Article
Chemistry, Medicinal
Filippo Lunghini, Marcou Gilles, Philippe Azam, Marie-Helene Enrici, Erik Van Miert, Alexandre Varnek
Summary: Under the REACH regulation, industries have generated a large amount of toxicological data on substances produced or imported in Europe. The data distribution in the REACH chemical space was analyzed using GTM, generating a Universal REACH map with 11 endpoints, showing acceptable predictive performance.
MOLECULAR INFORMATICS
(2021)
Article
Multidisciplinary Sciences
Lijie Feng, Huyi Zhang, Jinfeng Wang, Kuo-Yi Lin, Jinzhang Li
Summary: This paper aims to identify technological innovation opportunities in civil aircraft manufacturing through the analysis of a technology map. By using LDA cluster analysis method and TF-IDF algorithm, the study constructs a technology map and identifies critical technical words. The research findings suggest the necessity of strengthening basic technology development and improving intelligence, integration, and flexibility in mechanical connection technology of civil aircraft.
Article
Engineering, Environmental
Pascal Bicherel, Paul C. Thomas
Summary: The proposed method estimates mixture toxicity by considering chemical activity and interactions among molecules to calculate the true toxicity concentration. Validation through experimental studies shows that the predictions are accurate and outperform the standard additivity method.
ENVIRONMENTAL SCIENCE & TECHNOLOGY
(2021)
Article
Marine & Freshwater Biology
Xinliang Yu, Qun Zeng
Summary: In this study, a quantitative structure-activity relationship (QSAR) model for the toxicity of organic pesticides to various fish species was developed using the random forest (RF) algorithm. The model achieved high prediction accuracies for the toxicity classes and outperformed other QSAR models reported in the literature, despite using a smaller subset of descriptors.
AQUATIC TOXICOLOGY
(2022)
Article
Environmental Sciences
Ukhyun Jung, Byongcheun Lee, Geunbae Kim, Hyun Kil Shin, Ki-Tae Kim
Summary: Limited studies have been conducted to predict interspecies toxicity of engineered nanomaterials, particularly focusing on silver nanoparticles. A meta-analysis of acute toxicity data of AgNPs to daphnia and fish showed meaningful correlations when considering coating material descriptors and physicochemical properties. The inclusion of these factors improved the goodness-of-fit in predicting aquatic toxicity between species, providing insight for future in silico research.
Article
Business
Fei Teng, Yuling Sun, Fang Chen, Aning Qin, Qi Zhang
Summary: This paper proposes a systematic approach to discover unexplored areas of technology by processing patent text data, guiding the direction of technological development. Through supervised machine learning methods and clustering technology, patent text data is transformed into keyword vectors and visualized. The use of principal component analysis method has improved the accuracy and reliability of identifying patent vacancies.
TECHNOLOGICAL FORECASTING AND SOCIAL CHANGE
(2021)
Article
Engineering, Environmental
Mainak Chatterjee, Kunal Roy
Summary: This paper developed QSAR models for predicting aquatic toxicity, using Partial Least Squares regression as a statistical tool. The models were based on structural features of individual chemicals and mixture components, with quality assessed by strict validation parameters. The final models are robust, highly predictive, and mechanistically interpretable for predicting toxicity of untested chemical mixtures within the domain of applicability.
JOURNAL OF HAZARDOUS MATERIALS
(2021)
Article
Environmental Sciences
Mainak Chatterjee, Kunal Roy
Summary: This study developed a quantitative structure-activity relationship (QSAR) model to assess the environmental risk of pharmaceutical and pesticide mixtures. The developed partial least squares (PLS) model was rigorously validated and proved to be reliable and highly predictive.
Article
Environmental Sciences
Siyun Yang, Supratik Kar
Summary: The Toxic Substances Control Act mandates the EPA to document chemicals entering the US. In this study, in silico methods like QSAR and read-across were used to prioritize testing for chemicals lacking ecotoxicity data. The researchers curated acute LC50 toxicity data for three Tilapia species and developed predictive models to understand toxicological mode of action and predict aquatic toxicity of untested chemicals.
SCIENCE OF THE TOTAL ENVIRONMENT
(2024)
Article
Environmental Sciences
Guohui Sun, Yifan Zhang, Luyu Pei, Yuqing Lou, Yao Mu, Jiayi Yun, Feifan Li, Yachen Wang, Zhaoqi Hao, Sha Xi, Chen Li, Chuhan Chen, Lijiao Zhao, Na Zhang, Rugang Zhong, Yongzhen Peng
Summary: The study developed computational methods for evaluating acute oral toxicity of PAHs in rats, identified main influencing factors, compared with existing predictions, and demonstrated the prediction reliability.
ECOTOXICOLOGY AND ENVIRONMENTAL SAFETY
(2021)
Article
Business
Zhenfeng Liu, Jian Feng, Lorna Uden
Summary: This study proposes a new systematic approach using cross-cutting patent analysis to show the way from technology opportunities to ideas generation. The approach includes three stages: establishing cross-cutting relationships between target and reference technologies, constructing patent-keyword vector matrices, and migrating corresponding ideas using cosine similarity and link prediction. Empirical research on exploitation technology in NGH and CBM fields demonstrates the feasibility and effectiveness of the proposed approach. This study expands existing TOA research by providing more detailed schemes for technology opportunities and contributes to generating creative ideas.
TECHNOLOGICAL FORECASTING AND SOCIAL CHANGE
(2023)
Article
Environmental Sciences
Shuo Chen, Guohui Sun, Tengjiao Fan, Feifan Li, Yuancong Xu, Na Zhang, Lijiao Zhao, Rugang Zhong
Summary: This study investigated the quantitative structure-activity relationship (QSAR) between fused/non-fused polycyclic aromatic hydrocarbons (FNFPAHs) and their toxicity for the aquatic environment using Pimephales promelas as a model organism for the first time. A single QSAR model (SM1) containing five simple and interpretable 2D molecular descriptors was developed and showed good fitting and robustness. Consensus models (CMs) constructed using three qualified single models (SMs) further improved prediction accuracy.
SCIENCE OF THE TOTAL ENVIRONMENT
(2023)
Article
Chemistry, Multidisciplinary
Kabiruddin Khan, Kunal Roy
Summary: Organic chemicals (OCs) are a significant output of chemical and allied industries and their detection in aquatic compartments has raised ecological concerns. In this study, in silico techniques were employed to develop interspecies models for ecotoxicity prediction using data from the ECOTOX database. The results show that SSD-derived models offer more reliable predictions compared to other in silico techniques.
Article
Marine & Freshwater Biology
Kabiruddin Khan, Supratik Kar, Kunal Roy
Summary: Fighting COVID-19 with a large number of medications and bioproducts has led to a new challenge of ecotoxicity. Improper disposal of unused drugs can lead to unimaginable ecotoxicity in the long run. Therefore, an initial ecotoxicity assessment of the majorly used pharmaceuticals is urgently needed.
AQUATIC TOXICOLOGY
(2023)
Article
Toxicology
Sanjeeva J. Wijeyesakere, Tyler Auernhammer, Amanda Parks, Dan Wilson
Summary: We developed a mechanistic machine-learning model to predict mammalian acute oral toxicity. The model was trained using a rat toxicity database and accurately predicted the oral LD50 of compounds. It showed high sensitivity and has potential applications in assessing highly toxic substances.
TOXICOLOGICAL SCIENCES
(2023)
Article
Biochemical Research Methods
Karina Pikalyova, Alexey Orlov, Arkadii Lin, Olga Tarasova, Marcou Gilles, Dragos Horvath, Vladimir Poroikov, Alexandre Varnek
Summary: A new methodology based on generative topographic mapping (GTM) was introduced for predicting the drug resistance of HIV strains. The approach combines high accuracy and interpretability, allowing for visualization and analysis of sequence space and treatment optimization. Several case studies demonstrate the practicality of this method.
Article
Chemistry, Medicinal
Yuliana Zabolotna, Dmitriy M. Volochnyuk, Sergey Ryabukhin, Kostiantyn Gavrylenko, Dragos Horvath, Olga Klimchuk, Oleksandr Oksiuta, Gilles Marcou, Alexandre Varnek
Summary: Most existing computational tools for de novo library design focus on generating, selecting, and combining structural motifs to form new library members. However, these approaches appear to be more theoretical and disconnected from reality due to the lack of a direct link between the chemical space of the retrosynthesized fragments and the pool of available reagents. This paper presents a new open-source toolkit called Synthons Interpreter (SynthI), which merges these two chemical spaces into a single synthons space.
JOURNAL OF CHEMICAL INFORMATION AND MODELING
(2022)
Article
Chemistry, Medicinal
Yuliana Zabolotna, Dmitriy M. Volochnyuk, Sergey V. Ryabukhin, Dragos Horvath, Konstantin S. Gavrilenko, Gilles Marcou, Yurii S. Moroz, Oleksandr Oksiuta, Alexandre Varnek
Summary: Efficient synthesis of desired compounds is crucial for chemical space exploration in drug discovery, which is influenced by both established synthetic protocols and the availability of corresponding building blocks (BBs). This study analyzes the chemical space of 400,000 purchasable BBs, examining their physicochemical properties and diversity to assess their coverage of medicinal chemistry needs. The analysis is based on a universal topographic map that visualizes libraries and their differences in coverage.
JOURNAL OF CHEMICAL INFORMATION AND MODELING
(2022)
Article
Chemistry, Medicinal
Regina Pikalyova, Yuliana Zabolotna, Dmitriy M. Volochnyuk, Dragos Horvath, Gilles Marcou, Alexandre Varnek
Summary: DNA-Encoded Library (DEL) technology is a method for discovering bioactive molecules in medicinal chemistry. This project aimed to generate and analyze an ultra-large chemical space of DEL using commercially available building blocks. The study compared the DEL compounds to biologically relevant compounds from ChEMBL and identified optimal DELs covering the chemical space of ChEMBL. Different combinations of DELs were analyzed to achieve even higher coverage of ChEMBL than with a single DEL.
MOLECULAR INFORMATICS
(2022)
Article
Biochemistry & Molecular Biology
Enrico Gandini, Gilles Marcou, Fanny Bonachera, Alexandre Varnek, Stefano Pieraccini, Maurizio Sironi
Summary: Molecular similarity is a widely applicable and significant topic in chemistry. It has various applications in pharmaceutical research, such as studying structure-activity relationships, and in determining the status of orphan drugs. Models were built and evaluated using expert judgments to reduce human efforts. A dataset of new molecules and an online tool for molecular similarity estimation have been made freely available.
INTERNATIONAL JOURNAL OF MOLECULAR SCIENCES
(2022)
Article
Biochemistry & Molecular Biology
Youssef El Khoury, Marie Gebelin, Jerome de Seze, Christine Patte-Mensah, Gilles Marcou, Alexandre Varnek, Ayikoe-Guy Mensah-Nyagan, Petra Hellwig, Nicolas Collongues
Summary: Neuromyelitis optica spectrum disorder (NMOSD) and multiple sclerosis (MS) are autoimmune inflammatory and demyelinating diseases of the central nervous system. Differentiating between NMOSD and MS is crucial for the timely and appropriate treatment. In this study, infrared spectroscopy combined with machine learning successfully distinguished NMOSD and MS patients with 100% sensitivity and specificity. The method shows promise as a cost-effective and rapid diagnostic tool to help save valuable treatment time for patients.
INTERNATIONAL JOURNAL OF MOLECULAR SCIENCES
(2022)
Article
Chemistry, Multidisciplinary
Iuri Casciuc, Artem Osypenko, Bohdan Kozibroda, Dragos Horvath, Gilles Marcou, Fanny Bonachera, Alexandre Varnek, Jean-Marie Lehn
Summary: This study proposes a chemoinformatic model for assessing the composition of dynamic combinatorial libraries (DCLs) theoretically. The model predicts the constants for DCL constituents and provides a virtual illustration on how effector affinity regulates DCL members.
ACS CENTRAL SCIENCE
(2022)
Article
Chemistry, Multidisciplinary
Alexey A. Orlov, Alain Valtz, Christophe Coquelet, Xavier Rozanska, Erich Wimmer, Gilles Marcou, Dragos Horvath, Benedicte Poulain, Alexandre Varnek, Frederick de Meyer
Summary: Researchers have developed a computational approach that combines kinetic experiments, molecular simulations, and machine learning to identify a class of tertiary amines that absorb CO2 faster than a typical commercial solvent when mixed with piperazine.
COMMUNICATIONS CHEMISTRY
(2022)
Article
Chemistry, Medicinal
Yuliana Zabolotna, Fanny Bonachera, Dragos Horvath, Arkadii Lin, Gilles Marcou, Olga Klimchuk, Alexandre Varnek
Summary: Nowadays, drug discovery requires understanding of chemotype composition and physicochemical properties of large compound collections. ChemSpace Atlas is a freely accessible tool that allows multifaceted analysis and visualization of chemical libraries, supporting activity profiling and analogue search. It will be expanded to include new chemical subspaces and functionalities.
JOURNAL OF CHEMICAL INFORMATION AND MODELING
(2022)
Article
Biochemistry & Molecular Biology
Alexey 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 Ryabukhin, Alexandre Varnek
Summary: New models for ACE2 receptor binding were developed using QSAR and docking algorithms, and the selectivity of ACE2-binding ligands towards NEP and ACE was evaluated. Virtual screening of the Enamine screening collection was conducted to find potential ACE2-chemical probes for studying SARS-CoV2-induced neurological disorders. An enzymology inhibition assay for ACE2 was optimized, and the predicted selective ACE2-binding molecules from QSAR modeling, docking, and ultrafast docking were screened in vitro, resulting in the identification of two novel chemotypes suitable for further optimization.
Article
Chemistry, Medicinal
William Bort, Daniyar Mazitov, Dragos Horvath, Fanny Bonachera, Arkadii Lin, Gilles Marcou, Igor Baskin, Timur Madzhidov, Alexandre Varnek
Summary: This paper proposes a new attention-based conditional variational autoencoder neural network architecture to solve the inverse QSAR problem. Using this method, it is possible to generate novel compounds with desired activity, and these compounds exhibit acceptable druglikeness and synthetic accessibility. Pharmacophore and docking studies validate the accuracy of the activity predictions for some of these novel structures.
JOURNAL OF CHEMICAL INFORMATION AND MODELING
(2022)
Article
Chemistry, Medicinal
Giuseppe Lamanna, Pietro Delre, Gilles Marcou, Michele Saviano, Alexandre Varnek, Dragos Horvath, Giuseppe Felice Mangiatordi
Summary: This 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. GENERA was applied to the angiotensin-converting enzyme 2 (ACE2) target, and its ability to de novo design promising candidates was assessed using docking programs PLANTS and GLIDE. The study demonstrates that GENERA can effectively perform multiobjective optimization and generate focused libraries with better scores compared to a starting set of known ACE-2 binders.
JOURNAL OF CHEMICAL INFORMATION AND MODELING
(2023)
Article
Chemistry, Medicinal
Regina Pikalyova, Yuliana Zabolotna, Dragos Horvath, Gilles Marcou, Alexandre Varnek
Summary: The development of DNA-encoded library (DEL) technology has brought new challenges to the analysis of chemical libraries. This study introduces the concept of chemical library space (CLS) and compares four representations obtained using generative topographic mapping. These encodings allow for effective comparison of libraries and fine-tuning of matching criteria. The proposed CLS can be used for efficient analysis and selection of chemical libraries.
JOURNAL OF CHEMICAL INFORMATION AND MODELING
(2023)
Article
Chemistry, Medicinal
Regina Pikalyova, Yuliana Zabolotna, Dragos Horvath, Gilles Marcou, Alexandre Varnek
Summary: In chemical library analysis, it can be beneficial to describe libraries as individual items rather than collections of compounds. This is especially true for large non-selectable compound mixtures like DNA-encoded libraries (DELs). The chemical library space (CLS) is useful for managing a portfolio of libraries, similar to how chemical space (CS) helps manage portfolios of molecules. Mapping the CLS on meta-GTMs allows for analysis beyond pairwise library comparison, facilitating the selection of the most suitable libraries for specific projects.
JOURNAL OF CHEMICAL INFORMATION AND MODELING
(2023)
Article
Biochemistry & Molecular Biology
Julia Revillo Imbernon, Celien Jacquemard, Guillaume Bret, Gilles Marcou, Esther Kellenberger
Summary: The screening of fragment libraries is crucial in drug discovery, with the success depending on the quality and design of the library meeting specific research requirements. This study conducted an inventory of commercial fragment libraries and developed a methodology to classify any library based on its similarity, coverage, and structural features, leading to the creation of a model that considers fragment diversity and ease of interpretation.
RSC MEDICINAL CHEMISTRY
(2022)