Journal of Chemical Information and Modeling 最新文献

{"title":"","authors":"Ivan A. Bespalov*, Nikolai V. Krivoshchapov, Alexey A. Lisov, Vasiliy A. Chaliy and Michael G. Medvedev*, ","doi":"","DOIUrl":"","url":null,"abstract":"","PeriodicalId":44,"journal":{"name":"Journal of Chemical Information and Modeling ","volume":"65 12","pages":"2305–2315 XXX-XXX"},"PeriodicalIF":5.6,"publicationDate":"2025-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://pubs.acs.org/doi/pdf/10.1021/acs.jcim.5c00522","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144469270","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}

{"title":"","authors":"Eleonora Serra, Alessia Ghidini, Riccardo Aguti, Mattia Bernetti*, Sergio Decherchi* and Andrea Cavalli, ","doi":"","DOIUrl":"","url":null,"abstract":"","PeriodicalId":44,"journal":{"name":"Journal of Chemical Information and Modeling ","volume":"65 12","pages":"2305–2315 XXX-XXX"},"PeriodicalIF":5.6,"publicationDate":"2025-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://pubs.acs.org/doi/pdf/10.1021/acs.jcim.5c00452","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144469273","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}

{"title":"","authors":"Yongrui Wang, Zhen Wang, Yanjun Li, Pengju Yan and Xiaolin Li*, ","doi":"","DOIUrl":"","url":null,"abstract":"","PeriodicalId":44,"journal":{"name":"Journal of Chemical Information and Modeling ","volume":"65 12","pages":"2305–2315 XXX-XXX"},"PeriodicalIF":5.6,"publicationDate":"2025-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://pubs.acs.org/doi/pdf/10.1021/acs.jcim.5c00944","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144428048","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}

{"title":"","authors":"Nupur Nagar, Krishnakant Gangele, Purba Daripa, Deepak Kumar Tripathi, Dinesh Kumar and Krishna Mohan Poluri*, ","doi":"","DOIUrl":"","url":null,"abstract":"","PeriodicalId":44,"journal":{"name":"Journal of Chemical Information and Modeling ","volume":"65 12","pages":"2305–2315 XXX-XXX"},"PeriodicalIF":5.6,"publicationDate":"2025-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://pubs.acs.org/doi/pdf/10.1021/acs.jcim.5c00260","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144428052","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}

{"title":"","authors":"Luca Chiesa, Dina Khasanova and Esther Kellenberger*, ","doi":"","DOIUrl":"","url":null,"abstract":"","PeriodicalId":44,"journal":{"name":"Journal of Chemical Information and Modeling ","volume":"65 12","pages":"2305–2315 XXX-XXX"},"PeriodicalIF":5.6,"publicationDate":"2025-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://pubs.acs.org/doi/pdf/10.1021/acs.jcim.5c00489","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144469280","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}

{"title":"Machine Learning Based Quantitative Structure-Dissolution Profile Relationship.","authors":"Lap Au-Yeung, Chih-Yuan Tseng, Yun K Tam, Peichun Amy Tsai","doi":"10.1021/acs.jcim.5c00197","DOIUrl":"10.1021/acs.jcim.5c00197","url":null,"abstract":"<p><p>Determining accurate drug dissolution processes in the gastrointestinal tract is critical in drug discovery as dissolution profiles provide essential information for estimating the bioavailability of orally administered drugs. While various methods have been developed to predict drug solubility based on chemical structures, no reliable tools currently exist for predicting the dissolution rate constant. This study presents a novel two-stage machine learning approach, termed Machine Learning based Quantitative Structure-Dissolution Profile Relationship, which integrates physics-informed neural networks (PINNs) and deep neural networks (DNNs) to predict drug dissolution profiles in water, with varying concentrations of surfactant Sodium Lauryl Sulfate. In the first stage, PINNs extract key dissolution parameters─namely the dissolution rate constant (<i>k</i>) and the dissolved mass fraction at saturation (ϕ_<i>s</i>)─from existing dissolution data. By leveraging a physical law governing the dissolution process, PINNs aim to enhance prediction performance and reduce data requirements. Assuming first-order kinetics of the drug dissolution process as described by the Noyes-Whitney equation, PINNs, with 8 hidden layers and 40 neurons per layer, may outperform traditional nonlinear regression by effectively filtering noise and focusing on physically meaningful data. In the second stage, these extracted parameters (<i>k</i> and ϕ_<i>s</i>) are used to train a DNN to predict dissolution profiles based on the drug's chemical structure and dissolution medium. Using the FDA-recommended metrics: the difference and similarity factors (<i>f</i>₁ and <i>f</i>₂), the DNN─with 128 neurons in two hidden layers and a learning rate of 10^-2.8─achieved an average testing accuracy of 61.7% at an 80:20 train-to-test split. Although this current accuracy is below the generally acceptable range of 70-80%, this approach shows significant potential as a low-cost, time-efficient tool for early phase drug formulation. Future improvements are expected as data quality and diversity increase.</p>","PeriodicalId":44,"journal":{"name":"Journal of Chemical Information and Modeling ","volume":" ","pages":"6273-6286"},"PeriodicalIF":5.6,"publicationDate":"2025-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144223731","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":"Improving Covalent and Noncovalent Molecule Generation via Reinforcement Learning with Functional Fragments.","authors":"Yongrui Wang, Zhen Wang, Yanjun Li, Pengju Yan, Xiaolin Li","doi":"10.1021/acs.jcim.5c00944","DOIUrl":"10.1021/acs.jcim.5c00944","url":null,"abstract":"<p><p>Small-molecule drugs play a critical role in cancer therapy by selectively targeting key signaling pathways that drive tumor growth. While deep learning models have advanced drug discovery, there remains a lack of generative frameworks for <i>de novo</i> covalent molecule design using a fragment-based approach. To address this, we propose MOFF (MOlecule generation with Functional Fragments), a reinforcement learning framework for molecule generation. MOFF is specifically designed to generate both covalent and noncovalent compounds based on functional fragments. The model leverages docking scores as reward functions and is trained using the Soft Actor-Critic algorithm. We evaluate MOFF through case studies targeting Bruton's tyrosine kinase (BTK) and the epidermal growth factor receptor (EGFR), demonstrating that MOFF can generate ligand-like molecules with favorable docking scores and drug-like properties, compared to baseline models and ChEMBL compounds. As a computational validation, molecular dynamics (MD) simulations were conducted on selected top-scoring molecules to assess potential binding stability. These results highlight MOFF as a flexible and extensible framework for fragment-based molecule generation, with the potential to support downstream applications.</p>","PeriodicalId":44,"journal":{"name":"Journal of Chemical Information and Modeling ","volume":" ","pages":"5934-5944"},"PeriodicalIF":5.6,"publicationDate":"2025-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144232668","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":"Identification of DSC2 as a Key Biomarker for Induction Chemotherapy Sensitivity in Locally Advanced Laryngeal and Hypopharyngeal Squamous Cell Carcinoma.","authors":"Qianyue Yang, Jiayi Liu, Zhiwei Lin, Shuang Liu, Zhaoming Hu, Xiaowen Zhang, Baoqing Sun","doi":"10.1021/acs.jcim.5c00557","DOIUrl":"10.1021/acs.jcim.5c00557","url":null,"abstract":"<p><p>Patients with locally advanced laryngeal and hypopharyngeal squamous cell carcinoma (LA-LHSCC) urgently need precise treatment strategies to improve the prognosis due to severe laryngeal functional impairment following traditional surgery and chemoradiotherapy. This study focuses on the mechanism of sensitivity to induction chemotherapy (IC), integrating the GSE184072 and TCGA-HNSC data sets to screen for differentially expressed genes (DEGs). Combining weighted gene coexpression network analysis (WGCNA) and machine learning methods, including MCC, MCODE, LASSO, SVM-RFE, and Random Forest (RF), the core gene DSC2 (Desmocollin-2) was identified. The results show that DSC2 is significantly highly expressed in the IC-sensitive group with a receiver operating characteristic (ROC) curve area under the curve (AUC) of 0.9111, indicating its high predictive efficacy as a biomarker. Immune infiltration analysis further revealed a significant correlation between DSC2 and the infiltration levels of immune cells such as M1 macrophages, suggesting its potential to influence IC sensitivity by regulating apoptosis and the immune microenvironment. Furthermore, the TCGA clinical data validated the correlation between DSC2 expression and patient survival rates. Our study is the first to establish DSC2 as a pivotal biomarker for IC sensitivity in LA-LHSCC patients, offering a novel avenue for the development of targeted therapeutic strategies and personalized diagnosis and treatment.</p>","PeriodicalId":44,"journal":{"name":"Journal of Chemical Information and Modeling ","volume":" ","pages":"5899-5911"},"PeriodicalIF":5.6,"publicationDate":"2025-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144245348","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":"Advancing Drug Discovery with Enhanced Chemical Understanding via Asymmetric Contrastive Multimodal Learning.","authors":"Yifei Wang,Yunrui Li,Lin Liu,Pengyu Hong,Hao Xu","doi":"10.1021/acs.jcim.5c00430","DOIUrl":"https://doi.org/10.1021/acs.jcim.5c00430","url":null,"abstract":"The versatility of multimodal deep learning holds tremendous promise for advancing scientific research and practical applications. As this field continues to evolve, the collective power of cross-modal analysis promises to drive transformative innovations, opening new frontiers in chemical understanding and drug discovery. Hence, we introduce asymmetric contrastive multimodal learning (ACML), a specifically designed approach to enhance molecular understanding and accelerate advancements in drug discovery. ACML harnesses the power of effective asymmetric contrastive learning to seamlessly transfer information from various chemical modalities to molecular graph representations. By combining pretrained chemical unimodal encoders and a shallow-designed graph encoder with 5 layers, ACML facilitates the assimilation of coordinated chemical semantics from different modalities, leading to comprehensive representation learning with efficient training. We demonstrate the effectiveness of this framework through large-scale cross-modality retrieval and isomer discrimination tasks. Additionally, ACML enhances interpretability by revealing chemical semantics in graph presentations and bolsters the expressive power of graph neural networks, as evidenced by improved performance in molecular property prediction tasks from MoleculeNet and Therapeutics Data Commons (TDC). Ultimately, ACML exemplifies its potential to revolutionize molecular representational learning, offering deeper insights into the chemical semantics of diverse modalities and paving the way for groundbreaking advancements in chemical research and drug discovery.","PeriodicalId":44,"journal":{"name":"Journal of Chemical Information and Modeling ","volume":"147 1","pages":""},"PeriodicalIF":5.6,"publicationDate":"2025-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144370178","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":"Moltiverse: Molecular Conformer Generation Using Enhanced Sampling Methods.","authors":"Mauricio Bedoya, Francisco Adasme-Carreño, Paula Andrea Peña-Martínez, Camila Muñoz-Gutiérrez, Luciano Peña-Tejo, José C E Márquez Montesinos, Erix W Hernández-Rodríguez, Wendy González, Leandro Martínez, Jans Alzate-Morales","doi":"10.1021/acs.jcim.5c00871","DOIUrl":"10.1021/acs.jcim.5c00871","url":null,"abstract":"<p><p>Accurately predicting the diverse bound-state conformations of small molecules is crucial for successful drug discovery and design, particularly when detailed protein-ligand interactions are unknown. Established tools exist, but efficiently exploring the vast conformational space remains challenging. This work introduces Moltiverse, a novel protocol using enhanced sampling molecular dynamics (MD) simulations for conformer generation. The extended adaptive biasing force (eABF) algorithm combined with metadynamics, guided by a single collective variable (radius of gyration, RDGYR), efficiently samples the conformational landscape of a small molecule. Moltiverse demonstrates comparable accuracy and, in some cases, superior quality when benchmarked against established software like RDKit, CONFORGE, Balloon, iCon, and Conformator in the Platinum Diverse Data set for drug-like small molecules and the Prime data set for macrocycles. We present multiple quantitative metrics and statistical analysis for robust conformer generation algorithm comparisons and provide recommendations for their improvement based on our findings. Our extensive evaluation shows that Moltiverse is particularly effective for challenging systems with high conformational flexibility, such as macrocycles, where it achieves the highest accuracy among the tested algorithms. The physics-based approach employed by Moltiverse effectively handles a wide range of molecular complexities, positioning it as a valuable tool for computational drug discovery workflows requiring accurate representation of molecular flexibility.</p>","PeriodicalId":44,"journal":{"name":"Journal of Chemical Information and Modeling ","volume":" ","pages":"5998-6013"},"PeriodicalIF":5.6,"publicationDate":"2025-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144148666","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}