Search

Abstract 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 We report a novel approach for grading chemical structure drawings for remote teaching, integrated into the Moodle platform. Typically, existing online platforms use a binary grading system, which often fails to give a nuanced evaluation of the answers given by the students. Therefore, such platforms are unevenly adapted to different disciplines. This is particularly true in the case of chemical structures, where most questions simply cannot be evaluated on a true/false basis. Specifically, a strict comparison of candidate and expected chemical structures is not sufficient when some tolerance is deemed acceptable. To overcome this limitation, we have developed a grading workflow based on the pairwise similarity score of two considered chemical structures. This workflow is implemented as a Moodle plugin, using the Chemdoodle engine for drawing structures and communicating with a REST server to compute the similarity score using molecular descriptors. The plugin ( https://github.com/Laboratoire-de-Chemoinformatique/moodle-qtype_molsimilarity ) is easily adaptable to any academic user; both embedding and similarity measures can be configured.

Amine mixtures are industrially used for carbon capture, whereby sluggish reaction kinetics are sped up with piperazine additives. Here, the authors report an experimentally verified computational approach that combines kinetic experiments, molecular simulations, and machine learning to identify a class of tertiary amines that absorbs CO2 faster than a typical commercial solvent when mixed with piperazine.

Abstract The “creativity” of Artificial Intelligence (AI) in terms of generating de novo molecular structures opened a novel paradigm in compound design, weaknesses (stability & feasibility issues of such structures) notwithstanding. Here we show that “creative” AI may be as successfully taught to enumerate novel chemical reactions that are stoichiometrically coherent. Furthermore, when coupled to reaction space cartography, de novo reaction design may be focused on the desired reaction class. A sequence-to-sequence autoencoder with bidirectional Long Short-Term Memory layers was trained on on-purpose developed “SMILES/CGR” strings, encoding reactions of the USPTO database. The autoencoder latent space was visualized on a generative topographic map. Novel latent space points were sampled around a map area populated by Suzuki reactions and decoded to corresponding reactions. These can be critically analyzed by the expert, cleaned of irrelevant functional groups and eventually experimentally attempted, herewith enlarging the synthetic purpose of popular synthetic pathways.

The design of effective target-specific drugs for COVID-19 treatment has become an intriguing challenge for modern science. The SARS-CoV-2 main protease, Mpro, responsible for the processing of SARS-CoV-2 polyproteins and production of individual components of viral replication machinery, is an attractive candidate target for drug discovery. Specific Mpro inhibitors have turned out to be promising anticoronaviral agents. Thus, an effective platform for quantitative screening of Mpro-targeting molecules is urgently needed. Here, we propose a pre–steady-state kinetic analysis of the interaction of Mpro with inhibitors as a basis for such a platform. We examined the kinetic mechanism of peptide substrate binding and cleavage by wild-type Mpro and by its catalytically inactive mutant C145A. The enzyme induces conformational changes of the peptide during the reaction. The inhibition of Mpro by boceprevir, telaprevir, GC-376, PF-00835231, or thimerosal was investigated. Detailed pre–steady-state kinetics of the interaction of the wild-type enzyme with the most potent inhibitor, PF-00835231, revealed a two-step binding mechanism, followed by covalent complex formation. The C145A Mpro mutant interacts with PF-00835231 approximately 100-fold less effectively. Nevertheless, the binding constant of PF-00835231 toward C145A Mpro is still good enough to inhibit the enzyme. Therefore, our results suggest that even noncovalent inhibitor binding due to a fine conformational fit into the active site is sufficient for efficient inhibition. A structure-based virtual screening and a subsequent detailed assessment of inhibition efficacy allowed us to select two compounds as promising noncovalent inhibitor leads of SARS-CoV-2 Mpro.