{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"institution":[{"name":"bioRxiv"}],"indexed":{"date-parts":[[2026,3,16]],"date-time":"2026-03-16T21:47:36Z","timestamp":1773697656433,"version":"3.50.1"},"posted":{"date-parts":[[2025,10,15]]},"group-title":"Immunology","reference-count":41,"publisher":"openRxiv","license":[{"start":{"date-parts":[[2025,10,15]],"date-time":"2025-10-15T00:00:00Z","timestamp":1760486400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"name":"U.S. Department of Defence","award":["W81XWH-22-1-0339"],"award-info":[{"award-number":["W81XWH-22-1-0339"]}]},{"name":"U.S. Department of Defence","award":["W81XWH-22-1-0340"],"award-info":[{"award-number":["W81XWH-22-1-0340"]}]},{"name":"U.S. Department of Defence","award":["W81XWH-22-1-0341"],"award-info":[{"award-number":["W81XWH-22-1-0341"]}]},{"name":"US National Institutes of Health, National Cancer Institute","award":["R01-CA259387"],"award-info":[{"award-number":["R01-CA259387"]}]},{"name":"US National Institutes of Health, National Cancer Institute","award":["P30-CA076292"],"award-info":[{"award-number":["P30-CA076292"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"accepted":{"date-parts":[[2026,3,13]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                <jats:p>Adoptive cell therapy (ACT) with tumor-infiltrating lymphocytes (TIL) is a form of personalized immunotherapy that requires ex vivo expansion of autologous TILs and their reinfusion back into the patient. Predicting TIL expansion at the time of diagnosis may improve selection of patients that can benefit from ACT-TIL. It can also prevent high treatment-related costs and delays in treatment of patients whose cancer specimens would not yield successful TIL growth. We developed PETIL, a machine-learning model optimized for data of a medium size to determine a minimal combination of features (demographic, clinical, and biological specimen-based) that is predictive of expansion of TILs from a resected bladder cancer. We used a retrospectively identified set of data from bladder cancer patients at Moffitt Cancer Center for the training and testing cohorts. Additionally, we used data from a recent feasibility clinical trial at Moffitt Cancer Center as a blinded validation cohort. PETIL uses random forest method to identify a combination of robust predictive features, support vector machine model to determine the optimal classification hyperparameters, and Matthews correlation coefficient method to adjust the decision-boundary threshold for imbalanced data. Our model yielded AUC=0.740 for the testing cohort and AUC=0.857 for blinded validation cohort. Thus, our PETIL model optimized for data of medium size has favorable performance metrics for predicting TIL expansion from a given tumor.<\/jats:p>\n                <jats:sec>\n                  <jats:title>Authors Summary<\/jats:title>\n                  <jats:p>Treatment with autologous tumor-infiltrating lymphocytes (TIL) that are expanded ex vivo from a given tumor and then reinfused into the patient is a promising personalized immunotherapy. However, the TIL expansion takes about 4-6 weeks, thus developing tools that predict whether TIL growth will be successful can help to avoid delays in treatment of patients whose cancer specimens would not yield successful TIL expansion. Our Predictor of Expansion of TIL (PETIL) is a machine-learning model that uses patients\u2019 demographic information, clinical tumor classification, and biological tumor specimen-based measurements to determine a minimal set of these data features that are predictive of TIL expansion outcome. We applied this model to data from bladder cancer patients collected at Moffitt Cancer Center and showed that PETIL has favorable performance metrics for the dataset of a moderate size. This computational predictor can support clinicians in determining which patients are candidates for TIL immunotherapy. The developed PETIL pipeline can also be adjusted to data from other solid tumors.<\/jats:p>\n                <\/jats:sec>","DOI":"10.1101\/2025.10.15.682695","type":"posted-content","created":{"date-parts":[[2025,10,16]],"date-time":"2025-10-16T05:20:19Z","timestamp":1760592019000},"source":"Crossref","is-referenced-by-count":0,"title":["PETIL: Predicting Expansion of Tumor Infiltrating Lymphocytes for the Adoptive Cell Immunotherapy in Bladder Cancers"],"prefix":"10.64898","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1569-4351","authenticated-orcid":false,"given":"Kayode D.","family":"Olumoyin","sequence":"first","affiliation":[{"name":"Department of Integrated Mathematical Oncology, H. Lee Moffitt Cancer Center & Research Institute, Tampa, FL, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ahmet Murat","family":"Aydin","sequence":"additional","affiliation":[{"name":"Department of Genitourinary Oncology, H. Lee Moffitt Cancer Center & Research Institute, Tampa, FL, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sarah","family":"Bazargan","sequence":"additional","affiliation":[{"name":"Department of Immunology, H. Lee Moffitt Cancer Center & Research Institute, Tampa, FL, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Brittany","family":"Bunch","sequence":"additional","affiliation":[{"name":"Department of Immunology, H. Lee Moffitt Cancer Center & Research Institute, Tampa, FL, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ibrahim","family":"Chamseddine","sequence":"additional","affiliation":[{"name":"Department of Integrated Mathematical Oncology, H. Lee Moffitt Cancer Center & Research Institute, Tampa, FL, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8430-7138","authenticated-orcid":false,"given":"Aleksandra","family":"Karolak","sequence":"additional","affiliation":[{"name":"Department of Machine Learning, H. Lee Moffitt Cancer Center & Research Institute, Tampa, FL, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Matthew","family":"Beatty","sequence":"additional","affiliation":[{"name":"Department of Immunology, H. Lee Moffitt Cancer Center & Research Institute, Tampa, FL, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shari","family":"Pilon-Thomas","sequence":"additional","affiliation":[{"name":"Department of Immunology, H. Lee Moffitt Cancer Center & Research Institute, Tampa, FL, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michael A.","family":"Poch","sequence":"additional","affiliation":[{"name":"Department of Genitourinary Oncology, H. Lee Moffitt Cancer Center & Research Institute, Tampa, FL, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2093-2422","authenticated-orcid":false,"given":"Katarzyna A.","family":"Rejniak","sequence":"additional","affiliation":[{"name":"Department of Integrated Mathematical Oncology, H. Lee Moffitt Cancer Center & Research Institute, Tampa, FL, USA"},{"name":"University of South Florida, Morsani College of Medicine, Department of Oncologic Sciences, Tampa, FL, USA"},{"name":"Department of Integrated Mathematical Oncology, H. Lee Moffitt Cancer Center & Research Institute, Tampa, FL, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"54368","reference":[{"key":"2026031613501086000_2025.10.15.682695v2.1","unstructured":"Key Statistics for Bladder Cancer. The American Cancer Society The American Cancer Society; 2026"},{"key":"2026031613501086000_2025.10.15.682695v2.2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eururo.2009.12.024"},{"key":"2026031613501086000_2025.10.15.682695v2.3","doi-asserted-by":"publisher","DOI":"10.1016\/j.eururo.2008.07.031"},{"key":"2026031613501086000_2025.10.15.682695v2.4","doi-asserted-by":"publisher","DOI":"10.1126\/science.aaa4967"},{"key":"2026031613501086000_2025.10.15.682695v2.5","doi-asserted-by":"publisher","DOI":"10.1158\/1078-0432.CCR-10-0041"},{"key":"2026031613501086000_2025.10.15.682695v2.6","doi-asserted-by":"publisher","DOI":"10.1200\/JCO.2014.58.9093"},{"key":"2026031613501086000_2025.10.15.682695v2.7","doi-asserted-by":"publisher","DOI":"10.1097\/CJI.0b013e31826e8f5f"},{"key":"2026031613501086000_2025.10.15.682695v2.8","doi-asserted-by":"publisher","DOI":"10.1126\/science.aaa4971"},{"key":"2026031613501086000_2025.10.15.682695v2.9","doi-asserted-by":"publisher","DOI":"10.1038\/nature12965"},{"key":"2026031613501086000_2025.10.15.682695v2.10","doi-asserted-by":"publisher","DOI":"10.1002\/(SICI)1097-0215(19970516)71:4<585::AID-IJC13>3.0.CO;2-B"},{"key":"2026031613501086000_2025.10.15.682695v2.11","doi-asserted-by":"publisher","DOI":"10.3389\/fimmu.2021.628063"},{"issue":"9","key":"2026031613501086000_2025.10.15.682695v2.12","doi-asserted-by":"crossref","first-page":"e1476816","DOI":"10.1080\/2162402X.2018.1476816","article-title":"Expansion of tumor infiltrating lymphocytes (TIL) from bladder cancer","volume":"7","year":"2018","journal-title":"Oncoimmunology"},{"key":"2026031613501086000_2025.10.15.682695v2.13","unstructured":"NCT05768347. Intravesical Adoptive Cell Therapy w\/ TIL for BCG Exposed High Grade NMIBC 2023 [Available from: https:\/\/clinicaltrials.gov\/study\/NCT05768347]."},{"key":"2026031613501086000_2025.10.15.682695v2.14","doi-asserted-by":"publisher","DOI":"10.1002\/m12510"},{"issue":"4","key":"2026031613501086000_2025.10.15.682695v2.15","doi-asserted-by":"crossref","first-page":"533","DOI":"10.1038\/s41379-021-00955-y","article-title":"Prediction of non-muscle invasive bladder cancer recurrence using machine learning of quantitative nuclear features","volume":"35","year":"2022","journal-title":"Mod Pathol"},{"issue":"9","key":"2026031613501086000_2025.10.15.682695v2.16","doi-asserted-by":"crossref","first-page":"100382","DOI":"10.1016\/j.xcrm.2021.100382","article-title":"Predictive models of response to neoadjuvant chemotherapy in muscle-invasive bladder cancer using nuclear morphology and tissue architecture","volume":"2","year":"2021","journal-title":"Cell Rep Med"},{"key":"2026031613501086000_2025.10.15.682695v2.17","first-page":"2825","article-title":"Scikit-learn: Machine Learning in Python","volume":"12","year":"2011","journal-title":"Journal of Machine Learning Research"},{"issue":"9","key":"2026031613501086000_2025.10.15.682695v2.18","first-page":"1","article-title":"Efficient Multiple Imputation for Diverse Data in Python and R: MIDASpy and rMIDAS","volume":"107","year":"2023","journal-title":"J Stat Softw"},{"issue":"1","key":"2026031613501086000_2025.10.15.682695v2.19","first-page":"763","article-title":"Feature selection using mutual information based uncertainty measures for tumor classification","volume":"24","year":"2014","journal-title":"Biomed Mater Eng"},{"key":"2026031613501086000_2025.10.15.682695v2.20","first-page":"211","article-title":"Tree induction vs","volume":"4","year":"2003","journal-title":"logistic regression: a learning-curve analysis Journal of Machine Learning Research"},{"key":"2026031613501086000_2025.10.15.682695v2.21","doi-asserted-by":"publisher","DOI":"10.1186\/1472-6947-12-8"},{"key":"2026031613501086000_2025.10.15.682695v2.22","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1000173"},{"key":"2026031613501086000_2025.10.15.682695v2.23","doi-asserted-by":"publisher","DOI":"10.1109\/72.788646"},{"key":"2026031613501086000_2025.10.15.682695v2.24","doi-asserted-by":"publisher","DOI":"10.1023\/A:1012487302797"},{"key":"2026031613501086000_2025.10.15.682695v2.25","doi-asserted-by":"publisher","DOI":"10.1001\/JAMA.2016.7653"},{"key":"2026031613501086000_2025.10.15.682695v2.26","doi-asserted-by":"crossref","first-page":"522","DOI":"10.1016\/j.ins.2021.05.055","article-title":"Approximating XGBoost with an interpretable decision tree","volume":"572","year":"2021","journal-title":"Inform Sciences"},{"key":"2026031613501086000_2025.10.15.682695v2.27","doi-asserted-by":"publisher","DOI":"10.1023\/A:1010933404324"},{"key":"2026031613501086000_2025.10.15.682695v2.28","unstructured":"Borboudakis G , Tsamardinos I. Forward-Backward Selection with Early Dropping. Journal of Machine Learning Research. 2019;20."},{"key":"2026031613501086000_2025.10.15.682695v2.29","doi-asserted-by":"publisher","DOI":"10.1186\/1471-2105-10-213"},{"key":"2026031613501086000_2025.10.15.682695v2.30","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/bty373"},{"key":"2026031613501086000_2025.10.15.682695v2.31","doi-asserted-by":"crossref","unstructured":"Yu S , Principe JC . Simple Stopping Criteria for Information Theoretic Feature Selection. Entropy (Basel). 2019;21(1).","DOI":"10.3390\/e21010099"},{"key":"2026031613501086000_2025.10.15.682695v2.32","doi-asserted-by":"crossref","unstructured":"Lange A , Madiraju S , Petros FG . Therapeutic Advances in Bladder Preservation for BCG-Unresponsive Non-Muscle Invasive Bladder Cancer. Cancers (Basel). 2025;17(4).","DOI":"10.3390\/cancers17040636"},{"key":"2026031613501086000_2025.10.15.682695v2.33","doi-asserted-by":"publisher","DOI":"10.1016\/S1470-2045(21)00147-9"},{"key":"2026031613501086000_2025.10.15.682695v2.34","doi-asserted-by":"publisher","DOI":"10.1097\/JU.0000000000004020"},{"key":"2026031613501086000_2025.10.15.682695v2.35","doi-asserted-by":"publisher","DOI":"10.5555\/2999611.2999712"},{"key":"2026031613501086000_2025.10.15.682695v2.36","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.69.066138"},{"issue":"2","key":"2026031613501086000_2025.10.15.682695v2.37","first-page":"108714","article-title":"Ovarian cancer detection from mutual information-ranked clinical biomarkers using an explainable attention-based residual multilayer perceptron","volume":"120","year":"2025","journal-title":"Comput Biol Chem"},{"key":"2026031613501086000_2025.10.15.682695v2.38","doi-asserted-by":"publisher","DOI":"10.1162\/NECO_a_00434"},{"key":"2026031613501086000_2025.10.15.682695v2.39","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0177678"},{"key":"2026031613501086000_2025.10.15.682695v2.40","doi-asserted-by":"publisher","DOI":"10.1186\/s12864-019-6413-7"},{"key":"2026031613501086000_2025.10.15.682695v2.41","doi-asserted-by":"publisher","DOI":"10.1016\/j.cpc.2010.04.018"}],"container-title":[],"original-title":[],"link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1101\/2025.10.15.682695","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,16]],"date-time":"2026-03-16T20:50:20Z","timestamp":1773694220000},"score":1,"resource":{"primary":{"URL":"http:\/\/biorxiv.org\/lookup\/doi\/10.1101\/2025.10.15.682695"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,15]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1101\/2025.10.15.682695","relation":{},"subject":[],"published":{"date-parts":[[2025,10,15]]},"subtype":"preprint"}}