Springer最新文献

{"title":"Classification models and SAR analysis of anaplastic lymphoma kinase (ALK) inhibitors using machine learning algorithms with two data division methods.","authors":"Dan Qu, Aixia Yan","doi":"10.1007/s11030-024-10990-x","DOIUrl":"10.1007/s11030-024-10990-x","url":null,"abstract":"<p><p>Anaplastic lymphoma kinase (ALK) plays a critical role in the development of various cancers. In this study, the dataset of 1810 collected inhibitors were divided into a training set and a test set by the self-organizing map (SOM) and random method, respectively. We developed 32 classification models using Support Vector Machines (SVM), Decision Trees (DT), Random Forests (RF), and Extreme Gradient Boosting (XGBoost) to distinguish between highly and weakly active ALK inhibitors, with the inhibitors represented by MACCS and ECFP4 fingerprints. Model 7D which was built by the RF algorithm using training set 1/test set 1 divided by the SOM method, provided the best performance with a prediction accuracy of 90.97% and a Matthews correlation coefficient (MCC) value of 0.79 on the test set. We clustered the 1810 inhibitors into 10 subsets by K-Means algorithm to find out the structural characteristics of highly active ALK inhibitors. The main scaffolds of highly active ALK inhibitors were also analyzed based on ECFP4 fingerprints. It was found that some substructures have a significant effect on high activity, such as 2,4-diarylaminopyrimidine analogues, pyrrolo[2,1-f][1,2,4]triazin, indolo[2,3-b]quinoline-11-one, benzo[d]imidazol and pyrrolo[2,3-b]pyridine. In addition, the subsets were summarized into several clusters, among which four clusters showed a significant relationship with ALK inhibitory activity. Finally, Shapley additive explanations (SHAP) was also used to explain the influence of modeling features on model prediction results. The SHAP results indicated that our models can well reflect the structural features of ALK inhibitors.</p>","PeriodicalId":708,"journal":{"name":"Molecular Diversity","volume":" ","pages":"2919-2943"},"PeriodicalIF":3.9,"publicationDate":"2025-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142611847","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":"A multitask interpretable model with graph attention mechanism for activity prediction of low-data PIM inhibitors.","authors":"Zixiao Wang, Lili Sun, Yu Chang, Fang Yang, Kai Jiang","doi":"10.1007/s11030-024-11060-y","DOIUrl":"10.1007/s11030-024-11060-y","url":null,"abstract":"<p><p>The aberrant expression of proviral integration site for Moloney murine leukemia virus (PIM) kinases is closely related to various tumors and chemotherapy resistance, making them attractive targets for cancer therapy. However, due to the extremely high homology among the three PIM isoforms (PIM1, PIM2, PIM3) and the limited availability of existing bioactivity data, screening and designing selective PIM inhibitors remain a daunting challenge. To address this issue, this study constructed a multitask regression model that can simultaneously predict the half-maximal inhibitory concentration (IC₅₀ values). The model utilizes an attention mechanism to capture effects within local atomic groups and the interactions between different groups of atoms. Through weight sharing, the model enhances the accuracy of predicting PIM3 inhibitors by leveraging the rich and highly correlated data from PIM1 and PIM2 isoforms. Additionally, visualizing the weights of nodes (atoms in the molecule) in the model helps us to intuitively understand the relationship between molecular features and prediction outcomes, thereby enhancing the interpretability of the model. In summary, this work provides new insights and methods for performing activity prediction tasks for multiple similar targets in low-data scenarios.</p>","PeriodicalId":708,"journal":{"name":"Molecular Diversity","volume":" ","pages":"3101-3112"},"PeriodicalIF":3.9,"publicationDate":"2025-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142765266","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":"Machine learning approaches for predicting the small molecule-miRNA associations: a comprehensive review.","authors":"Ashish Panghalia, Vikram Singh","doi":"10.1007/s11030-025-11211-9","DOIUrl":"10.1007/s11030-025-11211-9","url":null,"abstract":"<p><p>MicroRNAs (miRNAs) are evolutionarily conserved small regulatory elements that are ubiquitous in cells and are found to be abnormally expressed during the onset and progression of several human diseases. miRNAs are increasingly recognized as potential diagnostic and therapeutic targets that could be inhibited by small molecules (SMs). The knowledge of SM-miRNA associations (SMAs) is sparse, mainly because of the dynamic and less predictable 3D structures of miRNAs that restrict the high-throughput screening of SMs. Toward augmenting the costly and laborious experiments determining the SM-miRNA interactions, machine learning (ML) has emerged as a cost-effective and efficient platform. In this article, various aspects associated with the ML-guided predictions of SMAs are thoroughly reviewed. Firstly, a detailed account of the SMA data resources useful for algorithms training is provided, followed by an elaboration of various feature extraction methods and similarity measures utilized on SMs and miRNAs. Subsequent to a summary of the ML algorithms basics and a brief description of the performance measures, an exhaustive census of all the 32 ML-based SMA prediction methods developed so far is outlined. Distinctive features of these methods have been described by classifying them into six broad categories, namely, classical ML, deep learning, matrix factorization, network propagation, graph learning, and ensemble learning methods. Trend analyses are performed to investigate the patterns in ML algorithms usage and performance achievement in SMA prediction. Outlining key principles behind the up-to-date methodologies and comparing their accomplishments, this review offers valuable insights into critical areas for future research in ML-based SMA prediction.</p>","PeriodicalId":708,"journal":{"name":"Molecular Diversity","volume":" ","pages":"3825-3856"},"PeriodicalIF":3.9,"publicationDate":"2025-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144109420","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":"First report on analysis of chemical space, scaffold diversity, critical structural features of HDAC11 inhibitors.","authors":"Rinki Prasad Bhagat, Jyotisha, Indrasis Dasgupta, Sk Abdul Amin, Pranay Jakkula, Arijit Bhattacharya, Insaf Ahmed Qureshi, Shovanlal Gayen","doi":"10.1007/s11030-025-11217-3","DOIUrl":"10.1007/s11030-025-11217-3","url":null,"abstract":"<p><p>In the histone deacetylase (HDAC) family, HDAC11 is the smallest and a single member under the class IV subtype. It is important as a drug target mainly in cancer, inflammatory and autoimmune diseases. The design and development of selective HDAC11 inhibitors is quite a challenge for the chemist community due to the unavailability of the crystal structure of HDAC11. Ligand-based drug design (LBDD) strategies are the hope to speed up the development of its inhibitors. Here, an in-depth analysis of 712 HDAC11 inhibitors is performed through compound space networks and various cheminformatics approaches. The analyses demonstrated significant clustering of similar compounds based on their chemical structures, offering valuable insights into the chemical space occupied by HDAC11 inhibitors. Furthermore, the current work aimed to develop robust classification-based QSAR models that deliver the essential structural fingerprints. This study highlighted that the compounds bearing scaffolds such as isoindoline, benzimidazole, carboxamide/hydroxamate moieties, etc., are important for HDAC11 inhibitors. Molecular docking and MD simulations further provide an in-depth analysis of the binding interaction of the identified fingerprints in the catalytic site of HDAC11. In brief, our study delivers some important structural attributes that will aid medicinal chemists in designing and developing future potent HDAC11 inhibitors.</p>","PeriodicalId":708,"journal":{"name":"Molecular Diversity","volume":" ","pages":"3679-3702"},"PeriodicalIF":3.9,"publicationDate":"2025-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144085631","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":"Effect of focused ultrasound on shearwave production in a hyperelastic media.","authors":"Aniket Sabale, Mohd Suhail Rizvi, Viswanath Chinthapenta, Avinash Eranki","doi":"10.1007/s10237-025-01967-2","DOIUrl":"10.1007/s10237-025-01967-2","url":null,"abstract":"<p><p>Focused ultrasound (FUS) is an emerging noninvasive modality for treating various medical conditions. It encompasses both therapeutic and diagnostic applications, utilizing ultrasound waves at different intensities. In diagnostic modalities, ultrasound energy is deposited at the focus to generate acoustic radiation force (ARF), resulting in the generation of shear stress and waves, which are utilized in elastography to evaluate the mechanical properties of tissue. However, therapeutic modalities utilizing higher intensities may lead to elevated shear stress levels. The shear stress induced in the focal region during FUS procedures can potentially affect biological processes, such as cell membrane permeability and gene regulation. To better understand the mechanical stress generated during FUS procedures, we developed a finite element model (FEM) to simulate sonication using a single-element FUS transducer. We modeled soft tissue using a neo-Hookean hyperelastic constitutive behavior, offering a more realistic representation of tissue behavior compared to the linear elasticity assumptions commonly employed in ultrasound-based elastography techniques. Operational parameters were varied to simulate different acoustic powers of the transducer by applying mechanical surface pressure at various operating frequencies. The model depicted FUS wave propagation with amplified surface pressure at the focus, generating relevant focal pressures consistent with clinical setups. The focal beam size within the soft tissue material was characterized and exhibited dependency on the operating frequency of the transducer. As the FUS wave converged at the focus, an ARF was exerted, resulting in displacement and induced shear stress around the focal region, which were quantified. The displacement and shear stress that were analyzed were dependent on the applied transducer surface pressure. These findings deepen the understanding of the mechanics of low-intensity FUS and provide valuable insights into its shear-related effects due to displacement and deformation of the media.</p>","PeriodicalId":489,"journal":{"name":"Biomechanics and Modeling in Mechanobiology","volume":" ","pages":"1279-1294"},"PeriodicalIF":3.0,"publicationDate":"2025-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144092443","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"QMGBP-DL: a deep learning and machine learning approach for quantum molecular graph band-gap prediction.","authors":"Outhman Abbassi, Soumia Ziti","doi":"10.1007/s11030-025-11178-7","DOIUrl":"10.1007/s11030-025-11178-7","url":null,"abstract":"<p><p>Predicting molecular and quantum material properties, especially the band gap, is crucial for accelerating discoveries in drug design and material science. Although graph neural networks and probabilistic encoders are well established in molecular data analysis, their targeted integration and application for band-gap prediction remain an active research area. This paper introduces QMGBP-DL, a deep learning approach that combines a molecular graph encoder with machine learning models to improve the prediction accuracy of molecular and material band-gap energy. The encoder uses graph convolutional networks to derive latent representations of chemical structures from SMILES strings, optimized via Kullback-Leibler divergence loss. These representations serve as inputs for training various machine learning models to predict properties. QMGBP-DL's effectiveness is assessed using the QM9, PCQM4M, and OPV datasets, demonstrating significant improvements, particularly with a random forest model for property prediction. A comparative analysis against established approaches DenseGNN, MEGNet, and ALIGNN reveals that QMGBP-DL excels in predicting HOMO, LUMO, and band gap, achieving notably lower MAE values. The integration of GCN-derived latent spaces with traditional machine learning models, especially Random Forest, provides a powerful approach for band-gap prediction. The results highlight the efficacy of our integrated approach, showcasing that graph-based molecular encoding combined with machine learning, particularly Random Forest, is highly effective for accurate band-gap prediction, thereby facilitating material discovery and design.</p>","PeriodicalId":708,"journal":{"name":"Molecular Diversity","volume":" ","pages":"3501-3515"},"PeriodicalIF":3.9,"publicationDate":"2025-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143954943","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":"Circ_0000758 Facilitates Bladder Cancer Cell Growth, Migration and Angiogenesis Via Severing as miR-1236-3p Sponge.","authors":"Qiang Chi, Zhiyong Wang, Hui Xu, Hongyang Li, Dianbin Song","doi":"10.1007/s10528-024-10855-w","DOIUrl":"10.1007/s10528-024-10855-w","url":null,"abstract":"<p><p>Circular RNA (circRNA) has been reported to regulate the development of bladder cancer (BCa). However, the role of circ_0000758 in BCa progression is unknown. Circ_0000758 and miR-1236-3p expression, as well as ZEB2 mRNA expression were determined by qRT-PCR. BCa cell biological functions were determined by MTT assay, EdU assay, flow cytometry, wound healing assay and tube formation assay. Protein expression was detected by western blot analysis. RNA pull-down assay and dual-luciferase reporter assay were used to confirm RNA interaction. Xenograft mice models were constructed to assess the effect of circ_0000758 on BCa tumor growth. Circ_0000758 had increased expression in BCa tissues and cells. Circ_0000758 silencing could inhibit BCa cell growth, migration, angiogenesis in vitro, and tumor growth in vivo. Circ_0000758 served as a molecular sponge for miR-1236-3p, and miR-1236-3p inhibitor reversed circ_0000758 knockdown-mediated the inhibition effect on BCa cell progression. ZEB2 was targeted by miR-1236-3p, and its overexpression also revoked the suppressive effect of miR-1236-3p on BCa cell growth, migration, and angiogenesis. Besides, circ_0000758 knockdown also restrained BCa tumor growth. Circ_0000758 might promote BCa cell growth, migration, and angiogenesis by regulating the miR-1236-3p/ZEB2 axis.</p>","PeriodicalId":482,"journal":{"name":"Biochemical Genetics","volume":" ","pages":"3031-3046"},"PeriodicalIF":2.1,"publicationDate":"2025-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141309367","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"First Insight into the Phylogenetic Diversity of Bovicola caprae Infesting Goats of Different Agro-climatic Locations in India.","authors":"Aman D Moudgil, Anil K Nehra, Ankur Sharma, Santosh Patel, Sukhdeep Vohra","doi":"10.1007/s10528-024-10886-3","DOIUrl":"10.1007/s10528-024-10886-3","url":null,"abstract":"<p><p>Bovicola caprae is an important obligate ectoparasite of goats worldwide including India. The present study aimed at the molecular confirmation, phylogenetics and population structure analyses of B. caprae infesting goats of three different agro-climatic locations in India, by targeting the mitochondrial cytochrome C oxidase subunit 1 (cox1) genetic marker. The phylogenetic tree exhibited the presence of two different lineages of B. caprae. The sequences generated herein clustered in lineage 2 along with the GenBank™ archived sequences from China and Iran. The sequences generated herein also showed the circulation of sub-lineages of B. caprae in India based on the analysis of pairwise genetic distances between sequences and median-joining haplotype network. The population structure analyses revealed low nucleotide (0.00353 ± 0.00291 and 0.02694 ± 0.00363) and high haplotype (0.667 ± 0.314 and 0.618 ± 0.104) diversities for the present study isolates as well as for the complete dataset, respectively, which evinced a recent demographic expansion. High genetic differentiation (F_ST value = 0.97826) and low gene flow (N_m = 0.00556) were also recorded in the different lineages/populations. In conclusion, the present study addressed the research gap and provided the first insight into the phylogenetics of the goat louse B. caprae and highlighted the circulation of sub-lineages of the ectoparasite in India.</p>","PeriodicalId":482,"journal":{"name":"Biochemical Genetics","volume":" ","pages":"3465-3478"},"PeriodicalIF":2.1,"publicationDate":"2025-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141603139","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"French Type Vertical Flow Constructed Wetland as a Sustainable Solution for Domestic Sewage Treatment.","authors":"Shivraj Anand, Deepak Gupta, Chhavi Siwach, Jens Nowak, Heribert Rustige, Virendra Kumar Mishra","doi":"10.1007/s00267-025-02186-2","DOIUrl":"10.1007/s00267-025-02186-2","url":null,"abstract":"<p><p>In order to mitigate the risk posed by discharge of untreated wastewater and enhance the quality of wastewater prior to its release or reuse, it is important to adopt nature based treatment technologies. The current study was performed with objective to treat the primary treated sewage collected from a traditional Moving Bed Biofilm Reactor (MBBR) based Sewage treatment plant (STP) by using a two-stage French Type Vertical Flow Constructed Wetland (FVFCW). This pilot-scale study was undertaken in Banaras Hindu University Campus Varanasi, Uttar Pradesh. The wetland unit was a two-stage Vertical Flow Constructed Wetland system (VFCW) filled with two different filter media gravel & sand and planted with two different macrophytes Canna indica and Typha latifolia which was operated for Sustainable treatment of primary sewage. The VFCW was operated at three different Hydraulic loading rate (HLR) i.e. 1800, 2700, 3600 L/day for nine months. The VFCW performed for the treatment of different physicochemical parameters at given loading rates. The maximum removal efficiency of 72.37, 76.47, 100, 87.23, 41.41, 40.77 27.07% was recorded for COD, BOD, Turbidity, TSS, TDS, Phosphate and Ammonia respectively. Most of the Parameters showed maximum removal efficiency at HLR 2700 L/day. The study suggested that Experimental VFCW can be a sustainable solution for wastewater treatment in remote and rural areas of India as well small colonies due to its eco-friendly, cost-effective, low maintenance cost and lack of operational expertise.</p>","PeriodicalId":543,"journal":{"name":"Environmental Management","volume":" ","pages":"2078-2088"},"PeriodicalIF":2.7,"publicationDate":"2025-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144257035","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Association between the temperature difference and acute exacerbation of chronic obstructive pulmonary disease in Lanzhou, China.","authors":"Hongran Ma, Furong Qu, Jiyuan Dong, Jiancheng Wang","doi":"10.1007/s00484-025-02947-y","DOIUrl":"10.1007/s00484-025-02947-y","url":null,"abstract":"<p><p>The aim of this study was to use the distributed lag non-linear model (DLNM) to investigate the association between temperature differences (including temperature change between neighboring days (TCN) and diurnal temperature range (DTR)) and acute exacerbation of chronic obstructive pulmonary disease (AECOPD) outpatient visits. We also stratify by sex (male, female) and age (< 65 years, 65-74 years and ≥ 75 years). The results showed that the maximum relative risk (RR) of low temperature for AECOPD outpatient visits was 1.175 (95% CI: 1.095-1.261) at lag 0. Risk estimates showed that the RR of AECOPD outpatient visits with extremely high DTR at lag 10 days was 1.017 (95% CI: 1.001-1.035). As for TCN, the risk of outpatient in AECOPD patients was found when exposed to low TCN with the most significant single-day effect at lag 0 (RR = 1.051, 95% CI: 1.016-1.088). Overall, the elderly (≥ 75 years) and males were more susceptible to lower temperature, lower TCN, and higher DTR than females, patients aged < 65 years and patients aged 65-74 years. This study concluded that exposure to low temperature, high DTR and low TCN were associated with an increased risk of AECOPD outpatient visits, indicating that patients with AECOPD need to take proactive actions in the face of temperature variation. Special consideration should be given to vulnerable populations, including males and the elderly (≥ 75 years).</p>","PeriodicalId":588,"journal":{"name":"International Journal of Biometeorology","volume":" ","pages":"2013-2033"},"PeriodicalIF":3.0,"publicationDate":"2025-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144126210","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}