{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"institution":[{"name":"Research Square"}],"indexed":{"date-parts":[[2026,10,8]],"date-time":"2026-10-08T13:58:01Z","timestamp":1791467881001,"version":"4.3.4"},"posted":{"date-parts":[[2026,8,13]]},"group-title":"In Review","reference-count":32,"publisher":"Springer Science and Business Media LLC","license":[{"start":{"date-parts":[[2026,8,13]],"date-time":"2026-08-13T00:00:00Z","timestamp":1786579200000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"accepted":{"date-parts":[[2026,8,4]]},"abstract":"<title>Abstract<\/title>\n                <p>\n                  Anthracycline-induced cardiotoxicity (AIC) remains a dose-limiting complication of cancer treatment, often leading to irreversible heart failure, yet effective cardioprotective therapies remain limited. Graph-driven drug repurposing offers a rapid pathway to identify cardioprotective therapies, but different computational models often generate divergent candidate lists that exceed experimental validation capacity. We applied a novel \"Union-then-Filter\" framework to prioritize therapeutics for AIC using AI-based approaches and evaluated candidates in zebrafish models. Three state-of-the-art graph learning models (TxGNN, CompGCN, and RLR) were trained on the PrimeKG to generate an initial candidate pool. A Large Language Model (LLM) agent automated evidence synthesis across 4,286 PubMed abstracts for the top 50 drugs from each model. Candidates were stratified using dual decision criteria and filtered against existing clinical trials. The pipeline narrowed 150 initial candidates to four novel candidates: Cysteine, Dasatinib, Tranilast, and Tretinoin. Prospective\n                  <italic>in vivo<\/italic>\n                  validation was subsequently conducted using an adult AIC (aAIC) zebrafish model. Phenotypic screening via echocardiography revealed that Cysteine, Tranilast, and Tretinoin significantly restored ejection fraction (EF) (overall one-way ANOVA: \\(\\:F\\left(\\text{4,95}\\right)=47.66,\\:\\:p&lt;0.0001\\); Tukey's post hoc: \\(\\:\\:\\:p&lt;0.01\\) for all three treatments vs. DOX+ control) and normalized cardiac remodeling markers in doxorubicin-treated subjects (Kruskal-Wallis: \\(\\:{\\chi\\:}^{2}\\left(4\\right)=17.21,\\:\\:p=0.0018\\); Dunn\u2019s post hoc: \\(\\:\\:\\:p&lt;0.01\\) for all three comparisons vs. DOX control). This study demonstrates the translational utility of an LLM-integrated AI pipeline for drug repurposing and highlights zebrafish AIC as an efficient bridge between\n                  <italic>in silico<\/italic>\n                  prediction and\n                  <italic>in vivo<\/italic>\n                  phenotypic validation in cardio-oncology.\n                <\/p>","DOI":"10.21203\/rs.3.rs-10594011\/v1","type":"posted-content","created":{"date-parts":[[2026,8,13]],"date-time":"2026-08-13T16:05:16Z","timestamp":1786637116000},"source":"Crossref","is-referenced-by-count":0,"title":["From Computational Prediction to In Vivo Experimental Validation: A Translational AI Pipeline for Anthracycline-Induced Cardiotoxicity"],"prefix":"10.21203","author":[{"given":"Manqi","family":"Li","sequence":"first","affiliation":[{"name":"Mayo Clinic in Florida"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jing","family":"Wei","sequence":"additional","affiliation":[{"name":"Mayo Clinic"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuteng","family":"Niu","sequence":"additional","affiliation":[{"name":"Mayo Clinic in Florida"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lu","family":"Kang","sequence":"additional","affiliation":[{"name":"Mayo Clinic in Florida"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ping","family":"Zhu","sequence":"additional","affiliation":[{"name":"Mayo Clinic"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Joerg","family":"Herrmann","sequence":"additional","affiliation":[{"name":"Mayo Clinic"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaolei","family":"Xu","sequence":"additional","affiliation":[{"name":"Mayo Clinic"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cui","family":"Tao","sequence":"additional","affiliation":[{"name":"Mayo Clinic in Florida"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","reference":[{"key":"ref1","first-page":"1","article-title":"N. Anthracyclines in the treatment of cancer. An overview","volume":"54","author":"Hortob\u00e1gyi G","year":"1997","unstructured":"Hortob\u00e1gyi, G. N. Anthracyclines in the treatment of cancer. An overview. Drugs 54, 1\u20137 (1997).","journal-title":"Drugs"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"1159","DOI":"10.1007\/s10741-020-09968-2","article-title":"Anthracycline-induced cardiotoxicity: mechanisms of action, incidence, risk factors, prevention, and treatment","volume":"26","author":"Saleh Y","year":"2021","unstructured":"Saleh, Y., Abdelkarim, O., Herzallah, K. & Abela, G. S. Anthracycline-induced cardiotoxicity: mechanisms of action, incidence, risk factors, prevention, and treatment. Heart Fail. Rev. 26, 1159\u20131173 (2021).","journal-title":"Heart Fail. Rev."},{"key":"ref3","doi-asserted-by":"crossref","first-page":"3530","DOI":"10.1002\/cncr.23942","article-title":"Cancer survivorship and aging: Moving the science forward","volume":"113","author":"Bellizzi KM","year":"2008","unstructured":"Bellizzi, K. M., Mustian, K. M., Palesh, O. G. & Diefenbach, M. Cancer survivorship and aging: Moving the science forward. Cancer 113, 3530\u20133539 (2008).","journal-title":"Cancer"},{"key":"ref4","author":"Lyon AR","year":"2022","unstructured":"Lyon, A. R. et al. 2022 ESC Guidelines on cardio-oncology developed in collaboration with the European Hematology Association (EHA), the European Society for Therapeutic Radiology and Oncology (ESTRO) and the International Cardio-Oncology Society (IC-OS). Eur. Heart J. 43, 4229\u20134361 (2022)."},{"key":"ref5","doi-asserted-by":"crossref","first-page":"279","DOI":"10.1161\/CIRCULATIONAHA.121.055801","article-title":"Identification of Drug Transporter Genomic Variants and Inhibitors That Protect Against Doxorubicin-Induced Cardiotoxicity","volume":"145","author":"Magdy T","year":"2022","unstructured":"Magdy, T. et al. Identification of Drug Transporter Genomic Variants and Inhibitors That Protect Against Doxorubicin-Induced Cardiotoxicity. Circulation 145, 279\u2013294 (2022).","journal-title":"Circulation"},{"key":"ref6","doi-asserted-by":"crossref","first-page":"oyaf370","DOI":"10.1093\/oncolo\/oyaf370","article-title":"Association of early dexrazoxane with reduced cardiotoxicity risk in sarcoma patients treated with anthracycline chemotherapy","volume":"30","author":"Jang KH","year":"2025","unstructured":"Jang, K. H. et al. Association of early dexrazoxane with reduced cardiotoxicity risk in sarcoma patients treated with anthracycline chemotherapy. The Oncologist 30, oyaf370 (2025).","journal-title":"The Oncologist"},{"key":"ref7","doi-asserted-by":"crossref","first-page":"521","DOI":"10.1038\/s41573-025-01164-x","article-title":"Computational drug repurposing: approaches, evaluation of in silico resources and case studies","volume":"24","author":"Tanoli Z","year":"2025","unstructured":"Tanoli, Z. et al. Computational drug repurposing: approaches, evaluation of in silico resources and case studies. Nat. Rev. Drug Discov. 24, 521\u2013542 (2025).","journal-title":"Nat. Rev. Drug Discov."},{"key":"ref8","doi-asserted-by":"crossref","first-page":"20","DOI":"10.1038\/s44401-026-00074-3","article-title":"Bridging the computational-experimental gap: leveraging large language model to prioritize Alzheimer\u2019s therapeutics based on comparison of learning models","volume":"3","author":"Li M","year":"2026","unstructured":"Li, M. et al. Bridging the computational-experimental gap: leveraging large language model to prioritize Alzheimer\u2019s therapeutics based on comparison of learning models. Npj Health Syst. 3, 20 (2026).","journal-title":"Npj Health Syst."},{"key":"ref9","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":"Huang K","year":"2024","unstructured":"Huang, K. et al. A foundation model for clinician-centered drug repurposing. Nat. Med. 30, 3601\u20133613 (2024).","journal-title":"Nat. Med."},{"key":"ref10","author":"Himmelstein DS","year":"2017","unstructured":"Himmelstein, D. S. et al. Systematic integration of biomedical knowledge prioritizes drugs for repurposing. eLife 6, e26726 (2017)."},{"key":"ref11","doi-asserted-by":"crossref","first-page":"174","DOI":"10.1093\/bib\/bbw110","article-title":"A review of validation strategies for computational drug repositioning","volume":"19","author":"Brown AS","year":"2018","unstructured":"Brown, A. S. & Patel, C. J. A review of validation strategies for computational drug repositioning. Brief. Bioinform. 19, 174\u2013177 (2018).","journal-title":"Brief. Bioinform."},{"key":"ref12","author":"Pillai M","year":"2023","unstructured":"Pillai, M. & Wu, D. Validation approaches for computational drug repurposing: a review. AMIA Annu. Symp. Proc. AMIA Symp. 2023, 559\u2013568 (2023)."},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1911.03082","author":"Vashishth S","year":"2019","unstructured":"Vashishth, S., Sanyal, S., Nitin, V. & Talukdar, P. Composition-based Multi-Relational Graph Convolutional Networks. Preprint at https:\/\/doi.org\/10.48550\/ARXIV.1911.03082 (2019)."},{"key":"ref14","doi-asserted-by":"crossref","first-page":"e1004259","DOI":"10.1371\/journal.pcbi.1004259","article-title":"Heterogeneous Network Edge Prediction: A Data Integration Approach to Prioritize Disease-Associated Genes","volume":"11","author":"Himmelstein DS","year":"2015","unstructured":"Himmelstein, D. S. & Baranzini, S. E. Heterogeneous Network Edge Prediction: A Data Integration Approach to Prioritize Disease-Associated Genes. PLOS Comput. Biol. 11, e1004259 (2015).","journal-title":"PLOS Comput. Biol."},{"key":"ref15","doi-asserted-by":"crossref","first-page":"1080299","DOI":"10.3389\/fcvm.2023.1080299","article-title":"Molecular mechanisms of anthracycline induced cardiotoxicity: Zebrafish come into play","volume":"10","author":"Moossavi M","year":"2023","unstructured":"Moossavi, M., Lu, X., Herrmann, J. & Xu, X. Molecular mechanisms of anthracycline induced cardiotoxicity: Zebrafish come into play. Front. Cardiovasc. Med. 10, 1080299 (2023).","journal-title":"Front. Cardiovasc. Med."},{"key":"ref16","doi-asserted-by":"crossref","first-page":"e166","DOI":"10.1161\/CIRCRESAHA.121.319104","article-title":"atg7-Based Autophagy Activation Reverses Doxorubicin-Induced Cardiotoxicity","volume":"129","author":"Wang Y","year":"2021","unstructured":"Wang, Y. et al. atg7-Based Autophagy Activation Reverses Doxorubicin-Induced Cardiotoxicity. Circ. Res. 129, e166\u2013e182 (2021).","journal-title":"Circ. Res."},{"key":"ref17","doi-asserted-by":"crossref","first-page":"659","DOI":"10.1096\/fj.07-9574LSF","article-title":"Dose translation from animal to human studies revisited","volume":"22","author":"Reagan-Shaw S","year":"2008","unstructured":"Reagan-Shaw, S., Nihal, M. & Ahmad, N. Dose translation from animal to human studies revisited. FASEB J. 22, 659\u2013661 (2008).","journal-title":"FASEB J."},{"key":"ref18","doi-asserted-by":"crossref","first-page":"27","DOI":"10.4103\/0976-0105.177703","article-title":"A simple practice guide for dose conversion between animals and human","volume":"7","author":"Nair A","year":"2016","unstructured":"Nair, A. & Jacob, S. A simple practice guide for dose conversion between animals and human. J. Basic Clin. Pharm. 7, 27 (2016).","journal-title":"J. Basic Clin. Pharm."},{"key":"ref19","doi-asserted-by":"crossref","first-page":"31","DOI":"10.1038\/s41536-023-00304-4","article-title":"A short dasatinib and quercetin treatment is sufficient to reinstate potent adult neuroregenesis in the aged killifish","volume":"8","author":"Houcke J","year":"2023","unstructured":"Van Houcke, J. et al. A short dasatinib and quercetin treatment is sufficient to reinstate potent adult neuroregenesis in the aged killifish. Npj Regen. Med. 8, 31 (2023).","journal-title":"Npj Regen. Med."},{"key":"ref20","author":"Abdullah CS","year":"2002","unstructured":"Abdullah, C. S. et al. Doxorubicin-induced cardiomyopathy associated with inhibition of autophagic degradation process and defects in mitochondrial respiration. Sci. Rep. 9, 2002 (2019)."},{"key":"ref21","doi-asserted-by":"crossref","first-page":"3143","DOI":"10.1016\/j.bbagen.2012.09.008","article-title":"Glutathione synthesis","volume":"1830","author":"Lu SC","year":"2013","unstructured":"Lu, S. C. Glutathione synthesis. Biochim. Biophys. Acta BBA - Gen. Subj. 1830, 3143\u20133153 (2013).","journal-title":"Biochim. Biophys. Acta BBA - Gen. Subj."},{"key":"ref22","author":"Chen Y","year":"2021","unstructured":"Chen, Y., Huang, M., Yan, Y. & He, D. Tranilast inhibits angiotensin II-induced myocardial fibrosis through S100A11\/ transforming growth factor-\u03b2 (TGF-\u03b21)\/Smad axis. Bioengineered 12, 8447\u20138456 (2021)."},{"key":"ref23","doi-asserted-by":"crossref","first-page":"e137593","DOI":"10.1172\/jci.insight.137593","article-title":"Cardiac retinoic acid levels decline in heart failure","volume":"6","author":"Yang N","year":"2021","unstructured":"Yang, N. et al. Cardiac retinoic acid levels decline in heart failure. JCI Insight 6, e137593 (2021).","journal-title":"JCI Insight"},{"key":"ref24","doi-asserted-by":"crossref","first-page":"509","DOI":"10.1038\/s41746-025-01840-7","article-title":"Accelerating clinical evidence synthesis with large language models","volume":"8","author":"Wang Z","year":"2025","unstructured":"Wang, Z. et al. Accelerating clinical evidence synthesis with large language models. Npj Digit. Med. 8, 509 (2025).","journal-title":"Npj Digit. Med."},{"key":"ref25","doi-asserted-by":"crossref","first-page":"559","DOI":"10.1016\/j.jchf.2022.03.006","article-title":"Sodium-Glucose Co-Transporter-2 Inhibitors and Cardiac Outcomes Among Patients Treated With Anthracyclines","volume":"10","author":"Gongora CA","year":"2022","unstructured":"Gongora, C. A. et al. Sodium-Glucose Co-Transporter-2 Inhibitors and Cardiac Outcomes Among Patients Treated With Anthracyclines. JACC Heart Fail. 10, 559\u2013567 (2022).","journal-title":"JACC Heart Fail."},{"key":"ref26","first-page":"58","article-title":"L\u00f3pez \u2013 Fern\u00e1ndez, T. Use of EMPAgliflozin in the prevention of CARDiotoxicity: the EMPACARD \u2013 PILOT trial","volume":"10","author":"Daniele AJ","year":"2024","unstructured":"Daniele, A. J., Gregorietti, V., Costa, D. & L\u00f3pez \u2013 Fern\u00e1ndez, T. Use of EMPAgliflozin in the prevention of CARDiotoxicity: the EMPACARD \u2013 PILOT trial. Cardio-Oncol. 10, 58 (2024).","journal-title":"Cardio-Oncol."},{"key":"ref27","doi-asserted-by":"crossref","first-page":"659","DOI":"10.1007\/s00204-020-02951-8","article-title":"Dapagliflozin suppresses ER stress and protects doxorubicin-induced cardiotoxicity in breast cancer patients","volume":"95","author":"Chang W-T","year":"2021","unstructured":"Chang, W.-T. et al. Dapagliflozin suppresses ER stress and protects doxorubicin-induced cardiotoxicity in breast cancer patients. Arch. Toxicol. 95, 659\u2013671 (2021).","journal-title":"Arch. Toxicol."},{"key":"ref28","doi-asserted-by":"crossref","first-page":"693","DOI":"10.3390\/biomedicines12030693","article-title":"Zebrafish as a Model for Cardiovascular and Metabolic Disease: The Future of Precision Medicine","volume":"12","author":"Angom RS","year":"2024","unstructured":"Angom, R. S. & Nakka, N. M. R. Zebrafish as a Model for Cardiovascular and Metabolic Disease: The Future of Precision Medicine. Biomedicines 12, 693 (2024).","journal-title":"Biomedicines"},{"key":"ref29","doi-asserted-by":"crossref","first-page":"67","DOI":"10.1038\/s41597-023-01960-3","article-title":"Building a knowledge graph to enable precision medicine","volume":"10","author":"Chandak P","year":"2023","unstructured":"Chandak, P., Huang, K. & Zitnik, M. Building a knowledge graph to enable precision medicine. Sci. Data 10, 67 (2023).","journal-title":"Sci. Data"},{"key":"ref30","doi-asserted-by":"crossref","first-page":"866","DOI":"10.1016\/j.omtn.2023.08.009","article-title":"Artificial intelligence enabled ChatGPT and large language models in drug target discovery, drug discovery, and development","volume":"33","author":"Chakraborty C","year":"2023","unstructured":"Chakraborty, C., Bhattacharya, M. & Lee, S.-S. Artificial intelligence enabled ChatGPT and large language models in drug target discovery, drug discovery, and development. Mol. Ther. - Nucleic Acids 33, 866\u2013868 (2023).","journal-title":"Mol. Ther. - Nucleic Acids"},{"key":"ref31","doi-asserted-by":"crossref","first-page":"63","DOI":"10.1038\/s41514-025-00253-w","article-title":"Nothobranchius furzeri: a vertebrate model for studying cardiac aging and cellular senescence","volume":"11","author":"Ma X","year":"2025","unstructured":"Ma, X. et al. Nothobranchius furzeri: a vertebrate model for studying cardiac aging and cellular senescence. Npj Aging 11, 63 (2025).","journal-title":"Npj Aging"},{"key":"ref32","doi-asserted-by":"crossref","first-page":"411","DOI":"10.1021\/ci960402j","article-title":"Data Analysis, and Scientific Graphing","volume":"37","author":"Swift ML","year":"1997","unstructured":"Swift, M. L. GraphPad Prism, Data Analysis, and Scientific Graphing. J. Chem. Inf. Comput. Sci. 37, 411\u2013412 (1997).","journal-title":"J. Chem. Inf. Comput. Sci."}],"container-title":[],"original-title":[],"link":[{"URL":"https:\/\/www.researchsquare.com\/article\/rs-10594011\/v1","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.researchsquare.com\/article\/rs-10594011\/v1.html","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,8]],"date-time":"2026-10-08T13:13:46Z","timestamp":1791465226000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.researchsquare.com\/article\/rs-10594011\/v1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,13]]},"references-count":32,"URL":"https:\/\/doi.org\/10.21203\/rs.3.rs-10594011\/v1","relation":{},"subject":[],"published":{"date-parts":[[2026,8,13]]},"subtype":"preprint"}}