Molecular Diversity最新文献

{"title":"Integrating ensemble machine-learning and fibril docking to discover potent, novel triazole-naphthalene tau-aggregation inhibitors.","authors":"Poulami Saha, Anuja Chouhan","doi":"10.1007/s11030-026-11507-4","DOIUrl":"10.1007/s11030-026-11507-4","url":null,"abstract":"<p><p>Tau-protein aggregation is a central pathological feature of Alzheimer's disease, so blocking fibril growth is an attractive therapeutic goal. We curated a high-quality set of 289 literature IC₅₀ measurements for human-tau aggregation and trained a stacked-ensemble QSAR model (SVR + RF + XGB) that achieves fivefold CV Q² = 0.63, external R² = 0.57 and RMSE = 0.73 log-units. Applicability-domain analysis revealed no high-influence outliers in the calibration set, and a 5-nearest-neighbour density test confirmed that each of sixteen previously unreported 1,2,4-triazole-naphthalene derivatives (TND, TND-1…TND-15) lies in locally populated chemical space, albeit at the edge of the global domain. The model predicts pIC₅₀ = 6.75-7.53 (IC₅₀ ≈ 30-177 nM), nominating TND-9, TND-15 and TND-5 as top-ranked candidates based on predicted potency. Nearly all TNDs fall within the BBB window (MW ≈ 350-450 Da, TPSA < 90 Ų); most obey cLogP ≤ 5, and the few slightly above still map to the BOILED-Egg CNS-positive zone. Retrospective docking against phosphorylated-tau fibrils (PDB ID 6HRF) highlighted TND, TND-5 and TND-14 with sub-micromolar predicted affinity, forming key contacts in the microtubule-binding cleft. These docking results support binding plausibility rather than quantitative aggregation inhibition. TND-8, although highly ranked by docking, was deprioritised owing to low predicted GI absorption. Physicochemical and CNS-oriented ADMET filters further support developability of the top leads. The integrated workflow-combining rigorously validated QSAR, structure-based docking on the 6HRF polymorph and developability profiling-provides an open-source blueprint for tau-aggregation inhibitor discovery. Consensus ranking prioritises TND-5 for immediate in-silico follow-up, with TND, TND-14, TND-9 and TND-15 as secondary leads.</p>","PeriodicalId":708,"journal":{"name":"Molecular Diversity","volume":" ","pages":"2853-2863"},"PeriodicalIF":3.8,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147353301","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":"KansFormer network based on a multimodal cross-attention mechanism for drug-target interaction prediction.","authors":"Anting Gao, Yuandong Liu, Kai Che, Longbo Zhang, Yifeng Gao, Linlin Xing","doi":"10.1007/s11030-026-11530-5","DOIUrl":"10.1007/s11030-026-11530-5","url":null,"abstract":"","PeriodicalId":708,"journal":{"name":"Molecular Diversity","volume":" ","pages":"2937-2953"},"PeriodicalIF":3.8,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147618322","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 learning-enhanced QSAR modeling for predicting developmental neurotoxicity based on molecular initiating events from adverse outcome pathways.","authors":"Eufrásia de Sousa Pereira, Vinícius Alexandre Fiaia Costa, Eder Soares de Almeida Santos, Bruno Junior Neves","doi":"10.1007/s11030-025-11454-6","DOIUrl":"10.1007/s11030-025-11454-6","url":null,"abstract":"<p><p>Developmental neurotoxicity (DNT) is linked to chemical exposure that disrupts the nervous system in humans or animals. Traditional methods for assessing chemical toxicity are valuable but often time-consuming, costly, and involve significant animal use, making it impractical to meet growing demands. To address this, we developed a deep learning-enhanced QSAR modeling framework aimed at predicting binding affinities towards molecular initiating events (MIEs) and key events (KEs) within the Adverse Outcome Pathway (AOP) relevant to exposure to pesticide-contaminated cannabis. Our model was trained on data from 24,476 compounds, sourced from the ChEMBL database, and tested against 4 MIE and 6 KE tasks. The DNNs showed superior performance, with an average correlation coefficient of 0.82 ± 0.05 and a root mean square error of 0.72 ± 0.08 for the test set. To enhance interpretability, we used SHAP values to explain the model's predictions clearly. Furthermore, ECFP4 feature contributions were mapped onto known neurotoxic compounds to highlight regions likely responsible for MIEs visually. Our results confirm that developed models accurately predict DNT and effectively identify the correct MIEs and KEs for several neurotoxicants.</p>","PeriodicalId":708,"journal":{"name":"Molecular Diversity","volume":" ","pages":"2627-2642"},"PeriodicalIF":3.8,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13139284/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146028154","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":"Capsule enclosed coordinate attention based dual batch depthwise convolutional knowledge distillation model for drug-drug interaction prediction.","authors":"Soni Sharmila Kadimi, S Thanga Revathi, Pokkuluri Kiran Sree","doi":"10.1007/s11030-025-11433-x","DOIUrl":"10.1007/s11030-025-11433-x","url":null,"abstract":"<p><p>Drug-drug interactions (DDIs) are a significant issue in drug discovery, impacting research efficiency and patient safety. Precise prediction of DDIs is important, particularly when drugs are co-administered. The combination of heterogeneous data sources that reflect drug relationships and properties can greatly enhance predictive accuracy. This paper proposes a new Capsule-enclosed Coordinate Attention-based Dual Batch Depthwise Convolutional Knowledge Distillation (CC-DBDKD) model for DDI prediction. The input data drawn from the DrugBank dataset is preprocessed with the RDKit to standardize SMILES strings into their canonical representations. Various techniques of molecular fingerprint generation, such as Extended Connectivity Fingerprints, MACCS keys, PubChem Fingerprints, 3D molecular fingerprints, and molecular dynamics fingerprints, are used to map drug chemical structures onto feature vectors. Drug similarities are subsequently calculated by the Tanimoto coefficient, and the Structural Similarity Profile (SSP) is calculated as an average of these fingerprint types. A lightweight model, CC-DBDKD, improves DDI prediction by introducing capsule networks to learn spatial hierarchies and complex drug relationships. Coordinate attention mechanisms improve feature extraction by attending to key interaction patterns. Adding dual-batch depthwise convolutional layers improves computational efficiency to support scalability with large datasets. In addition, knowledge distillation reinforces the model by mapping knowledge from a teacher model to a student model, enhancing accuracy and robustness. The proposed model realizes superior accuracy values of 0.987 and 0.989 and an F1-score of 0.986, which outshines other prevailing models like CNN, CNN-LSTM, Autoencoder, and D-CNN. The outcomes position the CC-DBDKD model as a strong and scalable instrument for accurate DDI prediction.</p>","PeriodicalId":708,"journal":{"name":"Molecular Diversity","volume":" ","pages":"2583-2605"},"PeriodicalIF":3.8,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145965006","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":"GRU-based de novo design and in-silico prioritization of EZH2 inhibitors.","authors":"Na Yu, Maoqi Wang, Xiaodie Chen, Rong Liu, Liang Zou, Mao Shu","doi":"10.1007/s11030-026-11481-x","DOIUrl":"10.1007/s11030-026-11481-x","url":null,"abstract":"<p><p>EZH2 (Enhancer-Homozygous Protein 2), as a key epigenetic regulator, is closely associated with multiple cancers. Consequently, the design of EZH2-targeting inhibitors has become a significant focus in drug development. The application of deep learning methods in the chemical field can accelerate the process of discovering new molecules. This study utilized the SMILES sequence information of 1,202,321 small molecules from the ChEMBL29 database and the known molecular structures of 11 compounds with EZH2 inhibitory activity. A molecular generation model based on a gated recurrent unit (GRU) network and transfer learning was constructed, generating 50,000 SMILES molecular sequences. Through classification prediction by an ECFP4-SVM model, 37,802 effective and novel molecular structures were screened. Subsequent virtual screening incorporated Lipinski's Rules, ADMET properties, and molecular docking, ultimately identifying 10 candidate compounds for 100 ns molecular dynamics simulations and density functional theory (DFT) calculations. MM-GBSA calculations revealed binding free energies ≤ - 42.3518 kcal/mol for the candidate compounds, suggesting strong interactions with EZH2. DFT calculations further characterized the electronic interaction features underlying ligand-protein binding. This study demonstrates the feasibility of a deep learning-driven computational framework for the virtual identification and prioritization of potential EZH2 inhibitor candidates.</p>","PeriodicalId":708,"journal":{"name":"Molecular Diversity","volume":" ","pages":"2713-2730"},"PeriodicalIF":3.8,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147281705","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":"Repurposing DrugBank compounds as NAD-dependent deacetylase sirtuin 2 inhibitors via QSAR modelling with gradient boosting algorithms and all-atom molecular simulations.","authors":"Yassir Boulaamane, Asmae Saih, Abdelkrim Guendouzi, Amal Maurady","doi":"10.1007/s11030-026-11504-7","DOIUrl":"10.1007/s11030-026-11504-7","url":null,"abstract":"<p><p>Sirtuin 2 (SIRT2), a NAD⁺-dependent histone deacetylase implicated in α-synuclein aggregation, is an emerging target for disease-modifying therapies in Parkinson's disease (PD). Here, we employed an integrated computational drug-repurposing strategy to identify potent SIRT2 inhibitors from the DrugBank database. A curated set of 949 inhibitors was used to construct quantitative structure-activity relationship (QSAR) models with four gradient-boosting algorithms, yielding CatBoost as the optimal predictor ([Formula: see text] = 0.74, [Formula: see text] = 0.72). The model screened 4947 drug-like compounds, from which 97 candidates with predicted pIC₅₀ ≥ 6 were prioritized. Molecular docking against the SIRT2 crystal structure (PDB: 4RMG) revealed high-affinity binding modes for multiple hits, notably DB14822, DB03571, and DB06506, engaging conserved residues (Phe119, Tyr139, Phe190, Ile232) through hydrophobic and π-stacking interactions. ADMET profiling indicated favorable drug-likeness and acceptable pharmacokinetic/toxicity properties for most candidates. All-atom molecular dynamics simulations (250 ns) demonstrated that top ligands maintained compact, stable complexes with low RMSD, restricted radius of gyration, and minimal solvent exposure. Principal component and free energy landscape analyses confirmed constrained global motions, while MM/GBSA calculations yielded favorable binding free energies (- 32.6 to - 35.7 kcal/mol) for lead compounds. Given SIRT2's established role in α-synuclein aggregation and neurodegeneration, these compounds represent potential therapeutic starting points for Parkinson's disease and merit experimental validation.</p>","PeriodicalId":708,"journal":{"name":"Molecular Diversity","volume":" ","pages":"2865-2888"},"PeriodicalIF":3.8,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147442118","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":"Multi-modal machine learning and molecular modelling reveal structurally diverse inhibitors of Mycobacterium tuberculosis protein tyrosine phosphatase B.","authors":"Mohd Imran","doi":"10.1007/s11030-026-11476-8","DOIUrl":"10.1007/s11030-026-11476-8","url":null,"abstract":"<p><p>Protein tyrosine phosphatase B (PtpB) is a virulence-associated phosphotyrosine phosphatase secreted by Mycobacterium tuberculosis (Mtb), known to disrupt host immune signaling by dephosphorylating key proteins. Targeting PtpB represents a rational strategy for anti-TB drug discovery. This study presents an integrative computational framework for identifying and evaluating small-molecule inhibitors of Mtb PtpB. QSAR models were constructed using four molecular fingerprint types, CDK, PubChem, MACCS, and AtomPairs2DCount, as regression models predicting pIC₅₀ values. Multiple machine learning algorithms were evaluated, with model performance assessed via R², RMSE, cross-validation, and Y-randomization. SHAP analysis was applied to the top-performing PubChem-SVR model to interpret key structural features. Top-ranked compounds were subjected to molecular docking followed by 250 ns MD simulations to examine binding stability. MM-GBSA and PCA were used for post-simulation analysis. Gene-level interactions were evaluated by comparing predicted compound targets with Mtb-related host genes. Among descriptors, the PubChem-RF model achieved the best performance. SHAP identified PubchemFP417 (alkyne), PubchemFP462 (carboxylic acid), PubchemFP143 (five-membered rings), and PubchemFP34 (sulfur-containing fragments) as major contributors. CHEMBL4635765 showed strong and stable binding within the PTP pocket, while isoxazole carboxylic acid maintained key interactions but with lower stability. Network analysis revealed four shared targets (APP, HDAC8, CACNA1B, pvdQ) and compound-specific links to immune-related genes, including PTPN1 and NFKB1. This integrative computational study combines machine learning, structural modeling, and network pharmacology to provide mechanistic insights into PtpB inhibition and to identify promising chemical scaffolds for future anti-tubercular research. As the analysis is entirely computational, experimental validation will be required to confirm the predicted activities.</p>","PeriodicalId":708,"journal":{"name":"Molecular Diversity","volume":" ","pages":"2677-2697"},"PeriodicalIF":3.8,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146218294","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-based graph neural network, molecular dynamics and biological evaluation for identification of potential FGFR1 kinase inhibitors.","authors":"Tao Wu, Tao Wei, Junwei Zhu, Hongliang Zhong, Jie Ouyang, Yucan Wu, Wenfei He, Jianzhang Wu, Wulan Li","doi":"10.1007/s11030-026-11494-6","DOIUrl":"10.1007/s11030-026-11494-6","url":null,"abstract":"","PeriodicalId":708,"journal":{"name":"Molecular Diversity","volume":" ","pages":"2801-2816"},"PeriodicalIF":3.8,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147324098","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":"AMDRP: adaptive drug feature fusion and multihead bidirectional cross-attention network for drug-cancer cell response prediction.","authors":"Shiqian Han, Kaifeng Huang, Jiahao Shi, Jun Wang","doi":"10.1007/s11030-026-11502-9","DOIUrl":"10.1007/s11030-026-11502-9","url":null,"abstract":"<p><p>Predicting cancer drug responses is crucial for precision medicine. This study proposes AMDRP, a novel model that predicts drug responses by integrating drug features-represented as molecular graphs and extended connectivity fingerprints (ECFP)-with multi-omics data from cancer cell lines. AMDRP incorporates an Adaptive Feature Fusion (AFF) module to dynamically weight and fuse these drug features, resulting in enhanced drug representations. Furthermore, a multi-head bidirectional cross-attention (MBCA) module is introduced to model deep interactions between drug and cell line features. Extensive experiments demonstrate that AMDRP achieves significantly higher prediction accuracy than state-of-the-art baselines. Ablation studies confirm the critical contribution of both modules, with ECFP features providing substantial performance gains. The model's robustness and generalization capability were rigorously evaluated through cross-dataset validation and leave-one-out experiments, demonstrating its effectiveness against data distribution shifts. Predictions and enrichment analysis on unknown drug-cell line pairs underscore the model's predictive power and biological relevance. These results indicate that AMDRP is an effective tool for predicting cancer drug responses and holds potential value for guiding anticancer drug discovery.</p>","PeriodicalId":708,"journal":{"name":"Molecular Diversity","volume":" ","pages":"2817-2832"},"PeriodicalIF":3.8,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147324107","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":"Rapid screening of potent and mechanistically insightful repurposable anticancer drugs targeting EGFR for non-small cell lung cancer: machine learning-aided and structure-guided approach.","authors":"Md Shakil Ahamed, Sheikh Abdullah Al Ashik","doi":"10.1007/s11030-026-11532-3","DOIUrl":"10.1007/s11030-026-11532-3","url":null,"abstract":"<p><p>Despite the initial success of EGFR-targeted therapies in non-small cell lung cancer (NSCLC), the emergence of drug resistance remains a significant clinical challenge. While several approved anticancer drugs exist, the development of resistance to current EGFR inhibitors necessitates the identification of novel repurposable drugs and rapid strategies to screen drugs that could address resistance. Therefore, this study aimed to develop a machine learning-aided and structure-guided rapid screening framework to identify repurposable inhibitors from an anticancer drug library with the potential activity against EGFR in NSCLC. We developed a Random Forest model (cross-validated R² = 0.8919 ± 0.0128) to predict EGFR inhibitory activity and validated it through molecular docking, molecular dynamics simulations, binding free energy calculations, computational bioactivity profiles, predicted cytotoxicity against NSCLC cell lines, and literature-based validation of inhibitory potential. Among screened compounds, Idarubicin and Larotrectinib emerged as putative candidates with predicted IC₅₀ values of 226.55 nM and 479.06 nM, respectively. Molecular docking revealed higher binding affinities for both Idarubicin (- 9.98 kcal/mol) and Larotrectinib (- 9.42 kcal/mol) compared to the reference drug Erlotinib (-8.91 kcal/mol). Subsequent molecular dynamics simulations revealed highly stable conformations for both compounds (RMSD: Idarubicin 1.49 ± 0.24 Å, Larotrectinib 1.34 ± 0.29 Å), with consistent binding modes throughout the 100 ns trajectory, where MET793 was a common and most stable hydrogen bond with reference drug Erlotinib. Additionally, they demonstrated favorable predicted cytotoxicity against NSCLC cell lines. In conclusion, our integrated bioinformatics analysis identifies idarubicin and larotrectinib as putative candidates for drug repurposing targeting EGFR in NSCLC, providing a rational foundation for future experimental validation and further preclinical and clinical investigations.</p>","PeriodicalId":708,"journal":{"name":"Molecular Diversity","volume":" ","pages":"2905-2935"},"PeriodicalIF":3.8,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147589326","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}