{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,20]],"date-time":"2026-08-20T06:23:57Z","timestamp":1787207037023,"version":"build-2736575974"},"reference-count":39,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,8,20]],"date-time":"2026-08-20T00:00:00Z","timestamp":1787184000000},"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. Artif. Intell."],"abstract":"<jats:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>Regulated cell death (RCD) pathways influence tumor progression and immune modulation. We previously constructed a signature database mapping 25 RCD forms across seven multi-omic layers and 33 tumor types (CancerRCDShiny). Despite their ability to identify risk populations, translating these signatures into personalized clinical workflows requires a shift from cohort stratification to individualized risk mapping by modeling patient risk (survival topologies) to capture the non-linear dynamics of RCD signatures.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>\n                      We engineered a pan-cancer multi-omic\n                      <jats:italic>SuperLearner<\/jats:italic>\n                      pipeline across 33 cancer types. Phase I performed zero-leakage harmonization and groupwise imputation to prevent cross-cohort amalgamation. Phase II deployed Elastic Net-regularized Cox regression as a CANARY diagnostic to map proportional hazards failures. Strata with a 35% missingness barrier entered Phase III, deploying a Quadripartite ensemble:\n                      <jats:italic>Random Survival Forests<\/jats:italic>\n                      ,\n                      <jats:italic>XGBoost<\/jats:italic>\n                      , Survival-\n                      <jats:italic>Boruta<\/jats:italic>\n                      , and Multi-Task Logistic Regression, fused within an Elastic Net Multi-View Meta-Learner (\n                      <jats:italic>MVL<\/jats:italic>\n                      ), with\n                      <jats:italic>post-hoc TreeSHAP<\/jats:italic>\n                      and\n                      <jats:italic>LIME<\/jats:italic>\n                      interpretability.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      The CANARY diagnostic demonstrated the structural invalidity of pan-cancer geometric proportional hazards. Across 96 admissible strata, Phase III executed algorithmic displacement: continuous multi-omic topologies suppressed static genomic mutations and copy number variations (85.7% vs. 0.0% apex retention). The MVL stabilized predictions against extreme variance;\n                      <jats:italic>LIME<\/jats:italic>\n                      surrogate validations (\n                      <jats:italic>R<\/jats:italic>\n                      <jats:sup>2<\/jats:sup>\n                      \u202f&amp;lt;\u202f0.10) confirmed the systematic failure of linear interpretative proxies. N-dimensional\n                      <jats:italic>TreeSHAP<\/jats:italic>\n                      interaction mapping exposed synergistic and antagonistic rescue trajectories defining individualized Survival Topologies, which were invisible to additive models. The architecture was deployed as CancerRCDPredictor, a digital molecular tumor board with integrated LLM capabilities. The\n                      <jats:italic>MVL SuperLearner<\/jats:italic>\n                      achieved a median C-index of 0.749 (IQR: 0.722\u20130.836) across 96 modelable strata, with 95% bootstrap confidence intervals confirming precision (median width: 0.052) and permutation significance in 93.8% of strata (\n                      <jats:italic>p<\/jats:italic>\n                      \u202f&amp;lt;\u202f0.001). External CPTAC validation across ten cancer types demonstrated significant cross-cohort generalizability in clear cell renal carcinoma (KIRC; C-index 0.675,\n                      <jats:italic>p<\/jats:italic>\n                      \u202f=\u202f0.017) and modest performance across the remaining adequately powered cancers (median 0.582), underscoring the need for larger multi-institutional validation cohorts.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>\n                      This pan-cancer multi-omic\n                      <jats:italic>SuperLearner<\/jats:italic>\n                      bypasses linear topological failures, advancing beyond generalized stratification to establish a deterministically mapped architecture for predicting RCD-related survival topologies. Through the CancerRCDPredictor interface, multi-omic insights translate into individualized survival topology exploration, providing a foundation for future precision oncology validation.\n                    <\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/frai.2026.1895164","type":"journal-article","created":{"date-parts":[[2026,8,20]],"date-time":"2026-08-20T05:28:29Z","timestamp":1787203709000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["A pan-cancer multi-omic SuperLearner for regulated cell death survival topologies"],"prefix":"10.3389","volume":"9","author":[{"given":"Emanuell","family":"Rodrigues de Souza","sequence":"first","affiliation":[{"name":"Laborat\u00f3rio de Biotecnologia, Centro de Bioci\u00eancias e Biotecnologia, Universidade Estadual do Norte Fluminense","place":["Campos dos Goytacazes, Brazil"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Higor","family":"Almeida Cordeiro Nogueira","sequence":"additional","affiliation":[{"name":"Laborat\u00f3rio de Biotecnologia, Centro de Bioci\u00eancias e Biotecnologia, Universidade Estadual do Norte Fluminense","place":["Campos dos Goytacazes, Brazil"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Victor dos Santos","family":"Lopes","sequence":"additional","affiliation":[{"name":"Laborat\u00f3rio de Biotecnologia, Centro de Bioci\u00eancias e Biotecnologia, Universidade Estadual do Norte Fluminense","place":["Campos dos Goytacazes, Brazil"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Enrique","family":"Medina-Acosta","sequence":"additional","affiliation":[{"name":"Laborat\u00f3rio de Biotecnologia, Centro de Bioci\u00eancias e Biotecnologia, Universidade Estadual do Norte Fluminense","place":["Campos dos Goytacazes, Brazil"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,8,20]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"8984","DOI":"10.1038\/s41598-023-35795-0","article-title":"Machine learning explainability in nasopharyngeal cancer survival using LIME and SHAP","volume":"13","author":"Alabi","year":"2023","journal-title":"Sci. Rep."},{"key":"ref2","doi-asserted-by":"publisher","first-page":"1806975","DOI":"10.3389\/fbinf.2026.1806975","article-title":"Geometric multidimensional representation of omic signatures","volume":"6","author":"Almeida Cordeiro Nogueira","year":"2026","journal-title":"Front. Bioinform."},{"key":"ref3","doi-asserted-by":"publisher","first-page":"1845099","DOI":"10.3389\/fmolb.2026.1845099","article-title":"A pan-cancer atlas of metabolic regulatory circuitries integrating multi-omic, immune, and clinical dimensions","volume":"13","author":"Almeida Cordeiro Nogueira","year":"2026","journal-title":"Front. Mol. Biosci."},{"key":"ref4","doi-asserted-by":"publisher","first-page":"31060","DOI":"10.1038\/s41598-024-82233-w","article-title":"Multiomics integration and machine learning reveal prognostic programmed cell death signatures in gastric cancer","volume":"14","author":"Bai","year":"2024","journal-title":"Sci. Rep."},{"key":"ref5","doi-asserted-by":"publisher","first-page":"1","DOI":"10.18637\/jss.v045.i03","article-title":"Mice: multivariate imputation by chained equations inR","volume":"45","author":"Buuren","year":"2011","journal-title":"J. Stat. Softw."},{"key":"ref6","doi-asserted-by":"publisher","first-page":"e2147","DOI":"10.7717\/peerj-cs.2147","article-title":"Survival analysis in breast cancer: evaluating ensemble learning techniques for prediction","volume":"10","author":"Buyrukoglu","year":"2024","journal-title":"PeerJ Comput. Sci."},{"key":"ref7","doi-asserted-by":"publisher","first-page":"104481","DOI":"10.1016\/j.compbiomed.2021.104481","article-title":"Integrating multi-omics data through deep learning for accurate cancer prognosis prediction","volume":"134","author":"Chai","year":"2021","journal-title":"Comput. Biol. Med."},{"key":"ref8","doi-asserted-by":"publisher","first-page":"1248","DOI":"10.1158\/1078-0432.CCR-17-0853","article-title":"Deep learning-based multi-omics integration robustly predicts survival in liver Cancer","volume":"24","author":"Chaudhary","year":"2018","journal-title":"Clin. Cancer Res."},{"key":"ref9","first-page":"785","author":"Chen","year":"2016"},{"key":"ref10","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1093\/bioinformatics\/btad113","article-title":"Interpretable meta-learning of multi-omics data for survival analysis and pathway enrichment","volume":"39","author":"Cho","year":"2023","journal-title":"Bioinformatics"},{"key":"ref11","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1109\/TIT.1967.1053964","article-title":"Nearest neighbor pattern classification","volume":"13","author":"Cover","year":"1967","journal-title":"IEEE Trans. Inf. Theory"},{"key":"ref12","doi-asserted-by":"publisher","first-page":"2707","DOI":"10.1021\/pr501254j","article-title":"The CPTAC data portal: a resource for cancer proteomics research","volume":"14","author":"Edwards","year":"2015","journal-title":"J. Proteome Res."},{"key":"ref13","doi-asserted-by":"publisher","first-page":"486","DOI":"10.1038\/s41418-017-0012-4","article-title":"Molecular mechanisms of cell death: recommendations of the nomenclature committee on cell death 2018","volume":"25","author":"Galluzzi","year":"2018","journal-title":"Cell Death Differ."},{"key":"ref14","doi-asserted-by":"publisher","first-page":"e136","DOI":"10.1002\/cai2.136","article-title":"Explainable artificial intelligence in breast cancer detection and risk prediction: a systematic scoping review","volume":"3","author":"Ghasemi","year":"2024","journal-title":"Canc. Innov."},{"key":"ref15","doi-asserted-by":"publisher","first-page":"675","DOI":"10.1038\/s41587-020-0546-8","article-title":"Visualizing and interpreting cancer genomics data via the Xena platform","volume":"38","author":"Goldman","year":"2020","journal-title":"Nat. Biotechnol."},{"key":"ref16","doi-asserted-by":"publisher","first-page":"515","DOI":"10.1093\/biomet\/81.3.515","article-title":"Proportional hazards tests and diagnostics based on weighted residuals","volume":"81","author":"Grambsch","year":"1994","journal-title":"Biometrika"},{"key":"ref17","first-page":"3367","article-title":"Matrix completion and low-rank SVD via fast alternating least squares","volume":"16","author":"Hastie","year":"2015","journal-title":"J. Mach. Learn. Res."},{"key":"ref18","doi-asserted-by":"publisher","first-page":"92","DOI":"10.1111\/j.0006-341X.2005.030814.x","article-title":"Survival model predictive accuracy and ROC curves","volume":"61","author":"Heagerty","year":"2005","journal-title":"Biometrics"},{"key":"ref19","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1093\/bib\/bbaa167","article-title":"Large-scale benchmark study of survival prediction methods using multi-omics data","volume":"22","author":"Herrmann","year":"2021","journal-title":"Brief. Bioinform."},{"key":"ref20","doi-asserted-by":"publisher","first-page":"841","DOI":"10.1214\/08-aoas169","article-title":"Random survival forests","volume":"2","author":"Ishwaran","year":"2008","journal-title":"Ann. Appl. Stat."},{"key":"ref21","first-page":"3146","author":"Ke","year":"2017"},{"key":"ref22","doi-asserted-by":"publisher","first-page":"541","DOI":"10.1146\/annurev-pathmechdis-051222-113147","article-title":"Toward explainable artificial intelligence for precision pathology","volume":"19","author":"Klauschen","year":"2024","journal-title":"Annu. Rev. Pathol."},{"key":"ref23","doi-asserted-by":"publisher","first-page":"1","DOI":"10.18637\/jss.v036.i11","article-title":"Feature selection with theBorutaPackage","volume":"36","author":"Kursa","year":"2010","journal-title":"J. Stat. Softw."},{"key":"ref24","doi-asserted-by":"publisher","first-page":"1200","DOI":"10.1038\/s42003-024-06891-2","article-title":"Facilitating integrative and personalized oncology omics analysis with UCSCXenaShiny","volume":"7","author":"Li","year":"2024","journal-title":"Commun. Biol."},{"key":"ref25","doi-asserted-by":"publisher","first-page":"637","DOI":"10.1200\/CCI.20.00002","article-title":"Machine learning-based interpretation and visualization of nonlinear interactions in prostate Cancer survival","volume":"4","author":"Li","year":"2020","journal-title":"JCO Clin. Canc. Inf."},{"key":"ref26","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1038\/s42256-019-0138-9","article-title":"From local explanations to global understanding with explainable AI for trees","volume":"2","author":"Lundberg","year":"2020","journal-title":"Nat Mach Intell"},{"key":"ref27","author":"Lundberg","year":"2017"},{"key":"ref28","doi-asserted-by":"publisher","first-page":"3728","DOI":"10.1038\/s41598-025-87622-3","article-title":"Leveraging survival analysis and machine learning for accurate prediction of breast cancer recurrence and metastasis","volume":"15","author":"Noman","year":"2025","journal-title":"Sci. Rep."},{"key":"ref29","first-page":"97","author":"Ribeiro","year":"2016"},{"key":"ref30","doi-asserted-by":"publisher","first-page":"1630518","DOI":"10.3389\/fbinf.2025.1630518","article-title":"Integrated multi-optosis model for pan-cancer candidate biomarker and therapy target discovery","volume":"5","author":"Rodrigues de Souza","year":"2025","journal-title":"Front. Bioinform."},{"key":"ref31","doi-asserted-by":"publisher","first-page":"112","DOI":"10.1093\/bioinformatics\/btr597","article-title":"MissForest\u2014non-parametric missing value imputation for mixed-type data","volume":"28","author":"Stekhoven","year":"2012","journal-title":"Bioinformatics"},{"key":"ref32","doi-asserted-by":"publisher","first-page":"25","DOI":"10.1186\/1471-2105-8-25","article-title":"Bias in random forest variable importance measures: illustrations, sources and a solution","volume":"8","author":"Strobl","year":"2007","journal-title":"BMC Bioinformatics"},{"key":"ref33","doi-asserted-by":"publisher","first-page":"1447970","DOI":"10.3389\/fphar.2024.1447970","article-title":"Unraveling the regulatory cell death pathways in gastric cancer: a multi-omics study","volume":"15","author":"Sun","year":"2024","journal-title":"Front. Pharmacol."},{"key":"ref34","doi-asserted-by":"publisher","first-page":"10114","DOI":"10.1038\/s41598-026-40565-9","article-title":"A comparative analysis of data-driven models for breast cancer survival prediction","volume":"16","author":"Takele","year":"2026","journal-title":"Sci. Rep."},{"key":"ref35","doi-asserted-by":"publisher","first-page":"347","DOI":"10.1038\/s41422-019-0164-5","article-title":"The molecular machinery of regulated cell death","volume":"29","author":"Tang","year":"2019","journal-title":"Cell Res."},{"key":"ref36","doi-asserted-by":"publisher","first-page":"Article25","DOI":"10.2202\/1544-6115.1309","article-title":"Super learner","volume":"6","author":"van der Laan","year":"2007","journal-title":"Stat. Appl. Genet. Mol. Biol."},{"key":"ref37","doi-asserted-by":"publisher","first-page":"527","DOI":"10.1093\/bioinformatics\/btab561","article-title":"UCSCXenaShiny: an R\/CRAN package for interactive analysis of UCSC Xena data","volume":"38","author":"Wang","year":"2022","journal-title":"Bioinformatics"},{"key":"ref38","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1093\/bib\/bbaf521","article-title":"SurvBoard: standardized benchmarking for multi-omics cancer survival models","volume":"26","author":"Wissel","year":"2025","journal-title":"Brief. Bioinform."},{"key":"ref39","author":"Yu","year":"2011"}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2026.1895164\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,20]],"date-time":"2026-08-20T05:28:32Z","timestamp":1787203712000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2026.1895164\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,20]]},"references-count":39,"alternative-id":["10.3389\/frai.2026.1895164"],"URL":"https:\/\/doi.org\/10.3389\/frai.2026.1895164","relation":{},"ISSN":["2624-8212"],"issn-type":[{"value":"2624-8212","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,20]]},"article-number":"1895164"}}