Journal of Chemical Information and Modeling 最新文献

{"title":"Prediction of Proteolysis-Targeting Chimeras Retention Time Using XGBoost Model Incorporated with Chromatographic Conditions.","authors":"Xinhao Qu, Chen Jiang, Mengyi Shan, Wenhao Ke, Jing Chen, Qiming Zhao, Youhong Hu, Jia Liu, Lu-Ping Qin, Gang Cheng","doi":"10.1021/acs.jcim.4c01732","DOIUrl":"10.1021/acs.jcim.4c01732","url":null,"abstract":"<p><p>Proteolysis-targeting chimeras (PROTACs) are heterobifunctional molecules that target undruggable proteins, enhance selectivity and prevent target accumulation through catalytic activity. The unique structure of PROTACs presents challenges in structural identification and drug design. Liquid chromatography (LC), combined with mass spectrometry (MS), enhances compound annotation by providing essential retention time (RT) data, especially when MS alone is insufficient. However, predicting RT for PROTACs remains challenging. To address this, we compiled the PROTAC-RT data set from literature and evaluated the performance of four machine learning algorithms─extreme gradient boosting (XGBoost), random forest (RF), K-nearest neighbor (KNN) and support vector machines (SVM)─and a deep learning model, fully connected neural network (FCNN), using 24 molecular fingerprints and descriptors. Through screening combinations of molecular fingerprints, descriptors and chromatographic condition descriptors (CCs), we developed an optimized XGBoost model (XGBoost + moe206+Path + Charge + CCs) that achieved an <i>R</i>² of 0.958 ± 0.027 and an RMSE of 0.934 ± 0.412. After hyperparameter tuning, the model's <i>R</i>² improved to 0.963 ± 0.023, with an RMSE of 0.896 ± 0.374. The model showed strong predictive accuracy under new chromatographic separation conditions and was validated using six experimentally determined compounds. SHapley Additive exPlanations (SHAP) not only highlights the advantages of XGBoost but also emphasizes the importance of CCs and molecular features, such as bond variability, van der Waals surface area, and atomic charge states. The optimized XGBoost model combines moe206, path, charge descriptors, and CCs, providing a fast and precise method for predicting the RT of PROTACs compounds, thus facilitating their annotation.</p>","PeriodicalId":44,"journal":{"name":"Journal of Chemical Information and Modeling ","volume":" ","pages":"613-625"},"PeriodicalIF":5.6,"publicationDate":"2025-01-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142941370","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":"CovCysPredictor: Predicting Selective Covalently Modifiable Cysteines Using Protein Structure and Interpretable Machine Learning.","authors":"Bryn Marie Reimer, Ernest Awoonor-Williams, Andrei A Golosov, Viktor Hornak","doi":"10.1021/acs.jcim.4c01281","DOIUrl":"10.1021/acs.jcim.4c01281","url":null,"abstract":"<p><p>Targeted covalent inhibition is a powerful therapeutic modality in the drug discoverer's toolbox. Recent advances in covalent drug discovery, in particular, targeting cysteines, have led to significant breakthroughs for traditionally challenging targets such as mutant KRAS, which is implicated in diverse human cancers. However, identifying cysteines for targeted covalent inhibition is a difficult task, as experimental and in silico tools have shown limited accuracy. Using the recently released CovPDB and CovBinderInPDB databases, we have trained and tested interpretable machine learning (ML) models to identify cysteines that are liable to be covalently modified (i.e., \"ligandable\" cysteines). We explored myriad physicochemical features (p<i>K</i>_a, solvent exposure, residue electrostatics, etc.) and protein-ligand pocket descriptors in our ML models. Our final logistic regression model achieved a median F₁ score of 0.73 on held-out test sets. When tested on a small sample of <i>holo</i> proteins, our model also showed reasonable performance, accurately predicting the most ligandable cysteine in most cases. Taken together, these results indicate that we can accurately predict potential ligandable cysteines for targeted covalent drug discovery, privileging cysteines that are more likely to be selective rather than purely reactive. We release this tool to the scientific community as CovCysPredictor.</p>","PeriodicalId":44,"journal":{"name":"Journal of Chemical Information and Modeling ","volume":" ","pages":"544-553"},"PeriodicalIF":5.6,"publicationDate":"2025-01-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142941456","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":"HIV OctaScanner: A Machine Learning Approach to Unveil Proteolytic Cleavage Dynamics in HIV-1 Protease Substrates.","authors":"Kashif Iqbal Sahibzada, Shumaila Shahid, Mohsina Akhter, Rizwan Abid, Muteeba Azhar, Yuansen Hu, Dong-Qing Wei","doi":"10.1021/acs.jcim.4c01808","DOIUrl":"10.1021/acs.jcim.4c01808","url":null,"abstract":"<p><p>The rise of resistance to antiretroviral drugs due to mutations in human immunodeficiency virus-1 (HIV-1) protease is a major obstacle to effective treatment. These mutations alter the drug-binding pocket of the protease and reduce the drug efficacy by disrupting interactions with inhibitors. Traditional methods, such as biochemical assays and structural biology, are crucial for studying enzyme function but are time-consuming and labor-intensive. To address these challenges, we developed HIV OctaScanner, a machine learning algorithm that predicts the proteolytic cleavage activity of octameric substrates at the HIV-1 protease cleavage sites. The algorithm uses a Random Forest (RF) classifier and achieves a prediction accuracy of 89% in the identification of cleavable octamers. This innovative approach facilitates the rapid screening of potential substrates for HIV-1 protease, providing critical insights into enzyme function and guiding the development of more effective therapeutic strategies. By improving the accuracy of substrate identification, HIV OctaScanner has the potential to support the development of next generation antiretroviral treatments.</p>","PeriodicalId":44,"journal":{"name":"Journal of Chemical Information and Modeling ","volume":" ","pages":"640-648"},"PeriodicalIF":5.6,"publicationDate":"2025-01-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142976865","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":"Free Energy of Membrane Pore Formation and Stability from Molecular Dynamics Simulations.","authors":"Timothée Rivel, Denys Biriukov, Ivo Kabelka, Robert Vácha","doi":"10.1021/acs.jcim.4c01960","DOIUrl":"10.1021/acs.jcim.4c01960","url":null,"abstract":"<p><p>Understanding the molecular mechanisms of pore formation is crucial for elucidating fundamental biological processes and developing therapeutic strategies, such as the design of drug delivery systems and antimicrobial agents. Although experimental methods can provide valuable information, they often lack the temporal and spatial resolution necessary to fully capture the dynamic stages of pore formation. In this study, we present two novel collective variables (CVs) designed to characterize membrane pore behavior, particularly its energetics, through molecular dynamics (MD) simulations. The first CV─termed Full-Path─effectively tracks both the nucleation and expansion phases of pore formation. The second CV─called Rapid─is tailored to accurately assess pore expansion in the limit of large pores, providing quick and reliable method for evaluating membrane line tension under various conditions. Our results clearly demonstrate that the line tension predictions from both our CVs are in excellent agreement. Moreover, these predictions align qualitatively with available experimental data. Specifically, they reflect higher line tension of 1-palmitoyl-2-oleoyl-<i>sn</i>-glycero-3-phosphocholine (POPC) membranes containing 1-palmitoyl-2-oleoyl-<i>sn</i>-glycero-3-phospho-l-serine (POPS) lipids compared to pure POPC, the decrease in line tension of POPC vesicles as the 1-palmitoyl-2-oleoyl-<i>sn</i>-glycero-3-phosphoglycerol (POPG) content increases, and higher line tension when ionic concentration is increased. Notably, these experimental trends are accurately captured only by the all-atom CHARMM36 and prosECCo75 force fields. In contrast, the all-atom Slipids force field, along with the coarse-grained Martini 2.2, Martini 2.2 polarizable, and Martini 3 models, show varying degrees of agreement with experiments. Our developed CVs can be adapted to various MD simulation engines for studying pore formation, with potential implications in membrane biophysics. They are also applicable to simulations involving external agents, offering an efficient alternative to existing methodologies.</p>","PeriodicalId":44,"journal":{"name":"Journal of Chemical Information and Modeling ","volume":" ","pages":"908-920"},"PeriodicalIF":5.6,"publicationDate":"2025-01-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142941461","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":"End-Point Affinity Estimation of Galectin Ligands by Classical and Semiempirical Quantum Mechanical Potentials.","authors":"Jan Choutka, Jakub Kaminský, Ercheng Wang, Kamil Parkan, Radek Pohl","doi":"10.1021/acs.jcim.4c01659","DOIUrl":"10.1021/acs.jcim.4c01659","url":null,"abstract":"<p><p>The use of quantum mechanical potentials in protein-ligand affinity prediction is becoming increasingly feasible with growing computational power. To move forward, validation of such potentials on real-world challenges is necessary. To this end, we have collated an extensive set of over a thousand galectin inhibitors with known affinities and docked them into galectin-3. The docked poses were then used to systematically evaluate several modern force fields and semiempirical quantum mechanical (SQM) methods up to the tight-binding level under consistent computational workflow. Implicit solvation models available with the tested methods were used to simulate solvation effects. Overall, the best methods in this study achieved a Pearson correlation of 0.7-0.8 between the computed and experimental affinities. There were differences between the tested methods in their ability to rank ligands across the entire ligand set as well as within subsets of structurally similar ligands. A major discrepancy was observed for a subset of ligands that bind to the protein via a halogen bond, which was clearly challenging for all the tested methods. The inclusion of an entropic term calculated by the rigid-rotor-harmonic-oscillator approximation at SQM level slightly worsened correlation with experiment but brought the calculated affinities closer to experimental values. We also found that the success of the prediction strongly depended on the solvation model. Furthermore, we provide an in-depth analysis of the individual energy terms and their effect on the overall prediction accuracy.</p>","PeriodicalId":44,"journal":{"name":"Journal of Chemical Information and Modeling ","volume":" ","pages":"762-777"},"PeriodicalIF":5.6,"publicationDate":"2025-01-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142925803","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":"Identifying Protein-Nucleotide Binding Residues via Grouped Multi-task Learning and Pre-trained Protein Language Models.","authors":"Jiashun Wu, Yan Liu, Ying Zhang, Xiaoyu Wang, He Yan, Yiheng Zhu, Jiangning Song, Dong-Jun Yu","doi":"10.1021/acs.jcim.4c02092","DOIUrl":"10.1021/acs.jcim.4c02092","url":null,"abstract":"<p><p>The accurate identification of protein-nucleotide binding residues is crucial for protein function annotation and drug discovery. Numerous computational methods have been proposed to predict these binding residues, achieving remarkable performance. However, due to the limited availability and high variability of nucleotides, predicting binding residues for diverse nucleotides remains a significant challenge. To address these, we propose NucGMTL, a new grouped deep multi-task learning approach designed for predicting binding residues of all observed nucleotides in the BioLiP database. NucGMTL leverages pre-trained protein language models to generate robust sequence embedding and incorporates multi-scale learning along with scale-based self-attention mechanisms to capture a broader range of feature dependencies. To effectively harness the shared binding patterns across various nucleotides, deep multi-task learning is utilized to distill common representations, taking advantage of auxiliary information from similar nucleotides selected based on task grouping. Performance evaluation on benchmark data sets shows that NucGMTL achieves an average area under the Precision-Recall curve (AUPRC) of 0.594, surpassing other state-of-the-art methods. Further analyses highlight that the predominant advantage of NucGMTL can be reflected by its effective integration of grouped multi-task learning and pre-trained protein language models. The data set and source code are freely accessible at: https://github.com/jerry1984Y/NucGMTL.</p>","PeriodicalId":44,"journal":{"name":"Journal of Chemical Information and Modeling ","volume":" ","pages":"1040-1052"},"PeriodicalIF":5.6,"publicationDate":"2025-01-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142941364","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":"deep-AMPpred: A Deep Learning Method for Identifying Antimicrobial Peptides and Their Functional Activities.","authors":"Jun Zhao, Hangcheng Liu, Leyao Kang, Wanling Gao, Quan Lu, Yuan Rao, Zhenyu Yue","doi":"10.1021/acs.jcim.4c01913","DOIUrl":"10.1021/acs.jcim.4c01913","url":null,"abstract":"<p><p>Antimicrobial peptides (AMPs) are small peptides that play an important role in disease defense. As the problem of pathogen resistance caused by the misuse of antibiotics intensifies, the identification of AMPs as alternatives to antibiotics has become a hot topic. Accurately identifying AMPs using computational methods has been a key issue in the field of bioinformatics in recent years. Although there are many machine learning-based AMP identification tools, most of them do not focus on or only focus on a few functional activities. Predicting the multiple activities of antimicrobial peptides can help discover candidate peptides with broad-spectrum antimicrobial ability. We propose a two-stage AMP predictor deep-AMPpred, in which the first stage distinguishes AMP from other peptides, and the second stage solves the multilabel problem of 13 common functional activities of AMP. deep-AMPpred combines the ESM-2 model to encode the features of AMP and integrates CNN, BiLSTM, and CBAM models to discover AMP and its functional activities. The ESM-2 model captures the global contextual features of the peptide sequence, while CNN, BiLSTM, and CBAM combine local feature extraction, long-term and short-term dependency modeling, and attention mechanisms to improve the performance of deep-AMPpred in AMP and its function prediction. Experimental results demonstrate that deep-AMPpred performs well in accurately identifying AMPs and predicting their functional activities. This confirms the effectiveness of using the ESM-2 model to capture meaningful peptide sequence features and integrating multiple deep learning models for AMP identification and activity prediction.</p>","PeriodicalId":44,"journal":{"name":"Journal of Chemical Information and Modeling ","volume":" ","pages":"997-1008"},"PeriodicalIF":5.6,"publicationDate":"2025-01-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142941457","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":"Adaptive Lambda Scheduling: A Method for Computational Efficiency in Free Energy Perturbation Simulations.","authors":"Scott D Midgley, Sofia Bariami, Matthew Habgood, Mark Mackey","doi":"10.1021/acs.jcim.4c01668","DOIUrl":"10.1021/acs.jcim.4c01668","url":null,"abstract":"<p><p>Recent increases in the availability of computational power have improved the accessibility of ligand-protein relative binding free energy (RBFE) calculations; however, these calculations remain resource-intensive, which can limit their practical application. RBFE calculations typically use a set of thermodynamic intermediates mediated by the transformation coordinate λ. Optimizing λ offers a way to tune the computational efforts required for a given RBFE calculation. Here, we present Adaptive Lambda Scheduling (ALS), a streamlined approach for on-the-fly bespoke λ scheduling. We show it can achieve substantial reductions in computational cost while retaining predictive performance.</p>","PeriodicalId":44,"journal":{"name":"Journal of Chemical Information and Modeling ","volume":" ","pages":"512-516"},"PeriodicalIF":5.6,"publicationDate":"2025-01-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142941455","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":"How Binding Site Flexibility Promotes RNA Scanning by TbRGG2 RRM: A Molecular Dynamics Simulation Study.","authors":"Toon Lemmens, Jiří Šponer, Miroslav Krepl","doi":"10.1021/acs.jcim.4c01954","DOIUrl":"10.1021/acs.jcim.4c01954","url":null,"abstract":"<p><p>RNA recognition motifs (RRMs) are a key class of proteins that primarily bind single-stranded RNAs. In this study, we applied standard atomistic molecular dynamics simulations to obtain insights into the intricate binding dynamics between uridine-rich RNAs and TbRGG2 RRM using the recently developed OL3-Stafix AMBER force field, which improves the description of single-stranded RNA molecules. Complementing structural experiments that unveil a primary binding mode with a single uridine bound, our simulations uncover two supplementary binding modes in which adjacent nucleotides encroach upon the binding pocket. This leads to a unique molecular mechanism through which the TbRGG2 RRM is capable of rapidly transitioning the U-rich sequence. In contrast, the presence of non-native cytidines induces stalling and destabilization of the complex. By leveraging extensive equilibrium dynamics and a large variety of binding states, TbRGG2 RRM effectively expedites diffusion along the RNA substrate while ensuring robust selectivity for U-rich sequences despite featuring a solitary binding pocket. We further substantiate our description of the complex dynamics by simulating the fully spontaneous association process of U-rich sequences to the TbRGG2 RRM. Our study highlights the critical role of dynamics and auxiliary binding states in interface dynamics employed by RNA-binding proteins, which is not readily apparent in traditional structural studies but could represent a general type of binding strategy employed by many RNA-binding proteins.</p>","PeriodicalId":44,"journal":{"name":"Journal of Chemical Information and Modeling ","volume":" ","pages":"896-907"},"PeriodicalIF":5.6,"publicationDate":"2025-01-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142968663","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-Activity Relationship of Ciprofloxacin towards S-Spike Protein of SARS-CoV-2: Synthesis and <i>In-Silico</i> Evaluation.","authors":"Sahil Kumar, Papiya Dey, Arup Kumar Pathak, Amey Wadawale, Dharmendra K Maurya, Kalyani Natu, Kakoli Bose, Dibakar Goswami","doi":"10.1021/acs.jcim.4c00918","DOIUrl":"10.1021/acs.jcim.4c00918","url":null,"abstract":"<p><p>The recent outbreak of the coronavirus (COVID-19) pandemic, caused by the SARS-CoV-2 virus, has posed serious threats to global health systems. Although several directions have been put by the WHO for effective treatment, use of antibiotics, particularly ciprofloxacin, in suspected and acquired Covid-19 patients has raised an even more serious concern of antibiotic resistance. Ciprofloxacin has been reported to inhibit entry of SARS-CoV-2 into the host cells via interacting with the spike (S) protein. However, a proper structure-activity relationship study of ciprofloxacin with the S-protein is lacking, which inhibits researchers from developing a more potent fluoroquinolone analogue, specific for inhibition of SARS-CoV-2 viral entry. Herein, in order to have a structure-activity relationship study, we have accomplished a short and convergent synthesis of different derivatives of ciprofloxacin and a detailed <i>in-silico</i> study using molecular docking to explore the interactions of the derivatives with S-protein. The ADMET studies also indicated the drug likeliness and nontoxicity of the derivatives. Furthermore, the molecular dynamics simulation approach was used to study the dynamical behavior after the best docked derivative binds to the protein, and the MM-PBSA approach was adopted to calculate the binding energies. This has led to a derivative that has higher interactions with the S-protein compared to ciprofloxacin, without hampering the dynamics of the interactions. The strong affinity of compound <b>5</b> with the SARS-CoV-2 spike RBD protein was further evaluated experimentally using biolayer interferometry (BLI). Furthermore, molecular docking and molecular dynamics simulation were extended to evaluate its binding with the mutated variants Delta and Omicron. We anticipate that the current study could lead to an alternative therapeutic viral inhibitor with a better efficacy than ciprofloxacin.</p>","PeriodicalId":44,"journal":{"name":"Journal of Chemical Information and Modeling ","volume":" ","pages":"825-844"},"PeriodicalIF":5.6,"publicationDate":"2025-01-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142968668","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}