Journal of Chemical Information and Modeling 最新文献_第2页

SynthMol: A Drug Safety Prediction Framework Integrating Graph Attention and Molecular Descriptors into Pre-Trained Geometric Models.

IF 5.6 2区化学

Journal of Chemical Information and Modeling Pub Date : 2025-02-25 DOI: 10.1021/acs.jcim.4c01320

Zidong Su, Rong Zhang, Xiaoyu Fan, Boxue Tian

{"title":"SynthMol: A Drug Safety Prediction Framework Integrating Graph Attention and Molecular Descriptors into Pre-Trained Geometric Models.","authors":"Zidong Su, Rong Zhang, Xiaoyu Fan, Boxue Tian","doi":"10.1021/acs.jcim.4c01320","DOIUrl":"https://doi.org/10.1021/acs.jcim.4c01320","url":null,"abstract":"Drug safety is affected by multiple molecular properties and safety assessment is critical for clinical application. Evaluating a drug candidate's therapeutic potential is facilitated by machine learning models trained on extensive compound bioactivity data sets, presenting a promising approach to drug safety assessment. Here, we introduce SynthMol, a deep learning framework that integrates pre-trained 3D structural features, graph attention networks, and molecular fingerprints to achieve high accuracy in molecular property prediction. Evaluation of SynthMol on 22 data sets, including MoleculeNet, MolData and published drug safety data, showed that it could provide higher prediction accuracy than state-of-the-art model in most tasks. SynthMol achieved an ROC-AUC value of 0.944 in the BBBP data set, 2.61% higher than the next best model, and an ROC-AUC of 0.906 on the hERG data set, a 2.38% improvement. Validation of SynthMol in real-world applications with experimentally determined hERG toxicity and CYP inhibition data supported its capacity to distinguish functional changes for drug development. The implementation code and data are available at https://github.com/ThomasSu1/SynthMol.","PeriodicalId":44,"journal":{"name":"Journal of Chemical Information and Modeling ","volume":" ","pages":""},"PeriodicalIF":5.6,"publicationDate":"2025-02-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143497549","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}

引用次数: 0

Mechanistic Insights into the Reversible Inhibition of d-Cycloserine in Alanine Racemase from Mycobacterium tuberculosis.

IF 5.6 2区化学

Journal of Chemical Information and Modeling Pub Date : 2025-02-25 DOI: 10.1021/acs.jcim.4c01763

Jingyuan Zhuang, Wei Yang, Gui-Juan Cheng

{"title":"Mechanistic Insights into the Reversible Inhibition of d-Cycloserine in Alanine Racemase from Mycobacterium tuberculosis.","authors":"Jingyuan Zhuang, Wei Yang, Gui-Juan Cheng","doi":"10.1021/acs.jcim.4c01763","DOIUrl":"https://doi.org/10.1021/acs.jcim.4c01763","url":null,"abstract":"d-Cycloserine (DCS), an antibiotic used in the treatment of drug-resistant tuberculosis, was traditionally believed to irreversibly inhibit the pyridoxal-5'-phosphate (PLP)-dependent alanine racemase from Mycobacterium tuberculosis (MtAlr). However, recent research suggests that the inhibition is reversible, as MtAlr can be reactivated by destructing DCS. This study employs the hybrid quantum mechanics/molecular mechanics (QM/MM) method to investigate the mechanisms of MtAlr inhibition and DCS destruction. Computational results indicate that the inhibition reaction via an \"isoxazole-forming\" pathway is kinetically favorable, while the DCS destruction reaction via an \"oxime-forming\" pathway is thermodynamically favorable, explaining the irreversible inhibition of DCS. For the inhibition reaction, the isoxazole product was found to prefer the keto form, contrary to the previously proposed enol form. Moreover, K44 and D322' were identified as key residues. K44 transfers the proton from Cα and Cβ of DCS, while D322' stabilizes the carbanion intermediate and isoxazole product via electrostatic interaction with the protonated K44. Such electrostatic interaction was eliminated in the DCS-resistance variant, D322'N, making the inhibition reaction unfavorable. For DCS destruction, an \"up-to-down\" conformational change is required to place the isoxazolidinone ring in an appropriate position for hydrolysis. The deprotonated Y273' facilitates the hydrolysis reaction by enhancing the nucleophilicity of the water molecule. Throughout the whole reaction of MtAlr, PLP plays multiple roles, including stabilizing the carbanion intermediate and acting as a proton shuttle. Overall, this study provides deeper insight into the catalytic mechanism of MtAlr and offers valuable insights for drug development.","PeriodicalId":44,"journal":{"name":"Journal of Chemical Information and Modeling ","volume":" ","pages":""},"PeriodicalIF":5.6,"publicationDate":"2025-02-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143490323","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}

引用次数: 0

Classification-Based Detection and Quantification of Cross-Domain Data Bias in Materials Discovery. 基于分类的材料发现中跨领域数据偏差的检测与量化。

IF 5.6 2区化学

Journal of Chemical Information and Modeling Pub Date : 2025-02-24 Epub Date: 2024-12-16 DOI: 10.1021/acs.jcim.4c01766

Giovanni Trezza, Eliodoro Chiavazzo

{"title":"Classification-Based Detection and Quantification of Cross-Domain Data Bias in Materials Discovery.","authors":"Giovanni Trezza, Eliodoro Chiavazzo","doi":"10.1021/acs.jcim.4c01766","DOIUrl":"10.1021/acs.jcim.4c01766","url":null,"abstract":"It stands to reason that the amount and the quality of data are of key importance for setting up accurate artificial intelligence (AI)-driven models. Among others, a fundamental aspect to consider is the bias introduced during sample selection in database generation. This is particularly relevant when a model is trained on a specialized data set to predict a property of interest and then applied to forecast the same property over samples having a completely different genesis. Indeed, the resulting biased model will likely produce unreliable predictions for many of those out-of-the-box samples, i.e., samples out of the training set. Neglecting such an aspect may hinder the AI-based discovery process, even when high-quality, sufficiently large, and highly reputable data sources are available. To address this challenge, we propose a new method that detects and quantifies data bias, reducing its impact on materials discovery. Our approach, aimed at identifying and excluding those out-of-the-box materials for which the predictions of a pretrained model are likely unreliable, leverages a classification strategy and is validated by means of superconductor and thermoelectric materials as two representative case studies. This methodology, designed to be simple, flexible, and easily adaptable to any architecture, including modern graph equivariant neural networks, aims to enhance the reliability of AI models when applied to diverse and previously unseen materials, thereby contributing to more reliable AI-driven materials discovery.","PeriodicalId":44,"journal":{"name":"Journal of Chemical Information and Modeling ","volume":" ","pages":"1747-1761"},"PeriodicalIF":5.6,"publicationDate":"2025-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142833213","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}

引用次数: 0

CL-GNN: Contrastive Learning and Graph Neural Network for Protein-Ligand Binding Affinity Prediction. CL-GNN：用于蛋白质配体结合亲和力预测的对比学习和图神经网络。

IF 5.6 2区化学

Journal of Chemical Information and Modeling Pub Date : 2025-02-24 Epub Date: 2025-02-06 DOI: 10.1021/acs.jcim.4c01290

Yunjiang Zhang, Chenyu Huang, Yaxin Wang, Shuyuan Li, Shaorui Sun

{"title":"CL-GNN: Contrastive Learning and Graph Neural Network for Protein-Ligand Binding Affinity Prediction.","authors":"Yunjiang Zhang, Chenyu Huang, Yaxin Wang, Shuyuan Li, Shaorui Sun","doi":"10.1021/acs.jcim.4c01290","DOIUrl":"10.1021/acs.jcim.4c01290","url":null,"abstract":"In the realm of drug discovery and design, the accurate prediction of protein-ligand binding affinity is of paramount importance as it underpins the functional interactions within biological systems. This study introduces a novel self-supervised learning (SSL) framework that combines contrastive learning and graph neural networks (CL-GNN) for predicting protein-ligand binding affinities, which is a critical aspect of drug discovery. Traditional methods for affinity prediction are expensive and time-consuming, prompting the development of more efficient computational approaches. CL-GNN utilizes a contrastive learning strategy, a form of SSL, to learn from a large data set of 371 458 unique unlabeled protein-ligand complexes. By employing graph neural networks and molecular graph enhancement techniques, the model effectively captures protein-ligand interactions in a self-supervised manner. The fine-tuned model demonstrates competitive performance, achieving high Pearson's correlation coefficients and low root-mean-square errors on benchmark data sets. The proposed method outperforms existing machine learning models, showcasing its potential for accelerating the drug development process. The method effectively quantifies the similarity between protein-ligand complex representations learned in the pretraining and downstream testing phases through cosine similarity assessment. This approach not only revealed potential connections between complexes in their binding properties but also provided new insights into the understanding of drug mechanisms of action. In addition, the transparency of the model is significantly improved by visualizing the importance of key protein residues and ligand atoms. This visualization tool provides insight into the model's predictive decision-making process, providing key biological insights for drug design and optimization.","PeriodicalId":44,"journal":{"name":"Journal of Chemical Information and Modeling ","volume":" ","pages":"1724-1735"},"PeriodicalIF":5.6,"publicationDate":"2025-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143363279","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}

引用次数: 0

Computational Chemistry in the Global South: A Latin American Perspective.

IF 5.6 2区化学

Journal of Chemical Information and Modeling Pub Date : 2025-02-24 DOI: 10.1021/acs.jcim.5c00148

Sergio Pantano, Luciana Capece, Laura Gagliardi, Kenneth M Merz, Victor Batista, Thereza A Soares

引用次数: 0

Head-to-Tail Cyclization Enhances Ice-Growth Inhibition by Linear Threonine Oligomers.

IF 5.6 2区化学

Journal of Chemical Information and Modeling Pub Date : 2025-02-24 DOI: 10.1021/acs.jcim.4c02418

Haipeng Wang, Xuyang Liu, Wensheng Cai, Xueguang Shao

{"title":"Head-to-Tail Cyclization Enhances Ice-Growth Inhibition by Linear Threonine Oligomers.","authors":"Haipeng Wang, Xuyang Liu, Wensheng Cai, Xueguang Shao","doi":"10.1021/acs.jcim.4c02418","DOIUrl":"https://doi.org/10.1021/acs.jcim.4c02418","url":null,"abstract":"Developing short antifreeze peptides with low immunogenicity is considered to be a promising strategy for improving cryopreservation. Inspired by the design principles of cyclic peptide drugs characterized by high stability and strong affinity, we propose to use the cyclization strategy as a principle for the design of antifreeze peptides, aiming to enhance their structural stability and ice-binding ability, thereby significantly improving their antifreeze activity. In this study, we choose linear threonine oligomers (L-(Thr)n), composed of common and biocompatible threonine residues, to investigate the mechanism and efficacy of cyclization. Molecular dynamics (MD) simulations are used to compare the ice-growth inhibition ability of a series of linear oligomers and their corresponding cyclic counterparts (49 molecular systems) on different ice planes, resulting in 80.8 μs MD trajectories. A detailed analysis of conformational changes during inhibition and their correlation with inhibitory efficiency reveals that conformational variability is detrimental to the binding of L-(Thr)n to ice, while β-sheet-like conformation has a significant advantage in inhibiting ice growth and is identified as a key factor for the superior performance of cyclized oligomers (C-(Thr)n) over their linear counterparts. Encouragingly, we find that C-(Thr)12 exhibits the most prominent performance, surpassing previously reported cyclic peptides of similar size due to its enhanced structural stability, superior ice binding, coverage, and antiengulfment capabilities. This study provides valuable insights into the design of small-sized ice-growth inhibitors through head-to-tail cyclization of linear oligomers. However, it should be noted that our findings are based purely on computational simulations, and experimental validation in actual cryopreservation conditions remains necessary.","PeriodicalId":44,"journal":{"name":"Journal of Chemical Information and Modeling ","volume":" ","pages":""},"PeriodicalIF":5.6,"publicationDate":"2025-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143490321","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}

引用次数: 0

Natural Language Processing Methods for the Study of Protein-Ligand Interactions.

IF 5.6 2区化学

Journal of Chemical Information and Modeling Pub Date : 2025-02-24 DOI: 10.1021/acs.jcim.4c01907

James Michels, Ramya Bandarupalli, Amin Ahangar Akbari, Thai Le, Hong Xiao, Jing Li, Erik F Y Hom

引用次数: 0

PUCHIK: A Python Package To Analyze Molecular Dynamics Simulations of Aspherical Nanoparticles.

IF 5.6 2区化学

Journal of Chemical Information and Modeling Pub Date : 2025-02-24 Epub Date: 2025-02-10 DOI: 10.1021/acs.jcim.4c02128

Hrachya Ishkhanyan, Alejandro Santana-Bonilla, Christian D Lorenz

{"title":"PUCHIK: A Python Package To Analyze Molecular Dynamics Simulations of Aspherical Nanoparticles.","authors":"Hrachya Ishkhanyan, Alejandro Santana-Bonilla, Christian D Lorenz","doi":"10.1021/acs.jcim.4c02128","DOIUrl":"10.1021/acs.jcim.4c02128","url":null,"abstract":"Accurately describing a nanoparticle's interface is crucial for understanding its internal structure, interfacial properties, and ultimately, its functionality. While current computational methods provide reasonable descriptions for spherical and quasi-spherical nanoparticles, there remains a need for effective models for aspherical structures such as capsules and rod-like systems. This work introduces Python Utility for Characterizing Heterogeneous Interfaces and Kinetics (PUCHIK), a novel algorithm developed to describe both spherelike and aspherical nanoparticles. With an accurate description of the location of the interface of the nanoparticle, this algorithm then allows for various other important quantities (e.g., densities of different atom/molecule types relative to the interface, volume of the nanoparticle, amount of solubilized molecules within the nanoparticle) to be calculated. Our software development, we focused on providing good performance to computationally demanding projects, while ensuring that the methodological approach can be adapted as a protocol for other code implementations.","PeriodicalId":44,"journal":{"name":"Journal of Chemical Information and Modeling ","volume":" ","pages":"1694-1701"},"PeriodicalIF":5.6,"publicationDate":"2025-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11863366/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143389503","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"化学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

MELD in Action: Harnessing Data to Accelerate Molecular Dynamics.

IF 5.6 2区化学

Journal of Chemical Information and Modeling Pub Date : 2025-02-24 Epub Date: 2025-02-02 DOI: 10.1021/acs.jcim.4c02108

Jokent Gaza, Emiliano Brini, Justin L MacCallum, Ken A Dill, Alberto Perez

引用次数: 0

Investigations into the Efficiency of Computer-Aided Synthesis Planning.

IF 5.6 2区化学

Journal of Chemical Information and Modeling Pub Date : 2025-02-24 Epub Date: 2025-01-31 DOI: 10.1021/acs.jcim.4c01821

Peter B R Hartog, Annie M Westerlund, Igor V Tetko, Samuel Genheden

{"title":"Investigations into the Efficiency of Computer-Aided Synthesis Planning.","authors":"Peter B R Hartog, Annie M Westerlund, Igor V Tetko, Samuel Genheden","doi":"10.1021/acs.jcim.4c01821","DOIUrl":"10.1021/acs.jcim.4c01821","url":null,"abstract":"The efficiency of machine learning (ML) models is crucial to minimize inference times and reduce the carbon footprints of models deployed in production environments. Current models employed in retrosynthesis to generate a synthesis route from a target molecule to purchasable compounds are prohibitively slow. The model operates in a single-step fashion in a tree search algorithm by predicting reactant molecules given a product molecule as input. In this study, we investigate the ability of alternative transformer architectures, knowledge distillation (KD), and simple hyper-parameter optimization to decrease inference times of the Chemformer model. Initially, we assess the ability of closely related transformer architectures and conclude that these models under-performed when using KD. Additionally, we investigate the effects of feature-based and response-based KD together with hyper-parameters optimized based on inference sample time and model accuracy. We find that although reducing model size and improving single-step speed are important, our results indicate that multi-step search efficiency is more significantly influenced by the diversity and confidence of single-step models. Based on this work, further research should use KD in combination with other techniques, as multi-step speed continues to prevent proper integration of synthesis planning. However, in Monte Carlo-based (MC) multi-step retrosynthesis, other factors play a crucial role in balancing exploration and exploitation during the search process, often outweighing the direct impact of single-step model speed and carbon footprints.","PeriodicalId":44,"journal":{"name":"Journal of Chemical Information and Modeling ","volume":" ","pages":"1771-1781"},"PeriodicalIF":5.6,"publicationDate":"2025-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11863376/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143070734","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"化学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0