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.

Increasing antimicrobial resistance (AMR) represents a global healthcare threat. To decrease the spread of AMR and associated mortality, methods for rapid selection of optimal antibiotic treatment are urgently needed. Machine learning (ML) models based on genomic data to predict resistant phenotypes can serve as a fast screening tool prior to phenotypic testing. Nonetheless, many existing ML methods lack interpretability. Therefore, we present a methodology for visualization of sequence space and AMR prediction based on the non‐linear dimensionality reduction method – generative topographic mapping (GTM). This approach, applied to AMR data of >5000 S. aureus isolates retrieved from the PATRIC database, yielded GTM models with reasonable accuracy for all drugs (balanced accuracy values ≥0.75). The Generative Topographic Maps (GTMs) represent data in the form of illustrative maps of the genomic space and allow for antibiotic‐wise comparison of resistant phenotypes. The maps were also found to be useful for the analysis of genetic determinants responsible for drug resistance. Overall, the GTM‐based methodology is a useful tool for both the illustrative exploration of the genomic sequence space and AMR prediction. [ABSTRACT FROM AUTHOR]

New models for ACE2 receptor binding, based on QSAR and docking algorithms were developed, using XRD structural data and ChEMBL 26 database hits as training sets. The selectivity of the potential ACE2-binding ligands towards Neprilysin (NEP) and ACE was evaluated. The Enamine screening collection (3.2 million compounds) was virtually screened according to the above models, in order to find possible ACE2-chemical probes, useful for the study of SARS-CoV2-induced neurological disorders. An enzymology inhibition assay for ACE2 was optimized, and the combined diversified set of predicted selective ACE2-binding molecules from QSAR modeling, docking, and ultrafast docking was screened in vitro. The in vitro hits included two novel chemotypes suitable for further optimization.

Kinetic aqueous or buffer solubility is important parameter measuring suitability of compounds for high throughput assays in early drug discovery while thermodynamic solubility is reserved for later stages of drug discovery and development. Kinetic solubility is also considered to have low inter‐laboratory reproducibility because of its sensitivity to protocol parameters [1]. Presumably, this is why little efforts have been put to build QSPR models for kinetic in comparison to thermodynamic aqueous solubility. Here, we investigate the reproducibility and modelability of kinetic solubility assays. We first analyzed the relationship between kinetic and thermodynamic solubility data, and then examined the consistency of data from different kinetic assays. In this contribution, we report differences between kinetic and thermodynamic solubility data that are consistent with those reported by others [1, 2] and good agreement between data from different kinetic solubility campaigns in contrast to general expectations. The latter is confirmed by achieving high performing QSPR models trained on merged kinetic solubility datasets. The poor performance of QSPR model trained on thermodynamic solubility when applied to kinetic solubility dataset reinforces the conclusion that kinetic and thermodynamic solubilities do not correlate: one cannot be used as an ersatz for the other. This encourages for building predictive models for kinetic solubility. The kinetic solubility QSPR model developed in this study is freely accessible through the Predictor web service of the Laboratory of Chemoinformatics (https://chematlas.chimie.unistra.fr/cgi‐bin/predictor2.cgi). [ABSTRACT FROM AUTHOR]

Molecules are complex dynamic objects that can exist in different molecular forms (conformations, tautomers, stereoisomers, protonation states, etc.) and often it is not known which molecular form is responsible for observed physicochemical and biological properties of a given molecule. This raises the problem of the selection of the correct molecular form for machine learning modeling of target properties. The same problem is common to biological molecules (RNA, DNA, proteins)—long sequences where only key segments, which often cannot be located precisely, are involved in biological functions. Multi‐instance machine learning (MIL) is an efficient approach for solving problems where objects under study cannot be uniquely represented by a single instance, but rather by a set of multiple alternative instances. Multi‐instance learning was formalized in 1997 and motivated by the problem of conformation selection in drug activity prediction tasks. Since then MIL has found a lot of applications in various domains, such as information retrieval, computer vision, signal processing, bankruptcy prediction, and so on. In the given review we describe the MIL framework and its applications to the tasks associated with ambiguity in the representation of small and biological molecules in chemoinformatics and bioinformatics. We have collected examples that demonstrate the advantages of MIL over the traditional single‐instance learning (SIL) approach. Special attention was paid to the ability of MIL models to identify key instances responsible for a modeling property. This article is categorized under:Data Science > ChemoinformaticsData Science > Artificial Intelligence/Machine Learning [ABSTRACT FROM AUTHOR]

In this paper, we report comprehensive experimental and chemoinformatics analyses of the solubility of small organic molecules (“fragments”) in dimethyl sulfoxide (DMSO) in the context of their ability to be tested in screening experiments. Here, DMSO solubility of 939 fragments has been measured experimentally using an NMR technique. A Support Vector Classification model was built on the obtained data using the ISIDA fragment descriptors. The analysis revealed 34 outliers: experimental issues were retrospectively identified for 28 of them. The updated model performs well in 5-fold cross-validation (balanced accuracy = 0.78). The datasets are available on the Zenodo platform (DOI:10.5281/zenodo.4767511) and the model is available on the website of the Laboratory of Chemoinformatics.

Conjugated QSPR models for reactions integrate fundamental chemical laws expressed by mathematical equations with machine learning algorithms. Herein we present a methodology for building conjugated QSPR models integrated with the Arrhenius equation. Conjugated QSPR models were used to predict kinetic characteristics of cycloaddition reactions related by the Arrhenius equation: rate constant logk ${{\rm l}{\rm o}{\rm g}k}$ , pre‐exponential factor logA ${{\rm l}{\rm o}{\rm g}A}$ , and activation energy Ea ${{E}_{{\rm a}}}$. They were benchmarked against single‐task (individual and equation‐based models) and multi‐task models. In individual models, all characteristics were modeled separately, while in multi‐task models logk ${{\rm l}{\rm o}{\rm g}k}$ , logA ${{\rm l}{\rm o}{\rm g}A}$ and Ea ${{E}_{{\rm a}}}$ were treated cooperatively. An equation‐based model assessed logk ${{\rm l}{\rm o}{\rm g}k}$ using the Arrhenius equation and logA ${{\rm l}{\rm o}{\rm g}A}$ and Ea ${{E}_{{\rm a}}}$ values predicted by individual models. It has been demonstrated that the conjugated QSPR models can accurately predict the reaction rate constants at extreme temperatures, at which reaction rate constants hardly can be measured experimentally. Also, in the case of small training sets conjugated models are more robust than related single‐task approaches. [ABSTRACT FROM AUTHOR]

This paper describes the development of the unified conformational sampling and docking tool called Sampler for Multiple Protein-Ligand Entities (S4MPLE). The main novelty in S4MPLE is the unified dealing with intra- and intermolecular degrees of freedom (DoF). While classically programs are either designed for folding or docking, S4MPLE transcends this artificial specialization. It supports folding, docking of a flexible ligand into a flexible site and simultaneous docking of several ligands. The trick behind it is the formal assimilation of inter-molecular to intra-molecular DoF associated to putative inter-molecular contact axes. This is implemented within the genetic operators powering a Lamarckian Genetic Algorithm (GA). Further novelty includes differentiable interaction fingerprints to control population diversity, and fitting a simple continuum solvent model and favorable contact bonus terms to the AMBER/GAFF force field. Novel applications—docking of fragment-like compounds, simultaneous docking of multiple ligands, including free crystallographic waters—were published elsewhere. This paper discusses: (a) methodology, (b) set-up of the force field energy functions and (c) their validation in classical redocking tests. More than 80% success in redocking was achieved (RMSD of top-ranked pose < 2.0 Å).

We report the major highlights of the School of Cheminformatics in Latin America, Mexico City, November 24–25, 2022. Six lectures, one workshop, and one roundtable with four editors were presented during an online public event with speakers from academia, big pharma, and public research institutions. One thousand one hundred eighty-one students and academics from seventy-nine countries registered for the meeting. As part of the meeting, advances in enumeration and visualization of chemical space, applications in natural product-based drug discovery, drug discovery for neglected diseases, toxicity prediction, and general guidelines for data analysis were discussed. Experts from ChEMBL presented a workshop on how to use the resources of this major compounds database used in cheminformatics. The school also included a round table with editors of cheminformatics journals. The full program of the meeting and the recordings of the sessions are publicly available at https://www.youtube.com/@SchoolChemInfLA/featured. [ABSTRACT FROM AUTHOR]

This user guide describes the rationale behind, and the modus operandi of a Unix script-driven package for evolutionary searching of optimal Support Vector Machine model parameters as computed by the libsvm package, leading to support vector machine models of maximal predictive power and robustness. Unlike common libsvm parameterizing engines, the current distribution includes the key choice of best-suited sets of attributes/descriptors, in addition to the classical libsvm operational parameters (kernel choice, kernel parameters, cost, and so forth), allowing a unified search in an enlarged problem space. It relies on an aggressive, repeated cross-validation scheme to ensure a rigorous assessment of model quality. Primarily designed for chemoinformatics applications, it also supports the inclusion of decoy instances, for which the explained property (bioactivity) is, strictly speaking, unknown but presumably “inactive”, thus additionally testing the robustness of a model to noise. The package was developed with parallel computing in mind, supporting execution on both multi-core workstations as well as compute cluster environments. It can be downloaded from http://infochim.u-strasbg.fr/spip.php?rubrique178.

We describe SILIRID (Simple Ligand–Receptor Interaction Descriptor), a novel fixed size descriptor characterizing protein–ligand interactions. SILIRID can be obtained from the binary interaction fingerprints (IFPs) by summing up the bits corresponding to identical amino acids. This results in a vector of 168 integer numbers corresponding to the product of the number of entries (20 amino acids and one cofactor) and 8 interaction types per amino acid (hydrophobic, aromatic face to face, aromatic edge to face, H-bond donated by the protein, H-bond donated by the ligand, ionic bond with protein cation and protein anion, and interaction with metal ion). Efficiency of SILIRID to distinguish different protein binding sites has been examined in similarity search in sc-PDB database, a druggable portion of the Protein Data Bank, using various protein–ligand complexes as queries. The performance of retrieval of structurally and evolutionary related classes of proteins was comparable to that of state-of-the-art approaches (ROC AUC ≈ 0.91). SILIRID can efficiently be used to visualize chemogenomic space covered by sc-PDB using Generative Topographic Mapping (GTM): sc-PDB SILIRID data form clusters corresponding to different protein types.

Following previous efforts to render the Conformational Space (CS) of flexible compounds by Generative Topographic Mapping (GTM), this polyvalent mapping technique is here adapted to the docking problem. Contact fingerprints (CF) characterize ligands from the perspective of the binding site by monitoring protein atoms that are “touched” by those of the ligand. A “Contact” (CF) map was built by GTM-driven dimensionality reduction of the CF vector space. Alternatively, a “Hybrid” (Hy) map used a composite descriptor of CFs concatenated with ligand fragment descriptors. These maps indirectly represent the active site and integrate the binding information of multiple ligands. The concept is illustrated by a docking study into the ATP-binding site of CDK2, using the S4MPLE program to generate thousands of poses for each ligand. Both maps were challenged to (1) Discriminate native from non-native ligand poses, e.g., create RMSD-landscapes “colored” by the conformer ensemble of ligands of known binding modes in order to highlight “native” map zones (poses with RMSD to PDB structures < 2Å). Then, projection of poses of other ligands on such landscapes might serve to predict those falling in native zones as being well-docked. (2) Distinguish ligands−characterized by their ensemble of conformers−by their potency, e.g., testing the hypotheses whether zones privileged by potent binders are clearly separated from the ones preferred by decoys on the maps. Hybrid maps were better in both challenges and outperformed the classical energy and individual contact satisfaction scores in discriminating ligands by potency. Moreover, the intuitive visualization and analysis of docking CS may, as already mentioned, have several applications−from highlighting of key contacts to monitoring docking calculation convergence.

Ab initio kinetic studies are important to understand and design novel chemical reactions. While the Artificial Force Induced Reaction (AFIR) method provides a convenient and efficient framework for kinetic studies, accurate explorations of reaction path networks incur high computational costs. In this article, we are investigating the applicability of Neural Network Potentials (NNP) to accelerate such studies. For this purpose, we are reporting a novel theoretical study of ethylene hydrogenation with a transition metal complex inspired by Wilkinson's catalyst, using the AFIR method. The resulting reaction path network was analyzed by the Generative Topographic Mapping method. The network's geometries were then used to train a state-of-the-art NNP model, to replace expensive ab initio calculations with fast NNP predictions during the search. This procedure was applied to run the first NNP-powered reaction path network exploration using the AFIR method. We discovered that such explorations are particularly challenging for general purpose NNP models, and we identified the underlying limitations. In addition, we are proposing to overcome these challenges by complementing NNP models with fast semiempirical predictions. The proposed solution offers a generally applicable framework, laying the foundations to further accelerate ab initio kinetic studies with Machine Learning Force Fields, and ultimately explore larger systems that are currently inaccessible. [ABSTRACT FROM AUTHOR]

In order to analyze the Chimiothèque Nationale (CN) – The French National Compound Library – in the context of screening and biologically relevant compounds, the library was compared with ZINC in‐stock collection and ChEMBL. This includes the study of chemical space coverage, physicochemical properties and Bemis‐Murcko (BM) scaffold populations. More than 5 K CN‐unique scaffolds (relative to ZINC and ChEMBL collections) were identified. Generative Topographic Maps (GTMs) accommodating those libraries were generated and used to compare the compound populations. Hierarchical GTM («zooming») was applied to generate an ensemble of maps at various resolution levels, from global overview to precise mapping of individual structures. The respective maps were added to the ChemSpace Atlas website. The analysis of synthetic accessibility in the context of combinatorial chemistry showed that only 29,7 % of CN compounds can be fully synthesized using commercially available building blocks. [ABSTRACT FROM AUTHOR]