Journal of Chemical Information and Modeling 最新文献

{"title":"Exploring Binding Sites in Chagas Disease Protein TcP21 Using Integrated Mixed Solvent Molecular Dynamics Approaches.","authors":"William Oliveira Soté, Moacyr Comar Junior","doi":"10.1021/acs.jcim.4c01927","DOIUrl":"https://doi.org/10.1021/acs.jcim.4c01927","url":null,"abstract":"<p><p>Chagas disease, caused by the protozoan Trypanosoma cruzi, remains a significant global health burden, particularly in Latin America, where millions are at risk. This disease predominantly affects socioeconomically vulnerable populations, aggravating economic inequality, marginalization, and low political visibility. Despite extensive research, effective treatments are still lacking, partly due to the complex biology of the parasite and its infection mechanisms. This study focuses on TcP21, a novel 21 kDa protein secreted by extracellular amastigotes, which has been implicated in <i>T. cruzi</i> infection via an alternative infective pathway. Although the potential of TcP21 for understanding Chagas disease is promising, further exploration is necessary, particularly in identifying potential binding sites on its surface. Computational tools offer a versatile and effective strategy for preliminary binding site assessment, facilitating a more cost-efficient allocation of experimental resources. In this study, we employed three independent computational approaches─mixed solvent molecular dynamics simulations (MSMD), fragment-based molecular docking, and pharmacophore model docking coupled with molecular dynamics simulations─to identify potential binding sites and provide comprehensive insights into TcP21. The three methodologies converged on a common site located on the external surface of the protein, characterized by key residues such as GLU55, ASP52, VAL70, ILE62, and TRP77. The protonated amino, acetamido, and phenyl groups of the pharmacophore probe were consistently observed to interact with the site via a network of salt bridges, hydrogen bonds, charge-charge interactions, and alkyl-π interactions, suggesting these groups play a significant role in ligand binding. This study does not aim to propose specific therapeutic hits but to highlight a still unknown and unexplored protein involved in <i>T. cruzi</i> cell invasion. In this regard, given the strong correlation between the three distinct approaches used for mapping, we consider this study offers valuable insights for further research into P21 and its role in Chagas disease.</p>","PeriodicalId":44,"journal":{"name":"Journal of Chemical Information and Modeling ","volume":" ","pages":""},"PeriodicalIF":5.6,"publicationDate":"2024-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142833216","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":"AI-Driven Drug Discovery for Rare Diseases.","authors":"Amit Gangwal, Antonio Lavecchia","doi":"10.1021/acs.jcim.4c01966","DOIUrl":"https://doi.org/10.1021/acs.jcim.4c01966","url":null,"abstract":"<p><p>Rare diseases (RDs), affecting 300 million people globally, present a daunting public health challenge characterized by complexity, limited treatment options, and diagnostic hurdles. Despite legislative efforts, such as the 1983 US Orphan Drug Act, more than 90% of RDs lack effective therapies. Traditional drug discovery models, marked by lengthy development cycles and high failure rates, struggle to meet the unique demands of RDs, often yielding poor returns on investment. However, the advent of artificial intelligence (AI), encompassing machine learning (ML) and deep learning (DL), offers groundbreaking solutions. This review explores AI's potential to revolutionize drug discovery for RDs by overcoming these challenges. It discusses AI-driven advancements, such as drug repurposing, biomarker discovery, personalized medicine, genetics, clinical trial optimization, corporate innovations, and novel drug target identification. By synthesizing current knowledge and recent breakthroughs, this review provides crucial insights into how AI can accelerate therapeutic development for RDs, ultimately improving patient outcomes. This comprehensive analysis fills a critical gap in the literature, enhancing understanding of AI's pivotal role in transforming RD research and guiding future research and development efforts in this vital area of medicine.</p>","PeriodicalId":44,"journal":{"name":"Journal of Chemical Information and Modeling ","volume":" ","pages":""},"PeriodicalIF":5.6,"publicationDate":"2024-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142845304","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":"Residue-Level Multiview Deep Learning for ATP Binding Site Prediction and Applications in Kinase Inhibitors.","authors":"Jaechan Lee, Dongmin Bang, Sun Kim","doi":"10.1021/acs.jcim.4c01255","DOIUrl":"https://doi.org/10.1021/acs.jcim.4c01255","url":null,"abstract":"<p><p>Accurate identification of adenosine triphosphate (ATP) binding sites is crucial for understanding cellular functions and advancing drug discovery, particularly in targeting kinases for cancer treatment. Existing methods face significant challenges due to their reliance on time-consuming precomputed features and the heavily imbalanced nature of binding site data without further investigations on their utility in drug discovery. To address these limitations, we introduced Multiview-ATPBind and ResiBoost. Multiview-ATPBind is an end-to-end deep learning model that integrates one-dimensional (1D) sequence and three-dimensional (3D) structural information for rapid and precise residue-level pocket-ligand interaction predictions. Additionally, ResiBoost is a novel residue-level boosting algorithm designed to mitigate data imbalance by enhancing the prediction of rare positive binding residues. Our approach outperforms state-of-the-art models on benchmark data sets, showing significant improvements in balanced metrics with both experimental and AI-predicted structures. Furthermore, our model seamlessly transfers to predicting binding sites and enhancing docking simulations for kinase inhibitors, including imatinib and dasatinib, underscoring the potential of our method in drug discovery applications.</p>","PeriodicalId":44,"journal":{"name":"Journal of Chemical Information and Modeling ","volume":" ","pages":""},"PeriodicalIF":5.6,"publicationDate":"2024-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142845308","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":"Ligand Binding and Functional Effect of Novel Bicyclic α5 GABA_A Receptor Negative Allosteric Modulators.","authors":"Balázs Krámos, Zoltán Béni, György István Túrós, Olivér Éliás, Attila Potor, Gábor László Kapus, György Szabó","doi":"10.1021/acs.jcim.4c01431","DOIUrl":"https://doi.org/10.1021/acs.jcim.4c01431","url":null,"abstract":"<p><p>The significant importance of GABA_A receptors in the treatment of central nervous system (CNS) disorders has been known for a long time. However, only in recent years have experimental protein structures been published that can open the door to understanding protein-ligand interactions and may effectively help the rational drug design for the future. In our previous work (Szabó, G. <i>J. Med. Chem.</i> 2022, 65(11), 7876), where a promising selective α5-GABA_A negative allosteric modulator (NAM) was developed containing the 3-(4-fluorophenyl)-5-methyl-1,2-oxazole headgroup, we noticed a switch-like effect of a single nitrogen atom for the receptor function in some derivatives having a dihydro-naphthyridinone or dihydro-isoquinolinone moiety. Here, we focused on this chemotype, and a small set of compounds were designed to investigate ligand-receptor interactions experimentally and through computational methods. Elaborated compounds were tested against GABA_A α1 and α5 subunit-containing receptors, and binding affinities and functional activities were measured. Starting from the published experimental structure of an engineered, homopentameric, basmisanil-binding GABA_A receptor-like construct consisting of modified α5 subunits and an α1-containing GABA_A structure, we created a new model of the ligand binding site at the α5/γ2 interface. Using this model, the measured ligand affinities were able to be reproduced well by free energy perturbation (FEP) calculations. In addition, calculations were able to explain the obtained structure-activity relationships, among others, the switch-like effect of the aromatic nitrogen position in the dihydro-naphthyridinone motif for the functional character, and suggest different binding poses for the ligands presenting silent versus negative allosteric effects in this set (SAMs vs. NAMs, respectively). We believe that our results can help design α5 selective GABA_A negative allosteric modulators and better understand the GABA_A receptor.</p>","PeriodicalId":44,"journal":{"name":"Journal of Chemical Information and Modeling ","volume":" ","pages":""},"PeriodicalIF":5.6,"publicationDate":"2024-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142833083","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":"ReLMM: Reinforcement Learning Optimizes Feature Selection in Modeling Materials.","authors":"Maitreyee Sharma Priyadarshini, Nikhil Kumar Thota, Rigoberto Hernandez","doi":"10.1021/acs.jcim.4c01934","DOIUrl":"https://doi.org/10.1021/acs.jcim.4c01934","url":null,"abstract":"<p><p>A challenge to materials discovery is the identification of the physical features that are most correlated to a given target material property without redundancy. Such variables necessarily comprise the optimal search domain in subsequent material design. Here, we introduce a reinforcement learning-based material model (ReLMM) as a tool for analyzing a given database in identifying a minimal or near minimal subset of physical features for the design of a material with a given target property. We aim for minimality in the selected subset with respect to its size─smaller being better─ while maintaining the desired accuracy of the prediction. We have shown, using synthetic multiscale data sets, that ReLMM can identify the relative importance of features, and thus help identify which should be selected across scales. In the context of semiconducting materials, ReLMM can be used to improve the prediction of the band gap by identifying which features should be selected in model building. For metal halide perovskites, ReLMM was seen to find a near minimal data set at least as well as, if not better than, state-of-the-art feature selection tools such as LASSO and XGBoost. We also found that our domain-science oriented approach can be used to uncover the hierarchical structure of a material from a database consisting of molecular-scale, mesoscale and device-scale features and labels in complementarity with an earlier hierarchical model called NestedAE.</p>","PeriodicalId":44,"journal":{"name":"Journal of Chemical Information and Modeling ","volume":" ","pages":""},"PeriodicalIF":5.6,"publicationDate":"2024-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142845307","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":"CoarsenConf: Equivariant Coarsening with Aggregated Attention for Molecular Conformer Generation.","authors":"Danny Reidenbach, Aditi S Krishnapriyan","doi":"10.1021/acs.jcim.4c01001","DOIUrl":"https://doi.org/10.1021/acs.jcim.4c01001","url":null,"abstract":"<p><p>Molecular conformer generation (MCG) is an important task in cheminformatics and drug discovery. The ability to efficiently generate low-energy 3D structures can avoid expensive quantum mechanical simulations, leading to accelerated virtual screenings and enhanced structural exploration. Several generative models have been developed for MCG, but many struggle to consistently produce high-quality conformers for meaningful downstream applications. To address these issues, we introduce CoarsenConf, which coarse-grains molecular graphs based on torsional angles and integrates them into an SE(3)-equivariant hierarchical variational autoencoder. Through equivariant coarse-graining, we aggregate the fine-grained atomic coordinates of subgraphs connected via rotatable bonds, creating a variable-length coarse-grained latent representation. Our model uses a novel aggregated attention mechanism to restore fine-grained coordinates from the coarse-grained latent representation, enabling efficient generation of accurate conformers. Furthermore, we evaluate the chemical and biochemical quality of our generated conformers on multiple downstream applications, including property prediction and large-scale oracle-based protein docking. Overall, CoarsenConf generates more accurate conformer ensembles compared to prior generative models.</p>","PeriodicalId":44,"journal":{"name":"Journal of Chemical Information and Modeling ","volume":" ","pages":""},"PeriodicalIF":5.6,"publicationDate":"2024-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142833214","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":"ProtChat: An AI Multi-Agent for Automated Protein Analysis Leveraging GPT-4 and Protein Language Model.","authors":"Huazhen Huang, Xianguo Shi, Hongyang Lei, Fan Hu, Yunpeng Cai","doi":"10.1021/acs.jcim.4c01345","DOIUrl":"https://doi.org/10.1021/acs.jcim.4c01345","url":null,"abstract":"<p><p>Large language models (LLMs) have transformed natural language processing, enabling advanced human-machine communication. Similarly, in computational biology, protein sequences are interpreted as natural language, facilitating the creation of protein large language models (PLLMs). However, applying PLLMs requires specialized preprocessing and script development, increasing the complexity of their use. Researchers have integrated LLMs with PLLMs to develop automated protein analysis tools to address these challenges, simplifying analytical workflows. Existing technologies often require substantial human intervention for specific protein-related tasks, maintaining high barriers to implementing automated protein analysis systems. Here, we propose ProtChat, an AI multiagent system for protein analysis that integrates the inference capabilities of PLLMs with the task-planning abilities of LLMs. ProtChat integrates GPT-4 with multiple PLLMs, like ESM and MASSA, to automate tasks such as protein property prediction and protein-drug interactions without human intervention. This AI agent enables users to input instructions directly, significantly improving efficiency and usability, making it suitable for researchers without a computational background. Experiments demonstrate that ProtChat can automate complex protein tasks accurately, avoiding manual intervention and delivering results rapidly. This advancement opens new research avenues in computational biology and drug discovery. Future applications may extend ProtChat's capabilities to broader biological data analysis. Our code and data are publicly available at github.com/SIAT-code/ProtChat.</p>","PeriodicalId":44,"journal":{"name":"Journal of Chemical Information and Modeling ","volume":" ","pages":""},"PeriodicalIF":5.6,"publicationDate":"2024-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142845306","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":"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":"https://doi.org/10.1021/acs.jcim.4c01766","url":null,"abstract":"<p><p>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.</p>","PeriodicalId":44,"journal":{"name":"Journal of Chemical Information and Modeling ","volume":" ","pages":""},"PeriodicalIF":5.6,"publicationDate":"2024-12-16","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}

{"title":"ModBind, a Rapid Simulation-Based Predictor of Ligand Binding and Off-Rates.","authors":"William Sinko, Blake Mertz, Takafumi Shimizu, Taisuke Takahashi, Yoh Terada, S Roy Kimura","doi":"10.1021/acs.jcim.4c01805","DOIUrl":"https://doi.org/10.1021/acs.jcim.4c01805","url":null,"abstract":"<p><p>In rational drug discovery, both free energy of binding and the binding half-life (<i>k</i>_off) are important factors in determining the efficacy of drugs. Numerous computational methods have been developed to predict these important properties, many of which rely on molecular dynamics (MD) simulations. While binding free-energy methods (thermodynamic equilibrium predictions) have been well validated and have demonstrated the ability to drive daily synthesis decisions in a commercial drug discovery setting, the prediction of <i>k</i>_off (kinetics predictions) has had limited validation, and predictive methods have largely not been deployed in drug discovery settings. We developed ModBind, a novel method for MD simulation-based <i>k</i>_off predictions. ModBind demonstrated similar accuracy to current state-of-the-art free-energy prediction methods. Additionally, ModBind performs ∼100 times faster than most available MD simulation-based free-energy or <i>k</i>_off methods, allowing for widespread use by the molecular modeling community. While most free-energy methods rely on relative free-energy changes and are primarily useful for optimization of a congeneric series, our method requires no structural similarity between ligands, making ModBind an absolute predictor of <i>k</i>_off. ModBind is thus a tool that can be used in virtual screening of diverse ligands, making it distinct from relative free-energy methods. We also discuss conditions that enable approximate prediction of ligand efficacy using ModBind and the limitations of this approach.</p>","PeriodicalId":44,"journal":{"name":"Journal of Chemical Information and Modeling ","volume":" ","pages":""},"PeriodicalIF":5.6,"publicationDate":"2024-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142833086","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":"Leveraging the Thermodynamics of Protein Conformations in Drug Discovery.","authors":"Bin W Zhang, Mikolai Fajer, Wei Chen, Francesca Moraca, Lingle Wang","doi":"10.1021/acs.jcim.4c01612","DOIUrl":"https://doi.org/10.1021/acs.jcim.4c01612","url":null,"abstract":"<p><p>As the name implies, structure-based drug design requires confidence in the holo complex structure. The ability to clarify which protein conformation to use when ambiguity arises would be incredibly useful. We present a large scale validation of the computational method Protein Reorganization Free Energy Perturbation (PReorg-FEP) and demonstrate its quantitative accuracy in selecting the correct protein conformation among candidate models in apo or ligand induced states for 14 different systems. These candidate conformations are pulled from various drug discovery related campaigns: cryptic conformations induced by novel hits in lead identification, binding site rearrangement during lead optimization, and conflicting structural biology models. We also show an example of a pH-dependent conformational change, relevant to protein design.</p>","PeriodicalId":44,"journal":{"name":"Journal of Chemical Information and Modeling ","volume":" ","pages":""},"PeriodicalIF":5.6,"publicationDate":"2024-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142833082","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}