{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T13:15:51Z","timestamp":1785417351598,"version":"3.56.0"},"reference-count":39,"publisher":"MDPI AG","issue":"6","license":[{"start":{"date-parts":[[2026,5,31]],"date-time":"2026-05-31T00:00:00Z","timestamp":1780185600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100009102","name":"Education Department of Jiangxi Province","doi-asserted-by":"publisher","award":["GJJ160786"],"award-info":[{"award-number":["GJJ160786"]}],"id":[{"id":"10.13039\/501100009102","id-type":"DOI","asserted-by":"publisher"}]},{"award":["GJJ160786"],"award-info":[{"award-number":["GJJ160786"]}],"id":[{"id":"https:\/\/ror.org\/04d8xwh61","id-type":"ROR","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100014868","name":"Jiangxi Provincial Department of Science and Technology","doi-asserted-by":"publisher","award":["20224BAB215023"],"award-info":[{"award-number":["20224BAB215023"]}],"id":[{"id":"10.13039\/501100014868","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100014868","name":"Jiangxi Provincial Department of Science and Technology","doi-asserted-by":"publisher","award":["20252BAC240091"],"award-info":[{"award-number":["20252BAC240091"]}],"id":[{"id":"10.13039\/501100014868","id-type":"DOI","asserted-by":"publisher"}]},{"award":["20224BAB215023"],"award-info":[{"award-number":["20224BAB215023"]}],"id":[{"id":"https:\/\/ror.org\/00t30yz20","id-type":"ROR","asserted-by":"publisher"}]},{"award":["20252BAC240091"],"award-info":[{"award-number":["20252BAC240091"]}],"id":[{"id":"https:\/\/ror.org\/00t30yz20","id-type":"ROR","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Pharmaceuticals"],"abstract":"<jats:p>Background\/Objectives: Machine learning has emerged as a transformative force in drug discovery, revolutionizing traditional research paradigms and profoundly improving the efficiency, cost-effectiveness, and speed of the drug development cycle for novel drugs. Colorectal cancer is one of the most prevalent malignant tumors and imposes a heavy burden on global public health due to its high morbidity, mortality, and poor prognosis. Cyclooxygenase-2 (COX-2) is a key therapeutic target of colorectal cancer and has been extensively applied in the development of novel anti-colorectal cancer drugs. Methods: In this study, we systematically compared the performance of Random Forest Classifier (RFC), deep learning (DL), and graph neural network (GNN) models, including GAT (Graph Attention Network), GCN (Graph Convolutional Network), and MPNN (Message Passing Neural Network), with diverse features in the classification task of COX-2 inhibitors, based on a custom COX-2 inhibitors dataset and a Traditional Chinese Medicine (TCM)-derived compound library. The optimal model was subsequently used to screen for potential COX-2 inhibitors. Additionally, the key substructures governing COX-2 inhibitory activity were also identified and analyzed. Finally, the prioritized candidate compounds underwent experimental validation. Results: Both RFC and DL models outperformed GNN models. Through further comparative analysis of models\u2019 predictive performance, the RFC model was ultimately verified as the optimal model for activity screening of TCM-derived compounds. The molecular interactions and binding affinities between predicted candidate compounds and COX-2 were further investigated. Finally, the selected lead compound, dehydrocostus lactone, was experimentally confirmed to possess potent COX-2 inhibitory activity. Conclusions: This study highlights that the RFC model is highly effective in screening bioactive components from TCM under small-dataset conditions, providing a solid foundation for subsequent related research in this field.<\/jats:p>","DOI":"10.3390\/ph19060878","type":"journal-article","created":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T01:08:02Z","timestamp":1780535282000},"page":"878","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Machine Learning-Aided Drug Repurposing for Screening COX-2 Inhibitors from Traditional Chinese Medicines"],"prefix":"10.3390","volume":"19","author":[{"given":"Zhi-Xian","family":"Zhu","sequence":"first","affiliation":[{"name":"School of Artificial Intelligence and Information Engineering, East China University of Technology, Nanchang 330013, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bin","family":"Liu","sequence":"additional","affiliation":[{"name":"Key Laboratory of Natural Microbial Medicine Research of Jiangxi Province, School of Life Science, Jiangxi Science and Technology Normal University, Nanchang 330013, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yi-Wen","family":"Xiao","sequence":"additional","affiliation":[{"name":"Key Laboratory of Natural Microbial Medicine Research of Jiangxi Province, School of Life Science, Jiangxi Science and Technology Normal University, Nanchang 330013, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-2110-8457","authenticated-orcid":false,"given":"Jun","family":"Chang","sequence":"additional","affiliation":[{"name":"Key Laboratory of Natural Microbial Medicine Research of Jiangxi Province, School of Life Science, Jiangxi Science and Technology Normal University, Nanchang 330013, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,5,31]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1159\/000543921","article-title":"Colorectal cancer: Epidemiology, risk factors, and public health strategies","volume":"106","author":"Matsuda","year":"2025","journal-title":"Digestion"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"102666","DOI":"10.1016\/j.arr.2025.102666","article-title":"Evolving landscape of colorectal cancer: Global and regional burden, risk factor dynamics, and future scenarios (the Global Burden of Disease 1990\u20132050)","volume":"104","author":"Zhou","year":"2025","journal-title":"Ageing Res. Rev."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"262","DOI":"10.7150\/jca.7988","article-title":"Early detection of colorectal cancer recurrence in patients undergoing surgery with curative intent: Current status and challenges","volume":"5","author":"Young","year":"2014","journal-title":"J. Cancer"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"781","DOI":"10.1038\/onc.2009.421","article-title":"The role of COX-2 in intestinal inflammation and colorectal cancer","volume":"29","author":"Wang","year":"2010","journal-title":"Oncogene"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"14","DOI":"10.1186\/s13020-023-00719-7","article-title":"Traditional Chinese medicine for colorectal cancer treatment: Potential targets and mechanisms of action","volume":"18","author":"Chen","year":"2023","journal-title":"Chin. Med."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"116074","DOI":"10.1016\/j.fct.2026.116074","article-title":"Curcumin inhibits colorectal cancer progression by regulating MDH2-mediated glycolysis and NAD+ metabolism","volume":"213","author":"Zhao","year":"2026","journal-title":"Food Chem. Toxicol."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"157765","DOI":"10.1016\/j.phymed.2026.157765","article-title":"Berberine promotes \u03b2-catenin ubiquitination and inhibits its nuclear translocation by targeting USP22 in colorectal cancers","volume":"152","author":"Xu","year":"2026","journal-title":"Phytomedicine"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"7247","DOI":"10.1038\/s41598-026-37091-z","article-title":"Ginsenoside Rg5 inhibits colorectal cancer, at least partially by blocking the lysosomal degradation of colorectal cancer cells","volume":"16","author":"Guo","year":"2026","journal-title":"Sci. Rep."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"542","DOI":"10.3892\/mmr.2021.12181","article-title":"Total saponins from Rhizoma Panacis Majoris inhibit proliferation, induce cell cycle arrest and apoptosis and influence MAPK signalling pathways on the colorectal cancer cell","volume":"24","author":"Chang","year":"2021","journal-title":"Mol. Med. Rep."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Zhou, E., Shen, Q., and Hou, Y. (2024). Integrating artificial intelligence into the modernization of traditional Chinese medicine industry: A review. Front. Pharmacol., 15.","DOI":"10.3389\/fphar.2024.1181183"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"23889","DOI":"10.1021\/acsomega.5c00549","article-title":"AI-driven drug discovery: A comprehensive review","volume":"10","author":"Ferreira","year":"2025","journal-title":"ACS Omega"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"43","DOI":"10.1186\/s13020-023-00741-9","article-title":"Machine learning in TCM with natural products and molecules: Current status and future perspectives","volume":"18","author":"Ma","year":"2023","journal-title":"Chin. Med."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Yang, L., Wang, H., Zhu, Z., Yang, Y., Xiong, Y., Cui, X., and Liu, Y. (2025). Network pharmacology-driven sustainability: AI and multi-omics synergy for drug discovery in traditional Chinese medicine. Pharmaceuticals, 18.","DOI":"10.3390\/ph18071074"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"18884","DOI":"10.1039\/D5SC04631A","article-title":"DeepMetab: A comprehensive and mechanistically informed graph learning framework for end-to-end drug metabolism prediction","volume":"16","author":"Zhou","year":"2025","journal-title":"Chem. Sci."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"e70121","DOI":"10.1002\/jcc.70121","article-title":"Graph neural network for 3-dimensional structures including dihedral angles for molecular property prediction","volume":"46","author":"Sangala","year":"2025","journal-title":"J. Comput. Chem."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"LeCun","year":"2015","journal-title":"Nature"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"11","DOI":"10.1186\/s40649-019-0069-y","article-title":"Graph convolutional networks: A comprehensive review","volume":"6","author":"Zhang","year":"2019","journal-title":"Comput. Soc. Netw."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"113","DOI":"10.1016\/j.bbrc.2023.07.018","article-title":"A deep learning-based drug repurposing screening and validation for anti-SARS-CoV-2 compounds by targeting the cell entry mechanism","volume":"675","author":"Yao","year":"2023","journal-title":"Biochem. Biophys. Res. Commun."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Yao, Q., Chen, Z., Cao, Y., and Hu, H. (2025). Enhancing drug-target interaction prediction with graph representation learning and knowledge-based regularization. Front. Bioinform., 5.","DOI":"10.3389\/fbinf.2025.1649337"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"5085","DOI":"10.2147\/DDDT.S523769","article-title":"Discovery of novel anti-acetylcholinesterase peptides using a machine learning and molecular docking approach","volume":"19","author":"Xiao","year":"2025","journal-title":"Drug Des. Dev. Ther."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"49","DOI":"10.1186\/s13321-018-0304-9","article-title":"Evaluating parameters for ligand-based modeling with random forest on sparse data sets","volume":"10","author":"Kensert","year":"2018","journal-title":"J. Cheminform."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"69","DOI":"10.58496\/BJML\/2024\/007","article-title":"Random Forest algorithm overview","volume":"2024","author":"Salman","year":"2024","journal-title":"Babylon. J. Mach. Learn."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"6394","DOI":"10.1038\/s41467-023-41967-3","article-title":"Limitations of representation learning in small molecule property prediction","volume":"14","author":"Dias","year":"2023","journal-title":"Nat. Commun."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"112928","DOI":"10.1016\/j.asoc.2025.112928","article-title":"A unified transductive and inductive learning framework for few-shot learning using graph neural networks","volume":"173","author":"Chang","year":"2025","journal-title":"Appl. Soft Comput."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"6086388","DOI":"10.1155\/2023\/6086388","article-title":"Discovery and validation of traditional Chinese and western medicine combination antirheumatoid arthritis drugs based on machine learning (Random Forest model)","volume":"2023","author":"Sun","year":"2023","journal-title":"Biomed Res. Int."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"100344","DOI":"10.1016\/j.comtox.2025.100344","article-title":"Drugs inhibition prediction in P-gp enzyme: A comparative study of machine learning and graph neural network","volume":"34","author":"Rehman","year":"2025","journal-title":"Comput. Toxicol."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"1605","DOI":"10.1021\/acs.jcim.9b00041","article-title":"Deep learning and random forest approach for finding the optimal traditional chinese medicine formula for treatment of alzheimer\u2019s disease","volume":"59","author":"Chen","year":"2019","journal-title":"J. Chem. Inf. Model."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"134","DOI":"10.2174\/1573409919666230417080832","article-title":"Screening of inhibitors against idiopathic pulmonary fibrosis: Few-shot machine learning and molecule docking based drug repurposing","volume":"20","author":"Chang","year":"2024","journal-title":"Curr. Comput. Aided Drug Des."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"105088","DOI":"10.1016\/j.engappai.2022.105088","article-title":"An adaptively balanced grey wolf optimization algorithm for feature selection on high-dimensional classification","volume":"114","author":"Wang","year":"2022","journal-title":"Eng. Appl. Artif. Intell."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"1","DOI":"10.18637\/jss.v036.i11","article-title":"Feature selection with the Boruta package","volume":"36","author":"Kursa","year":"2010","journal-title":"J. Stat. Softw."},{"key":"ref_31","first-page":"105","article-title":"Inhibition of in vitro leukotriene B4 biosynthesis in human neutrophil granulocytes and docking studies of natural quinones","volume":"8","author":"Landa","year":"2013","journal-title":"Nat. Prod. Commun."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"180","DOI":"10.1023\/B:DDAS.0000017436.05273.fd","article-title":"Functional mechanism underlying COX-2 expression following administration of indomethacin in rat stomachs: Importance of gastric hypermotility","volume":"49","author":"Takeuchi","year":"2004","journal-title":"Dig. Dis. Sci."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"6163","DOI":"10.1016\/j.apsb.2025.10.011","article-title":"Graph neural networks driven acceleration in drug discovery","volume":"15","author":"Wang","year":"2025","journal-title":"Acta Pharm. Sin. B"},{"key":"ref_34","first-page":"e44359","article-title":"Artificial intelligence and machine learning in pharmacological research: Bridging the gap between data and drug discovery","volume":"15","author":"Singh","year":"2023","journal-title":"Cureus"},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"100991","DOI":"10.1016\/j.patter.2024.100991","article-title":"Reducing overconfident errors in molecular property classification using Posterior Network","volume":"5","author":"Fan","year":"2024","journal-title":"Patterns"},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"115762","DOI":"10.1016\/j.addr.2025.115762","article-title":"Small data, big challenges: Machine- and deep-learning strategies for data-limited drug discovery","volume":"229","author":"Pallikkavaliyaveetil","year":"2026","journal-title":"Adv. Drug Deliv. Rev."},{"key":"ref_37","unstructured":"Landrum, G. (2023, July 19). RDKit: Open-Source Cheminformatics from Machine Learning to Chemical Registration. Available online: https:\/\/github.com\/rdkit\/rdkit."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"15069","DOI":"10.1074\/jbc.M116.725713","article-title":"Substrate-selective inhibition of cyclooxygeanse-2 by fenamic acid derivatives is dependent on peroxide tone","volume":"291","author":"Orlando","year":"2016","journal-title":"J. Biol. Chem."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"26","DOI":"10.1186\/s13321-015-0078-2","article-title":"Open drug discovery toolkit (ODDT): A new open-source player in the drug discovery field","volume":"7","author":"Zielenkiewicz","year":"2015","journal-title":"J. Cheminform."}],"container-title":["Pharmaceuticals"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8247\/19\/6\/878\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T01:18:07Z","timestamp":1780535887000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8247\/19\/6\/878"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,31]]},"references-count":39,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2026,6]]}},"alternative-id":["ph19060878"],"URL":"https:\/\/doi.org\/10.3390\/ph19060878","relation":{},"ISSN":["1424-8247"],"issn-type":[{"value":"1424-8247","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,31]]}}}