Search

Accurate prediction of thermodynamic solubility by machine learning remains a challenge. Recent models often display good performances, but their reliability may be deceiving when used prospectively. This study investigates the origins of these discrepancies, following three directions: a historical perspective, an analysis of the aqueous solubility dataverse and data quality. We investigated over 20 years of published solubility datasets and models, highlighting overlooked datasets and the overlaps between popular sets. We benchmarked recently published models on a novel curated solubility dataset and report poor performances. We also propose a workflow to cure aqueous solubility data aiming at producing useful models for bench chemist. Our results demonstrate that some state-of-the-art models are not ready for public usage because they lack a well-defined applicability domain and overlook historical data sources. We report the impact of factors influencing the utility of the models: interlaboratory standard deviation, ionic state of the solute and data sources. The herein obtained models, and quality-assessed datasets are publicly available. [ABSTRACT FROM AUTHOR]

In this paper, support vector machine and condensed graph of reaction (CGR) approaches have been used to predict the regioselectivity of aromatic hydroxylation for human CYP1A2 substrates. Experimental data on aromatic hydroxylation for human cytochrome CYP1A2 (observed molecular or “real” transformations) used in the modeling were extracted from the Metabolite database and the XenoSite database. In addition, all potential but unobserved (“unreal”) transformations were generated. The dataset containing “real” and “unreal” transformations was converted into an ensemble of CGRs representing pseudomolecules with conventional (single, double, aromatic, etc.) bonds and dynamic bonds characterizing chemical transformations. ISIDA fragment descriptors generated for CGRs were used for the modeling. The models have been validated in three times repeated fivefold cross-validation on the training set and then on an external set. The final model was constructed by consensus over models built on different descriptors sets. Predictive performance of our model on the external test set was similar to that of XenoSite and Way2Drug tools. Unlike previously used atom labeling-based approaches, the proposed CGR-based representation of metabolic transformations could be applied to different types of reactions catalyzed by the same enzyme and therefore, it is more suitable for automatized handling of metabolic data. [ABSTRACT FROM AUTHOR]

An abstract for the article "Online Chemical Modeling Environment (OCHEM): Web Platform for Data Storage, Model Development and Publishing of Chemical Information," by I. Sushko, A.K. Pandey, S. Novotarskyi, W. Teetz, S. Brandmaier, A. Abdelaziz, V.V. Prokopenko and colleagues is presented.

An abstract of the article "Learning antibacterial activity against S. Aureus on the Chimiothèque Nationale dataset," by several researchers including, G. Marcou, N. Lachiche, and L. Brillet is presented.

Carbon capture and storage technologies are projected to increasingly contribute to cleaner energy transitions by significantly reducing CO 2 emissions from fossil fuel-driven power and industrial plants. The industry standard technology for CO 2 capture is chemical absorption with aqueous alkanolamines, which are often being mixed with an activator, piperazine, to increase the overall CO 2 absorption rate. Inefficiency of the process due to the parasitic energy required for thermal regeneration of the solvent drives the search for new tertiary amines with better kinetics. Improving the efficiency of experimental screening using computational tools is challenging due to the complex nature of chemical absorption. We have developed a novel computational approach that combines kinetic experiments, molecular simulations and machine learning for the in silico screening of hundreds of prospective candidates and identify a class of tertiary amines that absorbs CO 2 faster than a typical commercial solvent when mixed with piperazine, which was confirmed experimentally., (© 2022. The Author(s).)