Elsevier, a global research publishing and information analytics provider, is collaborating with Pending.AI (PAI), a start-up focused on developing artificial intelligence (AI) solutions for drug discovery, to develop the predictive retrosynthesis tool based on deep learning to support innovation in synthetic and medicinal chemistry. The tool was initially developed via Elsevier’s R&D Collaboration Network and is now being integrated into Elsevier’s flagship chemistry solution, Reaxys, combining Reaxys’ content with cutting-edge AI and machine learning technologies developed by PAI.
The Reaxys-PAI Predictive Retrosynthesis solution uses a model that incorporates deep neural networks trained on Reaxys data. The results are found using a Monte Carlo tree search approach to quickly discover promising candidate routes. Hundreds of thousands of reaction rules (>400,000) are algorithmically extracted from the Reaxys source data (>15 million single-step organic reactions), enabling it to be non-reliant on hand-encoded rules that are typically used in other solutions.
Prof. Dr. Mark Waller, Director at Pending.AI, said: “AI is becoming essential as scientific data grows in abundance. Our mission is to develop pragmatic solutions using AI and machine learning to empower scientists to advance drug discovery and development of other chemical compounds. We are proud to be working with Elsevier to meet this goal. The Reaxys-PAI Predictive Retrosynthesis tool will complement the knowledge of scientists and teams and help them to rapidly make more informed decisions.”
The tool has been tested rigorously by the world’s leading pharmaceutical and chemical companies and has been demonstrated to provide scientifically robust, diverse and innovative synthetic route suggestions. It is a valuable tool that is easy and intuitive to use and supports the needs of the business and researchers by being a very good assistant and idea generator. The predictive retrosynthesis solution has been trained on both positive and negative reaction data and solves synthesis design questions for novel molecules with direct links to experimental reactions available in the most trusted chemistry solution Reaxys. The predictive model training and creation is fast, allowing it to “self-learn” from the rapidly ever-growing chemistry knowledge. Reaxys-PAI Predictive Retrosynthesis can be further augmented by training on proprietary chemistry reaction data, including a customer’s own reaction dataset and building block library.
“AI is set to revolutionize the domain of chemical design and synthesis of small molecules,” said Dr. Ivan Krstic, Director Product Management, Life Science Solutions at Elsevier. “Over the past decade, the exponential growth in chemistry data; the ability to curate and harmonize data; coupled with advancements in computational and digital technologies such as deep learning has provided ideal grounds for addressing the problem of computer-aided synthesis design.
“We are very happy and honoured that this innovative work is enabled by a partnership between Elsevier and PAI to provide a best-in-class predictive retrosynthesissolution which combines high quality Reaxys reaction data with industry-leading predictive algorithms developed by PAI,” added Ivan. “We have strong evidence that the addition of AI-based retrosynthesis to Reaxys can help drive innovation, save researchers considerable time and radically change how we approach chemical synthesis, but I also want to share with my fellow chemists our strong belief that AI won’t replace chemists, instead it will support chemists and their decision making by paving the way in a more and more complex landscape of data.”
This is a step in Elsevier Life Science’s Chemistry solution strategy of building next-generation AI & machine learning enabled decision support tools that will help to bring drugs to market for patients most in need, help to find synthesis routes for novel chemical compounds that may be more environmentally friendly and help design scale-up processes which may be greener.
The Reaxys-PAI Predictive Retrosynthesis tool is now available as an add-on module for Reaxys customers. For more information, please visit the Reaxys homepage.
About Pending.AI (PAI)
Pending.AI is a start-up that develops scalable AI-based solutions which are trained on large-scale chemical and biological datasets. In addition to their work on designing and implementing data-driven retrosynthesis tools, PAI is also developing AI-based solutions for both ligand and structure-based drug-design. pending.ai
Reaxys is a chemistry research and education database providing chemical substance, properties, reaction and medicinal chemistry information for both bench chemistry and machine learning methods used in drug discovery and chemical/pharmaceutical R&D. Reaxys provides the most comprehensive manually extracted and curated chemistry, medicinal chemistry and pharmacology data including 118 million organic, inorganic and organometallic compounds, 49 million chemical reactions, 500 million published experimental facts, 36 million bioactivities from 37 million documents including patents and journals.
Elsevier is a global information analytics business that helps scientists and clinicians to find new answers, reshape human knowledge, and tackle the most urgent human crises. For 140 years, we have partnered with the research world to curate and verify scientific knowledge. Today, we’re committed to bringing that rigor to a new generation of platforms. Elsevier provides digital solutions and tools in the areas of strategic research management, R&D performance, clinical decision support, and professional education; including ScienceDirect, Scopus, SciVal, ClinicalKey and Sherpath. Elsevier publishes over 2,500 digitized journals, including The Lancet and Cell, 39,000 e-book titles and many iconic reference works, including Gray’s Anatomy. Elsevier is part of RELX, a global provider of information-based analytics and decision tools for professional and business customers. www.elsevier.com