{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"institution":[{"name":"bioRxiv"}],"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T16:07:25Z","timestamp":1784304445854,"version":"3.55.0"},"posted":{"date-parts":[[2025,7,16]]},"group-title":"Bioinformatics","reference-count":60,"publisher":"openRxiv","license":[{"start":{"date-parts":[[2025,7,16]],"date-time":"2025-07-16T00:00:00Z","timestamp":1752624000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"name":"NIH","award":["HHSN316201200036W"],"award-info":[{"award-number":["HHSN316201200036W"]}]},{"name":"NIH","award":["1R01AI180118-01A"],"award-info":[{"award-number":["1R01AI180118-01A"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"accepted":{"date-parts":[[2026,7,14]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                <jats:p>\n                  Reproducible biomarker identification and transplant rejection risk prediction remain fundamental yet unsolved challenges in transplantation medicine. Traditional approaches rely on hypothesis-driven analyses and domain expertise, limiting scalability and generalizability across diverse populations. We introduce\n                  <jats:italic>Transplant-Agents<\/jats:italic>\n                  , a data-driven multi-agent AI framework integrating large language models (LLMs) with machine learning algorithms for automated biomarker identification and rejection risk prediction. Agents interact through structured, iterative dialogue governed by predefined rules and criteria, converging on optimal biomarker sets reproducible across multiple iterations. We evaluated three multicenter clinical trial transplant datasets from ImmPort, comprising 683 patients across kidney, liver, and heart transplant cohorts.\n                  <jats:italic>Transplant-Agents<\/jats:italic>\n                  achieve AUROC scores of 0.93, 0.88, and 0.88. Feature importance analysis further confirms the stability, interpretability and potential generalizability of identified biomarkers. This work demonstrates that AI-agent frameworks can reliably reproduce established transplant biomarkers while enabling transparent, validated, and standardized risk prediction pipelines.\n                <\/jats:p>","DOI":"10.1101\/2025.07.10.664265","type":"posted-content","created":{"date-parts":[[2025,7,16]],"date-time":"2025-07-16T21:41:28Z","timestamp":1752702088000},"source":"Crossref","is-referenced-by-count":0,"title":["<i>Transplant-Agents<\/i>\n                  : A Multi-Agent Artificial Intelligence Framework for Reproducibility Assessment of Post-Transplant Risk Prediction and Rejection Biomarkers"],"prefix":"10.64898","author":[{"given":"Sirui","family":"Ding","sequence":"first","affiliation":[{"name":"Bakar Computational Health Sciences Institute, University of California, San Francisco, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sanchita","family":"Bhattacharya","sequence":"additional","affiliation":[{"name":"Bakar Computational Health Sciences Institute, University of California, San Francisco, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Minnie M.","family":"Sarwal","sequence":"additional","affiliation":[{"name":"Division of Transplant Surgery, Department of Surgery, University of California San Francisco, San Francisco, California, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marina","family":"Sirota","sequence":"additional","affiliation":[{"name":"Bakar Computational Health Sciences Institute, University of California, San Francisco, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Atul J.","family":"Butte","sequence":"additional","affiliation":[{"name":"Bakar Computational Health Sciences Institute, University of California, San Francisco, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"54368","reference":[{"key":"2026071708351072000_2025.07.10.664265v2.1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cels.2021.06.006"},{"key":"2026071708351072000_2025.07.10.664265v2.2","doi-asserted-by":"publisher","DOI":"10.1097\/TP.0000000000002366"},{"key":"2026071708351072000_2025.07.10.664265v2.3","doi-asserted-by":"crossref","first-page":"432","DOI":"10.1016\/j.kint.2023.06.023","article-title":"Urine trumps the protocol biopsy for subclinical rejection surveillance","volume":"104","year":"2023","journal-title":"Kidney Int"},{"key":"2026071708351072000_2025.07.10.664265v2.4","doi-asserted-by":"crossref","unstructured":"Zhang, Z. , Zhang, H. & Khanal, M. K . Development of scoring system for risk stratification in clinical medicine: A step-by-step tutorial. Ann Transl Med 5, (2017).","DOI":"10.21037\/atm.2017.08.22"},{"key":"2026071708351072000_2025.07.10.664265v2.5","doi-asserted-by":"crossref","unstructured":"Lamarth\u00e9e, B. et al. Transcriptional and spatial profiling of the kidney allograft unravels a central role for FcyRIII+ innate immune cells in rejection. Nat Commun 14, 4359 (2023).","DOI":"10.1038\/s41467-023-39859-7"},{"key":"2026071708351072000_2025.07.10.664265v2.6","doi-asserted-by":"crossref","first-page":"1330","DOI":"10.1097\/TP.0000000000004017","article-title":"Urinary Biomarkers for Kidney Allograft Injury","volume":"106","year":"2022","journal-title":"Transplantation"},{"key":"2026071708351072000_2025.07.10.664265v2.7","doi-asserted-by":"publisher","DOI":"10.1053\/gast.2003.50016"},{"key":"2026071708351072000_2025.07.10.664265v2.8","doi-asserted-by":"publisher","DOI":"10.1016\/j.jceh.2012.11.002"},{"key":"2026071708351072000_2025.07.10.664265v2.9","doi-asserted-by":"publisher","DOI":"10.1016\/j.athoracsur.2008.05.007"},{"issue":"1","key":"2026071708351072000_2025.07.10.664265v2.10","doi-asserted-by":"crossref","first-page":"e2035048","DOI":"10.1001\/jamanetworkopen.2020.35048","article-title":"Molecular diversity of clinically stable human kidney allografts","volume":"4","year":"2021","journal-title":"JAMA Network Open"},{"key":"2026071708351072000_2025.07.10.664265v2.11","doi-asserted-by":"publisher","DOI":"10.1186\/s12874-022-01768-6"},{"key":"2026071708351072000_2025.07.10.664265v2.12","doi-asserted-by":"crossref","unstructured":"Xiao, L. & Zhao, F . Exploring the frontier of microbiome biomarker discovery with artificial intelligence. Natl Sci Rev 11, (2024).","DOI":"10.1093\/nsr\/nwae325"},{"key":"2026071708351072000_2025.07.10.664265v2.13","doi-asserted-by":"publisher","DOI":"10.1136\/bmjopen-2021-053674"},{"key":"2026071708351072000_2025.07.10.664265v2.14","doi-asserted-by":"crossref","unstructured":"Bhattacharya, S. et al. ImmPort, toward repurposing of open access immunological assay data for translational and clinical research. Sci Data 5, (2018).","DOI":"10.1038\/sdata.2018.15"},{"key":"2026071708351072000_2025.07.10.664265v2.15","unstructured":"Ke, G. et al. LightGBM: A Highly Efficient Gradient Boosting Decision Tree. https:\/\/github.com\/Microsoft\/LightGBM."},{"key":"2026071708351072000_2025.07.10.664265v2.16","doi-asserted-by":"crossref","unstructured":"Khalid, S. A Survey of Feature Selection and Feature Extraction Techniques in Machine Learning. vol. 372 www.conference.thesai.org (2014).","DOI":"10.1109\/SAI.2014.6918213"},{"key":"2026071708351072000_2025.07.10.664265v2.17","doi-asserted-by":"publisher","DOI":"10.1101\/2024.11.11.623004"},{"key":"2026071708351072000_2025.07.10.664265v2.18","doi-asserted-by":"crossref","first-page":"645","DOI":"10.1111\/ajt.16217","article-title":"Statistical performance of 16 posttransplant risk scores in a contemporary cohort of heart transplant recipients","volume":"21","year":"2021","journal-title":"American Journal of Transplantation"},{"key":"2026071708351072000_2025.07.10.664265v2.19","doi-asserted-by":"crossref","first-page":"1922","DOI":"10.1111\/ajt.12761","article-title":"External validation of the estimated posttransplant survival score for allocation of deceased donor kidneys in the United States","volume":"14","year":"2014","journal-title":"American Journal of Transplantation"},{"key":"2026071708351072000_2025.07.10.664265v2.20","doi-asserted-by":"crossref","first-page":"691","DOI":"10.3109\/0886022X.2010.486495","article-title":"Analyses of renal outcome following transplantation adjusting for informative right censoring and demographic factors: A longitudinal study","volume":"32","year":"2010","journal-title":"Ren Fail"},{"key":"2026071708351072000_2025.07.10.664265v2.21","doi-asserted-by":"crossref","first-page":"2515","DOI":"10.1111\/ajt.12928","article-title":"The kidney donor profile index (KDPI) of marginal donors allocated by standardized pretransplant donor biopsy assessment: Distribution and association with graft outcomes","volume":"14","year":"2014","journal-title":"American Journal of Transplantation"},{"key":"2026071708351072000_2025.07.10.664265v2.22","doi-asserted-by":"publisher","DOI":"10.1053\/j.gastro.2006.02.010"},{"key":"2026071708351072000_2025.07.10.664265v2.23","doi-asserted-by":"publisher","DOI":"10.1016\/j.athoracsur.2011.02.086"},{"key":"2026071708351072000_2025.07.10.664265v2.24","doi-asserted-by":"crossref","first-page":"1507","DOI":"10.1111\/ajt.15201","article-title":"Optimization of heart allocation: The transplant risk score","volume":"19","year":"2019","journal-title":"American Journal of Transplantation"},{"key":"2026071708351072000_2025.07.10.664265v2.25","doi-asserted-by":"publisher","DOI":"10.1016\/j.athoracsur.2011.04.030"},{"key":"2026071708351072000_2025.07.10.664265v2.26","unstructured":"Ding, Sirui , et al. \u201cMulti-task learning for post-transplant cause of death analysis: A case study on liver transplant.\u201d AMIA Annual Symposium Proceedings. Vol. 2023. 2024."},{"key":"2026071708351072000_2025.07.10.664265v2.27","unstructured":"Ding, Sirui , et al. \u201cFairly predicting graft failure in liver transplant for organ assigning.\u201d AMIA Annual Symposium Proceedings. Vol. 2022. 2023."},{"key":"2026071708351072000_2025.07.10.664265v2.28","doi-asserted-by":"publisher","DOI":"10.1023\/A:1010933404324"},{"key":"2026071708351072000_2025.07.10.664265v2.29","first-page":"2825","article-title":"Scikit-learn: Machine learning in Python","volume":"12","year":"2011","journal-title":"the Journal of machine Learning research"},{"key":"2026071708351072000_2025.07.10.664265v2.30","doi-asserted-by":"crossref","first-page":"919","DOI":"10.1016\/j.procs.2016.07.111","article-title":"A Survey on Feature Selection","volume":"91","year":"2016","journal-title":"Procedia Computer Science"},{"key":"2026071708351072000_2025.07.10.664265v2.31","doi-asserted-by":"crossref","unstructured":"Rozemberczki, B. , et al. The Shapley Value in Machine Learning. https:\/\/github.com\/AstraZeneca\/awesome-shapley-value. (2022).","DOI":"10.24963\/ijcai.2022\/778"},{"key":"2026071708351072000_2025.07.10.664265v2.32","unstructured":"OpenAI et al. GPT-4 Technical Report. http:\/\/arxiv.org\/abs\/2303.08774 (2023)."},{"key":"2026071708351072000_2025.07.10.664265v2.33","doi-asserted-by":"crossref","first-page":"218","DOI":"10.1016\/j.transproceed.2006.10.226","article-title":"Differential White Cell Count Relationships With Human Cardiac Allograft Rejection","volume":"39","year":"2007","journal-title":"Transplant Proc"},{"key":"2026071708351072000_2025.07.10.664265v2.34","first-page":"e1","article-title":"The International Society for Heart and Lung Transplantation (ISHLT) guidelines for the care of heart transplant recipients","volume":"42","year":"2023","journal-title":"Journal of Heart and Lung Transplantation"},{"key":"2026071708351072000_2025.07.10.664265v2.35","doi-asserted-by":"crossref","unstructured":"Costa, D. et al. Role of HLA matching and donor specific antibody development in long-term survival, acute rejection and cardiac allograft vasculopathy. Transpl Immunol 83, (2024).","DOI":"10.1016\/j.trim.2024.102011"},{"key":"2026071708351072000_2025.07.10.664265v2.36","doi-asserted-by":"crossref","unstructured":"Ho\u0161kova, L. et al. Relationship of cardiorenal biomarkers for prediction of renal dysfunction in patients after heart transplantation. Cor Vasa 55, (2013).","DOI":"10.1016\/j.crvasa.2013.03.004"},{"key":"2026071708351072000_2025.07.10.664265v2.37","doi-asserted-by":"crossref","first-page":"347","DOI":"10.1016\/j.jjcc.2014.12.010","article-title":"Neutrophil gelatinase-associated lipocalin (NGAL) in heart transplant recipients after conversion to everolimus therapy","volume":"66","year":"2015","journal-title":"J Cardiol"},{"key":"2026071708351072000_2025.07.10.664265v2.38","doi-asserted-by":"publisher","DOI":"10.1016\/j.healun.2006.03.008"},{"key":"2026071708351072000_2025.07.10.664265v2.39","doi-asserted-by":"crossref","first-page":"949","DOI":"10.1053\/j.ajkd.2014.12.020","article-title":"BK virus nephropathy in heart transplant recipients","volume":"65","year":"2015","journal-title":"American Journal of Kidney Diseases"},{"key":"2026071708351072000_2025.07.10.664265v2.40","doi-asserted-by":"crossref","unstructured":"Seino, K. , Kayagaki, N. , Bashuda, H. , Okumura, K. & Yagita, H. Contribution of Fas Ligand to Cardiac al Log Raft Rejection. International Immunology vol. 8 https:\/\/academic.oup.com\/intimm\/article\/8\/9\/1347\/730805 (1996).","DOI":"10.1093\/intimm\/8.9.1347"},{"key":"2026071708351072000_2025.07.10.664265v2.41","doi-asserted-by":"publisher","DOI":"10.1097\/HCO.0000000000001145"},{"key":"2026071708351072000_2025.07.10.664265v2.42","doi-asserted-by":"crossref","first-page":"1061","DOI":"10.1111\/ajt.15173","article-title":"Opposite acute potassium and sodium shifts during transplantation of hypothermic machine perfused donor livers","volume":"19","year":"2019","journal-title":"American Journal of Transplantation"},{"key":"2026071708351072000_2025.07.10.664265v2.43","doi-asserted-by":"crossref","unstructured":"Cho, Y. et al. Cumulative postoperative change in serum albumin levels and organ failure after livingdonor liver transplantation: A retrospective cohort analysis. PLoS One 18, (2023).","DOI":"10.1371\/journal.pone.0285734"},{"key":"2026071708351072000_2025.07.10.664265v2.44","doi-asserted-by":"crossref","first-page":"2750","DOI":"10.1016\/j.transproceed.2019.01.199","article-title":"Postoperative Course of Serum Albumin Levels and Organ Dysfunction After Liver Transplantation","volume":"51","year":"2019","journal-title":"Transplant Proc"},{"key":"2026071708351072000_2025.07.10.664265v2.45","doi-asserted-by":"crossref","unstructured":"V U, L., Balakrishnan, D. , M P, N. & Sudhindran, S . Antibody-mediated rejection in liver transplantation-An unresolved puzzle. Journal of Liver Transplantation 13, 100200 (2024).","DOI":"10.1016\/j.liver.2024.100200"},{"key":"2026071708351072000_2025.07.10.664265v2.46","doi-asserted-by":"publisher","DOI":"10.1002\/lt.500040503"},{"key":"2026071708351072000_2025.07.10.664265v2.47","doi-asserted-by":"crossref","unstructured":"Pillay, P. , Van Thiel, D. H. , Gavaler, J. S. & Starzl, T. E . Effect of Race Upon Organ Donation and Recipient Survival in Liver Transplantation. Dig Dis Sci vol. 35 (1990).","DOI":"10.1007\/BF01536746"},{"key":"2026071708351072000_2025.07.10.664265v2.48","doi-asserted-by":"publisher","DOI":"10.3748\/wjg.v24.i13.1386"},{"key":"2026071708351072000_2025.07.10.664265v2.49","doi-asserted-by":"publisher","DOI":"10.3389\/fcell.2015.00018"},{"key":"2026071708351072000_2025.07.10.664265v2.50","doi-asserted-by":"publisher","DOI":"10.1038\/ki.2008.457"},{"key":"2026071708351072000_2025.07.10.664265v2.51","doi-asserted-by":"publisher","DOI":"10.1111\/j.1399-0012.2006.00654.x"},{"key":"2026071708351072000_2025.07.10.664265v2.52","unstructured":"Ciftci, H. S. et al. International Journal of Organ Transplantation Medicine Urinary CXCL9 and CXCL10 Levels and Acute Renal Graft Rejection. www.ijotm.com."},{"key":"2026071708351072000_2025.07.10.664265v2.53","doi-asserted-by":"crossref","first-page":"467","DOI":"10.1053\/j.ajkd.2023.07.022","article-title":"Automated Urinary Chemokine Assays for Noninvasive Detection of Kidney Transplant Rejection: A Prospective Cohort Study","volume":"83","year":"2024","journal-title":"American Journal of Kidney Diseases"},{"key":"2026071708351072000_2025.07.10.664265v2.54","doi-asserted-by":"crossref","first-page":"2634","DOI":"10.1111\/ajt.12426","article-title":"Multicenter validation of urinary CXCL9 as a risk-stratifying biomarker for kidney transplant injury","volume":"13","year":"2013","journal-title":"American Journal of Transplantation"},{"key":"2026071708351072000_2025.07.10.664265v2.55","doi-asserted-by":"crossref","unstructured":"Mathur, V. , Reaven, N. L. , Funk, S. E. & Tangri, N . Serum Bicarbonate and Graft and Patient Outcomes Among Kidney Transplant Recipients: A Retrospective Cohort Study Evaluating Changes in Serum Bicarbonate Over Time. Kidney Med 5, (2023).","DOI":"10.1016\/j.xkme.2022.100573"},{"key":"2026071708351072000_2025.07.10.664265v2.56","doi-asserted-by":"publisher","DOI":"10.3389\/fcell.2015.00018"},{"key":"2026071708351072000_2025.07.10.664265v2.57","doi-asserted-by":"crossref","unstructured":"Betjes, M. G. H. & Litjens, N. H. R . High numbers of differentiated CD28null CD8+ T cells are associated with a lowered risk for late rejection and graft loss after kidney transplantation. PLoS One 15, (2020).","DOI":"10.1371\/journal.pone.0228096"},{"key":"2026071708351072000_2025.07.10.664265v2.58","doi-asserted-by":"crossref","unstructured":"Shi, T. et al. Single-cell transcriptomic analysis of renal allograft rejection reveals insights into intragraft TCR clonality. Journal of Clinical Investigation 133, (2023).","DOI":"10.1172\/JCI170191"},{"key":"2026071708351072000_2025.07.10.664265v2.59","doi-asserted-by":"crossref","first-page":"527","DOI":"10.1111\/j.1600-6143.2006.01654.x","article-title":"Beneficial effects of CCR1 blockade on the progression of chronic renal allograft damage","volume":"7","year":"2007","journal-title":"American Journal of Transplantation"},{"key":"2026071708351072000_2025.07.10.664265v2.60","doi-asserted-by":"publisher","DOI":"10.1093\/ndt\/gfm007"}],"container-title":[],"original-title":[],"link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1101\/2025.07.10.664265","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T15:35:25Z","timestamp":1784302525000},"score":1,"resource":{"primary":{"URL":"http:\/\/biorxiv.org\/lookup\/doi\/10.1101\/2025.07.10.664265"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,16]]},"references-count":60,"URL":"https:\/\/doi.org\/10.1101\/2025.07.10.664265","relation":{},"subject":[],"published":{"date-parts":[[2025,7,16]]},"subtype":"preprint"}}