Molecular Diversity最新文献

{"title":"Leveraging machine learning to predict drug permeation: impact of menthol and limonene as enhancers.","authors":"Manisha Yadav, Baddipadige Raju, Gera Narendra, Jasveer Kaur, Manoj Kumar, Om Silakari, Bharti Sapra","doi":"10.1007/s11030-024-11062-w","DOIUrl":"10.1007/s11030-024-11062-w","url":null,"abstract":"<p><p>The present study aimed to develop robust machine learning (ML) models to predict the skin permeability of poorly water-soluble drugs in the presence of menthol and limonene as penetration enhancers (PEs). The ML models were also applied in virtual screening (VS) to identify hydrophobic drugs that exhibited better skin permeability in the presence of permeation enhancers i.e. menthol and limonene. The drugs identified through ML-based VS underwent experimental validation using in vitro skin penetration studies. The developed model predicted 80% probability of permeability enhancement for Sumatriptan Succinate (SS), Voriconazole (VCZ), and Pantoprazole Sodium (PS) with menthol and limonene. The in vitro release studies revealed that menthol increased penetration by approximately 2.49-fold, 2.25-fold, and 4.96-fold for SS, VCZ, and PS, respectively, while limonene enhanced permeability by approximately 1.32-fold, 2.27-fold, and 3.7-fold for SS, VCZ, and PS. The results from in silico and in vitro studies were positively correlated, indicating that the developed ML models could effectively reduce the need for extensive in vitro and in vivo experimentation.</p>","PeriodicalId":708,"journal":{"name":"Molecular Diversity","volume":" ","pages":"3131-3146"},"PeriodicalIF":3.9,"publicationDate":"2025-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142827139","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":"\"Several birds with one stone\": exploring the potential of AI methods for multi-target drug design.","authors":"Muhetaer Mukaidaisi, Madiha Ahmed, Karl Grantham, Aws Al-Jumaily, Shoukat Dedhar, Michael Organ, Alain Tchagang, Jinqiang Hou, Syed Ejaz Ahmed, Renata Dividino, Yifeng Li","doi":"10.1007/s11030-024-11042-0","DOIUrl":"10.1007/s11030-024-11042-0","url":null,"abstract":"<p><p>Drug discovery is a time-consuming and expensive process. Artificial intelligence (AI) methodologies have been adopted to cut costs and speed up the drug development process, serving as promising in silico approaches to efficiently design novel drug candidates targeting various health conditions. Most existing AI-driven drug discovery studies follow a single-target approach which focuses on identifying compounds that bind a target (i.e., one-drug-one-target approach). Polypharmacology is a relatively new concept that takes a systematic approach to search for a compound (or a combination of compounds) that can bind two or more carefully selected protein biomarkers simultaneously to synergistically treat the disease. Recent studies have demonstrated that multi-target drugs offer superior therapeutic potentials compared to single-target drugs. However, it is intuitively thought that searching for multi-target drugs is more challenging than finding single-target drugs. At present, it is unclear how AI approaches perform in designing multi-target drugs. In this paper, we comprehensively investigated the performance of multi-objective AI approaches for multi-target drug design. Our findings are quite counter-intuitive demonstrating that, in fact, AI approaches for multi-target drug design are able to efficiently generate more high-quality novel compounds than the single-target approaches while satisfying a number of constraints.</p>","PeriodicalId":708,"journal":{"name":"Molecular Diversity","volume":" ","pages":"3023-3039"},"PeriodicalIF":3.9,"publicationDate":"2025-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142708671","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":"Probing the dark chemical matter against PDE4 for the management of psoriasis using in silico, in vitro and in vivo approach.","authors":"B Swapna, Satvik Kotha, Divakar Selvaraj, Siddamsetty Ramachandra, Aruna Acharya","doi":"10.1007/s11030-025-11159-w","DOIUrl":"10.1007/s11030-025-11159-w","url":null,"abstract":"<p><p>The potential downsides for the present treatment for psoriasis are drug resistance, reduced efficacy, risk of mental episodes, and drug interactions. Hence, this study aims to discover a new drug for psoriasis by considering global research efforts and exploring underrepresented chemical space regions. The objective was to identify novel PDE4D inhibitors from the dark chemical matter (DCM) database for treating psoriasis. To address this we have coupled molecular docking and pharmacophore screening with molecular dynamics (MD) to identify hit molecules. Additionally, pharmacokinetics optimization was performed using machine learning and artificial intelligence which are key parts of drug discovery and development processes. The 139,353 DCM molecules were evaluated for their binding mode and interaction with critical residues such as GLN369, ILE336, PHE340, and PHE372 of the phosphodiesterase-4D (PDE4D) enzyme. Here, 15 hits were obtained through successive virtual screening procedures and all the 15 molecules were subjected to MD simulations for hit identification. In the MD studies, a stable root mean square deviation (RMSD) and ligand-protein interactions were found with four molecules, namely 027230, 060628, 060576, and 085881. The ligand 085881 was found promising because it inhibits LPS-induced IL-6 and TNF-alpha secretion from THP-1 cells with IC₅₀ of 18.41 μM and 34.43 μM, respectively. In vivo erythema grading showed that 085881 possesses mild to moderate anti-psoriatic action. This study demonstrates the effective use of computational techniques to discover novel PDE4D inhibitors and provides insight into their therapeutic potential for treating inflammatory diseases such as psoriasis.</p>","PeriodicalId":708,"journal":{"name":"Molecular Diversity","volume":" ","pages":"3449-3464"},"PeriodicalIF":3.9,"publicationDate":"2025-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143646905","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":"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":"3485-3500"},"PeriodicalIF":3.9,"publicationDate":"2025-08-01","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: Python tools for studying biomolecules and drug design.","authors":"Fedor V Ryzhkov, Yuliya E Ryzhkova, Michail N Elinson","doi":"10.1007/s11030-025-11199-2","DOIUrl":"10.1007/s11030-025-11199-2","url":null,"abstract":"<p><p>The increasing adoption of computational methods and artificial intelligence in scientific research has led to a growing interest in versatile tools like Python. In the fields of medical chemistry, biochemistry, and bioinformatics, Python has emerged as a key language for tackling complex challenges. It is used to solve various tasks, such as drug discovery, high-throughput and virtual screening, protein and genome analysis, and predicting drug efficacy. This review presents a list of tools for these tasks, including scripts, libraries, and ready-made programs, and serves as a starting point for scientists wishing to apply automation or optimization to routine tasks in medical chemistry and bioinformatics.</p>","PeriodicalId":708,"journal":{"name":"Molecular Diversity","volume":" ","pages":"3789-3824"},"PeriodicalIF":3.9,"publicationDate":"2025-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143956964","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 in the discovery of antiviral peptides and peptidomimetics: databases and prediction tools.","authors":"Maryam Nawaz, Yao Huiyuan, Fahad Akhtar, Ma Tianyue, Heng Zheng","doi":"10.1007/s11030-025-11173-y","DOIUrl":"10.1007/s11030-025-11173-y","url":null,"abstract":"<p><p>Antiviral peptides (AVPs) represent a novel and promising therapeutic alternative to conventional antiviral treatments, due to their broad-spectrum activity, high specificity, and low toxicity. The emergence of zoonotic viruses such as Zika, Ebola, and SARS-CoV-2 have accelerated AVP research, driven by advancements in data availability and artificial intelligence (AI). This review focuses on the development of AVP databases, their physicochemical properties, and predictive tools utilizing machine learning for AVP discovery. Machine learning plays a pivotal role in advancing and developing antiviral peptides and peptidomimetics, particularly through the development of specialized databases such as DRAVP, AVPdb, and DBAASP. These resources facilitate AVP characterization but face limitations, including small datasets, incomplete annotations, and inadequate integration with multi-omics data.The antiviral efficacy of AVPs is closely linked to their physicochemical properties, such as hydrophobicity and amphipathic α-helical structures, which enable viral membrane disruption and specific target interactions. Computational prediction tools employing machine learning and deep learning have significantly advanced AVP discovery. However, challenges like overfitting, limited experimental validation, and a lack of mechanistic insights hinder clinical translation.Future advancements should focus on improved validation frameworks, integration of in vivo data, and the development of interpretable models to elucidate AVP mechanisms. Expanding predictive models to address multi-target interactions and incorporating complex biological environments will be crucial for translating AVPs into effective clinical therapies.</p>","PeriodicalId":708,"journal":{"name":"Molecular Diversity","volume":" ","pages":"3753-3788"},"PeriodicalIF":3.9,"publicationDate":"2025-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143735606","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 and cheminformatics-based Identification of lichen-derived compounds targeting mutant PBP4^R200L in Staphylococcus aureus.","authors":"Shalini Mathpal, Tushar Joshi, P Priyamvada, Sudha Ramaiah, Anand Anbarasu","doi":"10.1007/s11030-025-11125-6","DOIUrl":"10.1007/s11030-025-11125-6","url":null,"abstract":"<p><p>Penicillin-binding protein 4 (PBP4) is essential in imparting significant β-lactam antibiotics resistance in Staphylococcus aureus (S. aureus) and the mutation R200L in PBP4 is linked to β-lactam non-susceptibility in natural strains, complicating treatment options. Therefore, discovering novel therapeutics against the mutant PBP4 is crucial, and natural compounds from lichen have found relevance in this regard. The aim of our study was to identify novel inhibitors against the R200L mutation by applying machine learning (ML) approach. Predictive classification models were developed using six machine learning algorithms to categorize lichen-derived compounds as either active or inactive. The models were evaluated using ROC curves, confusion matrices, and relevant statistical parameters. Among these, the Extra Trees algorithm showed superior predictive accuracy at 81%. The model identified 115 potentially active compounds from lichen, which were further evaluated for drug-likeness and structural similarity to β-lactam antibiotics. The top 23 compounds, showing similarity to β-lactam drug, were subjected to molecular docking. Among the top 10 compounds, two compounds, Barbatolic acid and Orcinyl lecanorate, displayed promising results in 200 ns molecular dynamics (MD) simulations and MM-PBSA analysis, exhibiting better docking score compare to reference compound. Additionally, DFT calculations revealed negative binding energies and smaller HOMO-LUMO gaps for both compounds. The obtained results prove the utility of ML in screening natural compounds, and provide novel opportunities for the design of antimicrobial compounds in the future.</p>","PeriodicalId":708,"journal":{"name":"Molecular Diversity","volume":" ","pages":"3345-3370"},"PeriodicalIF":3.9,"publicationDate":"2025-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143424483","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":"Integrated AI and machine learning pipeline identifies novel WEE1 kinase inhibitors for targeted cancer therapy.","authors":"Jaikanth Chandrasekaran, Dhanushya Gopal, Lokesh Vishwa Sureshkumar, Infant Xavier Santhiyagu, Varsha Senthil Kumar, Bhuvaneshwari Munuswamy, Beevi Fathima Harshatha Mohamed Yousuf Gani, Mohit Agrawal","doi":"10.1007/s11030-025-11157-y","DOIUrl":"10.1007/s11030-025-11157-y","url":null,"abstract":"<p><p>The dysregulation of the cell cycle in cancer underscores the therapeutic potential of targeting WEE1 kinase, a key regulator of the G2/M checkpoint. This study harnessed artificial intelligence (AI)-driven methodologies, particularly the MORLD platform, to identify novel WEE1 inhibitors. Starting with clinically validated WEE1 inhibitors as references, we generated 20,000 structurally diverse compounds optimized for binding affinity, synthetic accessibility, and drug-likeness. A rigorous cheminformatics pipeline-comprising PAINS filtering, physicochemical property assessments, and molecular fingerprinting-refined this library to 242 promising candidates. Dimensionality reduction using UMAP and clustering via K-means enabled the prioritization of structurally unique leads. Molecular docking studies highlighted two compounds, MORLD5036 and MORLD6305, with exceptional binding affinities and interactions with key WEE1 active site residues. Molecular dynamics simulations and MM-GBSA binding free energy calculations further validated MORLD5036 as the most stable and potent inhibitor. Scaffold analysis revealed novel chemotypes distinct from existing inhibitors, enhancing potential for intellectual property. Comprehensive ADME profiling confirmed favorable pharmacokinetics, while synthetic accessibility evaluations indicated practicality for experimental validation. The identified lead compound, MORLD5036, exhibits favorable pharmacokinetics and novel chemotypes, positioning it as a potential therapeutic candidate for cancers reliant on WEE1-mediated cell cycle control. This integrated, AI-driven pipeline expedites the identification of next-generation WEE1 inhibitors, paving the way for advancements in precision oncology. Unlike traditional methods reliant on pre-existing datasets, this study leverages MORLD's reinforcement learning framework to autonomously generate inhibitors, enabling exploration of uncharted chemical space. These findings establish MORLD5036 as a computationally promising WEE1 inhibitor candidate warranting further experimental validation.</p>","PeriodicalId":708,"journal":{"name":"Molecular Diversity","volume":" ","pages":"3425-3448"},"PeriodicalIF":3.9,"publicationDate":"2025-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143661904","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, network pharmacology, and molecular dynamics reveal potent cyclopeptide inhibitors against dengue virus proteins.","authors":"Mohammed A Imam, Thamir A Alandijany, Hashim R Felemban, Roba M Attar, Arwa A Faizo, Hattan S Gattan, Vivek Dhar Dwivedi, Esam I Azhar","doi":"10.1007/s11030-024-10975-w","DOIUrl":"10.1007/s11030-024-10975-w","url":null,"abstract":"<p><p>The dengue virus is a major global health hazard responsible for an estimated 390 million diseases yearly. This study focused on identifying cyclopeptide inhibitors for envelope structural proteins E, NS1, NS3, and NS5. Additionally, 5579 cyclopeptides were individually screened against the four target proteins using a machine learning-based quantitative structure-activity relationship model. Subsequently, the best 10 cyclopeptides from each protein were selected for molecular docking with their corresponding proteins. Moreover, the protein-peptide complexes with the highest affinity were subjected to a 100-ns molecular dynamics simulation. The protein-protein complexes exhibited superior structural stability and binding interactions. Based on the results of the MD simulation analyses, which included checking values for Root Mean Square Deviation, Root Mean Square Fluctuation, Principal Component Analysis (PCA), free energy landscapes, and energetic components, it was found that NS5-CP03714 complex is more stable and has stronger binding interactions than NS3-CP02054. PCA and free energy landscape plots have confirmed the higher conformational stability of NS5-CP03714. Analysis of the energetic components revealed that NS5-CP03714 (total binding energy = - 47.19 kcal/mol) exhibits more favorable interaction energies and overall binding energy compared to NS3-CP02054 (total binding energy = - 27.36 kcal/mol), suggesting a stronger and more stable formation of the complex. In addition, the drug-target network of two specific peptides (CP02950 and CP05582) and their associated target proteins were analyzed. This analysis revealed valuable information about their ability to target several proteins and their potential for broad-spectrum activity. Additional experimental investigations are necessary to validate these computational results and assess the efficacy of identified peptide inhibitors in biological systems.</p>","PeriodicalId":708,"journal":{"name":"Molecular Diversity","volume":" ","pages":"2899-2917"},"PeriodicalIF":3.9,"publicationDate":"2025-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142124393","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":"ASS1 is a hub gene and possible therapeutic target for regulating metabolic dysfunction-associated steatotic liver disease modulated by a carbohydrate-restricted diet.","authors":"Shaojun Chen, Yanhua Bi, Lihua Zhang","doi":"10.1007/s11030-025-11187-6","DOIUrl":"10.1007/s11030-025-11187-6","url":null,"abstract":"<p><p>Metabolic dysfunction-associated steatotic liver disease (MASLD) is the leading cause of chronic liver disease globally. A low-carbohydrate diet (LCD) offers benefits to MASLD patients, albeit its exact mechanism is not fully understood. Using public liver transcriptome data from MASLD patients before/after LCD intervention, we applied differential expression analysis and machine learning to identify key genes. We initially identified 162 differentially expressed genes in the GSE107650 dataset. Secondly, employing two machine learning algorithms, we found that PRAMENP, LEAP2, LOC105379013, and argininosuccinate synthetase 1 (ASS1) are potential hub genes. Additionally, protein-protein interaction and single-cell RNA location analyses suggested that ASS1 was the most crucial hub gene. Then, L1000CDS² analysis of the gene-expression signatures was employed for drug repurposing studies. CGP71683, an appetite suppressant, was predicted to improve MASLD and may mimic the ASS1 expression pattern induced by an LCD. Molecular dynamics confirmed spontaneous, stable CGP71683-ASS1 complex formation. Overall, this work based on analysis of machine learning algorithms, essential gene identification, and drug repurposing studies suggested that ASS1 is an essential gene in MASLD and CGP71683 is a potential drug candidate for treating MASLD by targeting ASS1 and mimicking the beneficial effects of an LCD. However, due to the inherent limitations of a purely computational approach, further experimental investigation is necessary to validate the anticipated results.</p>","PeriodicalId":708,"journal":{"name":"Molecular Diversity","volume":" ","pages":"3717-3732"},"PeriodicalIF":3.9,"publicationDate":"2025-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143951699","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}