{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,12]],"date-time":"2026-10-12T08:50:18Z","timestamp":1791795018253,"version":"4.3.4"},"reference-count":69,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,9,18]],"date-time":"2026-09-18T00:00:00Z","timestamp":1789689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Pharmacol."],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Artificial intelligence (AI)-assisted drug repurposing seeks to identify new therapeutic applications for existing drugs. Nevertheless, most of the existing studies are centered on prediction scores and candidate ranking, and there is still relatively little attention paid to the pharmacological mechanisms, safety and translational validation.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>This critical review summarizes existing AI approaches to drug repurposing, identifies their mechanistic, safety, and translational barriers, and incorporates the emerging evidence gaps into a mechanism-driven and safety-proven translational pharmacology model.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Findings<\/jats:title>\n                    <jats:p>The literature reviewed shows that machine learning, deep learning, network medicine, knowledge graphs, graph neural networks, and foundation models have the potential to significantly increase the number of candidates identified, but they have marked variations in terms of interpretability, biological support, safety integration, external validation, and clinical applicability. In all of these strategies, common shortcomings are inadequate mechanism validation, poor causal evidence, incomplete dose and safety evaluation, weak pharmacovigilance integration, and reliance on internal validation, and varying experimental or real-world confirmatory evidence. These persistent evidence gaps were incorporated into a sequence of steps that incorporates candidate predictions, mechanism mapping, determination of causal plausibility, safety and toxicity evaluation, pharmacovigilance, real-world validation, expert pharmacology review and evidence-based candidate prioritization.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>AI-driven drug repurposing presents huge potential in the field of therapeutic innovation, but current applications require more clinical evidence and pharmacological mechanisms demonstrating safety, as well as clinical relevance. The proposed framework can support the more reliable prioritization of candidates for experimental testing, real world validation and future clinical testing.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fphar.2026.1915973","type":"journal-article","created":{"date-parts":[[2026,9,18]],"date-time":"2026-09-18T08:41:58Z","timestamp":1789720918000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Mechanism-aware and safety-validated AI for drug repurposing: a critical review and translational pharmacology framework"],"prefix":"10.3389","volume":"17","author":[{"given":"Moumita","family":"Hazra","sequence":"first","affiliation":[{"name":"Department of Pharmacology, Maharajah\u2019s Institute of Medical Sciences and Hospital, Dr. N. T. R. University of Health Sciences, Dr. Y. S. R. University of Health Sciences","place":["Andhra Pradesh, India"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Harishchander","family":"Anandaram","sequence":"additional","affiliation":[{"name":"Amrita School of Artificial Intelligence, Coimbatore, Amrita Vishwa Vidyapeetham","place":["Coimbatore, Tamil Nadu, India"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,9,18]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"1663","DOI":"10.1093\/bib\/bbz103","article-title":"Computational\/in silico methods in drug target and lead prediction","volume":"21","author":"Agamah","year":"2020","journal-title":"Briefings Bioinformatics"},{"key":"B2","volume-title":"Reflection Paper on the Use of Artificial Intelligence (AI) in the Medicinal Product Lifecycle","author":"Agency","year":"2024"},{"key":"B3","doi-asserted-by":"publisher","first-page":"4155","DOI":"10.32604\/cmc.2025.065571","article-title":"A comprehensive review of multimodal deep learning for enhanced medical diagnostics","volume":"84","author":"Al-Zoghby","year":"2025","journal-title":"Comput. Mater. & Continua"},{"key":"B4","doi-asserted-by":"publisher","first-page":"7874","DOI":"10.1021\/jm5006463","article-title":"Polypharmacology: challenges and opportunities in drug discovery: miniperspective","volume":"57","author":"Anighoro","year":"2014","journal-title":"J. Medicinal Chemistry"},{"key":"B5","volume-title":"Self-Rag: Learning to Retrieve, Generate, and Critique Through self-reflection","author":"Asai","year":"2024"},{"key":"B6","doi-asserted-by":"publisher","first-page":"1186","DOI":"10.3390\/pharmaceutics17091186","article-title":"Machine learning for multi-target drug discovery: challenges and opportunities in systems pharmacology","volume":"17","author":"Bi","year":"2025","journal-title":"Pharmaceutics"},{"key":"B7","doi-asserted-by":"publisher","first-page":"651","DOI":"10.3390\/biology14060651","article-title":"Ai-driven transcriptome prediction in human pathology: from molecular insights to clinical applications","volume":"14","author":"Chen","year":"2025","journal-title":"Biology"},{"key":"B8","doi-asserted-by":"publisher","first-page":"2691","DOI":"10.1038\/s41467-018-05116-5","article-title":"Network-based approach to prediction and population-based validation of in silico drug repurposing","volume":"9","author":"Cheng","year":"2018","journal-title":"Nat. Communications"},{"key":"B9","doi-asserted-by":"publisher","first-page":"e078378","DOI":"10.1136\/bmj-2023-078378","article-title":"TRIPOD+ AI statement: updated guidance for reporting clinical prediction models that use regression or machine learning methods","volume":"385","author":"Collins","year":"2024","journal-title":"Bmj"},{"key":"B10","first-page":"415257","volume-title":"Disease Networks and Their Contribution to Disease Understanding and Drug Repurposing. A Survey of the State of the Art","author":"del Valle","year":"2018"},{"key":"B12","volume-title":"The Fda\u2019s Draft Guidance, Use of AI in Regulatory Decision-Making for Drug & Biological Products","author":"DiFrancesco","year":"2026"},{"key":"B13","volume-title":"Use of Artificial Intelligence (AI) in the Medicinal Product Lifecycle - Scientific Guideline","year":"2024"},{"key":"B15","doi-asserted-by":"publisher","first-page":"625","DOI":"10.1038\/s41586-024-07421-0","article-title":"Detecting hallucinations in large language models using semantic entropy","volume":"630","author":"Farquhar","year":"2024","journal-title":"Nature"},{"key":"B16","article-title":"In vitro drug interaction studies\u2014Cytochrome P450 enzyme-and transporter-mediated drug interactions guidance for industry","volume":"46","author":"Fda","year":"2020","journal-title":"Cent. Drug Eval. Res. U. S. Food Drug Adm."},{"key":"B17","volume-title":"Emergency Use Authorizations for Drugs and Non-vaccine Biological Products","author":"Food","year":"2022"},{"key":"B18","doi-asserted-by":"publisher","first-page":"585","DOI":"10.1007\/s40264-024-01423-7","article-title":"The REporting of A disproportionality analysis for DrUg safety signal detection using individual case safety reports in PharmacoVigilance (READUS-PV): explanation and elaboration","volume":"47","author":"Fusaroli","year":"2024","journal-title":"Drug Saf."},{"key":"B19","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s10115-023-01894-7","article-title":"Computer-aided diagnosis systems: a comparative study of classical machine learning versus deep learning-based approaches","volume":"65","author":"Guetari","year":"2023","journal-title":"Knowl. Inf. Syst."},{"key":"B20","doi-asserted-by":"publisher","first-page":"10331","DOI":"10.1038\/ncomms10331","article-title":"Network-based in silico drug efficacy screening","volume":"7","author":"Guney","year":"2016","journal-title":"Nat. Communications"},{"key":"B21","doi-asserted-by":"publisher","first-page":"758","DOI":"10.1093\/aje\/kwv254","article-title":"Using big data to emulate a target trial when a randomized trial is not available","volume":"183","author":"Hern\u00e1n","year":"2016","journal-title":"Am. Journal Epidemiology"},{"key":"B22","doi-asserted-by":"publisher","first-page":"e26726","DOI":"10.7554\/eLife.26726","article-title":"Systematic integration of biomedical knowledge prioritizes drugs for repurposing","volume":"6","author":"Himmelstein","year":"2017","journal-title":"Elife"},{"key":"B23","doi-asserted-by":"publisher","first-page":"186","DOI":"10.1002\/wsbm.1337","article-title":"In silico methods for drug repurposing and pharmacology","volume":"8","author":"Hodos","year":"2016","journal-title":"Wiley Interdiscip. Rev. Syst. Biol. Med."},{"key":"B24","doi-asserted-by":"publisher","first-page":"1752396","DOI":"10.3389\/fpubh.2026.1752396","article-title":"Rehabilitation assistive technology transfer in the AI era: network dynamics and public health impacts in the yangtze river Delta, China","volume":"14","author":"Hu","year":"2026","journal-title":"Front. Public Health"},{"key":"B25","doi-asserted-by":"crossref","first-page":"3601","DOI":"10.1038\/s41591-024-03233-x","article-title":"A foundation model for clinician-centered drug repurposing","volume":"30","author":"Huaneg","year":"2024","journal-title":"Nat. Med."},{"key":"B26","article-title":"Zero-shot drug repurposing with geometric deep learning and clinician centered design","author":"Huang","year":"2023"},{"key":"B27","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/N19-1357","article-title":"Attention is not explanation","author":"Jain","year":"2019"},{"key":"B28","doi-asserted-by":"publisher","first-page":"16587","DOI":"10.1038\/s41598-024-67163-x","article-title":"Explainable drug repurposing via path based knowledge graph completion","volume":"14","author":"Jim\u00e9nez","year":"2024","journal-title":"Sci. Rep."},{"key":"B29","doi-asserted-by":"publisher","first-page":"109880","DOI":"10.1016\/j.neuropharm.2024.109880","article-title":"Using artificial intelligence to identify drugs for repurposing to treat l-DOPA-induced dyskinesia","volume":"248","author":"Johnston","year":"2024","journal-title":"Neuropharmacology"},{"key":"B30","doi-asserted-by":"publisher","first-page":"795","DOI":"10.1056\/nejmoa2031994","article-title":"Baricitinib plus remdesivir for hospitalized adults with Covid-19","volume":"384","author":"Kalil","year":"2021","journal-title":"N. Engl. J. Med."},{"key":"B31","doi-asserted-by":"publisher","first-page":"9607","DOI":"10.1073\/pnas.1219099110","article-title":"Systematic functional regulatory assessment of disease-associated variants","volume":"110","author":"Karczewski","year":"2013","journal-title":"Proc. Natl. Acad. Sci."},{"key":"B32","doi-asserted-by":"crossref","DOI":"10.1101\/2025.02.28.25323115","volume-title":"Medical Hallucinations in Foundation Models and Their Impact on Healthcare","author":"Kim","year":"2025"},{"key":"B14","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/2024.findings-emnlp.726","volume-title":"Language Models Are Surprisingly Fragile to Drug Names in Biomedical Benchmarks","author":"Gallifant","year":"2024"},{"key":"B33","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1111\/j.1472-8206.2007.00548.x","article-title":"Drugs and their molecular targets: an updated overview","volume":"22","author":"Landry","year":"2008","journal-title":"Fundam. & Clinical Pharmacology"},{"key":"B34","doi-asserted-by":"publisher","first-page":"1632046","DOI":"10.3389\/fchem.2025.1632046","article-title":"Recent advances in AI-based toxicity prediction for drug discovery","volume":"13","author":"Lee","year":"2025","journal-title":"Front. Chem."},{"key":"B35","first-page":"9459","article-title":"Retrieval-augmented generation for knowledge-intensive nlp tasks","volume":"33","author":"Lewis","year":"2020","journal-title":"Adv. Neural Information Processing Systems"},{"key":"B36","doi-asserted-by":"publisher","first-page":"676","DOI":"10.1016\/j.omtn.2020.07.003","article-title":"An improved anticancer drug-response prediction based on an ensemble method integrating matrix completion and ridge regression","volume":"21","author":"Liu","year":"2020","journal-title":"Mol. Ther. Nucleic Acids"},{"key":"B37","doi-asserted-by":"publisher","first-page":"68","DOI":"10.1038\/s42256-020-00276-w","article-title":"A deep learning framework for drug repurposing via emulating clinical trials on real-world patient data","volume":"3","author":"Liu","year":"2021","journal-title":"Nat. Machine Intelligence"},{"key":"B38","doi-asserted-by":"publisher","first-page":"2586335","DOI":"10.1080\/21645515.2025.2586335","article-title":"Pharmacovigilance analysis of FcRn antagonists in the treatment of myasthenia gravis: a disproportionality analysis based on the FAERS database","volume":"21","author":"Liu","year":"2025","journal-title":"Hum. Vaccines & Immunother."},{"key":"B39","doi-asserted-by":"publisher","first-page":"114333","DOI":"10.1016\/j.ab.2021.114333","article-title":"Peptide-based system for sensing Pb2+ and molecular logic computing","volume":"630","author":"Lu","year":"2021","journal-title":"Anal. Biochemistry"},{"key":"B40","doi-asserted-by":"publisher","first-page":"giad057","DOI":"10.1093\/gigascience\/giad057","article-title":"KGML-xDTD: a knowledge graph\u2013based machine learning framework for drug treatment prediction and mechanism description","volume":"12","author":"Ma","year":"2023","journal-title":"GigaScience"},{"key":"B41","doi-asserted-by":"publisher","first-page":"1057","DOI":"10.1080\/17460441.2021.1910673","article-title":"Knowledge graphs and their applications in drug discovery","volume":"16","author":"MacLean","year":"2021","journal-title":"Expert Opinion Drug Discovery"},{"key":"B42","doi-asserted-by":"crossref","first-page":"1461","DOI":"10.1007\/978-3-031-35529-5_92","article-title":"Artificial intelligence in drug discovery and development","author":"Mak","year":"2024","journal-title":"Drug Discovery Evaluation Safety Pharmacokinetic Assays"},{"key":"B43","doi-asserted-by":"publisher","first-page":"1407","DOI":"10.1016\/s2213-2600(21)00331-3","article-title":"Efficacy and safety of baricitinib for the treatment of hospitalised adults with COVID-19 (COV-BARRIER): a randomised, double-blind, parallel-group, placebo-controlled phase 3 trial","volume":"9","author":"Marconi","year":"2021","journal-title":"Lancet Respir. Medicine"},{"key":"B44","doi-asserted-by":"publisher","first-page":"bbad431","DOI":"10.1093\/bib\/bbad431","article-title":"Drug repositioning based on weighted local information augmented graph neural network","volume":"25","author":"Meng","year":"2024","journal-title":"Briefings Bioinformatics"},{"key":"B45","doi-asserted-by":"publisher","first-page":"502","DOI":"10.1038\/clpt.2013.54","article-title":"Model\u2010based drug development: a rational approach to efficiently accelerate drug development","volume":"93","author":"Milligan","year":"2013","journal-title":"Clin. Pharmacol. & Ther."},{"key":"B11","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/2024.naacl-long.482","article-title":"Investigating data contamination in modern benchmarks for large language models","author":"Deng","year":"2024"},{"key":"B46","doi-asserted-by":"publisher","first-page":"59","DOI":"10.12793\/tcp.2019.27.2.59","article-title":"A review of computational drug repurposing","volume":"27","author":"Park","year":"2019","journal-title":"Transl. Clinical Pharmacology"},{"key":"B47","doi-asserted-by":"publisher","first-page":"bbae461","DOI":"10.1093\/bib\/bbae461","article-title":"Knowledge graphs for drug repurposing: a review of databases and methods","volume":"25","author":"Perdomo-Quinteiro","year":"2024","journal-title":"Briefings Bioinforma."},{"key":"B48","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1038\/nrd.2018.168","article-title":"Drug repurposing: progress, challenges and recommendations","volume":"18","author":"Pushpakom","year":"2019","journal-title":"Nat. Reviews Drug Discovery"},{"key":"B49","doi-asserted-by":"publisher","first-page":"e30","DOI":"10.1016\/S0140-6736(20)30304-4","article-title":"Baricitinib as potential treatment for 2019-nCoV acute respiratory disease","volume":"395","author":"Richardson","year":"2020","journal-title":"Lancet"},{"key":"B50","doi-asserted-by":"publisher","first-page":"232","DOI":"10.1038\/nchembio.1199","article-title":"Target identification and mechanism of action in chemical biology and drug discovery","volume":"9","author":"Schenone","year":"2013","journal-title":"Nat. Chemical Biology"},{"key":"B51","doi-asserted-by":"publisher","first-page":"3255","DOI":"10.1038\/s41467-020-16969-0","article-title":"Genetic drug target validation using Mendelian randomisation","volume":"11","author":"Schmidt","year":"2020","journal-title":"Nat. Communications"},{"key":"B52","doi-asserted-by":"publisher","DOI":"10.7759\/cureus.44359","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":"B53","doi-asserted-by":"publisher","first-page":"EMMM202012697","DOI":"10.15252\/emmm.202012697","article-title":"Mechanism of baricitinib supports artificial intelligence\u2010predicted testing in COVID\u201019 patients","volume":"12","author":"Stebbing","year":"2020","journal-title":"EMBO Molecular Medicine"},{"key":"B54","doi-asserted-by":"publisher","first-page":"397","DOI":"10.1080\/17460441.2020.1704729","article-title":"Challenges and opportunities with drug repurposing: finding strategies to find alternative uses of therapeutics","volume":"15","author":"Talevi","year":"2020","journal-title":"Expert Opinion Drug Discovery"},{"key":"B55","doi-asserted-by":"publisher","first-page":"603615","DOI":"10.3389\/fimmu.2020.603615","article-title":"Indicator regularized non-negative matrix factorization method-based drug repurposing for COVID-19","volume":"11","author":"Tang","year":"2021","journal-title":"Front. Immunol."},{"key":"B56","doi-asserted-by":"publisher","first-page":"111","DOI":"10.1007\/s44371-026-00567-y","article-title":"Network pharmacology in the multi-omics era: uncovering novel therapeutic strategies","volume":"3","author":"Thombre","year":"2026","journal-title":"Discov. Chem."},{"key":"B57","volume-title":"Considerations for the Use of Artificial Intelligence to Support Regulatory Decision-Making for Drug and Biological Products","author":"UsfaDA","year":"2025"},{"key":"B58","doi-asserted-by":"publisher","first-page":"251","DOI":"10.2174\/1389203721666200921152853","article-title":"Drug repurposing approaches: existing leads for novel threats and drug targets","volume":"22","author":"Usha","year":"2021","journal-title":"Curr. Protein Peptide Sci."},{"key":"B59","doi-asserted-by":"publisher","first-page":"463","DOI":"10.1038\/s41573-019-0024-5","article-title":"Applications of machine learning in drug discovery and development","volume":"18","author":"Vamathevan","year":"2019","journal-title":"Nat. Reviews Drug Discovery"},{"key":"B60","doi-asserted-by":"publisher","first-page":"351","DOI":"10.1007\/s40264-019-00899-y","article-title":"Investigating overlap in signals from EVDAS, FAERS, and VigiBase\u00ae","volume":"43","author":"Vogel","year":"2020","journal-title":"Drug Safety"},{"key":"B61","doi-asserted-by":"publisher","first-page":"2411325","DOI":"10.1002\/advs.202411325","article-title":"Applications of artificial intelligence in drug repurposing","volume":"12","author":"Wan","year":"2025","journal-title":"Adv. Sci."},{"key":"B62","doi-asserted-by":"publisher","first-page":"114347","DOI":"10.1016\/j.jconrel.2025.114347","article-title":"A biocompatible tea polyphenol nanoplatform for efficient cytosolic delivery of protein therapeutics","volume":"388","author":"Wang","year":"2025","journal-title":"J. Control. Release"},{"key":"B63","volume-title":"Large Language Models Meet Biomedical Knowledge Graphs for Mechanistically Grounded Therapeutic Prioritization","author":"Wei","year":"2026"},{"key":"B64","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/2024.findings-acl.372","volume-title":"Benchmarking retrieval-augmented Generation for Medicine","author":"Xiong","year":"2024"},{"key":"B65","doi-asserted-by":"publisher","first-page":"46","DOI":"10.1038\/s41746-024-01038-3","article-title":"Leveraging generative AI to prioritize drug repurposing candidates for Alzheimer\u2019s disease with real-world clinical validation","volume":"7","author":"Yan","year":"2024","journal-title":"NPJ Digital Medicine"},{"key":"B66","doi-asserted-by":"publisher","first-page":"104960","DOI":"10.1016\/j.jbi.2025.104960","article-title":"Predicting drug-target interactions based on multivariate information fusion and graph contrast learning","volume":"172","author":"Yang","year":"2025","journal-title":"J. Biomed. Inf."},{"key":"B67","doi-asserted-by":"publisher","first-page":"5191","DOI":"10.1093\/bioinformatics\/btz418","article-title":"deepDR: a network-based deep learning approach to in silico drug repositioning","volume":"35","author":"Zeng","year":"2019","journal-title":"Bioinformatics"},{"key":"B68","doi-asserted-by":"publisher","first-page":"bbaf533","DOI":"10.1093\/bib\/bbaf533","article-title":"Computational toxicology in drug discovery: applications of artificial intelligence in ADMET and toxicity prediction","volume":"26","author":"Zhang","year":"2025","journal-title":"Briefings Bioinforma."},{"key":"B69","doi-asserted-by":"publisher","first-page":"103217","DOI":"10.1016\/j.isci.2021.103217","article-title":"Progresses and challenges in link prediction","volume":"24","author":"Zhou","year":"2021","journal-title":"Iscience"}],"updated-by":[{"DOI":"10.3389\/fphar.2026.2009326","type":"correction","label":"Correction","source":"publisher","updated":{"date-parts":[[2026,10,12]],"date-time":"2026-10-12T00:00:00Z","timestamp":1791763200000}}],"container-title":["Frontiers in Pharmacology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fphar.2026.1915973\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,12]],"date-time":"2026-10-12T08:44:20Z","timestamp":1791794660000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fphar.2026.1915973\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,18]]},"references-count":69,"alternative-id":["10.3389\/fphar.2026.1915973"],"URL":"https:\/\/doi.org\/10.3389\/fphar.2026.1915973","relation":{},"ISSN":["1663-9812"],"issn-type":[{"value":"1663-9812","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,18]]},"article-number":"1915973"}}