Molecular Diversity最新文献

{"title":"Advancements of anticancer agents by targeting the Hippo signalling pathway: biological activity, selectivity, docking analysis, and structure-activity relationship.","authors":"E Haripriya, K Hemalatha, Gurubasavaraja Swamy Purawarga Matada, Rohit Pal, Pronoy Kanti Das, M D Ashadul Sk, S Mounika, M P Viji, I Aayishamma, K R Jayashree","doi":"10.1007/s11030-024-11009-1","DOIUrl":"10.1007/s11030-024-11009-1","url":null,"abstract":"<p><p>The Hippo signalling pathway is prominent and governs cell proliferation and stem cell activity, acting as a growth regulator and tumour suppressor. Defects in Hippo signalling and hyperactivation of its downstream effector's Yes-associated protein (YAP) and transcriptional co-activator with PDZ-binding motif (TAZ) play roles in cancer development, implying that pharmacological inhibition of YAP and TAZ activity could be an effective cancer treatment strategy. Conversely, YAP and TAZ can also have beneficial effects in promoting tissue repair and regeneration following damage, therefore their activation may be therapeutically effective in certain instances. Recently, a complex network of intracellular and extracellular signalling mechanisms that affect YAP and TAZ activity has been uncovered. The YAP/TAZ-TEAD interaction leads to tumour development and the protein structure of YAP/TAZ-TEAD includes three interfaces and one hydrophobic pocket. There are clinical and preclinical trial drugs available to inhibit the hippo signalling pathway, but these drugs have moderate to severe side effects, so researchers are in search of novel, potent, and selective hippo signalling pathway inhibitors. In this review, we have discussed the hippo pathway in detail, including its structure, activation, and role in cancer. We have also provided the various inhibitors under clinical and preclinical trials, and advancement of small molecules their detailed docking analysis, structure-activity relationship, and biological activity. We anticipate that the current study will be a helpful resource for researchers.</p>","PeriodicalId":708,"journal":{"name":"Molecular Diversity","volume":" ","pages":"2829-2862"},"PeriodicalIF":3.9,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142455374","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":"Discovery of novel purine analogues against breast cancer selectively targeting CDK2: optimization, synthesis, biological evaluation and docking study.","authors":"Mahesh Rupapara, Nishith Teraiya, Chetan Sangani, Khushal Kapadiya, Nishant Patel","doi":"10.1007/s11030-025-11227-1","DOIUrl":"https://doi.org/10.1007/s11030-025-11227-1","url":null,"abstract":"<p><p>CDK2 inhibition is a promising breast cancer treatment. Purines target CDK2 and are effective against breast cancer, proving a therapeutic scaffold. New purine-based compounds, 5a-5j were synthesized using chloro-amine coupling and phenacylation in a two-step procedure, characterized, and tested for anticancer activity. The highest yield (82%), without column purification or a costly catalyst like Pd/Cu, was achieved with concentrated HCl. The synthesis and site-selective substitution at the purine ring's C-2 position were confirmed by ¹H NMR, ¹³C NMR, IR, MS, and HMBC spectroscopy. In the NCI-60 study, compounds 5e and 5f inhibited growth of MDA-MB-231 cells by 93% and 91%, respectively. In addition, compound 5f exhibited higher cytotoxicity against MDA-MB-231 and MDA-MB-468, with IC_50s of 0.19 and 0.72 µM, respectively (triple-negative breast cancer). Furthermore, 5f demonstrated higher selective cytotoxicity against MDA-MB-231 and MDA-MB-468 than the Vero (non-cancerous) cell line, with selectivity indexes of 460.63 and 121.55, respectively. Compared to the reference (IC₅₀ = 0.79 µM), 5f demonstrated a greater affinity against CDK2 with a lower IC₅₀ of 0.47 µM, confirming its anticancer potential. Moreover, higher docking score of 5f than standard shows that the purine derivative acted via inhibition of CDK2.</p>","PeriodicalId":708,"journal":{"name":"Molecular Diversity","volume":" ","pages":""},"PeriodicalIF":3.9,"publicationDate":"2025-05-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144179538","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":"Computational prediction of cyclotides from Viola odorata as potential inhibitors against the neuraminidase of Streptococcus pneumoniae.","authors":"Sreejanani Sankar, Ajaya Kumar Sahoo, Shanmuga Priya Baskaran, R Babu, Smita Srivastava, Areejit Samal","doi":"10.1007/s11030-025-11224-4","DOIUrl":"https://doi.org/10.1007/s11030-025-11224-4","url":null,"abstract":"<p><p>Cyclotides are naturally occurring peptides characterized by a cyclic cystine knot, which provides them with exceptional structural stability. In addition to their stability, cyclotides exhibit diverse therapeutic activities including antimicrobial, antiviral and antitumor activities, making them promising candidates in drug discovery. Despite their potential, computational studies aimed at identifying cyclotide-based inhibitors for infectious diseases remain limited. To address this gap, this study performed a virtual screening of cyclotides from an Indian medicinal plant Viola odorata to identify potential inhibitors against a bacterial pathogen causing respiratory infections. We compiled a library of 93 cyclotides by retrieving their structures from public domain or predicting them using the AlphaFold server. We then docked these cyclotides against the neuraminidase protein of Streptococcus pneumoniae and analyzed the interacting residues and binding energies to identify the potential inhibitors. The docking based investigation identified five cyclotides namely, kalata S, kalata B1, cycloviolacin O15, vodo L12, and cycloviolacin O36 as potential inhibitors, with maximum binding energy and forming interactions with key residues of the neuraminidase protein. Thereafter, we performed molecular dynamics simulations of the protein-cyclotide complexes, and observed that the cyclotides remained stable within the complex. Notably, this study is the first computational effort to identify potential cyclotide inhibitors against Streptococcus pneumoniae, thereby providing key insights into the development of novel therapeutics for respiratory infections. In future, a more directed approach to characterize the structure and property of these cyclotides, along with further experimental validation could enhance their potential as therapeutic agents for respiratory diseases.</p>","PeriodicalId":708,"journal":{"name":"Molecular Diversity","volume":" ","pages":""},"PeriodicalIF":3.9,"publicationDate":"2025-05-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144172160","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":"Application of high-precision solubility prediction models in the assisted design of drug-like compounds.","authors":"Yutong Gao","doi":"10.1007/s11030-025-11239-x","DOIUrl":"https://doi.org/10.1007/s11030-025-11239-x","url":null,"abstract":"<p><p>Machine learning (ML) techniques are rapidly being applied to drug-assisted design. In order to provide more efficient methods to aid the solubility prediction aspect of drug design, two machine learning models are developed and trained with two distinct feature sets derived from the Zenodo dataset. The machine models are constructed with the multilayer perceptron as the core, combining Bayesian optimization and Monte Carlo methods to improve prediction accuracy. The training process leverages RMSprop to expedite convergence, utilizes Dropout to avert overfitting, and incorporates a Self-Attention mechanism to focus on important features. Based on the three types of compounds, the correlation coefficients all remain above 0.99 compared to the actual solubility. The average absolute errors of the solubility prediction results of the two models are less than 0.200 mol/L and 0.050 mol/L. Both trained models are capable of predicting the solubility of thousands of compounds in just 94.7 ms and 57.7 ms. Using these two models, it is possible to assist with faster and more rational design of drug-like compounds.</p>","PeriodicalId":708,"journal":{"name":"Molecular Diversity","volume":" ","pages":""},"PeriodicalIF":3.9,"publicationDate":"2025-05-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144155483","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":"Drug repurposing to identify potential FDA-approved drugs targeting three main angiogenesis receptors through a deep learning framework.","authors":"Mohammadreza Torabi, Soroush Sardari, Alejandro Rodríguez-Martínez, Nooshin Arabi, Horacio Pérez-Sánchez, Fahimeh Ghasemi","doi":"10.1007/s11030-025-11214-6","DOIUrl":"https://doi.org/10.1007/s11030-025-11214-6","url":null,"abstract":"<p><p>Tumor cell survival depends on the presence of oxygen and nutrients provided by existing blood vessels, particularly when cancer is in its early stage. Along with tumor growth in the vicinity of blood vessels, malignant cells require more nutrients; hence, capillary sprouting occurs from parental vessels, a process known as angiogenesis. Although multiple cellular pathways have been identified, controlling them with one single biomolecule as a multi-target inhibitor could be an attractive strategy for reducing medication side effects. Three critical pathways in angiogenesis have been identified, which are activated by the vascular endothelial growth factor receptor (VEGFR), fibroblast growth factor receptor (FGFR), and epidermal growth factor receptor (EGFR). This study aimed to develop a methodology to discover multi-target inhibitors among over 2000 FDA-approved drugs. Hence, a novel ensemble approach was employed, comprising classification and regression models. First, three different deep autoencoder classifications were generated for each target individually. The top 100 trained models were selected for the high-throughput virtual screening step. After that, all identified molecules with a probability of more than 0.9 in more than 70% of the models were removed to ensure accurate consideration in the regression step. Since the ultimate aim of virtual screening is to discover molecules with the highest success rate in the pharmaceutical industry, various aspects of the molecules in different assays were considered by integrating ten different regression models. In conclusion, this paper contributes to pharmaceutical sciences by introducing eleven diverse scaffolds and eight approved drugs that can potentially be used as inhibitors of angiogenesis receptors, including VEGFR, FGFR, and EGFR. Considering three target receptors simultaneously is another central concept and contribution used. This concept could increase the chance of success, while reducing the possibility of resistance to these agents.</p>","PeriodicalId":708,"journal":{"name":"Molecular Diversity","volume":" ","pages":""},"PeriodicalIF":3.9,"publicationDate":"2025-05-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144141085","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":"Harnessing virtual screening and MD simulations: a multistage approach to identifying potent and nontoxic agonists for protein kinase A.","authors":"Muneeb Ali, Nadeem Ahmad, Madiha Sardar, Sajjad Haider, Mamona Mushtaq, Mohammad Nur-E-Alam, Mohammed F Hawwal, Pinghua Sun, Zaheer Ul-Haq","doi":"10.1007/s11030-025-11223-5","DOIUrl":"https://doi.org/10.1007/s11030-025-11223-5","url":null,"abstract":"<p><p>Obesity-induced insulin resistance impairs glucose tolerance and β-cell function, significantly contributing to the pathogenesis of type 2 diabetes (T2D). Protein kinase A (PKA), being one of the key effector molecules of the cyclic AMP (cAMP) pathway, increases insulin secretion via membrane activity, gene expression, and exocytosis of insulin granules. The previous studies were limited to either target cAMP analogs as PKA agonist or mostly flavonoids using In vivo and In vitro studies (Hameed in Int J Biol Macromol 119:149-156, 2018;Shahab in Biomed Pharmacother 177, 2024;Hameed in Eur J Pharmacol 820:245-255, 2018;Hameed in Eur J Pharmacol 858, 2019;Hafizur in Med Chem Res 27:1408-1418, 2018;). To speed up the process, this study aimed to identify potential PKA activators as therapeutic agents for restoring β-cell function in Type 2 Diabetes (T2D) using a multistage virtual screening approach. In the initial phase, a ligand-based pharmacophore model was constructed to screen an in-house small molecule database for potential PKA agonists. By targeting the essential pharmacophoric features necessary for interaction with the cyclic nucleotide-binding (CNB) domain of PKA, the goal was to identify compounds with strong binding affinities and therapeutic promise. To gain deeper insights into the molecular mechanisms of PKA activation and evaluate key interactions and dynamic stability, a subset of promising hits was subjected to all-atom molecular dynamics simulations. Simulations showed significant conformational changes in PKA complexes, with average backbone root mean square deviations (RMSD) of 0.37 ± 0.15 nm for Comp-03, 0.53 ± 0.18 nm for Comp-11, 0.31 ± 0.06 nm for Comp-17, 0.28 ± 0.03 nm for Comp-38, and 0.48 ± 0.13 nm for Comp-41. The N3A motif showed consistent fluctuations, suggesting increased flexibility. Binding free energy calculations showed binding free energies (ΔGbind) for cAMP, Comp-03, Comp-17, Comp-38, and Comp-41, with ΔGbind values of - 62.87 ± 10.04, - 68.57 ± 12.77, - 78.13 ± 16.36, - 62.67 ± 13.06, and - 80.87 ± 10.45 kcal/mol, respectively. To further probe the conformational stability of these complexes, multidimensional scaling and free energy profiling were carried out. This exhaustive research study, involving examination of stability dynamics, deviation patterns, interaction networks, conformational changes, and energy profiles, provides profound understanding about mechanisms that activate PKA. The findings highlight several promising lead compounds, notably Comp-03, Comp-17, Comp-38, and Comp-41, which exhibit superior potential to activate PKA compared to cAMP. These findings lay a strong foundation for the development of novel PKA activators as potential therapeutic agents for managing T2D.</p>","PeriodicalId":708,"journal":{"name":"Molecular Diversity","volume":" ","pages":""},"PeriodicalIF":3.9,"publicationDate":"2025-05-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144141089","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":"De novo synthesis of tryptanthrin and its derivatives from indole: engineering a sustainable photocatalytic strategy.","authors":"Ya Zhou, Junrong Zhang, Ya Xiao, Hongwu Liu, Guoqing Wang, Linli Yang, Wujun Jian, Dan Zeng, Xiang Zhou, Song Yang","doi":"10.1007/s11030-025-11222-6","DOIUrl":"https://doi.org/10.1007/s11030-025-11222-6","url":null,"abstract":"<p><p>Tryptanthrin is a natural alkaloidal molecule [IUPAC name 6,12-dihydro-6,12-dioxoindolo-(2,1-b)-quinazoline], possessing an indoloquinazoline moiety. Since first being discovered in 1979, it and its analogs generated great interest in the fields of medicinal chemistry, life science, and materials science. Protocols for synthesizing tryptanthrins with the features of facile, eco-friendly, and mild reaction conditions remain an underdeveloped area. This new protocol, leveraging Rose Bengal as a photo-catalyst and commercially available substituted indoles as starting materials, enables selective synthesis under mild reaction conditions, expanding the substrate scope, complementing existing methods, and investigating the possible reaction mechanism. This approach emphasizes eco-friendliness, cost-effectiveness, and scalability, making it suitable for diverse applications. This innovation holds promise for synthesizing tryptanthrin-based bioactive compounds and materials relevant to chemistry and beyond.</p>","PeriodicalId":708,"journal":{"name":"Molecular Diversity","volume":" ","pages":""},"PeriodicalIF":3.9,"publicationDate":"2025-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144126361","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":"Novel pyrazole carboxylate derivatives as lonazolac bioisosteres with selective COX-2 inhibition: design, synthesis and anti-inflammatory activity.","authors":"Wael A A Fadaly, Ahmed Elshewy, Ahmed H A Abusabaa, Dina M E Amin, Hoda Khalifa Abdelhady, Haredy Hassan Haredy, Asmaa M Mahmoud, Nashwa A Ibrahim, Mohamed T M Nemr","doi":"10.1007/s11030-025-11220-8","DOIUrl":"https://doi.org/10.1007/s11030-025-11220-8","url":null,"abstract":"<p><p>Two novel series of di-aryl/tri-aryl substituted pyrazole ester derivatives 15a-h and 19a-d were designed, synthesized as novel non-acidic lonazolac analogs and tested for its COX-2, 5-LOX, 15-LOX, iNOS, pro-inflammatory cytokines TNF-α and PGE2 inhibitory activities. All the tested compounds showed excellent COX-2 inhibitory activity (IC₅₀ = 0.059-3.89 μM), compared to that of celecoxib (IC₅₀ = 0.22 μM), where derivatives 15c, 15d, 15 h and 19d were found to be the most potent showing COX-2 selectivity index in range of (S.I. = 28.56-98.71) compared to celecoxib (S.I. = 13.65). Moreover, the most potent four derivatives 15c, 15d, 15 h and 19d showed outstanding 5-LOX and 15-LOX inhibitory activities (IC₅₀ = 0.24-0.81, 0.20-2.2 respectively, compared to zileuton IC₅₀ = 1.52 and 0.54, respectively). Further investigation of the anti-inflammatory mechanistic study of derivatives 15c, 15d, 15 h and 19d revealed that these four compounds exhibited comparable TNF-α and PGE2 (LPS-induced pro-inflammatory cytokines) inhibitory activities (IC₅₀ = 0.77-1.20 μM and 0.28-0.52 μM respectively) when compared to celecoxib (IC₅₀ = 0.87 μM and 0.38 μM respectively) as reference drug using lipopolysaccharide-activated RAW 264.7 macrophages. Based on the advanced inhibitory activity of compounds 15c, 15d, 15 h and 19d against LPS-induced pro-inflammatory mediators (TNF-α and PGE2), inducible nitric oxide synthase (iNOS) inhibition assay was carried out. Remarkably, compounds 15c, 15d, 15 h and 19d showed higher potency with lower IC₅₀ (0.41-0.61 µM) when compared to the reference drug celecoxib (0.48 µM). Prior to in vivo anti-inflammatory activity screening, cytotoxicity testing was performed to ascertain safe and non-toxic concentrations of each compound. Safe doses of compounds were determined using lipopolysaccharide-activated RAW 264.7 macrophages, moreover results showed that compounds 15c, 15d, 15 h and 19d were more safer (less cytotoxic) with higher IC₅₀ (178.95-301.40 µM) when compared to the reference drug celecoxib (148.90 µM). In vivo anti-inflammatory activity of the target compounds 15c, 15d, 15 h and 19d reinforced the results of in vitro screening as the derivatives 15c, 15d, 15 h and 19d showed (ED₅₀ = 8.22-31.22 mg/kg, respectively) and were more potent than celecoxib (ED₅₀ = 40.39 mg/kg). All screened derivatives 15c, 15d, 15 h and 19d were less ulcerogenic (ulcer indexes = 1.22-3.93) than lonazolac (ulcer index = 20.30) and comparable to celecoxib (ulcer index = 3.02). In silico docking and ADME studies were carried out in order to clarify the interactions of the most active derivatives 15c, 15d, 15 h and 19d with the target enzymes and their pharmacokinetic parameters.</p>","PeriodicalId":708,"journal":{"name":"Molecular Diversity","volume":" ","pages":""},"PeriodicalIF":3.9,"publicationDate":"2025-05-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144126431","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":"Discovery of novel potential 11β-HSD1 inhibitors through combining deep learning, molecular modeling, and bio-evaluation.","authors":"Xiaodie Chen, Liang Zou, Lu Zhang, Jiali Li, Rong Liu, Yueyue He, Mao Shu, Kuilong Huang","doi":"10.1007/s11030-025-11171-0","DOIUrl":"https://doi.org/10.1007/s11030-025-11171-0","url":null,"abstract":"<p><p>11β-Hydroxysteroid dehydrogenase type 1 (11β-HSD1) has been shown to play an important role in the treatment of impaired glucose tolerance, insulin resistance, dyslipidemia, and obesity and is a promising drug target. In this study, we built a gated recurrent unit (GRU)-based recurrent neural network using 1,854,484 (processed) drug-like molecules from ChEMBL and the US patent database and successfully built a molecular generative model of 11βHSD1 inhibitors by using the known 11β-HSD1 inhibitors that have undergone transfer learning, our constructed GRU model was able to accurately capture drug-like molecules evaluated using traditional machine model-related syntax, and transfer learning can also easily generate potential 11β-HSD1 inhibitors. By combining Lipinski's and absorption, distribution, metabolism, excretion, and toxicity (ADME/T) analyses to filter nonconforming molecules and stepwise screening through molecular docking and molecular dynamics simulation, we finally obtained 5 potential compounds. We found that compound 02 is identical to a previously published inhibitor of 11β-HSD1. We selected compounds 02 and 05 with the lowest binding free energy for in vitro activity validation and found that compound 02 possessed inhibitory activity but was not as potent as the control. In conclusion, our study provides new ideas and methods for the development of new drugs and the discovery of new 11β-HSD1 inhibitors.</p>","PeriodicalId":708,"journal":{"name":"Molecular Diversity","volume":" ","pages":""},"PeriodicalIF":3.9,"publicationDate":"2025-05-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144109463","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":"https://doi.org/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":""},"PeriodicalIF":3.9,"publicationDate":"2025-05-20","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}