Journal of Chemical Information and Modeling 最新文献

{"title":"Accelerated Hydration Site Localization and Thermodynamic Profiling.","authors":"Florian B Hinz, Matthew R Masters, Julia T Nguyen, Amr H Mahmoud, Markus A Lill","doi":"10.1021/acs.jcim.4c02349","DOIUrl":"https://doi.org/10.1021/acs.jcim.4c02349","url":null,"abstract":"<p><p>Water plays a fundamental role in the structure and function of proteins and other biomolecules. The thermodynamic profile of water molecules surrounding a protein is critical for ligand recognition and binding. Therefore, identifying the location and thermodynamic properties of relevant water molecules is important for generating and optimizing lead compounds for affinity and selectivity for a given target. Computational methods have been developed to identify these hydration sites (HS), but are largely limited to simplified models that fail to capture multibody interactions or dynamics-based methods that rely on extensive sampling. Here, we present a method for fast and accurate localization and thermodynamic profiling of HS for protein structures. The method is based on a geometric deep neural network trained on a large, novel data set of explicit water molecular dynamics simulations. We confirm the accuracy and robustness of our model on experimental data and demonstrate its utility on several case studies.</p>","PeriodicalId":44,"journal":{"name":"Journal of Chemical Information and Modeling ","volume":" ","pages":""},"PeriodicalIF":5.6,"publicationDate":"2025-02-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143527852","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"化学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"SynTemp: Efficient Extraction of Graph-Based Reaction Rules from Large-Scale Reaction Databases.","authors":"Tieu-Long Phan, Klaus Weinbauer, Marcos E González Laffitte, Yingjie Pan, Daniel Merkle, Jakob L Andersen, Rolf Fagerberg, Christoph Flamm, Peter F Stadler","doi":"10.1021/acs.jcim.4c01795","DOIUrl":"https://doi.org/10.1021/acs.jcim.4c01795","url":null,"abstract":"<p><p>Reaction templates are graphs that represent the reaction center as well as the surrounding context in order to specify salient features of chemical reactions. They are subgraphs of <i>imaginary transition states</i>, which are equivalent to double pushout graph rewriting rules and thus can be applied directly to predict reaction outcomes at the structural formula level. We introduce here SynTemp, a framework designed to extract and hierarchically cluster reaction templates from large-scale reaction data repositories. Rule inference is implemented as a robust graph-theoretic approach, which first computes an atom-atom mapping (AAM) as a consensus over partial predictions from multiple state-of-the-art tools and then augments the raw AAM by mechanistically relevant hydrogen atoms and extracts the reactions center extended by relevant context. SynTemp achieves an exceptional accuracy of 99.5% and a success rate of 71.23% in obtaining AAMs on the <i>chemical reaction dataset</i>. Hierarchical clustering of the extended reaction centers based on topological features results in a library of 311 transformation rules explaining 86% of the reaction dataset.</p>","PeriodicalId":44,"journal":{"name":"Journal of Chemical Information and Modeling ","volume":" ","pages":""},"PeriodicalIF":5.6,"publicationDate":"2025-02-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143522085","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"化学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"GLMCyp: A Deep Learning-Based Method for CYP450-Mediated Reaction Site Prediction.","authors":"Xuhai Huang, Jiamin Chang, Boxue Tian","doi":"10.1021/acs.jcim.4c02051","DOIUrl":"https://doi.org/10.1021/acs.jcim.4c02051","url":null,"abstract":"<p><p>Cytochrome P450 enzymes (CYP450s) play crucial roles in metabolizing many drugs, and thus, local chemical structure can profoundly influence drug efficacy and toxicity. Therefore, the accurate prediction of CYP450-mediated reaction sites can increase the efficiency of drug discovery and development. Here, we present GLMCyp, a deep learning-based approach, for predicting CYP450 reaction sites on small molecules. By integrating two-dimensional (2D) molecular graph features, three-dimensional (3D) features from Uni-Mol, and relevant CYP450 protein features generated by ESM-2, GLMCyp could accurately predict bonds of metabolism (BoMs) targeted by a panel of nine human CYP450s. Incorporating protein features allowed GLMCyp application in broader CYP450 metabolism prediction tasks. Additionally, substrate molecular feature processing enhanced the accuracy and interpretability of the predictions. The model was trained on the EBoMD data set and reached an area under the receiver operating characteristic curve (ROC-AUC) of 0.926. GLMCyp also showed a relatively strong capacity for feature extraction and generalizability in validation with external data sets. The GLMCyp model and data sets are available for public use (https://github.com/lvimmind/GLMCyp-Predictor) to facilitate drug metabolism screening.</p>","PeriodicalId":44,"journal":{"name":"Journal of Chemical Information and Modeling ","volume":" ","pages":""},"PeriodicalIF":5.6,"publicationDate":"2025-02-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143514021","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"化学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Correction to \"Development of a Pantetheine Force Field Library for Molecular Modeling\".","authors":"Shiji Zhao, Andrew J Schaub, Shiou-Chuan Tsai, Ray Luo","doi":"10.1021/acs.jcim.5c00282","DOIUrl":"https://doi.org/10.1021/acs.jcim.5c00282","url":null,"abstract":"","PeriodicalId":44,"journal":{"name":"Journal of Chemical Information and Modeling ","volume":" ","pages":""},"PeriodicalIF":5.6,"publicationDate":"2025-02-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143522067","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"化学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Predicting the Mutagenic Activity of Nitroaromatics Using Conceptual Density Functional Theory Descriptors and Explainable No-Code Machine Learning Approaches.","authors":"Andrés Halabi Diaz, Mario Duque-Noreña, Elizabeth Rincón, Eduardo Chamorro","doi":"10.1021/acs.jcim.4c02401","DOIUrl":"https://doi.org/10.1021/acs.jcim.4c02401","url":null,"abstract":"<p><p>Nitroaromatic compounds (NAs) are widely used in industrial applications but pose significant genotoxic risks, necessitating accurate mutagenicity prediction for chemical safety assessments. This study integrates conceptual density functional theory (CDFT) descriptors with explainable no-code machine learning (ML) models to predict NA mutagenicity based on Ames test results. Following OECD QSAR guidelines, feature selection and model development were performed using decision-tree-based algorithms (Random Tree, JCHAID*, SPAARC) and multilayer perceptrons (MLPs). These models exhibited high predictive accuracy (internal: >80%, κ = 0.21-0.37; external: ∼90%, κ = 0.41-0.62) with strong interpretability. The study also explores the role of metabolic activation and aqueous-phase descriptors, evaluating a novel electronic analog to LogP (LogQP) to assess hydrophobicity-mutagenicity relationships. Results demonstrate that aqueous-phase electronic properties and electrophilicity descriptors outperform vacuum-based methods in mutagenicity prediction. The combination of CDFT descriptors with shallow ML models proves to be a robust, interpretable, and accessible framework for predictive toxicology. This approach enhances chemical risk assessment and bridges computational chemistry with toxicology for regulatory applications.</p>","PeriodicalId":44,"journal":{"name":"Journal of Chemical Information and Modeling ","volume":" ","pages":""},"PeriodicalIF":5.6,"publicationDate":"2025-02-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143522070","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"化学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Large Model Era: Deep Learning in Osteoporosis Drug Discovery.","authors":"Junlin Xu, Xiaobo Wen, Li Sun, Kunyue Xing, Linyuan Xue, Sha Zhou, Jiayi Hu, Zhijuan Ai, Qian Kong, Zishu Wen, Li Guo, Minglu Hao, Dongming Xing","doi":"10.1021/acs.jcim.4c02264","DOIUrl":"https://doi.org/10.1021/acs.jcim.4c02264","url":null,"abstract":"<p><p>Osteoporosis is a systemic microstructural degradation of bone tissue, often accompanied by fractures, pain, and other complications, resulting in a decline in patients' life quality. In response to the increased incidence of osteoporosis, related drug discovery has attracted more and more attention, but it is often faced with challenges due to long development cycle and high cost. Deep learning with powerful data processing capabilities has shown significant advantages in the field of drug discovery. With the development of technology, it is more and more applied to all stages of drug discovery. In particular, large models, which have been developed rapidly recently, provide new methods for understanding disease mechanisms and promoting drug discovery because of their large parameters and ability to deal with complex tasks. This review introduces the traditional models and large models in the deep learning domain, systematically summarizes their applications in each stage of drug discovery, and analyzes their application prospect in osteoporosis drug discovery. Finally, the advantages and limitations of large models are discussed in depth, in order to help future drug discovery.</p>","PeriodicalId":44,"journal":{"name":"Journal of Chemical Information and Modeling ","volume":" ","pages":""},"PeriodicalIF":5.6,"publicationDate":"2025-02-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143497544","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"化学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Binding Affinity Prediction and Pesticide Screening against <i>Phytophthora sojae</i> Using a Heterogeneous Interaction Graph Attention Network-Based Model.","authors":"Youxu Dai, Aiping Han, Huijun Ma, Xuebo Jin, Danyang Zhu, Shiguang Sun, Ruiheng Li","doi":"10.1021/acs.jcim.4c02295","DOIUrl":"https://doi.org/10.1021/acs.jcim.4c02295","url":null,"abstract":"<p><p>Phytophthora root and stem rot in soybeans results in substantial economic losses worldwide. In this study, a machine learning model based on a heterogeneous interaction graph attention network model was constructed. The PDBbind data set, comprising 13,285 complexes with experimental <i>pK</i>_a or <i>p</i>K_i values, was utilized to train and evaluate the model, which was subsequently employed to screen candidate compounds against chitin synthase of <i>Phytophthora sojae</i> (<i>Ps</i>Chs1) in the Traditional Chinese Medicine Systems Pharmacology database, comprising 14,249 compounds. High-scoring candidate compounds were docked with <i>Ps</i>Chs1 protein using Discovery Studio, and their interaction energies were evaluated. Molecular dynamic simulations spanning 50 ns were performed using GROMACS to explore the stability of the complexes, trajectory analysis was conducted with root-mean-square deviations, and the hydrogen bonds, radius of gyration, MMPBSA binding free energy, and binding modes were analyzed. MOL011832 and MOL011833 were identified as potential pesticides, both of which were present in the herb <i>Schizonepeta</i> through database retrieval. The inhibitory effects of an ethanol extract of <i>Schizonepeta</i> against <i>P. sojae</i> were subsequently explored and confirmed in biological experiments. Overall, this study proves the feasibility and high efficiency of pesticide discovery using graph neural network-based models.</p>","PeriodicalId":44,"journal":{"name":"Journal of Chemical Information and Modeling ","volume":" ","pages":""},"PeriodicalIF":5.6,"publicationDate":"2025-02-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143514013","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"化学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Computational Investigation of Site-Specific Doping Effects on Electronic Structure, Electrochemical Performance, Lithium-Ion Diffusion, and Transport in Li₂GeO₃ Anode.","authors":"Mayank Shriwastav, Abhishek Kumar Gupta, D K Dwivedi","doi":"10.1021/acs.jcim.4c02267","DOIUrl":"https://doi.org/10.1021/acs.jcim.4c02267","url":null,"abstract":"<p><p>Li₂GeO₃ has gained attention as a potential anode material for lithium-ion batteries due to its high ion diffusion rate. This research uses advanced computational modeling to examine how different types of dopants and their substitution sites affect the defect properties, electronic structure, and lithium-ion diffusion in Li₂GeO₃. By analyzing isovalent and aliovalent dopants at various crystallographic positions, the study aims to uncover the mechanisms by which doping influences the material's performance as an anode. The findings indicate that halide dopants at the oxygen sites notably alter the electronic structure and ion diffusion rate. A decreasing trend in the band gap was observed with increasing concentrations of tetra- and trivalent dopants. Moreover, except for fluoride (F^-), other halide dopants at the 4a oxygen site exhibited the opposite effect on the electronic structure and ion diffusion rate. The 8b site was identified as the most favorable for F^- substitution, showing the lowest formation energy. Substitution of F^- at the 8b site significantly reduced the band gap (from 3.77 to 2.19 eV) by shifting the valence band maxima from the <i>Z</i>-point to the <i>Y</i>-point in high-symmetry representation and substantially increased the ion diffusion rate (1.70 × 10^-10 cm²/s) by broadening the diffusion pathway.</p>","PeriodicalId":44,"journal":{"name":"Journal of Chemical Information and Modeling ","volume":" ","pages":""},"PeriodicalIF":5.6,"publicationDate":"2025-02-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143514017","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"化学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Structure-Based Identification of Non-covalent Prolyl Oligopeptidase 80 Inhibitors Targeting <i>Trypanosoma cruzi</i> Cell Entry.","authors":"Vinícius Alexandre Fiaia Costa, Flávia Nader Motta, Alexandra Maria Dos Santos Carvalho, Felipe da Silva Mendonça de Melo, Melina Mottin, Sébastien Charneau, Philippe Grellier, Jaime Martins Santana, Izabela Marques Dourado Bastos, Bruno Junior Neves","doi":"10.1021/acs.jcim.4c02152","DOIUrl":"https://doi.org/10.1021/acs.jcim.4c02152","url":null,"abstract":"<p><p>Chagas disease remains a persistent public health challenge due to the limited efficacy and significant toxicity of current pharmacological treatments. This highlights the urgent need for novel drugs with innovative mechanisms of action, specifically targeting cell infection pathways. The prolyl oligopeptidase of <i>Trypanosoma cruzi</i> (POPTc80) has emerged as a promising target for developing inhibitors to block the parasite's infection process. In this study, we developed a robust structure-based virtual screening pipeline to discover potent POPTc80 inhibitors. The customized protocol integrated structural analysis of the 3D structure of POPTc80 and enrichment analysis of molecular docking and shape-based models to optimize the selection of potential inhibitors. After optimization, a large-scale virtual screening of 1.3 million compounds prioritized 19 putative hits for experimental validation. Nine of these compounds demonstrated inhibitory activity at nanomolar concentrations. The most potent inhibitors─LC-44 (<i>K</i>_<i>i</i> = 0.175 μM), LC-45 (<i>K</i>_<i>i</i> = 0.054 μM), LC-46 (<i>K</i>_<i>i</i> = 0.513 μM), LC-50 (<i>K</i>_<i>i</i> = 0.44 μM), LC-53 (<i>K</i>_<i>i</i> = 0.158 μM), and LC-55 (<i>K</i>_<i>i</i> = 0.83 μM)─demonstrated superior inhibitory activity, consistent with the competitive inhibition mechanism predicted by our computational protocol. Subsequently, a phenotypic assay confirmed their ability to effectively inhibit <i>T. cruzi</i> entry into host cells in a dose-dependent manner, further validating their mechanism of action. These findings establish these compounds as promising chemical scaffolds for prospective hit-to-lead optimization, offering a unique opportunity to develop novel, mechanism-driven therapeutics targeting a critical step in the parasite's infection process.</p>","PeriodicalId":44,"journal":{"name":"Journal of Chemical Information and Modeling ","volume":" ","pages":""},"PeriodicalIF":5.6,"publicationDate":"2025-02-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143497548","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"化学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Redox-Activated Proton Transfer through a Redundant Network in the Q_o Site of Cytochrome <i>bc</i>₁.","authors":"Guilherme M Arantes","doi":"10.1021/acs.jcim.4c02361","DOIUrl":"https://doi.org/10.1021/acs.jcim.4c02361","url":null,"abstract":"<p><p>Proton translocation catalyzed by cytochrome <i>bc</i>₁ (respiratory complex III) during coenzyme-Q redox cycling is a critical bioenergetic process, yet its detailed molecular mechanism remains incompletely understood. In this study, the energetics of the long-range proton transfers through multiple proton-conducting wires in the Q_o site of the <i>bc</i>₁ complex was investigated computationally using hybrid QM/MM simulations and a specialized reaction coordinate. Key reactive groups and proton transfer mechanisms were characterized, confirming the propionate-A group of heme <i>b</i>_<i>L</i> as a plausible proton acceptor. Upon coenzyme-Q oxidation, a Grotthuss hopping mechanism is activated, facilitating proton transfer along three distinct pathways with comparable barriers and stability. These pathways operate redundantly, forming a robust proton-conducting network, and account for the unusual experimental behavior observed in single-point mutations. Energetic analyses exclude charged closed-shell species as likely intermediates and propose a reaction sequence for coenzyme-Q oxidation proceeding as QH₂ → QH^• → Q⁰, either via coupled proton-electron transfers or stepwise mechanisms involving open-shell intermediates. These findings elucidate mechanistic details of the Q-cycle and improve our understanding of the catalytic reactions supporting redox-activated proton transfer in respiratory enzymes.</p>","PeriodicalId":44,"journal":{"name":"Journal of Chemical Information and Modeling ","volume":" ","pages":""},"PeriodicalIF":5.6,"publicationDate":"2025-02-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143497546","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"化学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}