Chemical.AI, a global leader in artificial intelligence (AI) for synthetic route design and prediction, and Chemaxon, a leading company in chemical and biological software development, have announced a strategic partnership that will allow access to Chemical.AI's reverse synthesis tool, ChemAIRS, as an option from Chemaxon's drug discovery platform, Design Hub. This collaboration creates compatibility between Chemical.AI's ChemAIRS and Chemaxon's Design Hub, enabling a seamless user workflow and one-stop service that integrates compound design tracking and prioritization features from Design Hub with the innovative synthetic routes generated in minutes using ChemAIRS's diverse strategies. For more details, please visit our website.

Accurately calculated molecular properties significantly impact the understanding of the relationship between predicted properties and measured values, the training of predictive models for new targets, and the prediction of properties for novel entities. ChemAxon's predictive tool, Calculator Plugins, is widely accepted and utilized in both industry and academic research, particularly for more complex molecular property predictions such as ionization, lipophilicity, and solubility. Continuous accuracy evaluation has been part of our strategy in the development of these algorithms. To make this step automated, reproducible, and transparent, we have decided to develop and publish a program that automatically generates reports on the system. For more details regarding this report, please check the link.

As the library of existing and hypothetical chemical substances continues to grow, reaching sizes of many orders of magnitude, traditional cheminformatics tools and hardware infrastructure become inadequate. Questions that seem simple yet are fundamentally important for drug design, such as "Is this compound included in the library?" and "What are the ten most similar compounds in this collection?" become challenging to answer within acceptable response times in these ultra-large spaces. This paper discusses the current challenges in searching large chemical libraries and explores approaches that could provide drug designers, medicinal chemists, and cheminformaticians—who are trying to explore far beyond chemical space to track the next optimal and novel synthetically accessible bioactive structures—with groundbreaking solutions at the "Mars helicopter" level.

▶ChemAxon's Response to CVE-2021-44228 ("Log4Shell") and CVE-2021-45046 Initial Release: December 15, 2021 Update: January 3, 2022 This vulnerability was disclosed by the Apache Log4j project on December 9, 2021 (Thursday). If exploited, it could allow remote attackers to execute code on the server if the system logs a string value controlled by the attacker to the affected endpoint. Immediately upon recognizing this vulnerability, ChemAxon evaluated all cloud hosting systems and on-premises software for customers, identified those that could be affected, and systematically began to address any exposures. All affected ChemAxon products have been updated to use log4j2.16, so no new incidents pose additional threats. For more details, please visit the Patcore or ChemAxon website.

The SAMPL (Statistical Assessment of the Modeling of Proteins and Ligands) challenge aims to evaluate the accuracy of biomolecular and physical modeling for rational drug design. The recently announced SAMPL6 assessment focused on the prediction of the octanol-water partition coefficient (logP). In this blind challenge, 91 predictions were submitted from 17 research groups for 11 compounds, utilizing quantum mechanics, molecular mechanics, knowledge-based, empirical, and hybrid methods. Among these, highly accurate methods were identified, with RMSE remaining below 0.5 logP units for 10 different methods. Inspired by these results, we verified the accuracy of ChemAxon's logP prediction tool. As a result, only one case (SM11) out of 11 had an absolute error exceeding 0.5, which was found to be the largest average error among empirical methods. The calculations of ChemAxon logP demonstrated high accuracy in predictions, suggesting that this model can contribute to the optimization of new molecules or experimental conditions throughout drug discovery projects. For more details, please see the link.

The pharmaceutical industry is constantly under immense pressure to address the high attrition rates in drug development. Efforts to reduce the number of failures related to efficacy and safety through the analysis of potential correlations with the physicochemical properties of low molecular weight candidate compounds have not yielded clear conclusions due to limitations in data volume at various companies. This paper retrospectively analyzes drug candidates from AstraZeneca, Eli Lilly, GlaxoSmithKline, and Pfizer, discussing their efficacy. The aforementioned companies use ChemAxon's property calculation tools to perform physicochemical property calculations.