Sommaire de la page
Publications
- Article dans une revue
- Chapitre d'ouvrage
- Communication dans un congrès
- Pré-publication, Document de travail
- Article dans une revue
Mixture‐Quantitative Structure–Property Relationship Approaches for Jet Fuel‐Component Blends: A Review
Erik Yeghyan, Benoit Creton, Mickaël Matrat, Gilles Marcou
Molecular Informatics, 2026, 45 (9), pp.e70050. ⟨10.1002/minf.70050⟩
Article dans une revueAbstractJet fuels (JFs) and sustainable aviation fuels (SAFs) are complex hydrocarbon mixtures whose properties must meet strict international specifications to ensure consistent quality. Their increasing variability, driven by environmental and process constraints, raises multiple questions regarding the relationship between fuel composition, safety, and performance. In this context, predictive models can help support fuel formulation while reducing experimental effort. Quantitative structure–property relationship (QSPR) methods have been applied to fuel components such as hydrocarbons to predict various properties, showing promising results but often with limited accuracy and applicability. Several studies have also investigated mixture‐QSPR (M‐QSPR) approaches for hydrocarbon systems involving constituents also present in fuels; however, very few studies directly address real fuel mixtures. This is because M‐QSPR remains particularly challenging due to mixture interactions, data scarcity, representation difficulties, and validation issues. This review evaluates past M‐QSPR studies on fuels, fuel‐component mixtures, and general M‐QSPR methodologies to identify current advances, limitations, and gaps and to outline strategies for developing M‐QSPR models for JFs.
Leveraging the Condensed Graph of Reaction for Clustering Retrosynthetic Pathways
Almaz Gilmullin, Tagir Akhmetshin, Dmitry Zankov, Olga Klimchuk, Dragos Horvath, Timur Madzhidov, Alexandre Varnek
Journal of Chemical Information and Modeling, 2026, 66 (17), pp.10919-10934. ⟨10.1021/acs.jcim.6c00489⟩
Article dans une revueAbstractAbstract Modern retrosynthetic tools can propose hundreds of alternative pathways for a single target, making it challenging to effectively explore and navigate the resulting route space. We present a CGR-based framework for the analysis and clustering of synthetic routes that integrates both target-centered and all-species-centered perspectives. Entire reaction pathways are encoded as single-molecule graphs (RouteCGR) or reduced representations retaining only target atoms (SB-CGR), enabling automatic identification of strategic bond patterns (SBPs). These representations can be transformed into Morgan fingerprints for a quantitative route similarity assessment. We propose a two-level clustering strategy in which routes are first grouped by shared SBPs, ensuring high interpretability based on key retrosynthetic disconnections, and then further differentiated using RouteCGR similarity to capture variations in starting materials and auxiliary transformations. The method demonstrates near-linear scalability and computational efficiency for large data sets. Application to synthetic routes for apatinib generated by multiple planning tools reveals tool-dependent diversity in strategic disconnections and highlights the benefit of combining tools to expand route space. The framework also supports cross-target analysis, enabling the identification of reusable route families that share common strategic disconnections and building blocks across related molecules. Overall, the SBP-based approach provides an interpretable and scalable solution for automated synthesis route analysis and informed decision-making. The proposed approach is implemented in SynPlanner retrosynthesis planning software and is available as a standalone module at https://github.com/Laboratoire-de-Chemoinformatique/SynPlanner.
Interpretable and Scalable Similarity Metrics for DNA‐Encoded Library Design Using Generative Topographic Mapping
Louis Plyer, Alexey Orlov, Tagir Akhmetshin, Erik Yeghyan, Fanny Bonachera, Dragos Horvath, Alexandre Varnek
Molecular Informatics, 2026, 45 (3), pp.e70026. ⟨10.1002/minf.70026⟩
Article dans une revueAbstractThe growing number and size of DNA-encoded libraries (DELs), together with the vast space of possible DEL designs, demand interpretable and scalable criteria for selecting which libraries to construct and screen against a given target. An ideal target-focused DEL shows both strong similarity with an active reference compound collection and high intra-DEL diversity. Chemography with Generative Topographic Mapping (GTM) was shown to be a promising approach for selecting DELs, offering both intuitive visualization and fast quantitative analysis scalable to thousands of DEL designs. This is achieved by defining each library by a "stand-alone" vector, the comparison of which precludes costly pairwise inter-molecular similarity calculations. However, the extent to which such "stand-alone" (SA) approaches in general, and GTM-derived SA metrics in particular, recover DELs that are reference-proximal and chemically diverse as evaluated by conventional compound pair-matching (CP) metrics in the initial descriptor space remains insufficiently characterized. In this article, the comparative analysis of the Morgan count fingerprint-based chemical-library similarity versus GTM-derived metrics, using 100 diverse DEL subsets and a reference set of compounds tested against cyclin-dependent kinase 2 (CDK2) from ChEMBL, was performed. GTM-based SA metrics provide robust approximations for "gold standard" molecular descriptor space CP metrics for DEL selection: Spearman rank correlations fall in the 0.6-0.7 range. Our results demonstrate that GTM helps to identify DELs that best span the reference space according to same "gold standard" molecular descriptor space metrics: SA GTM-driven rankings of libraries achieve enrichment factors at 5% (EF5%) of 4-12 (in terms of finding "gold standard" top libraries within the 5% best ranked by GTM)-always picking 2 out of the top 3 libraries. The accompanying two-dimensional landscapes make intra-and interlibrary diversity visually accessible, supporting rapid, interpretable screening of alternative DEL designs. Collectively, these results position GTM as an efficient tool for chemical-library similarity assessment and target-focused DEL selection.
Peptidomimetics Inspired by α-Synuclein or Its Chaperone αB-Crystallin Differentially Modulate α-Synuclein Aggregation
Nicolo Bisi, Josine Kothuis, Julia Kaffy, Helena Pérez Peña, Celina Schulz, Chiara Maria Giulia de Luca, Arianna Ciullini, Ilaria Linda Dellarole, Léa Radal, Fabio Moda, Graziella Cappelletti, Dragos Horvath, Stefano Pieraccini, Wolfgang Hoyer, Frédéric Halgand, Nicolo Tonali, Sandrine Ongeri
Journal of Medicinal Chemistry, 2026, 69 (4), pp.4059-4077. ⟨10.1021/acs.jmedchem.5c02716⟩
Article dans une revueAbstractAggregation of the α-Synuclein protein in neurons is responsible for synucleinopathies such as Parkinson's Disease. In healthy cells, αSyn is primarly present as monomers. Under pathological conditions, oligomers and fibrils are formed, leading to neuronal toxicity and death. No treatment prevents fatal synucleinopathies. We designed small peptidomimetics based on the structure of αSyn aggregates and on its chaperone protein αB-crystallin. Interestingly, a relationship between the impact of peptidomimetics on the αSyn aggregation process, their sequences and secondary conformation has been evidenced. In vitro and in cellular assays demonstrated that one compound based on αB-crystallin was able to interfere with αSyn folding and aggregation by reducing the formation of oligomers and promoting an off-pathway aggregation. The demonstration that physiological chaperone proteins can be mimicked by small peptide derivatives paves the way for new strategies to design inhibitors of amyloid protein aggregation, a hallmark of around 50 neurodegenerative and systemic amyloid diseases.
Design of Highly Potent Antibiofilm, Antimicrobial Peptides Using Explainable Artificial Intelligence
Karina Pikalyova, Tagir Akhmetshin, Alexey Orlov, Evan F Haney, Noushin Akhoundsadegh, Jiaying You, Robert E W Hancock, Dragos Horvath, Gilles Gérard Marcou, Artem Cherkasov, Alexandre Varnek
Journal of Chemical Information and Modeling, 2025, 66 (1), pp.744 - 755. ⟨10.1021/acs.jcim.5c01992⟩
Article dans une revueAbstractAntimicrobial peptides have emerged as a potential alternative to traditional small-molecule antimicrobials. They possess broad-spectrum efficacy and increasingly confront the challenges of bacterial resistance, especially the adaptive resistance of biofilms. However, advanced rational peptide design methods are still required to ensure optimal property profiles of such peptides, while limiting the cost of their synthesis and screening. Here, we present a computational pipeline for the rational de novo design of antimicrobial and antibiofilm peptides based on an explainable artificial intelligence (XAI) framework. The developed framework combines a Wasserstein Autoencoder (WAE) and a nonlinear dimensionality reduction method�generative topographic mapping (GTM). The WAE was used to learn the latent representation of the peptide space, while the GTM guided the generation of novel AMPs through an illustrative depiction of the latent space in the form of 2D maps. The generated peptides were subjected to screening by machine learning models, resulting in the final hit list based on their predicted activity. The efficacy of the peptides generated with the developed pipeline was experimentally verified by synthesis and testing for activity against methicillin-resistant Staphylococcus aureus (MRSA), achieving a 100% hit rate in targeting biofilms. Notably, the most potent antibiofilm peptide developed in this study demonstrated almost one order of magnitude improvement in IC 50 value compared with the potent antibiofilm peptide reference "1018", used as a positive control. The developed pipeline is readily extendable for the optimization of additional peptide properties, including cytotoxicity, tendency to aggregate, and proteolytic stability, underscoring its potential utility for rational design of the peptide-based therapeutics.
Machine Learning-Based Thermodynamic Modeling of Acid Gas Absorption in Aqueous Methyldiethanolamine and Aqueous Piperazine
Kyrylo Klimenko, Rui Afonso, Paolo Stringari, Karen Gonzalez Tovar, Gilles Marcou, Dragos Horvath, Eric Cloarec, Alexandre Varnek, Frédérick de Meyer
Journal of Physical Chemistry B, 2025, 130 (1), pp.447-460. ⟨10.1021/acs.jpcb.5c06728⟩
Article dans une revueAsymmetric Total Synthesis of (−)‐Glycybridin B, a Pharmacophore Screened Candidate for Tubulin Binding
Alice Maiocchi, Maxim Shevelev, Zlata Boiarska, Juan Estévez‐gallego, Francesca Bonato, Paolo Orlando, Alessandra Chinosi, Emanuele A Marcone, Andrea Citarella, Dragos Horvath, Michel O Steinmetz, Andrea E Prota, Alexandre Varnek, Valerio Fasano, Daniele Passarella
Chemistry - A European Journal, 2025, 31 (55), ⟨10.1002/chem.202502228⟩
Article dans une revueAbstractMicrotubule-targeting agents (MTAs) represent a pivotal class of therapeutic compounds designed to disrupt microtubule dynamics, leading to cell cycle arrest and apoptosis in malignant cells. Nevertheless, their off-target effects on healthy, rapidly dividing cells result in significant neurotoxicity and myelosuppression. Ongoing research aims to enhance their specificity and identify novel active scaffolds to minimize adverse effects and fight drug resistance. Searching for new potential tubulin binders with a pharmacophore screening method, we identified glycybridin B as a promising natural product. Here, we report the first total synthesis of this compound via a five-step route, involving a key chalcone intermediate, along with its biological evaluation.
Predicting reaction conditions: a data-driven perspective
Matthew Ball, Dragos Horvath, Thierry Kogej, Mikhail Kabeshov, Alexandre Varnek
Chemical Science, 2025, 16 (38), pp.17523 - 17541. ⟨10.1039/d5sc03045e⟩
Article dans une revueAbstractThe selection of optimal reaction conditions is a critical challenge in synthetic chemistry, influencing the efficiency, sustainability, and scalability of chemical processes. While machine learning (ML) has emerged as a promising tool for predicting reaction conditions in computer-aided synthesis planning (CASP), existing approaches face many significant challenges, including data quality, sparsity, choice of reaction representation and method evaluation. Recent studies have suggested that these models may fail to surpass literature-derived popularity baselines, underscoring these problems. In this work, we provide a critical review of state-of-the-art ML techniques, identifying innovations which have addressed the key challenges facing researchers when modelling conditions. To illustrate how relevant reaction representations can improve existing models, we perform a case study of heteroaromatic Suzuki-Miyaura reactions, derived from US patent data (USPTO). Using Condensed Graph of Reaction-based inputs, we demonstrate how this alternative representation can enhance the predictive power of a model beyond popularity baselines. Finally, we propose future directions for the field beyond improving data quality, suggesting potential options to mitigate data issues prevalent in existing literature data. This perspective aims to guide researchers in understanding and overcoming current limitations in computational reaction condition prediction.
What Works, What Doesn’t, and Why? An Industrial Perspective on Absorption Modeling
Pierre Llompart, Claire Minoletti, Gilles Marcou, Alexandre Varnek
Journal of Medicinal Chemistry, 2025, 68 (14), pp.14609 - 14627. ⟨10.1021/acs.jmedchem.5c00744⟩
Article dans une revueAbstract<div><p>Lead optimization failures are often linked to poor absorption, compounded by efflux transport and low recovery. We report a comprehensive modeling of public and industrial data on organic molecules' absorption. Comparative analysis of an industrial chemical space examined the relationship among key permeability parameters, revealing misconceptions in transport route characterization. We demonstrated the importance of recovery, distribution coefficient, and topological polar surface area in multiparameter optimization (MPO). A multitask learning approach was used for model development. Models built on public data were validated on industrial data, revealing discrepancies driven by variations in the protocols. Our results highlight the value of industrial data to avoid applicability domain issues and ensure standardized measurements. Finally, coupling predictive models with generative topographic mapping offers a visual strategy to explore chemical space and understand optimization challenges. This work proposes an approach to support MPO and improve drug discovery efficiency.</p></div>
Spherical GTM: A New Proposition for Visualization of Chemical Data
Farah Asgarkhanova, Marcou Gilles, Mikhail Volkov, Murielle Muzard, Richard Plantier-Royon, Caroline Rémond, Dragos Horvath, Alexandre Varnek
Molecular Informatics, 2025, 44 (5-6), ⟨10.1002/minf.202500045⟩
Article dans une revueAbstractThe Spherical Generative Topographic Mapping (SGTM) method represents an intuitive approach to visualize chemical data. Unlike the original Generative Topographic Mapping algorithm, which utilizes a bounded flat Euclidean space as a manifold, our proposed modification introduces a spherical manifold to address known nonflat topology issues. In this study, we describe the mathematical formalism of this new approach and showcase its ability to visualize 2D electron density patterns of water and benzene and the CosMoPoly chemical library—an enumeration of synthetically accessible molecules. By comparing the outcomes with established references, it is demonstrated that SGTM emerges as a novel 3D data visualization method, offering improved accuracy in the depiction of chemical structures.
Harnessing Medicinal Chemical Intuition from Collective Intelligence
Pierre Llompart, Kwame Amaning, Marc Bianciotto, Bruno Filoche-Rommé, Yann Foricher, Pablo Mas, David Papin, Jean-Philippe Rameau, Laurent Schio, Gilles Marcou, Alexandre Varnek, Mehdi Moussaid, Claire Minoletti, Paraskevi Gkeka
Journal of Medicinal Chemistry, 2025, 68 (11), pp.10860-10876. ⟨10.1021/acs.jmedchem.4c03066⟩
Article dans une revueCoLiNN: A Tool for Fast Chemical Space Visualization of Combinatorial Libraries Without Enumeration
Regina Pikalyova, Tagir Akhmetshin, Dragos Horvath, Alexandre Varnek
Molecular Informatics, 2025, 44 (3), pp.e202400263. ⟨10.1002/minf.202400263⟩
Article dans une revueAbstractVisualization of the combinatorial library chemical space provides a comprehensive overview of available compound classes, their diversity, and physicochemical property distribution ‐ key factors in drug discovery. Typically, this visualization requires time‐ and resource‐consuming compound enumeration, standardization, descriptor calculation, and dimensionality reduction. In this study, we present the Combinatorial Library Neural Network (CoLiNN) designed to predict the projection of compounds on a 2D chemical space map using only their building blocks and reaction information, thus eliminating the need for compound enumeration. Trained on 2.5 K virtual DNA‐Encoded Libraries (DELs), CoLiNN demonstrated high predictive performance, accurately predicting the compound position on Generative Topographic Maps (GTMs). GTMs predicted by CoLiNN were found very similar to the maps built for enumerated structures. In the library comparison task, we compared the GTMs of DELs and the ChEMBL database. The similarity‐based DELs/ChEMBL rankings obtained with “true” and CoLiNN predicted GTMs were consistent. Therefore, CoLiNN has the potential to become the go‐to tool for combinatorial compound library design – it can explore the library design space more efficiently by skipping the compound enumeration.
Higher education in chemoinformatics: achievements and challenges
Alexandre Varnek, Gilles Marcou, Dragos Horvath
Journal of Cheminformatics, 2025, 17 (1), pp.89. ⟨10.1186/s13321-025-01036-x⟩
Article dans une revueAbstractWhile chemoinformatics is a well-established scientific field, its integration into university curricula is rarely discussed. In this work, we share our experience in developing a chemoinformatics curriculum at the University of Strasbourg and highlight the main challenges in higher education for this discipline.
From High Dimensions to Human Insight: Exploring Dimensionality Reduction for Chemical Space Visualization
Alexey Orlov, Tagir N Akhmetshin, Dragos Horvath, Gilles Marcou, Alexandre Varnek
Molecular Informatics, 2025, 44 (1), ⟨10.1002/minf.202400265⟩
Article dans une revueAbstractDimensionality reduction is an important exploratory data analysis method that allows high-dimensional data to be represented in a human-interpretable lower-dimensional space. It is extensively applied in the analysis of chemical libraries, where chemical structure data -represented as high-dimensional feature vectors-are transformed into 2D or 3D chemical space maps. In this paper, commonly used dimensionality reduction techniques -Principal Component Analysis (PCA), t-Distributed Stochastic Neighbor Embedding (t-SNE), Uniform Manifold Approximation and Projection (UMAP), and Generative Topographic Mapping (GTM) -are evaluated in terms of neighborhood preservation and visualization capability of sets of small molecules from the ChEMBL database.
The freedom space – a new set of commercially available molecules for hit discovery
Mykola Protopopov, Valentyna Tararina, Fanny Bonachera, Igor Dzyuba, Anna Kapeliukha, Serhii Hlotov, Oleksii Chuk, Gilles Marcou, Olga Klimchuk, Dragos Horvath, Erik Yeghyan, Olena Savych, Olga Tarkhanova, Alexandre Varnek, Yurii Moroz
Molecular Informatics, 2024, 43 (12), ⟨10.1002/minf.202400114⟩
Article dans une revueAbstractThe advent of high‐performance virtual screening techniques nowadays allows drug designers to explore ultra‐large sets of candidate compounds in search of molecules predicted to have desired properties. However, the success of such an endeavor heavily relies on the pertinence (drug‐likeness and, foremost, chemical feasibility) of these candidates, or otherwise, virtual screening will return valueless “hits”, by the garbage in/garbage out principle. The huge popularity of the judiciously enumerated Enamine REAL Space is clear proof of the strength of this Big Data trend in drug discovery. Here we describe a new dataset of make‐on‐demand compounds called the Freedom space. It follows the principles of Enamine REAL Space and contains highly feasible molecules (synthesis success rate over 75 percent). However, the scaffold and chemography analysis revealed significant differences to both the REAL and biologically annotated compounds from the ChEMBL database. The Freedom Space is a significant extension of the REAL Space and can be utilized for a more comprehensive exploration of the synthetically feasible chemical space in hit finding and hit‐to‐lead campaigns.
Assessment of the concomitant action of XBD173 and interferon β in a mouse model of multiple sclerosis using infrared marker bands
Krongkarn Sirinukunwattana, Christian Klein, Paul F A Clarke, Gilles Marcou, Laurence Meyer, Nicolas Collongues, Jérôme de Sèze, Petra Hellwig, Christine Patte-Mensah, Youssef El Khoury, Ayikoé-Guy Mensah-Nyagan
Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy [1994-..], 2024, 327, pp.125390. ⟨10.1016/j.saa.2024.125390⟩
Article dans une revueAbstractDisease modifying therapies including interferon-β (IFNβ) effectively counteract the inflammatory component in relapsing-remitting multiple sclerosis (RRMS) but this action, generally associated with severe side effects, does not prevent axonal/neuronal damages. Hence, axonal neuroprotection, which is pivotal for MS effective treatment, remains a difficult clinical challenge. Growing evidence suggested as promising candidate for neuroprotection, Emapunil (AC-5216) or XBD173, a ligand of the mitochondrial translocator protein highly expressed in glial cells and neurons. Indeed, elegant studies previously showed that low and well tolerated doses of XBD173 efficiently improved clinical symptoms and neuropathological markers in MS mice. Here we combined clinical scoring in vivo with Fourier transform infrared spectroscopy of sera samples to investigate the hypothesis that the concomitant treatment of RRMS mice with low doses of IFNβ and XBD173 may increase their beneficial effects against MS symptoms and additionally decrease IFNβ-induced side effects. Our results show a significant alteration of the composition of serum protein and lipids in the spectra of the sera of RRMS mice. While the signature of proteins remains altered upon treatment, the signature of lipids is recovered comparatively well with 20 kIU IFNβ and upon concomitant treatment with a low dose of XBD173 (10 mg/kg) and IFNβ (10 kIU), but not with 10 kIU of IFNβ alone. The concomitant therapy with XBD173 (10 mg/kg) and IFNβ (10 kIU), devoid of side effects, exhibited at least equal or even better efficacy than IFNβ (20 kIU) treatment against RRMS symptoms.
Benchmarking of BMDC assay and related QSAR study for identifying sensitizing chemicals
Lisa Chedik, Shamkhal Baybekov, Gilles Marcou, Frédéric Cosnier, Mélanie Mourot-Bousquenaud, Sandrine Jacquenet, Alexandre Varnek, Fabrice Battais
Regulatory Toxicology and Pharmacology, 2024, 149, pp.105623. ⟨10.1016/j.yrtph.2024.105623⟩
Article dans une revueWill we ever be able to accurately predict solubility?
Pierre Llompart, Claire Minoletti, Shamkhal Baybekov, Dragos Horvath, Gilles Marcou, Alexandre Varnek
Scientific Data , 2024, 11 (1), pp.303. ⟨10.1038/s41597-024-03105-6⟩
Article dans une revueAbstractAccurate 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-ofthe-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.</p></div>
Predicting S. aureus antimicrobial resistance with interpretable genomic space maps
Karina Pikalyova, Alexey Orlov, Dragos Horvath, Gilles Marcou, Alexandre Varnek
Molecular Informatics, 2024, 43 (5), pp.e202300263. ⟨10.1002/minf.202300263⟩
Article dans une revueAbstractIncreasing 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.
an update of skin permeability data based on a systematic review of recent research
Lisa Chedik, Shamkhal Baybekov, Frédéric Cosnier, Gilles Marcou, Alexandre Varnek, Catherine Champmartin
Scientific Data , 2024, 11 (1), pp.224. ⟨10.1038/s41597-024-03026-4⟩
Article dans une revueAbstractThe cutaneous absorption parameters of xenobiotics are crucial for the development of drugs and cosmetics, as well as for assessing environmental and occupational chemical risks. Despite the great variability in the design of experimental conditions due to uncertain international guidelines, datasets like HuskinDB have been created to report skin absorption endpoints. this review updates available skin permeability data by rigorously compiling research published between 2012 and 2021. Inclusion and exclusion criteria have been selected to build the most harmonized and reusable dataset possible. the Generative topographic Mapping method was applied to the present dataset and compared to HuskinDB to monitor the progress in skin permeability research and locate chemotypes of particular concern. The open-source dataset (SkinPiX) includes steady-state flux, maximum flux, lag time and permeability coefficient results for the substances tested, as well as relevant information on experimental parameters that can impact the data. It can be used to extract subsets of data for comparisons and to build predictive models.
Kinetic solubility: Experimental and machine‐learning modeling perspectives
Shamkhal Baybekov, Pierre Llompart, Gilles Marcou, Patrick Gizzi, Jean-Luc Galzi, Pascal Ramos, Olivier Saurel, Claire Bourban, Claire Minoletti, Alexandre Varnek
Molecular Informatics, 2024, 43 (2), pp.e202300216. ⟨10.1002/minf.202300216⟩
Article dans une revueAbstractKinetic 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 ).
Implementation of a soft grading system for chemistry in a Moodle plugin: reaction handling
Louis Plyer, Gilles Marcou, Céline Perves, Fanny Bonachera, Alexander Varnek
Journal of Cheminformatics, 2024, 16 (1), pp.90. ⟨10.1186/s13321-024-00889-y⟩
Article dans une revueAbstractHere, we present a new method for evaluating questions on chemical reactions in the context of remote education. This method can be used when binary grading is not sufficient as some tolerance may be acceptable. In order to determine a grade, the developed workflow uses the pairwise similarity assessment of two considered reactions, each encoded by a single molecular graph with the help of the Condensed Graph of Reaction (CGR) approach. This workflow is part of the ChemMoodle project and is implemented as a Moodle Plugin. It uses the Chemdoodle engine for reaction drawing and visualization and communicates with a REST server calculating the similarity score using ISIDA fragment descriptors. The plugin is open-source, accessible in GitHub (https:// github. com/ Labor atoirede-Chemo infor matiq ue/ moodle-qtype_ reacs imila rity) and on the Moodle plugin store (https:// moodle. org/ plugi ns/ qtype_ reacs imila rity? lang= en). Both similarity measures and fragmentation can be configured.
De Novo Drug Design – Do We Really Want to Be “Original”?
Maxim Shevelev, Dragos Horvath, Gilles Marcou, Alexandre Varnek
Lecture Notes in Computer Science, 2024, Artificial Neural Networks and Machine Learning – ICANN 2024 33rd International Conference on Artificial Neural Networks, Lugano, Switzerland, September 17–20, 2024, Proceedings, Part X, 15025, pp.15 - 30. ⟨10.1007/978-3-031-72359-9_2⟩
Article dans une revueAbstractAn Attention-basesd Conditional Variational Autoencoder (ACoVAE) architecture was employed to generate novel putative colchicine site binders of tubulin. Generation relied on commercially available "seed" compounds, predicted to be active according to a QSAR model calibrated on the pertinent structureactivity data for this key anti-cancer target. This QSAR model followed by docking served to score the generated compounds in terms of their propensity to bind tubulin. Generated compounds included many molecules matching the structural patterns seen in the seed compounds and closely related to other commercially available compounds. Four of the latter were used for a soaking experiment of tubulin crystals, with no success. Genuinely original and intriguing molecules were also generated by the ACoVAE, some containing the "iconic" seven-membered ring typical of colchicine, albeit this was not seen in the seed compounds. However, these compounds are difficult to synthesize, and project partners considered the trustworthiness of the models that selected them to be insufficient to justify the high synthesis costs. This highlights the actual bottleneck limiting the breakthrough of de novo compound design: the in silico scoring and assessment of the candidate compounds.
Meta-GTM: Visualization and Analysis of the Chemical Library Space
Regina Pikalyova, Yuliana Zabolotna, Dragos Horvath, Gilles Marcou, Alexandre Varnek
Journal of Chemical Information and Modeling, 2023, 63 (17), pp.5571-5582. ⟨10.1021/acs.jcim.3c00719⟩
Article dans une revueGENERA: A Combined Genetic/Deep-Learning Algorithm for Multiobjective Target-Oriented De Novo Design
Giuseppe Lamanna, Pietro Delre, Gilles Marcou, Michele Saviano, Alexandre Varnek, Dragos Horvath, Giuseppe Felice Mangiatordi
Journal of Chemical Information and Modeling, 2023, 63 (16), pp.5107-5119. ⟨10.1021/acs.jcim.3c00963⟩
Article dans une revueAbstractThis study introduces a new de novo design algorithm called GENERA that combines the capabilities of a deep-learning algorithm for automated drug-like analogue design, called DeLA-Drug, with a genetic algorithm for generating molecules with desired target-oriented properties. Specifically, GENERA was applied to the angiotensin-converting enzyme 2 (ACE2) target, which is implicated in many pathological conditions, including COVID-19. The ability of GENERA to de novo design promising candidates for a specific target was assessed using two docking programs, PLANTS and GLIDE. A fitness function based on the Pareto dominance resulting from computed PLANTS and GLIDE scores was applied to demonstrate the algorithm’s ability to perform multiobjective optimizations effectively. GENERA can quickly generate focused libraries that produce better scores compared to a starting set of known ACE-2 binders. This study is the first to utilize a DL-based algorithm designed for analogue generation as a mutational operator within a GA framework, representing an innovative approach to target-oriented de novo design.
French dispatch: GTM‐based analysis of the Chimiothèque Nationale Chemical Space
Polina Oleneva, Yuliana Zabolotna, Dragos Horvath, Gilles Marcou, Fanny Bonachera, Alexandre Varnek
Molecular Informatics, 2023, 42 (4), pp.2200208. ⟨10.1002/minf.202200208⟩
Article dans une revueChemical Library Space: Definition and DNA-Encoded Library Comparison Study Case
Regina Pikalyova, Yuliana Zabolotna, Dragos Horvath, Gilles Marcou, Alexandre Varnek
Journal of Chemical Information and Modeling, 2023, 63 (13), pp.4042-4055. ⟨10.1021/acs.jcim.3c00520⟩
Article dans une revueAbstractThe development of DNA-encoded library (DEL) technology introduced new challenges for the analysis of chemical libraries. It is often useful to consider a chemical library as a standalone chemoinformatic object represented both as a collection of independent molecules, and yet an individual entity in particular, when they are inseparable mixtures, like DELs. Herein, we introduce the concept of chemical library space (CLS), in which resident items are individual chemical libraries. We define and compare four vectorial library representations obtained using generative topographic mapping. These allow for an effective comparison of libraries, with the ability to tune and chemically interpret the similarity relationships. In particular, property-tuned CLS encodings enable us to simultaneously compare libraries with respect to both property and chemotype distributions. We apply the various CLS encodings for the selection problem of DELs that optimally "match" a reference collection (here ChEMBL28), showing how the choice of the CLS descriptors may help to fine-tune the "matching" (overlap) criteria. Hence, the proposed CLS may represent a new efficient way for polyvalent analysis of thousands of chemical libraries. Selection of an easily accessible compound collection for drug discovery, as a substitute for a difficult to produce reference library, can be tuned for either primary or target-focused screening, also considering property distributions of compounds. Alternatively, selection of libraries covering novel regions of the chemical space with respect to a reference compound subspace may serve for library portfolio enrichment. on the Virtual Screening Web Server of the Laboratory of 178 Chemoinformatics at the University of Strasbourg, using the 179 ChemAxon Standardizer. 11 This procedure included dearoma-180 tization and final aromatization (heterocycles like pyridone are 181 not aromatized), dealkalization, conversion to canonical 182 SMILES, removal of salts and mixtures, neutralization of all 183 species except nitrogen(IV), and generation of the major 184 tautomer according to ChemAxon. It resulted in 1,853,565 185 unique ChEMBL compounds. This set is extremely diverse: for 186 example, molecular mass spans a range between 7 (Li + , a 187 normorhythmic agent) and 2255 g/mol. In principle, there is
Computational Approaches to the Rational Design of Tubulin-Targeting Agents
Helena Pérez-Peña, Anne-Catherine Abel, Maxim Shevelev, Andrea Prota, Stefano Pieraccini, Dragos Horvath
Biomolecules, 2023, 13 (2), pp.285. ⟨10.3390/biom13020285⟩
Article dans une revueAbstractMicrotubules are highly dynamic polymers of α,β-tubulin dimers which play an essential role in numerous cellular processes such as cell proliferation and intracellular transport, making them an attractive target for cancer and neurodegeneration research. To date, a large number of known tubulin binders were derived from natural products, while only one was developed by rational structure-based drug design. Several of these tubulin binders show promising in vitro profiles while presenting unacceptable off-target effects when tested in patients. Therefore, there is a continuing demand for the discovery of safer and more efficient tubulin-targeting agents. Since tubulin structural data is readily available, the employment of computer-aided design techniques can be a key element to focus on the relevant chemical space and guide the design process. Due to the high diversity and quantity of structural data available, we compiled here a guide to the accessible tubulin-ligand structures. Furthermore, we review different ligand and structure-based methods recently used for the successful selection and design of new tubulin-targeting agents.
Maytansinol Functionalization: Towards Useful Probes for Studying Microtubule Dynamics
Zlata Boiarska, Helena Pérez-Peña, Anne‐catherine Abel, Paola Marzullo, Beatriz Álvarez‐bernad, Francesca Bonato, Benedetta Santini, Dragos Horvath, Daniel Lucena‐agell, Francesca Vasile, Maurizio Sironi, J. Fernando Díaz, Andrea E Prota, Stefano Pieraccini, Daniele Passarella
Chemistry - A European Journal, 2022, 29 (5), pp.e202203431. ⟨10.1002/chem.202203431⟩
Article dans une revueAbstractMaytansinoids are a successful class of natural and semisynthetic tubulin binders, known for their potent cytotoxic activity. Their wider application as cytotoxins and chemical probes to study tubulin dynamics has been held back by the complexity of natural product chemistry. Here we report the synthesis of long‐chain derivatives and maytansinoid conjugates. We confirmed that bulky substituents do not impact their high activity or the scaffold's binding mode. These encouraging results open new avenues for the design of new maytansine‐based probes.
Inverse QSAR: Reversing Descriptor-Driven Prediction Pipeline Using Attention-Based Conditional Variational Autoencoder
William Bort, Daniyar Mazitov, Dragos Horvath, Fanny Bonachera, Arkadii Lin, Gilles Marcou, Igor Baskin, Timur Madzhidov, Alexandre Varnek
Journal of Chemical Information and Modeling, 2022, 62 (22), pp.5471-5484. ⟨10.1021/acs.jcim.2c01086⟩
Article dans une revueAbstractTo better formalize the notorious inverse-QSAR problem (finding structures of given QSAR-predicted properties) is considered in this paper as a two-step process including (i) finding "seed" descriptor vectors corresponding to user-constrained QSAR model output values and (ii) identifying the chemical structures best matching the "seed" vectors. The main development effort here was focused on the latter stage, proposing a new attentionbased conditional variational autoencoder neural-network architecture based on recent developments in attention-based methods. The obtained results show that this workflow was capable of generating compounds predicted to display desired activity while being completely novel compared to the training database (ChEMBL). Moreover, the generated compounds show acceptable druglikeness and synthetic accessibility. Both pharmacophore and docking studies were carried out as "orthogonal" in silico validation methods, proving that some of de novo structures are, beyond being predicted active by 2D-QSAR models, clearly able to match binding 3D pharmacophores and bind the protein pocket. given in Supporting Information, Figures S1 (training 180 stage) and S2 (inference stage). During the training, a 181
Implementation of a soft grading system for chemistry in a Moodle plugin
Louis Plyer, Gilles Marcou, Céline Perves, Rachel Schurhammer, Alexandre Varnek
Journal of Cheminformatics, 2022, 14 (1), pp.72. ⟨10.1186/s13321-022-00645-0⟩
Article dans une revueAbstractWe 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.
Chemspace Atlas: Multiscale Chemography of Ultralarge Libraries for Drug Discovery
Yuliana Zabolotna, Fanny Bonachera, Dragos Horvath, Arkadii Lin, Gilles Marcou, Olga Klimchuk, Alexandre Varnek
Journal of Chemical Information and Modeling, 2022, 62 (18), pp.4537-4548. ⟨10.1021/acs.jcim.2c00509⟩
Article dans une revueAbstractNowadays, drug discovery is inevitably intertwined with the usage of large compound collections. Understanding of their chemotype composition and physicochemical property profiles is of the highest importance for successful hit identification. Efficient polyfunctional tools allowing multifaceted analysis of constantly growing chemical libraries must be Big Data-compatible. Here, we present the freely accessible ChemSpace Atlas (https://chematlas.chimie.unistra.fr), which includes almost 40K hierarchically organized Generative Topographic Maps (GTM) accommodating up to 500 M compounds covering fragment-like, lead-like, drug-like, PPI-like, and NP-like chemical subspaces. They allow users to navigate and analyze ZINC, ChEMBL, and COCONUT from multiple perspectives on different scales: from a bird's eye view of the entire library to structural pattern detection in small clusters. Around 20 physicochemical properties and almost 750 biological activities can be visualized (associated with map zones), supporting activity profiling and analogue search. Moreover, ChemScape Atlas will be extended toward new chemical subspaces (e.g., DNA-encoded libraries and synthons) and functionalities (ADMETox profiling and property-guided de novo compound generation).
Molecular Similarity Perception Based on Machine-Learning Models
Enrico Gandini, Gilles Marcou, Fanny Bonachera, Alexandre Varnek, Stefano Pieraccini, Maurizio Sironi
International Journal of Molecular Sciences, 2022, 23 (11), pp.6114. ⟨10.3390/ijms23116114⟩
Article dans une revueAbstractMolecular similarity is an impressively broad topic with many implications in several areas of chemistry. Its roots lie in the paradigm that 'similar molecules have similar properties'. For this reason, methods for determining molecular similarity find wide application in pharmaceutical companies, e.g., in the context of structure-activity relationships. The similarity evaluation is also used in the field of chemical legislation, specifically in the procedure to judge if a new molecule can obtain the status of orphan drug with the consequent financial benefits. For this procedure, the European Medicines Agency uses experts' judgments. It is clear that the perception of the similarity depends on the observer, so the development of models to reproduce the human perception is useful. In this paper, we built models using both 2D fingerprints and 3D descriptors, i.e., molecular shape and pharmacophore descriptors. The proposed models were also evaluated by constructing a dataset of pairs of molecules which was submitted to a group of experts for the similarity judgment. The proposed machine-learning models can be useful to reduce or assist human efforts in future evaluations. For this reason, the new molecules dataset and an online tool for molecular similarity estimation have been made freely available.
Toward in Silico Modeling of Dynamic Combinatorial Libraries
Iuri Casciuc, Artem Osypenko, Bohdan Kozibroda, Dragos Horvath, Gilles Marcou, Fanny Bonachera, Alexandre Varnek, Jean-Marie Lehn
ACS Central Science, 2022, 8 (6), pp.804-813. ⟨10.1021/acscentsci.2c00048⟩
Article dans une revueAbstractDynamic combinatorial libraries (DCLs) display adaptive behavior, enabled by the reversible generation of their molecular constituents from building blocks, in response to external effectors, e.g., protein receptors. So far, chemoinformatics has not yet been used for the design of DCLswhich comprise a radically different set of challenges compared to classical library design. Here, we propose a chemoinformatic model for theoretically assessing the composition of DCLs in the presence and the absence of an effector. An imine-based DCL in interaction with the effector human carbonic anhydrase II (CA II) served as a case study. Support vector regression models for the imine formation constants and imine-CA II binding were derived from, respectively, a set of 276 imines synthesized and experimentally studied in this work and 4350 inhibitors of CA II from ChEMBL. These models predict constants for all DCL constituents, to feed software assessing equilibrium concentrations. They are publicly available on the dedicated website. Models rationally selected two amines and two aldehydes predicted to yield stable imines with high affinity for CA II and provided a virtual illustration on how effector affinity regulates DCL members.
A Close-up Look at the Chemical Space of Commercially Available Building Blocks for Medicinal Chemistry
Yuliana Zabolotna, Dmitriy Volochnyuk, Sergey Ryabukhin, Dragos Horvath, Konstantin Gavrilenko, Gilles Marcou, Yurii Moroz, Oleksandr Oksiuta, Alexandre Varnek
Journal of Chemical Information and Modeling, 2022, 62 (9), pp.2171-2185. ⟨10.1021/acs.jcim.1c00811⟩
Article dans une revueHIV-1 drug resistance profiling using amino acid sequence space cartography
Karina Pikalyova, Alexey Orlov, Arkadii Lin, Olga Tarasova, Gilles Marcou, Dragos Horvath, Vladimir Poroikov, Alexandre Varnek
Bioinformatics, 2022, 38 (8), pp.2307-2314. ⟨10.1093/bioinformatics/btac090⟩
Article dans une revueAbstractAbstract Motivation Human immunodeficiency virus (HIV) drug resistance is a global healthcare issue. The emergence of drug resistance influenced the efficacy of treatment regimens, thus stressing the importance of treatment adaptation. Computational methods predicting the drug resistance profile from genomic data of HIV isolates are advantageous for monitoring drug resistance in patients. However, existing computational methods for drug resistance prediction are either not suitable for emerging HIV strains with complex mutational patterns or lack interpretability, which is of paramount importance in clinical practice. The approach reported here overcomes these limitations and combines high accuracy of predictions and interpretability of the models. Results In this work, a new methodology based on generative topographic mapping (GTM) for biological sequence space representation and quantitative genotype–phenotype relationships prediction purposes was introduced. The GTM-based resistance landscapes allowed us to predict the resistance of HIV strains based on sequencing and drug resistance data for three viral proteins [integrase (IN), protease (PR) and reverse transcriptase (RT)] from Stanford HIV drug resistance database. The average balanced accuracy for PR inhibitors was 0.89 ± 0.01, for IN inhibitors 0.85 ± 0.01, for non-nucleoside RT inhibitors 0.73 ± 0.01 and for nucleoside RT inhibitors 0.84 ± 0.01. We have demonstrated in several case studies that GTM-based resistance landscapes are useful for visualization and analysis of sequence space as well as for treatment optimization purposes. Here, GTMs were applied for the in-depth analysis of the relationships between mutation pattern and drug resistance using mutation landscapes. This allowed us to predict retrospectively the importance of the presence of particular mutations (e.g. V32I, L10F and L33F in HIV PR) for the resistance development. This study highlights some perspectives of GTM applications in clinical informatics and particularly in the field of sequence space exploration. Availability and implementation https://github.com/karinapikalyova/ISIDASeq. Supplementary information Supplementary data are available at Bioinformatics online.
Exploration of the Chemical Space of DNA‐encoded Libraries
Regina Pikalyova, Yuliana Zabolotna, Dmitriy Volochnyuk, Dragos Horvath, Gilles Marcou, Alexandre Varnek
Molecular Informatics, 2022, 41 (6), pp.2100289. ⟨10.1002/minf.202100289⟩
Article dans une revueComputational screening methodology identifies effective solvents for CO2 capture
Alexey Orlov, Alain Valtz, Christophe Coquelet, Xavier Rozanska, Erich Wimmer, Gilles Marcou, Dragos Horvath, Bénédicte Poulain, Alexandre Varnek, Frédérick de Meyer
Communications Chemistry, 2022, 5 (1), pp.37. ⟨10.1038/s42004-022-00654-y⟩
Article dans une revueAbstractCarbon capture and storage technologies are projected to increasingly contribute to cleaner energy transitions by significantly reducing CO<sub>2</sub>emissions from fossil fuel-driven power and industrial plants. The industry standard technology for CO<sub>2</sub> capture is chemical absorption with aqueous alkanolamines, which are often being mixed with an activator, piperazine, to increase the overall CO<sub>2</sub> 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<sub>2</sub> faster than a typical commercial solvent when mixed with piperazine, which was confirmed experimentally.
Rapid Discrimination of Neuromyelitis Optica Spectrum Disorder and Multiple Sclerosis Using Machine Learning on Infrared Spectra of Sera
Youssef El Khoury, Marie Gebelin, Jerome de Seze, Christine Patte-Mensah, Gilles Marcou, Alexandre Varnek, Ayikoe-Guy Mensah-Nyagan, Petra Hellwig, Nicolas Collongues
International Journal of Molecular Sciences, 2022, 23 (5), pp.2791. ⟨10.3390/ijms23052791⟩
Article dans une revueAbstractNeuromyelitis optica spectrum disorder (NMOSD) and multiple sclerosis (MS) are both autoimmune inflammatory and demyelinating diseases of the central nervous system. NMOSD is a highly disabling disease and rapid introduction of the appropriate treatment at the acute phase is crucial to prevent sequelae. Specific criteria were established in 2015 and provide keys to distinguish NMOSD and MS. One of the most reliable criteria for NMOSD diagnosis is detection in patient’s serum of an antibody that attacks the water channel aquaporin-4 (AQP-4). Another target in NMOSD is myelin oligodendrocyte glycoprotein (MOG), delineating a new spectrum of diseases called MOG-associated diseases. Lastly, patients with NMOSD can be negative for both AQP-4 and MOG antibodies. At disease onset, NMOSD symptoms are very similar to MS symptoms from a clinical and radiological perspective. Thus, at first episode, given the urgency of starting the anti-inflammatory treatment, there is an unmet need to differentiate NMOSD subtypes from MS. Here, we used Fourier transform infrared spectroscopy in combination with a machine learning algorithm with the aim of distinguishing the infrared signatures of sera of a first episode of NMOSD from those of a first episode of relapsing-remitting MS, as well as from those of healthy subjects and patients with chronic inflammatory demyelinating polyneuropathy. Our results showed that NMOSD patients were distinguished from MS patients and healthy subjects with a sensitivity of 100% and a specificity of 100%. We also discuss the distinction between the different NMOSD serostatuses. The coupling of infrared spectroscopy of sera to machine learning is a promising cost-effective, rapid and reliable differential diagnosis tool capable of helping to gain valuable time in patients’ treatment.
In Vitro Evaluation of In Silico Screening Approaches in Search for Selective ACE2 Binding Chemical Probes
Alexey V Rayevsky, Andrii S Poturai, Iryna O Kravets, Alexander E Pashenko, Tatiana A Borisova, Ganna M Tolstanova, Dmitriy M Volochnyuk, Petro O Borysko, Olga B Vadzyuk, Diana O Alieksieieva, Yuliana Zabolotna, Olga Klimchuk, Dragos Horvath, Gilles Marcou, Sergey V Ryabukhin, Alexandre Varnek
Molecules, 2022, 27 (17), pp.5400. ⟨10.3390/molecules27175400⟩
Article dans une revueAbstractNew 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.
Discovery of novel chemical reactions by deep generative recurrent neural network
William Bort, Igor Baskin, Timur Gimadiev, Artem Mukanov, Ramil Nugmanov, Pavel Sidorov, Gilles Marcou, Dragos Horvath, Olga Klimchuk, Timur Madzhidov, Alexandre Varnek
Scientific Reports, 2021, 11 (1), ⟨10.1038/s41598-021-81889-y⟩
Article dans une revueAbstractThe “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 esired 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.
Chemoinformatics-Driven Design of New Physical Solvents for Selective CO 2 Absorption
Alexey Orlov, Daryna Yu. Demenko, Charles Bignaud, Alain Valtz, Gilles Marcou, Dragos Horvath, Christophe Coquelet, Alexandre Varnek, Frédérick de Meyer
Environmental Science and Technology, 2021, 55 (22), pp.15542-15553. ⟨10.1021/acs.est.1c04092⟩
Article dans une revueSynthI: A New Open-Source Tool for Synthon-Based Library Design
Yuliana Zabolotna, Dmitriy M. Volochnyuk, Sergey V. Ryabukhin, Kostiantyn Gavrylenko, Dragos Horvath, Olga Klimchuk, Oleksandr Oksiuta, Gilles Marcou, Alexandre Varnek
Journal of Chemical Information and Modeling, 2021, 62 (9), pp.2151-2163. ⟨10.1021/acs.jcim.1c00754⟩
Article dans une revueNP Navigator: A New Look at the Natural Product Chemical Space
Yuliana Zabolotna, Peter Ertl, Dragos Horvath, Fanny Bonachera, Gilles Marcou, Alexandre Varnek
Molecular Informatics, 2021, 40 (9), pp.2100068. ⟨10.1002/minf.202100068⟩
Article dans une revueAbstractNatural products (NPs), being evolutionary selected over millions of years to bind to biological macromolecules, remained an important source of inspiration for medicinal chemists even after the advent of efficient drug discovery technologies such as combinatorial chemistry and high-throughput screening. Thus, there is a strong demand for efficient and user-friendly computational tools that allow to analyze large libraries of NPs. In this context, we introduce NP Navigator – a freely available intuitive online tool for visualization and navigation through the chemical space of NPs and NP-like molecules. It is based on the hierarchical ensemble of generative topographic maps, featuring NPs from the COlleCtion of Open NatUral producTs (COCONUT), bioactive compounds from ChEMBL and commercially available molecules from ZINC. NP Navigator allows to efficiently analyze different aspects of NPs - chemotype distribution, physicochemical properties, biological activity and commercial availability of NPs. The latter concerns not only purchasable NPs but also their close analogs that can be considered as synthetic mimetics of NPs or pseudo-NPs.
DMSO Solubility Assessment for Fragment-Based Screening
Shamkhal Baybekov, Gilles Marcou, Pascal Ramos, Olivier Saurel, Jean-Luc Galzi, Alexandre Varnek
Molecules, 2021, 26 (13), pp.3950. ⟨10.3390/molecules26133950⟩
Article dans une revueAbstractIn 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.
CATMoS: Collaborative Acute Toxicity Modeling Suite
Kamel Mansouri, Agnes L. Karmaus, Jeremy Fitzpatrick, Grace Patlewicz, Prachi Pradeep, Domenico Alberga, Nathalie Alepee, Timothy E.H. Allen, Dave Allen, Vinicius M. Alves, Carolina H. Andrade, Tyler R. Auernhammer, Davide Ballabio, Shannon Bell, Emilio Benfenati, Sudin Bhattacharya, Joyce V. Bastos, Stephen Boyd, J.B. Brown, Stephen J. Capuzzi, Yaroslav Chushak, Heather Ciallella, Alex M. Clark, Viviana Consonni, Pankaj R. Daga, Sean Ekins, Sherif Farag, Maxim Fedorov, Denis Fourches, Domenico Gadaleta, Feng Gao, Jeffery M. Gearhart, Garett Goh, Jonathan M. Goodman, Francesca Grisoni, Christopher M. Grulke, Thomas Hartung, Matthew Hirn, Pavel Karpov, Alexandru Korotcov, Giovanna J. Lavado, Michael Lawless, Xinhao Li, Thomas Luechtefeld, Filippo Lunghini, Giuseppe F. Mangiatordi, Gilles Marcou, Dan Marsh, Todd Martin, Andrea Mauri, Eugene N. Muratov, Glenn J. Myatt, Dac-Trung Nguyen, Orazio Nicolotti, Reine Note, Paritosh Pande, Amanda K. Parks, Tyler Peryea, Ahsan H. Polash, Robert Rallo, Alessandra Roncaglioni, Craig Rowlands, Patricia Ruiz, Daniel P. Russo, Ahmed Sayed, Risa Sayre, Timothy Sheils, Charles Siegel, Arthur C. Silva, Anton Simeonov, Sergey Sosnin, Noel Southall, Judy Strickland, Yun Tang, Brian Teppen, Igor V. Tetko, Dennis Thomas, Valery Tkachenko, Roberto Todeschini, Cosimo Toma, Ignacio Tripodi, Daniela Trisciuzzi, Alexander Tropsha, Alexandre Varnek, Kristijan Vukovic, Zhongyu Wang, Liguo Wang, Katrina M. Waters, Andrew J. Wedlake, Sanjeeva J. Wijeyesakere, Dan Wilson, Zijun Xiao, Hongbin Yang, Gergely Zahoranszky-Kohalmi, Alexey V. Zakharov, Fagen F. Zhang, Zhen Zhang, Tongan Zhao, Hao Zhu, Kimberley M. Zorn, Warren Casey, Nicole C. Kleinstreuer
Environmental Health Perspectives, 2021, 129 (4), pp.047013. ⟨10.1289/EHP8495⟩
Article dans une revueCHEMOGRAPHY: SEARCHING FOR HIDDEN TREASURES
Yuliana Zabolotna, Arkadii Lin, Dragos Horvath, Gilles Marcou, Dmitriy M Volochnyuk, Alexandre Varnek
Journal of Chemical Information and Modeling, 2021, 61 (1), pp.179-188. ⟨10.1021/acs.jcim.0c00936⟩
Article dans une revueAbstractThe days when medicinal chemistry was limited to a few series of compounds of therapeutic interest are long gone. Nowadays, no human may succeed to acquire a complete overview of more than a billion existing or feasible compounds within which the potential “blockbuster drugs” are well hidden and yet only a few mouse clicks away. To reach these “hidden treasures”, we adapted the generative topographic mapping method to enable efficient navigation through the chemical space, from a global overview to a structural pattern detection, covering, for the first time, the complete ZINC library of purchasable compounds, relative to 1.6 million biologically relevant ChEMBL molecules. About 40 000 hierarchical maps of the chemical space were constructed. Structural motifs inherent to only one library were identified. Roughly 20 000 off-market ChEMBL compound families represent incentives to enrich commercial catalogs. Alternatively, 125 000 ZINC-specific compound classes, absent in structure–activity bases, are novel paths to explore in medicinal chemistry. The complete list of these chemotypes can be downloaded using the link https://forms.gle/B6bUJj82t9EfmttV6.
Computer-Aided Design of New Physical Solvents for Hydrogen Sulfide Absorption
Alexey Orlov, Gilles Marcou, Dragos Horvath, Alvaro Echeverria Cabodevilla, Alexandre Varnek, Frédérick de Meyer
Industrial and engineering chemistry research, 2021, 60 (23), pp.8588-8596. ⟨10.1021/acs.iecr.0c05923⟩
Article dans une revueAbstractTreatment of hydrogen sulfide (H2S) is important in many industrial processes including oil refineries, natural and biogas processing, and coal gasification. The most mature technology for the selective capture of H2S is based on its absorption by chemical or physical solvents. However, only several compounds are currently used as physical (co)solvents in industry, and the search for new ones is an important task. The experimental screening of physical (co)solvents requires much time and many resources, while solubility modeling might enable one to reduce the number of solvents for the experimental evaluation. In this study, a workflow for the in silico discovery of new physical solvents for H2S absorption was suggested and experimentally validated. A data set composed of 99 H2S physical solvents was collected and predictive quantitative structure–property relationships for H2S solubility were built using a random forest algorithm and two types of molecular descriptors: ISIDA fragments and quantum-chemical descriptors. Virtual screening of industrially produced chemicals and their structural analogues enabled identification of the ones with predicted high solubility values. They can be suggested as starting points for further exploration of the H2S physical solvents chemical space. The predicted solubility value for one of the compounds found in virtual screening, 1,3-dimethyl-2-imidazolidinone, was confirmed experimentally.
Trustworthiness, the Key to Grid-Based Map-Driven Predictive Model Enhancement and Applicability Domain Control
Dragos Horvath, Gilles Marcou, Alexandre Varnek
Journal of Chemical Information and Modeling, 2020, 60 (12), pp.6020-6032. ⟨10.1021/acs.jcim.0c00998⟩
Article dans une revueParallel Generative Topographic Mapping: an Efficient Approach for Big Data Handling
Arkadii Lin, Igor I. Baskin, Gilles Marcou, Dragos Horvath, Bernd Beck, Alexandre Varnek
Molecular Informatics, 2020, 7th Strasbourg Summer School in Chemoinformatics, 39 (12), pp.2000009. ⟨10.1002/MINF.202000009⟩
Article dans une revueAbstractGenerative Topographic Mapping (GTM) can be efficiently used to visualize, analyze and model large chemical data. The GTM manifold needs to span the chemical space deemed relevant for a given problem. Therefore, the Frame set (FS) of compounds used for the manifold construction must well cover a given chemical space. Intuitively, the FS size must raise with the size and diversity of the target library. At the same time, the GTM training can be very slow or even becomes technically impossible at FS sizes of the order of 10 5 compounds-which is a very small number compared to today's commercially accessible compounds, and, especially, to the theoretically feasible molecules. In order to solve this problem, we propose a Parallel GTM algorithm based on the merging of "intermediate" manifolds constructed in parallel for different subsets of molecules. An ensemble of these subsets forms a FS for the "final" manifold. In order to assess the efficiency of the new algorithm, 80 GTMs were built on the FSs of different sizes ranging from 10 to 1.8 M compounds selected from the ChEMBL database. Each GTM was challenged to build classification models for up to 712 biological activities (depending on the FS size). With the novel parallel GTM procedure, we could thus cover the entire spectrum of possible FS sizes, whereas previous studies were forced to rely on the working hypothesis that FS sizes of few thousands of compounds are sufficient to describe the ChEMBL chemical space. In fact, this study formally proves this to be true: a FS containing only 5000 randomly picked compounds is sufficient to represent the entire ChEMBL collection (1.8 M molecules), in the sense that a further increase of FS compound numbers has no benefice impact on the predictive propensity of the above-mentioned 712 activity classification models. Parallel GTM may, however, be required to generate maps based on very large FS, that might improve chemical space cartography of big commercial and virtual libraries, approaching billions of compounds
Visualization and Analysis of the REACH‐chemical Space with Generative Topographic Mapping
Filippo Lunghini, Gilles Marcou, Philippe Azam, Marie‐hélène Enrici, Erik van Miert, Alexandre Varnek
Molecular Informatics, 2020, 40 (4), pp.2000232. ⟨10.1002/minf.202000232⟩
Article dans une revueConsensus QSAR models estimating acute toxicity to aquatic organisms from different trophic levels: algae, Daphnia and fish
Filippo Lunghini, Gilles Marcou, P. Azam, M.H. Enrici, E. van Miert, Alexandre Varnek
SAR and QSAR in Environmental Research, 2020, 31 (9), pp.655-675. ⟨10.1080/1062936X.2020.1797872⟩
Article dans une revueAbstractWe report new consensus models estimating acute toxicity for algae, Daphnia and fish endpoints. We assembled a large collection of 3680 public unique compounds annotated by, at least, one experimental value for the given endpoint. Support Vector Machine models were internally and externally validated following the OECD principles. Reasonable predictive performances were achieved (RMSEext = 0.56–0.78) which are in line with those of state-of-the-art models. The known structural alerts are compared with analysis of the atomic contributions to these models obtained using the ISIDA/ColorAtom utility. A benchmarking against existing tools has been carried out on a set of compounds considered more representative and relevant for the chemical space of the current chemical industry. Our model scored one of the best accuracy and data coverage. Nevertheless, industrial data performances were noticeably lower than those on public data, indicating that existing models fail to meet the industrial needs. Thus, final models were updated with the inclusion of new industrial compounds, extending the applicability domain and relevance for application in an industrial context. Generated models and collected public data are made freely available.
Autoignition temperature: comprehensive data analysis and predictive models
I.I. Baskin, S. Lozano, M. Durot, G. Marcou, Dragos Horvath, A. Varnek
SAR and QSAR in Environmental Research, 2020, 31 (8), pp.597-613. ⟨10.1080/1062936X.2020.1785933⟩
Article dans une revueAbstractHere we report a new predictive model for autoignition temperature (AIT), an important physical parameter widely used to assess potential safety hazards of combustible materials. Available structure -AIT data extracted from different sources were critically analysed. Support vector regression (SVR) models on different data subsets were built in order to identify a reliable compound set on which a realistic model could be built. This led to a selection of the dataset containing 875 compounds annotated with AIT values. The thereupon-based SVR model performs reasonably well in cross-validation with the determination coefficient r 2 = 0.77 and mean absolute error MAE = 37.8°C. External validation on 20 industrial compounds missing in the training set confirmed its good predic-tive power (MAE = 28.7°C). ARTICLE HISTORY
Publicly available QSPR models for environmental media persistence
Filippo Lunghini, Gilles Marcou, P. Azam, M.H. Enrici, E. van Miert, Alexandre Varnek
SAR and QSAR in Environmental Research, 2020, 31 (7), pp.493-510. ⟨10.1080/1062936X.2020.1776387⟩
Article dans une revue“Big Data” Fast Chemoinformatics Model to Predict Generalized Born Radius and Solvent Accessibility as a Function of Geometry
Dragos Horvath, Gilles Marcou, Alexandre Varnek
Journal of Chemical Information and Modeling, 2020, 60 (6), pp.2951-2965. ⟨10.1021/ACS.JCIM.9B01172⟩
Article dans une revueAbstractThe Generalized Born (GB) solvent model is offering the best accuracy/computing effort ratio yet requires drastic simplifications to estimate of the Effective Born Radii (EBR) in bypassing a too expensive volume integration step. EBRs are a measure of the degree of burial of an atom and not very sensitive to small changes of geometry: in molecular dynamics, the costly EBR update procedure is not mandatory at every step. This work however aims at implementing a GB model into the Sampler for Multiple Protein−Ligand Entities (S4MPLE) evolutionary algorithm with mandatory EBR updates at each step triggering arbitrarily large geometric changes. Therefore, a quantitative structure−property relationship has been developed in order to express the EBRs as a linear function of both the topological neighborhood and geometric occupancy of the space around atoms. A training set of 810 molecular systems, starting from fragment-like to drug-like compounds, proteins, host−guest systems, and ligand−protein complexes, has been compiled. For each species, S4MPLE generated several hundreds of random conformers. For each atom in each geometry of each species, its "standard" EBR was calculated by numeric integration and associated to topological and geometric descriptors of the atom neighborhood. This training set (EBR, atom descriptors) involving >5 M entries was subjected to a boot-strapping multilinear regression process with descriptor selection. In parallel, the strategy was repurposed to also learn atomic solvent-accessible areas (SA) based on the same descriptors. Resulting linear equations were challenged to predict EBR and SA values for a similarly compiled external set of >2000 new molecular systems. Solvation energies calculated with estimated EBR and SA match "standard" energies within the typical error of a force-field-based approach (a few kilocalories per mole). Given the extreme diversity of molecular systems covered by the model, this simple EBR/SA estimator covers a vast applicability domain.
Application of the mol2vec Technology to Large‐size Data Visualization and Analysis
Shojiro Shibayama, Gilles Marcou, Dragos Horvath, Igor I. Baskin, Kimito Funatsu, Alexandre Varnek
Molecular Informatics, 2020, 39 (6), pp.1900170. ⟨10.1002/MINF.201900170⟩
Article dans une revueA Chemographic Audit of anti‐Coronavirus Structure‐Activity Information from Public Databases (ChEMBL)
Dragos Horvath, Alexey Orlov, Dmitry I. Osolodkin, Aydar A Ishmukhametov, Gilles Marcou, Alexandre Varnek
Molecular Informatics, 2020, 39 (12), ⟨10.1002/MINF.202000080⟩
Article dans une revueAbstractDiscovery of drugs against newly emerged pathogenic agents like the SARS-CoV-2 coronavirus (CoV) must be based on previous research against related species. Scientists need to get acquainted with and develop a global oversight over so-far tested molecules. Chemography (here-in used Generative Topographic Mapping, in particular) places structures on a human-readable 2D map (obtained by dimensionality reduction of the chemical space of molecular descriptors) and is thus well suited for such an audit. The goal is to map medicinal chemistry efforts so far targeted against CoVs. This includes comparing libraries tested against various virus species/genera, predicting their polypharmacological profiles and highlighting often encountered chemotypes. Maps are challenged to provide predictive activity landscapes against viral proteins. Definition of "anti-CoV" map zones led to selection of therein residing 380 potential anti-CoV agents, out of a vast pool of 800 M organic compounds.
Modelling of ready biodegradability based on combined public and industrial data sources
F. Lunghini, G. Marcou, P. Gantzer, P. Azam, Dragos Horvath, E. van Miert, A. Varnek
SAR and QSAR in Environmental Research, 2020, 31 (3), pp.171-186. ⟨10.1080/1062936X.2019.1697360⟩
Article dans une revueAbstractThe European Registration, Evaluation, Authorization and Restriction of Chemical Substances Regulation, requires marketed chemicals to be evaluated for Ready Biodegradability (RB), considering in silico prediction as valid alternative to experimental testing. However, currently available models may not be relevant to predict compounds of industrial interest, due to accuracy and applicability domain restriction issues. In this work, we present a new and extended RB dataset (2830 compounds), issued by the merging of several public data sources. It was used to train classification models, which were externally validated and benchmarked against already-existing tools on a set of 316 compounds coming from the industrial context. New models showed good performances in terms of predictive power (Balance Accuracy (BA) = 0.74-0.79) and data coverage (83-91%). The Generative Topographic Mapping approach identified several chemotypes and structural motifs unique to the industrial dataset, highlighting for which chemical classes currently available models may have less reliable predictions. Finally, public and industrial data were merged into global dataset containing 3146 compounds. This is the biggest dataset reported in the literature so far, covering some chemotypes absent in the public data. Thus, predictive model developed on the Global dataset has larger applicability domain than the existing ones. ARTICLE HISTORY
CoMPARA: Collaborative Modeling Project for Androgen Receptor Activity
Kamel Mansouri, Nicole Kleinstreuer, Ahmed Abdelaziz, Domenico Alberga, Vinicius Alves, Patrik Andersson, Carolina Andrade, Fang Bai, Ilya Balabin, Davide Ballabio, Emilio Benfenati, Barun Bhhatarai, Scott Boyer, Jingwen Chen, Viviana Consonni, Sherif Farag, Denis Fourches, Alfonso García-Sosa, Paola Gramatica, Francesca Grisoni, Chris Grulke, Huixiao Hong, Dragos Horvath, Xin Hu, Ruili Huang, Nina Jeliazkova, Jiazhong Li, Xuehua Li, Huanxiang Liu, Serena Manganelli, Giuseppe Mangiatordi, Uko Maran, Gilles Marcou, Todd Martin, Eugene Muratov, Dac-Trung Nguyen, Orazio Nicolotti, Nikolai Nikolov, Ulf Norinder, Ester Papa, Michel Petitjean, Geven Piir, Pavel Pogodin, Vladimir Poroikov, Xianliang Qiao, Ann Richard, Alessandra Roncaglioni, Patricia Ruiz, Chetan Rupakheti, Sugunadevi Sakkiah, Alessandro Sangion, Karl-Werner Schramm, Chandrabose Selvaraj, Imran Shah, Sulev Sild, Lixia Sun, Olivier Taboureau, Yun Tang, Igor V. Tetko, Roberto Todeschini, Weida Tong, Daniela Trisciuzzi, Alexander Tropsha, George van den Driessche, Alexandre Varnek, Zhongyu Wang, Eva Wedebye, Antony Williams, Hongbin Xie, Alexey Zakharov, Ziye Zheng, Richard Judson
Environmental Health Perspectives, 2020, 128 (2), pp.027002. ⟨10.1289/EHP5580⟩
Article dans une revueAbstractBACKGROUND: Endocrine disrupting chemicals (EDCs) are xenobiotics that mimic the interaction of natural hormones and alter synthesis, transport, or metabolic pathways. The prospect of EDCs causing adverse health effects in humans and wildlife has led to the development of scientific and regulatory approaches for evaluating bioactivity. This need is being addressed using high-throughput screening (HTS) in vitro approaches and computational modeling. OBJECTIVES: In support of the Endocrine Disruptor Screening Program, the U.S. Environmental Protection Agency (EPA) led two worldwide consortiums to virtually screen chemicals for their potential estrogenic and androgenic activities. Here, we describe the Collaborative Modeling Project for Androgen Receptor Activity (CoMPARA) efforts, which follows the steps of the Collaborative Estrogen Receptor Activity Prediction Project (CERAPP). METHODS: The CoMPARA list of screened chemicals built on CERAPP's list of 32,464 chemicals to include additional chemicals of interest, as well as simulated ToxCastTM metabolites, totaling 55,450 chemical structures. Computational toxicology scientists from 25 international groups contributed 91 predictive models for binding, agonist, and antagonist activity predictions. Models were underpinned by a common training set of 1,746 chemicals compiled from a combined data set of 11 ToxCastTM/Tox21 HTS in vitro assays. RESULTS: The resulting models were evaluated using curated literature data extracted from different sources. To overcome the limitations of single-model approaches, CoMPARA predictions were combined into consensus models that provided averaged predictive accuracy of approximately 80% for the evaluation set. DISCUSSION: The strengths and limitations of the consensus predictions were discussed with example chemicals; then, the models were implemented into the free and open-source OPERA application to enable screening of new chemicals with a defined applicability domain and accuracy assessment. This implementation was used to screen the entire EPA DSSTox database of ~ 875,000 chemicals, and their predicted AR activities have been made available on the EPA CompTox Chemicals dashboard and National Toxicology Program's Integrated Chemical Environment.
Consensus models to predict oral rat acute toxicity and validation on a dataset coming from the industrial context
F. Lunghini, G. Marcou, P. Azam, Dragos Horvath, R. Patoux, E. van Miert, A. Varnek
SAR and QSAR in Environmental Research, 2019, 30 (12), pp.879-897. ⟨10.1080/1062936X.2019.1672089⟩
Article dans une revueAbstractWe report predictive models of acute oral systemic toxicity representing a follow-up of our previous work in the framework of the NICEATM project. It includes the update of original models through the addition of new data and an external validation of the models using a dataset relevant for the chemical industry context. A regression model for LD 50 and multi-class classification model for toxicity classes according to the Global Harmonized System categories were prepared. ISIDA descrip-tors were used to encode molecular structures. Machine learning algorithms included support vector machine (SVM), random forest (RF) and naïve Bayesian. Selected individual models were combined in consensus. The different datasets were compared using the generative topo-graphic mapping approach. It appeared that the NICEATM datasets were lacking some relevant chemotypes for chemical industry. The new models trained on enlarged data sets have applicability domains (AD) sufficiently large to accommodate industrial compounds. The fraction of compounds inside the models' AD increased from 58% (NICEATM model) to 94% (new model). The increase of training sets improved models' prediction performance: RMSE values decreased from 0.56 to 0.47 and balanced accuracies increased from 0.69 to 0.71 for NICEATM and new models, respectively. ARTICLE HISTORY
Generative topographic mapping in drug design
Dragos Horvath, Gilles Marcou, Alexandre Varnek
Drug Discovery Today: Technologies, 2019, 32-33, pp.99-107. ⟨10.1016/j.ddtec.2020.06.003⟩
Article dans une revueDiversifying chemical libraries with generative topographic mapping
Arkadii Lin, Bernd Beck, Dragos Horvath, Gilles Marcou, Alexandre Varnek
Journal of Computer-Aided Molecular Design, 2019, 34, pp.805 - 815. ⟨10.1007/s10822-019-00215-x⟩
Article dans une revueAbstractGenerative topographic mapping was used to investigate the possibility to diversify the in-house compounds collection of Boehringer Ingelheim (BI). For this purpose, a 2D map covering the relevant chemical space was trained, and the BI compound library was compared to the Aldrich-Market Select (AMS) database of more than 8M purchasable compounds. In order to discover new (sub)structures, the “AutoZoom” tool was developed and applied in order to analyze chemotypes of molecules residing in heavily populated zones of a map and to extract the corresponding maximum common substructures. A set of 401K new structures from the AMS database was retrieved and checked for drug-likeness and biological activity.
Crystal structure of a xylulose 5-phosphate phosphoketolase. Insights into the substrate specificity for xylulose 5-phosphate
A.J. Scheidig, Dragos Horvath, S.E. Szedlacsek
Journal of Structural Biology, 2019, 207 (1), pp.85-102. ⟨10.1016/j.jsb.2019.04.017⟩
Article dans une revueGenerative Topographic Mapping of the Docking Conformational Space
Dragos Horvath, Gilles Marcou, Alexandre Varnek
Molecules, 2019, 24 (12), pp.2269. ⟨10.3390/molecules24122269⟩
Article dans une revueClassification of Metal Binders by Naïve Bayes Classifier on the Base of Molecular Fragment Descriptors and Ensemble Modeling
Vitaly Solov'Ev, Aslan Tsivadze, Gilles Marcou, Alexandre Varnek
Molecular Informatics, 2019, 38 (6), pp.1900002. ⟨10.1002/minf.201900002⟩
Article dans une revueQSPR models for bioconcentration factor (BCF): are they able to predict data of industrial interest?
F. Lunghini, G. Marcou, P. Azam, R. Patoux, M.H. H Enrici, F. Bonachera, Dragos Horvath, A. Varnek
SAR and QSAR in Environmental Research, 2019, 30 (7), pp.507-524. ⟨10.1080/1062936X.2019.1626278⟩
Article dans une revueAbstractThe bioconcentration factor (BCF), a key parameter required by the REACH regulation, estimates the tendency for a xenobiotic to concentrate inside living organisms. In silico methods can be valid alternatives to costly data measurements. However, in the industrial context, these theoretical approaches may fail to predict BCF with reasonable accuracy. We analyzed whether models built on public data only have adequate performances when challenged to predict industrial compounds. A new set of 1129 compounds has been collected by merging publicly available datasets. Generative Topographic Mapping was employed to compare this chemical space with a set of new compounds issued from the industry. Some new chemotypes absent in the training set (such as siloxanes) have been detected. A new BCF model has been built using ISIDA (In SIlico design and Data Analysis) fragment descrip-tors, support vector regression and random forest machine-learning methods. It has been externally validated on: (i) collected data from the literature and (ii) industrial data. The latter also served as benchmark for the freely available tools VEGA, EPISuite, TEST, OPERA. New model performs (RMSE of 0.58 log BCF units) comparably to existing ones but benefits of an extended applicability , covering the industrial set chemical space (78% data coverage). ARTICLE HISTORY
Prediction of the Glass-Transition Temperatures of Linear Homo/Heteropolymers and Cross-Linked Epoxy Resins
Chisa Higuchi, Dragos Horvath, Gilles Marcou, Kazunari Yoshizawa, Alexandre Varnek
ACS Applied Polymer Materials, 2019, 1 (6), pp.1430-1442. ⟨10.1021/ACSAPM.9B00198⟩
Article dans une revueAbstractThis work proposes a unified approach to predict glass transition temperatures (Tgs) of linear homo/hetero-polymers and cross-linked epoxy resins by machine-learning approaches based on descriptors of reagents undergoing polymerization, represented in a formal way such as to encompass all the three scenarios: linear homo-and heteropolymers, plus network heteropolymers. The "formal" representation of reagents is a problem-specific, herein designed standardization protocol of compounds, sometimes differing from typical structure curation rules in chemoinformatics. For example, heteropolymers are represented by the two partner reagents, while homopolymers are depicted as formal "heteropolymers" with identical partners. The key rule proposed here is to choose "formal" monomers such as to minimize the number of marked atoms, involved in bonds being formed or changing bond order. Accordingly, carbonyl compounds are rendered as the less stable vinyl alcohol tautomer, following the same formalism as in olefin polymerization, in order to minimize the total number of formal polymerization mechanisms and herewith provide the most general framework encompassing a maximum of polymerization processes. ISIDA (In Silico design and Data Analysis) fragment counts with special status given to the "marked atoms" participating in the polymerization process were combined using "mixture" strategies to generate the final polymer descriptors. Three predictive models based on SVR (Support Vector Regression) are discussed here. After reproducing results of Katritzky et al. with a local model applicable only to linear homo/hetero-polymers, an epoxy resin-specific model applicable to both linear and network forms was built. Eventually, the general model applicable to all these families was constructed. In 12 repeated 3-fold cross-validation challenges, it displayed the highest accuracy of Q 2 = 0.920, RMSE = 34.3 K over the training set of 270 polymers, and R 2 = 0.779, RMSE 35.9 K for an external test set of 119 polymers. GTM (Generative Topographic Mapping) analysis produced a 2D map of "polymer chemical space", highlighting the various classes of polymers included in the study and their relationship with respect to Tg values. The epoxy-specific and general models are publicly available on our web server: http://infochim.u-strasbg.fr/webserv/VSEngine.html. 2
Getting to Know the Neighbours with GTM: The Case of Antiviral Compounds
Alexey Orlov, Evgeny V. Khvatov, Alexander A. Koruchekov, Anastasia A. Nikitina, Anastasia D. Zolotareva, Anastasia A. Eletskaya, Liubov Kozlovskaya, Vladimir Palyulin, Dragos Horvath, Dmitry Osolodkin, Alexandre Varnek
Molecular Informatics, 2019, 38 (5), pp.1800166. ⟨10.1002/minf.201800166⟩
Article dans une revuePros and cons of virtual screening based on public “Big Data”: In silico mining for new bromodomain inhibitors
Iuri Casciuc, Dragos Horvath, Anastasiia Gryniukova, Kateryna Tolmachova, Oleksandr Vasylchenko, Petro Borysko, Yurii Moroz, Jürgen Bajorath, Alexandre Varnek
European Journal of Medicinal Chemistry, 2019, 165, pp.258-272. ⟨10.1016/j.ejmech.2019.01.010⟩
Article dans une revueAbstractThe Virtual Screening (VS) study described herein aimed at detecting novel Bromodomain BRD4 binders and relied on knowledge from public databases (ChEMBL, REAXYS) to establish a battery of predictive models of BRD activity for in silico selection of putative ligands. Beyond the actual discovery of new BRD ligands, this represented an opportunity to practically estimate the actual usefulness of public domain "Big Data" for robust predictive model building. Obtained models were used to virtually screen a collection of 2 million compounds from the Enamine company collection. This industrial partner then experimentally screened a subset of 2992 molecules selected by the VS procedure for their high likelihood to be active. Twenty nine confirmed hits were detected after experimental testing, representing 1% of the selected candidates. As a general conclusion, this study emphasizes once more that public structure-activity databases are nowadays key assets in drug discovery. Their usefulness is however limited by the state-of-the-art knowledge harvested so far by published studies. Target-specific structure activity information is rarely rich enough, and its heterogeneity makes it extremely difficult to exploit in rational drug design. Furthermore, published affinity measures serving to build models selecting compounds to be experimentally screened may not be well correlated with the experimental hit selection criterion (in practice, often imposed by equipment constraints). Nevertheless, a robust 2.6-fold increase in hit rate with respect to an equivalent, random screening campaign showed that machine learning is able to extract some real knowledge in spite of all the noise in structure-activity data.
Multi-task generative topographic mapping in virtual screening
Arkadii Lin, Dragos Horvath, Gilles Marcou, Bernd Beck, Alexandre Varnek
Journal of Computer-Aided Molecular Design, 2019, 33 (3), pp.331-343. ⟨10.1007/s10822-019-00188-x⟩
Article dans une revueAbstractThe previously reported procedure to generate “universal” Generative Topographic Maps (GTMs) of the drug-like chemical space is in practice a multi-task learning process, in which both operational GTM parameters (example: map grid size) and hyperparameters (key example: the molecular descriptor space to be used) are being chosen by an evolutionary process in order to fit/select “universal” GTM manifolds. After selection (a one-time task aimed at optimizing the compromise in terms of neighborhood behavior compliance, over a large pool of various biological targets), for any further use the manifolds are ready to provide “fit-free” predictive models. Using any structure–activity set—irrespectively whether the associated target served at map fitting stage or not—the generation or “coloring” a property landscape enables predicting the property for any external molecule, with zero additional fitable parameters involved. While previous works have signaled the excellent behavior of such models in aggressive three-fold cross-validation assessments of their predictive power, the present work wished to explore their behavior in Virtual Screening (VS), here simulated on hand of external DUD ligand and decoy series that are fully disjoint from the ChEMBL-extracted landscape coloring sets. Beyond the rather robust results of the universal GTM manifolds in this challenge, it could be shown that the descriptor spaces selected by the evolutionary multi-task learner were intrinsically able to serve as an excellent support for many other VS procedures, starting from parameter-free similarity searching, to local (target-specific) GTM models, to parameter-rich, nonlinear Random Forest and Neural Network approaches.
Evolution of commercially available compounds for HTS
Dmitriy Volochnyuk, Sergey Ryabukhin, Yurii Moroz, Olena Savych, Alexander Chuprina, Dragos Horvath, Yuliana Zabolotna, Alexandre Varnek, Duncan Judd
Drug Discovery Today, 2019, 24 (2), pp.390-402. ⟨10.1016/j.drudis.2018.10.016⟩
Article dans une revueVirtual Screening with Generative Topographic Maps: How Many Maps Are Required?
Iuri Casciuc, Yuliana Zabolotna, Dragos Horvath, Gilles Marcou, Jürgen Bajorath, Alexandre Varnek
Journal of Chemical Information and Modeling, 2019, 59 (1), pp.564-572. ⟨10.1021/acs.jcim.8b00650⟩
Article dans une revueCovaDOTS: In Silico Chemistry-Driven Tool to Design Covalent Inhibitors Using a Linking Strategy
Laurent Hoffer, Magali Saez-Ayala, Dragos Horvath, Alexandre Varnek, Xavier Morelli, Philippe Roche
Journal of Chemical Information and Modeling, 2019, 59 (4), pp.1472-1485. ⟨10.1021/acs.jcim.8b00960⟩
Article dans une revueAbstractWe recently reported an integrated fragment-based optimization strategy called DOTS (Diversity Oriented Target-focused Synthesis) that combines automated virtual screening (VS) with semirobotized organic synthesis coupled to in vitro evaluation. The molecular modeling part consists of hit-to-lead chemistry, based on the growing paradigm. Here, we have extended the applicability of the DOTS strategy by adding new functionalities, allowing a generic chemistry-driven linking approach with a particular emphasis on covalent drugs. Indeed, the covalent mode of action can be described as a specific case of linking, where suitable linkers are sought to fuse a bound organic compound with a nucleophilic protein side chain. The proof of concept is established using three retrospective study cases in which known noncovalent inhibitors have been converted to covalent inhibitors. Our method is able to automatically design reference covalent inhibitors (and/or analogs) from an initial activated substructure and predict their binding mode. More importantly, the reference compounds are ranked high among several hundred putative adducts, demonstrating the utility of the approach to design covalent inhibitors.
Serum-based differentiation between multiple sclerosis and amyotrophic lateral sclerosis by Random Forest classification of FTIR spectra
Youssef El Khoury, Nicolas Collongues, Jerome de Seze, Vildan Gulsari, Christine Patte-Mensah, Gilles Marcou, Alexandre Varnek, Ayikoé-Guy Mensah-Nyagan, Petra Hellwig
Analyst, 2019, 144 (15), pp.4647-4652. ⟨10.1039/C9AN00754G⟩
Article dans une revueDe Novo Molecular Design by Combining Deep Autoencoder Recurrent Neural Networks with Generative Topographic Mapping
Boris Sattarov, Igor Baskin, Dragos Horvath, Gilles Marcou, Esben Jannik Bjerrum, Alexandre Varnek
Journal of Chemical Information and Modeling, 2018, 59 (3), pp.1182-1196. ⟨10.1021/acs.jcim.8b00751⟩
Article dans une revueAbstractHere we show that Generative Topographic Mapping (GTM) can be used to explore the latent space of the SMILES-based autoencoders and generate focused molecular libraries of interest. We have built a sequence-to-sequence neural network with Bidirectional Long Short-Term Memory layers and trained it on the SMILES strings from ChEMBL23. Very high reconstruction rates of the test set molecules were achieved (>98%), which are comparable to the ones reported in related publications. Using GTM, we have visualized the autoencoder latent space on the two-dimensional topographic map. Targeted map zones can be used for generating novel molecular structures by sampling associated latent space points and decoding them to SMILES. The sampling method based on a genetic algorithm was introduced to optimize compound properties "on the fly". The generated focused molecular libraries were shown to contain original and a priori feasible compounds which, pending actual synthesis and testing, showed encouraging behavior in independent structure-based affinity estimation procedures (pharmacophore matching, docking).
Visualization and Analysis of Complex Reaction Data: The Case of Tautomeric Equilibria
Marta Glavatskikh, Timur Madzhidov, Igor Baskin, Dragos Horvath, Ramil Nugmanov, Timur Gimadiev, Gilles Marcou, Alexandre Varnek
Molecular Informatics, 2018, 37 (9-10), pp.1800056. ⟨10.1002/minf.201800056⟩
Article dans une revueAntiMalarial Mode of Action (AMMA) Database: Data Selection, Verification and Chemical Space Analysis
Pavel Sidorov, Elisabeth Davioud-Charvet, Gilles Marcou, Dragos Horvath, Alexandre Varnek
Molecular Informatics, 2018, 37 (9-10), pp.1800021. ⟨10.1002/minf.201800021⟩
Article dans une revuePredictive Models for Kinetic Parameters of Cycloaddition Reactions
Marta Glavatskikh, Timur Madzhidov, Dragos Horvath, Ramil Nugmanov, Timur Gimadiev, Daria Malakhova, Gilles Marcou, Alexandre Varnek
Molecular Informatics, 2018, 38 (1-2), pp.1800077. ⟨10.1002/minf.201800077⟩
Article dans une revueMapping of the Available Chemical Space versus the Chemical Universe of Lead-Like Compounds
Arkadii Lin, Dragos Horvath, Valentina Afonina, Gilles Marcou, Jean-Louis Reymond, Alexandre Varnek
ChemMedChem, 2018, 13 (6), pp.540-554. ⟨10.1002/cmdc.201700561⟩
Article dans une revueAbstractThis is, to our knowledge, the most comprehensive analysis to date based on generative topographic mapping (GTM) of fragment‐like chemical space (40 million molecules with no more than 17 heavy atoms, both from the theoretically enumerated GDB‐17 and real‐world PubChem/ChEMBL databases). The challenge was to prove that a robust map of fragment‐like chemical space can actually be built, in spite of a limited (≪105) maximal number of compounds (“frame set”) usable for fitting the GTM manifold. An evolutionary map building strategy has been updated with a “coverage check” step, which discards manifolds failing to accommodate compounds outside the frame set. The evolved map has a good propensity to separate actives from inactives for more than 20 external structure–activity sets. It was proven to properly accommodate the entire collection of 40 m compounds. Next, it served as a library comparison tool to highlight biases of real‐world molecules (PubChem and ChEMBL) versus the universe of all possible species represented by FDB‐17, a fragment‐like subset of GDB‐17 containing 10 million molecules. Specific patterns, proper to some libraries and absent from others (diversity holes), were highlighted.
Integrated Strategy for Lead Optimization Based on Fragment Growing: The Diversity-Oriented-Target-Focused-Synthesis Approach
Laurent Hoffer, Yuliia Voitovich, Brigitt Raux, Kendall Carrasco, Christophe Muller, Aleksey Fedorov, Carine Derviaux, Agnès Amouric, Stéphane Betzi, Dragos Horvath, Alexandre Varnek, Yves Collette, Sébastien Combes, Philippe Roche, Xavier Morelli
Journal of Medicinal Chemistry, 2018, 61 (13), pp.5719-5732. ⟨10.1021/acs.jmedchem.8b00653⟩
Article dans une revueAbstractOver the past few decades, hit identification has been greatly facilitated by advances in high-throughput and fragment-based screenings. One major hurdle remaining in drug discovery is process automation of hit-to-lead (H2L) optimization. Here, we report a time- and cost-efficient integrated strategy for H2L optimization as well as a partially automated design of potent chemical probes consisting of a focused-chemical-library design and virtual screening coupled with robotic diversity-oriented de novo synthesis and automated in vitro evaluation. The virtual library is generated by combining an activated fragment, corresponding to the substructure binding to the target, with a collection of functionalized building blocks using in silico encoded chemical reactions carefully chosen from a list of one-step organic transformations relevant in medicinal chemistry. The proof of concept was demonstrated using the optimization of bromodomain inhibitors as a test case, leading to the validation of several compounds with improved affinity by several orders of magnitude.
Monitoring of the Conformational Space of Dipeptides by Generative Topographic Mapping
Dragos Horvath, Gilles Marcou, Alexandre Varnek
Molecular Informatics, 2018, 37 (1-2), pp.1700115. ⟨10.1002/minf.201700115⟩
Article dans une revueFrom bird’s eye views to molecular communities: two-layered visualization of structure–activity relationships in large compound data sets
Shilva Kayastha, Ryo Kunimoto, Dragos Horvath, Alexandre Varnek, Jürgen Bajorath
Journal of Computer-Aided Molecular Design, 2017, 31 (11), pp.961-977. ⟨10.1007/s10822-017-0070-1⟩
Article dans une revueAbstractThe analysis of structure–activity relationships (SARs) becomes rather challenging when large and heterogeneous compound data sets are studied. In such cases, many different compounds and their activities need to be compared, which quickly goes beyond the capacity of subjective assessments. For a comprehensive large-scale exploration of SARs, computational analysis and visualization methods are required. Herein, we introduce a two-layered SAR visualization scheme specifically designed for increasingly large compound data sets. The approach combines a new compound pair-based variant of generative topographic mapping (GTM), a machine learning approach for nonlinear mapping, with chemical space networks (CSNs). The GTM component provides a global view of the activity landscapes of large compound data sets, in which informative local SAR environments are identified, augmented by a numerical SAR scoring scheme. Prioritized local SAR regions are then projected into CSNs that resolve these regions at the level of individual compounds and their relationships. Analysis of CSNs makes it possible to distinguish between regions having different SAR characteristics and select compound subsets that are rich in SAR information.
Neighboring Structure Visualization on a Grid-based Layout
Gilles Marcou, Dragos Horvath, Alexandre Varnek
Molecular Informatics, 2017, 36 (10), pp.1700047. ⟨10.1002/minf.201700047⟩
Article dans une revueVirtual screening, synthesis and biological evaluation of DNA intercalating antiviral agents
Kyrylo Klimenko, Sergey Lyakhov, Marina Shibinskaya, Alexander Karpenko, Gilles Marcou, Dragos Horvath, Marina Zenkova, Elena Goncharova, Rinat Amirkhanov, Andrei Krysko, Sergei Andronati, Igor Levandovskiy, Pavel Polishchuk, Victor Kuz'Min, Alexandre Varnek
Bioorganic and Medicinal Chemistry Letters, 2017, 27 (16), pp.3915-3919. ⟨10.1016/j.bmcl.2017.06.035⟩
Article dans une revuePrivileged Structural Motif Detection and Analysis Using Generative Topographic Maps
Shilva Kayastha, Dragos Horvath, Erik Gilberg, Michael Gütschow, Jürgen Bajorath, Alexandre Varnek
Journal of Chemical Information and Modeling, 2017, 57 (5), pp.1218-1232. ⟨10.1021/acs.jcim.7b00128⟩
Article dans une revueAbstractIdentification of “privileged structural motifs” associated with specific target families is of particular importance for designing novel bioactive compounds. Here, we demonstrate that they can be extracted from a data distribution represented on a two-dimensional map obtained by Generative Topographic Mapping (GTM). In GTM, structurally related molecules are grouped together on the map. Zones of the map preferentially populated by target-specific compounds were delineated, which helped to capture common substructures on the basis of which these compounds were grouped together by GTM. Such privileged structural motifs were identified across three major target superfamilies including proteases, kinases, and G protein coupled receptors. Traditionally, the search for privileged structural motifs focused on scaffolds, whereas motifs were detected here without prior knowledge of compound classification in GTMs. This alternative way of navigating medicinal chemistry space further extends the classical, scaffold-centric approach. Importantly, detected motifs might also comprise fuzzy sets of similar scaffolds, pharmacophore-like patterns, or, by contrast, well-defined scaffolds with specific substituent patterns.
Generative Topographic Mapping of Conformational Space
Dragos Horvath, Igor Baskin, Gilles Marcou, Alexandre Varnek
Molecular Informatics, 2017, 36 (10), pp.1700036. ⟨10.1002/minf.201700036⟩
Article dans une revueQSAR modeling1. and chemical space analysis of antimalarial compounds
Pavel Sidorov, Birgit Viira, Elisabeth Davioud-Charvet, Uko Maran, Gilles Marcou, Dragos Horvath, Alexandre Varnek
Journal of Computer-Aided Molecular Design, 2017, 31, pp.441-451. ⟨10.1007/s10822-017-0019-4⟩
Article dans une revuePrediction of Activity Cliffs Using Condensed Graphs of Reaction Representations, Descriptor Recombination, Support Vector Machine Classification, and Support Vector Regression
Dragos Horvath, Gilles Marcou, Alexandre Varnek, Shilva Kayasta, Antonio de La Vega de León, Jürgen Bajorath
Journal of Chemical Information and Modeling, 2016, 56 (9), pp.1631-1640. ⟨10.1021/acs.jcim.6b00359⟩
Article dans une revueChemical Space Mapping and Structure–Activity Analysis of the ChEMBL Antiviral Compound Set
Kyrylo Klimenko, Gilles Marcou, Dragos Horvath, Alexandre Varnek
Journal of Chemical Information and Modeling, 2016, 56 (8), pp.1438-1454. ⟨10.1021/acs.jcim.6b00192⟩
Article dans une revuePredictive Models for the Free Energy of Hydrogen Bonded Complexes with Single and Cooperative Hydrogen Bonds
Marta Glavatskikh, Timur Madzhidov, Vitaly Solovyev, Gilles Marcou, Dragos Horvath, Alexandre Varnek
Molecular Informatics, 2016, 35 (11-12), pp.629-638. ⟨10.1002/minf.201600070⟩
Article dans une revueCERAPP: Collaborative Estrogen Receptor Activity Prediction Project
Kamel Mansouri, Ahmed Abdelaziz, Aleksandra Rybacka, Alessandra Roncaglioni, Alexander Tropsha, Alexandre Varnek, Alexey Zakharov, Andrew Worth, Ann M. Richard, Christopher M. Grulke, Daniela Trisciuzzi, Denis Fourches, Dragos Horvath, Emilio Benfenati, Eugene Muratov, Eva Bay Wedebye, Francesca Grisoni, Giuseppe F. Mangiatordi, Giuseppina M. Incisivo, Huixiao Hong, Hui W. Ng, Igor V. Tetko, Ilya Balabin, Jayaram Kancherla, Jie Shen, Julien Burton, Marc Nicklaus, Matteo Cassotti, Nikolai G. Nikolov, Orazio Nicolotti, Patrik L. Andersson, Qingda Zang, Regina Politi, Richard D. Beger, Roberto Todeschini, Ruili Huang, Sherif Farag, Sine A. Rosenberg, Svetoslav Slavov, Xin Hu, Richard S. Judson
Environmental Health Perspectives, 2016, 124 (7), pp.1023-1033. ⟨10.1289/ehp.1510267⟩
Article dans une revueRedox Polypharmacology as an Emerging Strategy to Combat Malarial Parasites
Pavel Sidorov, Israel Desta, Matthieu Chessé, Dragos Horvath, Gilles Marcou, Alexandre Varnek, Elisabeth Davioud-Charvet, Mourad Elhabiri
ChemMedChem, 2016, 11 (12), pp.1339-1351. ⟨10.1002/cmdc.201600009⟩
Article dans une revueKernel Target Alignment Parameter: A New Modelability Measure for Regression Tasks
Gilles Marcou, Dragos Horvath, Alexandre Varnek
Journal of Chemical Information and Modeling, 2016, 56 (1), pp.6-11. ⟨10.1021/acs.jcim.5b00539⟩
Article dans une revueIn Silico Mining for Antimalarial Structure-Activity Knowledge and Discovery of Novel Antimalarial Curcuminoids
Birgit Viira, Thibault Gendron, Don Antoine Lanfranchi, Sandrine Cojean, Dragos Horvath, Gilles Marcou, Alexandre Varnek, Louis Maes, Uko Maran, Philippe Loiseau, Elisabeth Davioud-Charvet
Molecules, 2016, 21 (7), pp.853. ⟨10.3390/molecules21070853⟩
Article dans une revueAbstractMalaria is a parasitic tropical disease that kills around 600,000 patients every year. The emergence of resistant Plasmodium falciparum parasites to artemisinin-based combination therapies (ACTs) represents a significant public health threat, indicating the urgent need for new effective compounds to reverse ACT resistance and cure the disease. For this, extensive curation and homogenization of experimental anti-Plasmodium screening data from both in-house and ChEMBL sources were conducted. As a result, a coherent strategy was established that allowed compiling coherent training sets that associate compound structures to the respective antimalarial activity measurements. Seventeen of these training sets led to the successful generation of classification models discriminating whether a compound has a significant probability to be active under the specific conditions of the antimalarial test associated with each set. These models were used in consensus prediction of the most likely active from a series of curcuminoids available in-house. Positive predictions together with a few predicted as inactive were then submitted to experimental in vitro antimalarial testing. A large majority from predicted compounds showed antimalarial activity, but not those predicted as inactive, thus experimentally validating the in silico screening approach. The herein proposed consensus machine learning approach showed its potential to reduce the cost and duration of antimalarial drug discovery
Mappability of drug-like space: towards a polypharmacologically competent map of drug-relevant compounds
Pavel Sidorov, Héléna Gaspar, Gilles Marcou, Alexandre Varnek, Dragos Horvath
Journal of Computer-Aided Molecular Design, 2015, 29 (12), pp.1087-1108. ⟨10.1007/s10822-015-9882-z⟩
Article dans une revuePredictive Models for Halogen-bond Basicity of Binding Sites of Polyfunctional Molecules
Marta Glavatskikh, Timur Madzhidov, Vitaly Solovyev, Gilles Marcou, Dragos Horvath, Jérôme Graton, Jean-Yves Le questel, Alexandre Varnek
Molecular Informatics, 2015, 35 (2), pp.70-80. ⟨10.1002/minf.201500116⟩
Article dans une revueStargate GTM: Bridging Descriptor and Activity Spaces
Héléna Gaspar, Igor Baskin, Gilles Marcou, Dragos Horvath, Alexandre Varnek
Journal of Chemical Information and Modeling, 2015, 55 (11), pp.2403-2410. ⟨10.1021/acs.jcim.5b00398⟩
Article dans une revueS4MPLE—Sampler for Multiple Protein-Ligand Entities: Methodology and Rigid-Site Docking Benchmarking
Laurent Hoffer, Camelia Chira, Gilles Marcou, Alexandre Varnek, Dragos Horvath
Molecules, 2015, 20 (5), pp.8997-9028. ⟨10.3390/molecules20058997⟩
Article dans une revuePrediction of drug induced liver injury using molecular and biological descriptors
Christophe Muller, Dumrongsak Pekthong, Eliane Alexandre, Gilles Marcou, Dragos Horvath, Lysiane Richert, Alexandre Varnek
Combinatorial Chemistry and High Throughput Screening, 2015, 18 (3), pp.315-322. ⟨10.2174/1386207318666150305144650⟩
Article dans une revueExpert System for Predicting Reaction Conditions: The Michael Reaction Case
Gilles Marcou, J. Aires de Sousa, D. A. R. S. Latino, Aurélie de Luca, Dragos Horvath, V. Rietsch, Alexandre Varnek
Journal of Chemical Information and Modeling, 2015, 55 (2), pp.239-250. ⟨10.1021/ci500698a⟩
Article dans une revueGTM-Based QSAR Models and Their Applicability Domains
Héléna Gaspar, Igor Baskin, Gilles Marcou, Dragos Horvath, Alexandre Varnek
Molecular Informatics, 2015, 34 (6-7), pp.348-356. ⟨10.1002/minf.201400153⟩
Article dans une revueChemical Data Visualization and Analysis with Incremental Generative Topographic Mapping: Big Data Challenge
Héléna Gaspar, Igor Baskin, Gilles Marcou, Dragos Horvath, Alexandre Varnek
Journal of Chemical Information and Modeling, 2015, 55 (1), pp.84-94. ⟨10.1021/ci500575y⟩
Article dans une revueElectrochemical Properties of Substituted 2‐Methyl‐1,4‐Naphthoquinones: Redox Behavior Predictions
Mourad Elhabiri, Pavel Sidorov, Elena Cesar-Rodo, Gilles Marcou, Don Antoine Lanfranchi, Elisabeth Davioud-Charvet, Dragos Horvath, Alexandre Varnek
Chemistry - A European Journal, 2014, 21 (8), pp.3415-3424. ⟨10.1002/chem.201403703⟩
Article dans une revueAbstractAbstract In the context of the investigation of drug‐induced oxidative stress in parasitic cells, electrochemical properties of a focused library of polysubstituted menadione derivatives were studied by cyclic voltammetry. These values were used, together with compatible measurements from literature (quinones and related compounds), to build and evaluate a predictive structure–redox potential model (quantitative structure–property relationship, QSPR). Able to provide an online evaluation (through Web interface) of the oxidant character of quinones, the model is aimed to help chemists targeting their synthetic efforts towards analogues of desired redox properties
An Evolutionary Optimizer of libsvm Models
Dragos Horvath, J. Brown, Gilles Marcou, Alexandre Varnek
Challenges, 2014, 5 (2), pp.450-472. ⟨10.3390/challe5020450⟩
Article dans une revueDesign of a General-Purpose European Compound Screening Library for EU-OPENSCREEN
Dragos Horvath, Michael Lisurek, Bernd Rupp, Ronald Kühne, Edgar Specker, Jens Von kries, Didier Rognan, C. David Andersson, Fredrik Almqvist, Mikael Elofsson, Per-Anders Enqvist, Anna-Lena Gustavsson, Nikita Remez, Jordi Mestres, Gilles Marcou, Alexandre Varnek, Marcel Hibert, Jordi Quintana, Ronald Frank
ChemMedChem, 2014, 9 (10), pp.2309-2326. ⟨10.1002/cmdc.201402126⟩
Article dans une revueIndividual Hydrogen-Bond Strength QSPR Modelling with ISIDA Local Descriptors: a Step Towards Polyfunctional Molecules
Fiorella Ruggiu, Vitaly Solovyev, Gilles Marcou, Dragos Horvath, Jérôme Graton, Jean-Yves Le Questel, Alexandre Varnek
Molecular Informatics, 2014, 33 (6-7), pp.477-487. ⟨10.1002/minf.201400032⟩
Article dans une revueSimple Ligand–Receptor Interaction Descriptor (SILIRID) for alignment-free binding site comparison
Vladimir Chupakhin, Gilles Marcou, Héléna Gaspar, Alexandre Varnek
Computational and Structural Biotechnology Journal, 2014, 10 (16), pp.33-37. ⟨10.1016/j.csbj.2014.05.004⟩
Article dans une revueComputational chemogenomics: Is it more than inductive transfer?
J. B. Brown, Yasushi Okuno, Gilles Marcou, Alexandre Varnek, Dragos Horvath
Journal of Computer-Aided Molecular Design, 2014, 28 (6), pp.597-618. ⟨10.1007/s10822-014-9743-1⟩
Article dans une revueAbstractHigh-throughput assays challenge us to extract knowledge from multi-ligand, multi-target activity data. In QSAR, weights are statically fitted to each ligand descriptor with respect to a single endpoint or target. However, computational chemogenomics (CG) has demonstrated benefits of learning from entire grids of data at once, rather than building target-specific QSARs. A possible reason for this is the emergence of inductive knowledge transfer (IT) between targets, providing statistical robustness to the model, with no assumption about the structure of the targets. Relevant protein descriptors in CG should allow one to learn how to dynamically adjust ligand attribute weights with respect to protein structure. Hence, models built through explicit learning (EL) by including protein information, while benefitting from IT enhancement, should provide additional predictive capability, notably for protein deorphanization. This interplay between IT and EL in CG modeling is not sufficiently studied. While IT is likely to occur irrespective of the injected target information, it is not clear whether and when boosting due to EL may occur. EL is only possible if protein description is appropriate to the target set under investigation. The key issue here is the search for evidence of genuine EL exceeding expectations based on pure IT. We explore the problem in the context of Support Vector Regression, using more than 9,400 pKi values of 31 GPCRs, where compound–protein interactions are represented by the concatenation of vectorial descriptions of compounds and proteins. This provides a unified framework to generate both IT-enhanced and potentially EL-enabled models, where the difference is toggled by supplied protein information. For EL-enabled models, protein information includes genuine protein descriptors such as typical sequence-based terms, but also the experimentally determined affinity cross-correlation fingerprints. These latter benchmark the expected behavior of a quasi-ideal descriptor capturing the actual functional protein-protein relatedness, and therefore thought to be the most likely to enable EL. EL- and IT-based methods were benchmarked alongside classical QSAR, with respect to cross-validation and deorphanization challenges. A rational method for projecting benchmarked methodologies into a strategy space is given, in the aims that the projection will provide directions for the types of molecule designs possible using a given methodology. While EL-enabled strategies outperform classical QSARs and favorably compare to similar published results, they are, in all respects evaluated herein, not strongly distinguished from IT-enhanced models. Moreover, EL-enabled strategies failed to prove superior in deorphanization challenges. Therefore, this paper raises caution that, contrary to common belief and intuitive expectation, the benefits of chemogenomics models over classical QSAR are quite possibly due less to the injection of protein-related information, and rather impacted more by the effect of inductive transfer, due to simultaneous learning from all of the modeled endpoints. These results show that the field of protein descriptor research needs further improvements to truly realize the expected benefit of EL.
QSPR modelling -a valuable support in HTS quality control
Fiorella Ruggiu, Patrick Gizzi, Jean-Luc Galzi, Marcel Hibert, Jacques Haiech, Igor Baskin, Dragos Horvath, Gilles Marcou, Alexandre Varnek
Analytical Chemistry, 2014, ⟨10.1021/ac403544k⟩
Article dans une revueAbstractThe evaluation of important pharmacokinetic properties such as hydrophobicity using High Throughput Screening (HTS) methods is a major issue in drug discovery. In this article, we present the measurement of the Chromatographic Hydrophobicity Index (CHI) on a subset of the French chemical library, the "Chimiothèque Nationale" (CN). The data was used in QSPR modelling in order to annotate the CN. An algorithm is proposed to detect problematic molecules with large prediction errors, called outliers. In order to find an explanation for these large discrepancies between predicted and experimental values, these compounds were reanalysed experimentally. As the first selected outliers indeed had experimental problems, including hydrolysis or sheer absence of expected structure, we herewith propose the use of QSPR as a support tool for quality control of screening data and encourage the cooperation between experimental and theoretical teams to improve results. The corrected data was used to produce a model, which is freely available on our web server
Generative Topographic Mapping-Based Classification Models and Their Applicability Domain: Application to the Biopharmaceutics Drug Disposition Classification System (BDDCS)
Héléna Gaspar, Gilles Marcou, Dragos Horvath, Alban Arault, Sylvain Lozano, Philippe Vayer, Alexandre Varnek
Journal of Chemical Information and Modeling, 2013, 53 (12), pp.3318-3325. ⟨10.1021/ci400423c⟩
Article dans une revuePredicting Ligand Binding Modes from Neural Networks Trained on Protein–Ligand Interaction Fingerprints
Vladimir Chupakhin, Gilles Marcou, Igor Baskin, Alexandre Varnek, Didier Rognan
Journal of Chemical Information and Modeling, 2013, 53 (4), pp.763-772. ⟨10.1021/ci300200r⟩
Article dans une revue- Chapitre d'ouvrage
Generative Topographic Mapping Approach to Chemical Space Analysis
Dragos Horvath, Gilles Marcou, Alexandre Varnek
Advances in QSAR Modeling. Applications in Pharmaceutical, Chemical, Food, Agricultural and Environmental Sciences, Springer, pp.167-199, 2017, Challenges and Advances in Computational Chemistry and Physics, ⟨10.1007/978-3-319-56850-8_6⟩
Chapitre d'ouvrage- Communication dans un congrès
Combinatorial Library Neural Network (CoLiNN) for Combinatorial Library Visualization Without Compound Enumeration
Regina Pikalyova, Tagir Akhmetshin, Dragos Horvath, Alexandre Varnek
33rd International Conference on Artificial Neural Networks (ICANN 2024), Sep 2024, Lugano, Switzerland, Switzerland. pp.3-14, ⟨10.1007/978-3-031-72359-9_1⟩
Communication dans un congrèsClassical and covalent docking with S4MPLE
Dragos Horvath
3rd French-Israeli Workshop on Cheminformatics, Bar-Ilan University, Ramat-Gan, Israel, May 2022, Ramat-Gan, Israel
Communication dans un congrèsIn silico design of Tubulin activity modulators
Dragos Horvath
3rd French-Israeli Workshop on Cheminformatics, Bar-Ilan University, Ramat-Gan, Israel, May 2022, Ramat-Gan, Israel
Communication dans un congrèsMapping the Conformational Space of Docking Problems
Dragos Horvath
2nd French-Israeli Workshop on Cheminformatics, University of Strasbourg, 13-14 February 2020, Feb 2020, Strasbourg, France
Communication dans un congrèsAbstract2nd French-Israeli Workshop on Cheminformatics, University of Strasbourg, 13-14 February 2020
- Pré-publication, Document de travail
Interpretable and Scalable Similarity Metrics for DNA-Encoded Library Design Using Generative Topographic Mapping
Louis Plyer, Alexey A Orlov, Tagir N Akhmetshin, Erik Yeghyan, Fanny Bonachera, Dragos Horvath, Alexandre Varnek
2025
Pré-publication, Document de travailAbstractThe growing number and size of DNA-encoded libraries (DELs), together with the vast space of possible DEL designs, demand interpretable and scalable criteria for selecting which libraries to construct and screen against a given target. An ideal target-focused DEL shows both strong similarity with an active reference compound collection, and high intra-DEL diversity. Chemography with Generative Topographic Mapping (GTM) was shown to be a promising approach for selecting DELs, offering both intuitive visualization and fast quantitative analysis scalable to thousands of DEL designs. This is achieved by defining each library by a "stand-alone" vector, the comparison of which precludes costly pairwise inter-molecular similarity calculations. However, the extent to which such "stand-alone" (SA) approaches in general, and GTM-derived SA metrics in particular, recover DELs that are reference-proximal and chemically diverse as evaluated by conventional compound pairmatching (CP) metrics in the initial descriptor space, remains insufficiently characterized. In this paper, the comparative analysis of the Morgan count fingerprint-based chemical-library similarity versus GTM-derived metrics, using 100 diverse DEL subsets and a reference set of compounds tested against cyclin-dependent kinase 2 (CDK2) from ChEMBL was performed. GTM-based SA metrics provide robust approximations for "gold standard" molecular descriptor space CP metrics for DEL selection: Spearman rank correlations fall in the 0.6-0.7 range. Our results demonstrate that GTM helps to identify DELs that best span the reference space according to same "gold standard" molecular descriptor space metrics: SA GTM-driven rankings of libraries achieve enrichment factors at 5% (EF5%) of 4-12 (in terms of finding "gold standard" top libraries within the 5% best ranked by GTM) always picking 2 out of the top 3 libraries. The accompanying two-dimensional landscapes make intra-and inter-library diversity visually accessible, supporting rapid, interpretable screening of alternative DEL designs. Collectively, these results position GTM as an efficient tool for chemicallibrary similarity assessment and target-focused DEL selection.
Leveraging Condensed Graphs of Multi-step Reaction Routes for Clustering Retrosynthetic Pathways
Almaz Gilmullin, Tagir Akhmetshin, Dmitry Zankov, Olga Klimchuk, Dragos Horvath, Timur Madzhidov, Alexandre Varnek
2025
Pré-publication, Document de travailAbstractRetrosynthetic planning often produces a multitude of potential synthetic routes, creating challenges for chemists in selecting the most viable options. Existing clustering approaches used in tools like ASKCOS and AiZynthFinder rely on abstract or computationally intensive metrics that often lack chemical interpretability. In this work, we propose a novel, chemically intuitive clustering methodology implemented in the SynPlanner retrosynthetic tool, based on the concept of Strategic Bond Patterns (SBPs). By extending the Condensed Graph of Reaction (CGR) formalism to multi-step retrosynthetic pathways, we introduce the RouteCGR and its simplified variant, SB-CGR, which encodes the key disconnections leading to a target molecule. This two-level clustering strategy - first by SBP, then by generalized pseudo-reactions - groups routes by their underlying synthetic logic while tolerating variations in the reactions’ order and application of non-strategic steps (protection/deprotection). Comparison against clustering algorithms from ASKCOS and AiZynthFinder demonstrates that the SBP-based method produces fewer, more interpretable clusters and aligns more closely with chemists’ reasoning and intuition. SynPlanner’s SBP approach uncovers a broader diversity of unique synthetic strategies and demonstrates faster, more meaningful clustering. This framework facilitates efficient exploration of synthetic options, enhances interpretability, and offers a practical solution for navigating the combinatorial complexity of retrosynthetic planning.
Machine learning based thermodynamic modelling of acid gas absorption in aqueous MDEA and aqueous Piperazine
Kyrylo Klimenko, Rui Afonso, Paolo Stringari, Karen Gonzalez Tovar, Gilles Marcou, Dragos Horvath, Eric Cloarec, Alexandre Varnek, Frédérick de Meyer
2025
Pré-publication, Document de travailAbstractAcid gas chemical absorption with aqueous amine solvents is an important industrial technology for gas processing and CO2 capture. Vapor-Liquid Equilibrium (VLE) reflects the efficiency of solvents and is essential to model the thermodynamics of the absorption and solvent regeneration process. In this study, several machine learning (ML) approaches were used to develop VLE models for acid gas absorption in aqueous methyldiethanolamine (MDEA) and piperazine (Pz), namely CO2-MDEA-H2O, H2S-MDEA-H2O, CO2-H2S-MDEA-H2O and CO2-Pz-H2O systems. New experimental data are presented for the CO2-MDEA-H2O and H2S-MDEA-H2O ternary systems, and they are used to compare the accuracy of the ML models to an earlier reported activity coefficient (e-NRTL)-based thermodynamic model. For the quaternary system CO2-H2S-MDEA-H2O, the ML models and the physical model are compared using experimental data from literature, because the physical model of the quaternary system is only trained on the ternary experimental systems. The results indicate that the optimal ML approach is not systematically more accurate than the physics-based model.