tokyo 102-0081 Japan
CEO: Shinya Yuki
Established: November 4, 2016