Journal of Chemical Information and Modeling 最新文献

{"title":"StackDILI: Enhancing Drug-Induced Liver Injury Prediction through Stacking Strategy with Effective Molecular Representations.","authors":"Jiahui Guan, Danhong Dong, Peilin Xie, Zhihao Zhao, Yilin Guo, Tzong-Yi Lee, Lantian Yao, Ying-Chih Chiang","doi":"10.1021/acs.jcim.4c02079","DOIUrl":"10.1021/acs.jcim.4c02079","url":null,"abstract":"<p><p>Drug-induced liver injury (DILI) is a major challenge in drug development, often leading to clinical trial failures and market withdrawals due to liver toxicity. This study presents StackDILI, a computational framework designed to accelerate toxicity assessment by predicting DILI risk. StackDILI integrates multiple molecular descriptors to extract structural and physicochemical features, including the constitution, pharmacophore, MACCS, and E-state descriptors. Additionally, a genetic algorithm is employed for feature selection and optimization, ensuring that the most relevant features are used. These optimized features are processed through a stacking ensemble model comprising multiple tree-based machine learning models, improving prediction accuracy and interpretability. Notably, StackDILI demonstrates a strong performance on the DILIrank test set and maintains robustness across cross-validation. Moreover, interpretability analysis reveals key molecular features associated with DILI risks, providing valuable insights into toxicity prediction. To further improve accessibility, a user-friendly web interface is developed, allowing users to input SMILES strings and receive rapid predictions with ease. The StackDILI model provides a powerful tool for efficient DILI assessment, supporting safer drug development. The web interface is accessible at https://awi.cuhk.edu.cn/biosequence/StackDILI/.</p>","PeriodicalId":44,"journal":{"name":"Journal of Chemical Information and Modeling ","volume":" ","pages":"1027-1039"},"PeriodicalIF":5.6,"publicationDate":"2025-01-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142941373","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":"Engineering Protein Dynamics through Mutational Energy Landscape Traps.","authors":"Lucas de Almeida Machado, João Sartori, Paula Fernandes da Costa Franklin, Mauricio G S Costa, Ana Carolina Ramos Guimarães","doi":"10.1021/acs.jcim.4c01928","DOIUrl":"10.1021/acs.jcim.4c01928","url":null,"abstract":"<p><p>Protein dynamics is essential for various biological processes, influencing functions such as enzyme activity, molecular recognition, and signal transduction. However, traditional protein engineering methods often focus on static structures, lacking tools to precisely manipulate dynamic behaviors. Here, we developed Mutational Energy Landscape Trap (MELT), a novel method designed to control protein dynamics by combining Normal Mode Analysis (NMA) and <i>in silico</i> mutagenesis. MELT works by displacing protein structures along low-frequency normal modes and introducing mutations to either lock proteins in these conformations or increase dynamics along the chosen normal modes. We tested MELT using hen-egg lysozyme as a model system. The method was validated by monitoring relevant collective coordinates during molecular dynamics simulations and evaluation of the collective movements of each construct. Our experiments showed that MELT was able to consistently create new protein sequences with the desired dynamical behavior in simulations. It demonstrates its potential for applications in the field of protein engineering, being an unprecedented way of manipulating protein features.</p>","PeriodicalId":44,"journal":{"name":"Journal of Chemical Information and Modeling ","volume":" ","pages":"517-527"},"PeriodicalIF":5.6,"publicationDate":"2025-01-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142941458","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":"MVCL-DTI: Predicting Drug-Target Interactions Using a Multiview Contrastive Learning Model on a Heterogeneous Graph.","authors":"Bei Zhang, Lijun Quan, Zhijun Zhang, Lexin Cao, Qiufeng Chen, Liangchen Peng, Junkai Wang, Yelu Jiang, Liangpeng Nie, Geng Li, Tingfang Wu, Qiang Lyu","doi":"10.1021/acs.jcim.4c02073","DOIUrl":"10.1021/acs.jcim.4c02073","url":null,"abstract":"<p><p>Accurate prediction of drug-target interactions (DTIs) is pivotal for accelerating the processes of drug discovery and drug repurposing. MVCL-DTI, a novel model leveraging heterogeneous graphs for predicting DTIs, tackles the challenge of synthesizing information from varied biological subnetworks. It integrates neighbor view, meta-path view, and diffusion view to capture semantic features and employs an attention-based contrastive learning approach, along with a multiview attention-weighted fusion module, to effectively integrate and adaptively weight the information from the different views. Tested under various conditions on benchmark data sets, including varying positive-to-negative sample ratios, conducting hard negative sampling experiments, and masking known DTIs with different ratios, as well as redundant DTIs with various similarity metrics, MVCL-DTI exhibits strong robust generalization. The model is then employed to predict novel DTIs, with a particular focus on COVID-19-related drugs, highlighting its practical applicability. Ultimately, through features visualization and computational properties analysis, we've pinpointed critical elements, including Gene Ontology and substituent nodes, along with a proper initialization strategy, underscoring their vital role in DTI prediction tasks.</p>","PeriodicalId":44,"journal":{"name":"Journal of Chemical Information and Modeling ","volume":" ","pages":"1009-1026"},"PeriodicalIF":5.6,"publicationDate":"2025-01-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142981959","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":"PPI-CoAttNet: A Web Server for Protein-Protein Interaction Tasks Using a Coattention Model.","authors":"Qingyu Bian, Zheyuan Shen, Jian Gao, Liteng Shen, Yang Lu, Qingnan Zhang, Roufen Chen, Donghang Xu, Tao Liu, Jinxin Che, Yan Lu, Xiaowu Dong","doi":"10.1021/acs.jcim.4c01365","DOIUrl":"https://doi.org/10.1021/acs.jcim.4c01365","url":null,"abstract":"<p><p>Predicting protein-protein interactions (PPIs) is crucial for advancing drug discovery. Despite the proposal of numerous advanced computational methods, these approaches often suffer from poor usability for biologists and lack generalization. In this study, we designed a deep learning model based on a coattention mechanism that was capable of both PPI and site prediction and used this model as the foundation for PPI-CoAttNet, a user-friendly, multifunctional web server for PPI prediction. This platform provides comprehensive services for online PPI model training, PPI and site prediction, and prediction of interactions with proteins associated with highly prevalent cancers. In our <i>Homo sapiens</i> test set for PPI prediction, PPI-CoAttNet achieved an AUC of 0.9841 and an F1 score of 0.9440, outperforming most state-of-the-art models. Additionally, these results are generated in real time, delivering outcomes within minutes. We also evaluated PPI-CoAttNet for downstream tasks, including novel E3 ligase scoring, demonstrating outstanding accuracy. We believe that this tool will empower researchers, especially those without computational expertise, to leverage AI for accelerating drug development.</p>","PeriodicalId":44,"journal":{"name":"Journal of Chemical Information and Modeling ","volume":"65 2","pages":"461-471"},"PeriodicalIF":5.6,"publicationDate":"2025-01-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143044963","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":"Graph-Based Deep Learning Models for Thermodynamic Property Prediction: The Interplay between Target Definition, Data Distribution, Featurization, and Model Architecture.","authors":"Bowen Deng, Thijs Stuyver","doi":"10.1021/acs.jcim.4c02014","DOIUrl":"10.1021/acs.jcim.4c02014","url":null,"abstract":"<p><p>In this contribution, we examine the interplay between target definition, data distribution, featurization approaches, and model architectures on graph-based deep learning models for thermodynamic property prediction. Through consideration of five curated data sets, exhibiting diversity in elemental composition, multiplicity, charge state, and size, we examine the impact of each of these factors on model accuracy. We observe that target definition, i.e., using formation instead of atomization energy/enthalpy, is a decisive factor, and so is a careful selection of the featurization approach. Our attempts at directly modifying model architectures result in more modest, though not negligible, accuracy gains. Remarkably, we observe that molecule-level predictions tend to outperform atom-level increment predictions, in contrast to previous findings. Overall, this work paves the way toward the development of robust graph-based thermodynamic model architectures with more universal capabilities, i.e., architectures that can reach excellent accuracy across data sets and compound domains.</p>","PeriodicalId":44,"journal":{"name":"Journal of Chemical Information and Modeling ","volume":" ","pages":"649-659"},"PeriodicalIF":5.6,"publicationDate":"2025-01-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142941362","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":"Peptide-Aware Chemical Language Model Successfully Predicts Membrane Diffusion of Cyclic Peptides.","authors":"Aaron L Feller, Claus O Wilke","doi":"10.1021/acs.jcim.4c01441","DOIUrl":"10.1021/acs.jcim.4c01441","url":null,"abstract":"<p><p>Language modeling applied to biological data has significantly advanced the prediction of membrane penetration for small-molecule drugs and natural peptides. However, accurately predicting membrane diffusion for peptides with pharmacologically relevant modifications remains a substantial challenge. Here, we introduce PeptideCLM, a peptide-focused chemical language model capable of encoding peptides with chemical modifications, unnatural or noncanonical amino acids, and cyclizations. We assess this model by predicting membrane diffusion of cyclic peptides, demonstrating greater predictive power than existing chemical language models. Our model is versatile and can be extended beyond membrane diffusion predictions to other target values. Its advantages include the ability to model macromolecules using chemical string notation, a largely unexplored domain, and a simple, flexible architecture that allows for adaptation to any peptide or other macromolecule data set.</p>","PeriodicalId":44,"journal":{"name":"Journal of Chemical Information and Modeling ","volume":" ","pages":"571-579"},"PeriodicalIF":5.6,"publicationDate":"2025-01-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142941369","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":"Quotient Complex (QC)-Based Machine Learning for 2D Hybrid Perovskite Design.","authors":"Chuan-Shen Hu, Rishikanta Mayengbam, Kelin Xia, Tze Chien Sum","doi":"10.1021/acs.jcim.4c02033","DOIUrl":"10.1021/acs.jcim.4c02033","url":null,"abstract":"<p><p>With remarkable stability and exceptional optoelectronic properties, two-dimensional (2D) halide layered perovskites hold immense promise for revolutionizing photovoltaic technology. Effective data representations are key to the success of all learning models. Currently, the lack of comprehensive and accurate material representations has hindered AI-based design and discovery of 2D perovskites, limiting their potential for advanced photovoltaic applications. In this context, this work introduces a novel computational topology framework termed the quotient complex (QC), which serves as the foundation for the material representation. The proposed QC-based features are seamlessly integrated with learning models for the advancement of 2D perovskite design. At the heart of this framework lies the quotient complex descriptors (QCDs), representing a quotient variation of simplicial complexes derived from materials' unit cell and periodic boundary conditions. Differing from prior material representations, this approach encodes higher-order interactions and periodicity information simultaneously. Based on the well-established new materials for solar energetics (NMSE) databank, the proposed QC-based machine learning models exhibit superior performance against all existing counterparts. This underscores the paramount role of periodicity information in predicting material functionality, while also showcasing the remarkable efficiency of the QC-based model in characterizing materials' structural attributes.</p>","PeriodicalId":44,"journal":{"name":"Journal of Chemical Information and Modeling ","volume":" ","pages":"660-671"},"PeriodicalIF":5.6,"publicationDate":"2025-01-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142941371","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":"Enhanced Sampling Simulations of RNA-Peptide Binding Using Deep Learning Collective Variables.","authors":"Nisha Kumari, Sonam, Tarak Karmakar","doi":"10.1021/acs.jcim.4c01438","DOIUrl":"10.1021/acs.jcim.4c01438","url":null,"abstract":"<p><p>Enhanced sampling (ES) simulations of biomolecular recognition, such as binding small molecules to proteins and nucleic acid targets, protein-protein association, and protein-nucleic acid interactions, have gained significant attention in the simulation community because of their ability to sample long-time scale processes. However, a key challenge in implementing collective variable (CV)-based enhanced sampling methods is the selection of appropriate CVs that can distinguish the system's metastable states and, when biased, can effectively sample these states. This challenge is particularly acute when the binding of a flexible molecule to a conformationally rich host molecule is simulated, such as the binding of a peptide to an RNA. In such cases, a large number of CVs are required to capture the conformations of both the host and the guest as well as the binding process. Using such a large number of descriptors is impractical in any enhanced sampling simulation method. In our work, we used the recently developed deep targeted discriminant analysis (Deep-TDA) method to design CVs to study the binding of a cyclic peptide, L22, to a TAR RNA of HIV, which is a prototypical system. The Deep-TDA CV, obtained from a nonlinear combination of important contact pairs between the L22 peptide and the host RNA backbone atoms, along with the RNA apical loop RMSD as the second CV were used in the on-the-fly probability-based enhanced sampling (OPES) simulation to sample the reversible binding and unbinding of the L22 peptide to the TAR RNA target. The OPES simulation delineated the mechanism of peptide binding and unbinding to and from the RNA and enabled the calculation of the underlying free energy landscape. Our results demonstrate the potential of the Deep-TDA method for designing CVs to study complex biomolecular recognition processes.</p>","PeriodicalId":44,"journal":{"name":"Journal of Chemical Information and Modeling ","volume":" ","pages":"563-570"},"PeriodicalIF":5.6,"publicationDate":"2025-01-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142941459","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":"PairMap: An Intermediate Insertion Approach for Improving the Accuracy of Relative Free Energy Perturbation Calculations for Distant Compound Transformations.","authors":"Kairi Furui, Takafumi Shimizu, Yutaka Akiyama, S Roy Kimura, Yoh Terada, Masahito Ohue","doi":"10.1021/acs.jcim.4c01634","DOIUrl":"10.1021/acs.jcim.4c01634","url":null,"abstract":"<p><p>Accurate prediction of the difference in binding free energy between compounds is crucial for reducing the high costs associated with drug discovery. Relative binding free energy perturbation (RBFEP) calculations are effective for small structural changes; however, large topological changes pose significant challenges for calculations, leading to high errors and difficulties in convergence. To address such issues, we propose a new approach─PairMap─that focuses on introducing appropriate intermediates for complex transformations between two input compounds. PairMap-generated intermediates exhaustively, determined the optimal conversion paths, and introduced thermodynamic cycles into the perturbation map to improve accuracy and reduce computational cost. PairMap succeeded in introducing appropriate intermediates that could not be discovered by existing simple approaches by comprehensively considering intermediates. Furthermore, we evaluated the accuracy of the prediction of binding free energy using 9 compounds selected from Wang et al.'s benchmark set, which included particularly complex transformations. The perturbation map generated by PairMap achieved excellent accuracy with a mean absolute error of 0.93 kcal/mol compared to 1.70 kcal/mol when using the perturbation map generated by the conventional Flare FEP intermediate introduction method. Moreover, in a scaffold hopping experiment conducted with the PDE5a target involving complex transformations, PairMap provided more accurate free energy predictions than ABFEP calculations, yielding more reliable results compared to experimental data. Additionally, PairMap can be utilized to introduce intermediates into congeneric series, demonstrating that complex links on the perturbation map can be resolved with minimal addition of intermediates and links. In conclusion, PairMap overcomes the limitations of existing methods by enabling RBFEP calculations for more complex transformations, further streamlining lead optimization in drug discovery.</p>","PeriodicalId":44,"journal":{"name":"Journal of Chemical Information and Modeling ","volume":" ","pages":"705-721"},"PeriodicalIF":5.6,"publicationDate":"2025-01-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142968666","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":"Discovery of Brain-Penetrative Negative Allosteric Modulators of NMDA Receptors Using FEP-Guided Structure Optimization and Membrane Permeability Prediction.","authors":"Fabao Zhao, Liyang Jiang, Jieying Xie, Na Liu, Zhen Gao, Yue Yang, Yu Wang, Boshi Huang, Dongwei Kang, Peng Zhan, Feng Yi, Xinyong Liu","doi":"10.1021/acs.jcim.4c01636","DOIUrl":"10.1021/acs.jcim.4c01636","url":null,"abstract":"<p><p><i>N</i>-Methyl-d-aspartate (NMDA) receptors, a subtype of ionotropic glutamate receptors in the central nervous system (CNS), have garnered attention for their role in brain disorders. Specifically, GluN2A-containing NMDA receptors have emerged as a potential therapeutic target for the treatment of depressive disorders and epilepsy. However, the development of GluN2A-containing NMDA receptor-selective antagonists, represented by <i>N</i>-(4-(2-benzoylhydrazine-1-carbonyl)benzyl)-3-chloro-4-fluorobenzenesulfonamide (TCN-201) and its derivatives, faces a significant challenge due to their limited ability to penetrate the blood-brain barrier (BBB), hampering their <i>in vivo</i> characterization and further advancement. In this study, we reported a series of 2-((5-(phemylamino)-1,3,4-thiadiazol-2-yl)thio)-<i>N</i>-(cyclohexylmethyl)acetamide derivatives, achieved through a structure-guided optimization strategy using free energy perturbation (FEP) and BBB permeability estimation. Through systematic exploration of various phenyl substitutions, compound <b>1f</b> emerged as a standout compound, demonstrating substantially enhanced inhibitory activity compared with the lead compound TCN-213. Compound <b>1f</b> not only displayed satisfactory BBB permeability but also showed antidepressant-like potency in the hydrocortisone-induced zebrafish depression-like model. All results position it as a promising candidate for developing innovative therapeutics for NMDA receptor-related disorders.</p>","PeriodicalId":44,"journal":{"name":"Journal of Chemical Information and Modeling ","volume":" ","pages":"857-872"},"PeriodicalIF":5.6,"publicationDate":"2025-01-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142981957","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}