医療従事者の為の最新医療ニュースや様々な情報・ツールを提供する医療総合サイト

TOKYO

Elix, Inc., an AI drug discovery company with the mission of “Rethinking Drug Discovery” (CEO: Shinya Yuki/Headquarters: Tokyo; hereafter referred to as “Elix”) commenced joint research on the retrosynthetic analysis module “Elix Synthesize™” with Shionogi & Co., Ltd (President and CEO: Isao Teshirogi/Headquarters: Osaka, Japan; hereinafter referred to as “Shionogi”) for the purpose of verifying retrosynthetic analysis using chemical reaction data from Shionogi.

In the Pharmaceutical industry, artificial intelligence (AI) is being used for activity and property prediction as well as molecular design with desired properties. Moreover, there is an increased attention being given to the purpose of utilizing AI for retrosynthetic analysis. Currently, individual scientists study and design synthetic pathways to be lead; however, this process depends on their knowledge and experience, and it requires time to determine the feasibility of the synthesis and to study synthetic pathways. Given the difficulty in designing these pathways, a retrosynthetic analysis model would provide tremendous benefit in exploring various synthetic routes and reducing development times.

Despite its potential, there have been few projects developing retrosynthetic analysis models, with one fundamental reason being the models’ added complexity compared to more simplistic predictive models. The lack of high quality, abundant datasets, as well as the models processing speed, appears to also hamper any attempts at producing a level of accuracy desirable for the drug discovery industry. Improvements will need to be made before we see these models more widely adopted in industry.

Elix Synthesize™ features peerless high-speed processing using parallel computation and it can efficiently explore various synthetic routes by processing large amounts of data at high speed. It can propose a more optimized synthetic route, considering multiple factors, such as yield*, cost, and available reagents. In addition to the aforementioned variables, Elix Synthesize™ is highly customizable, making it possible to consider custom variables that are inline with the client’s objectives when proposing a route.

In this joint research, Elix Synthesize™ will be customized to match Shionogi’s proprietary data to validate a highly accurate, high-speed, practical retrosynthetic analysis model for drug discovery research.

Shinya Yuki, CEO of Elix, Inc. said: “In recent years, we have seen numerous examples of molecular design using AI, but those models have not been able to take into account the synthesizability. This is why retrosynthetic analysis models have been attracting attention. In reality, however, they are yet to see commercialization due to two major limitations: (1) the complexity of the algorithms and (2) the lack of data sets. We look forward to collaborating with Shionogi by leveraging our different strengths; Elix’s knowledge of algorithms and Shionogi’s data set and understanding of the field’s needs”.

*Yield: The ratio of the target molecule obtained in a chemical reaction to the amount of the target molecule that can be theoretically generated from the raw materials.

About Elix, Inc.

Elix, Inc. is an AI drug discovery company with the mission of “Rethinking drug discovery”. To significantly improve the time-consuming and expensive drug discovery process, we have applied cutting-edge deep learning and machine learning technologies to develop business for a variety of clients. These include pharmaceutical companies, chemical companies, and universities. Visit https://www.elix-inc.com/ for more details.

View source version on businesswire.com: https://www.businesswire.com/news/home/20220322006211/en/