{"doi":"10.1016/j.ccell.2024.12.002","title":"Classification of non-TCGA cancer samples to TCGA molecular subtypes using compact feature sets","abstract":"Molecular subtypes, such as defined by The Cancer Genome Atlas (TCGA), delineate a cancer’s underlying biology, bringing hope to inform a patient’s prognosis and treatment plan. However, most approaches used in the discovery of subtypes are not suitable for assigning subtype labels to new cancer specimens from other studies or clinical trials. Here, we address this barrier by applying five different machine learning approaches to multi-omic data from 8,791 TCGA tumor samples comprising 106 subtypes from 26 different cancer cohorts to build models based upon small numbers of features that can classify new samples into previously defined TCGA molecular subtypes—a step toward molecular subtype application in the clinic. We validate select classifiers using external datasets. Predictive performance and classifier-selected features yield insight into the different machine-learning approaches and genomic data platforms. For each cancer and data type we provide containerized versions of the top-performing models as a public resource. • Five machine learning methods used to train classifiers for 106 TCGA cancer subtypes • Classifier models based upon small numbers of features from five omic data types • Insights into methods, data types, and cohort size for effective classification • Public resource for classifying non-TCGA patient samples to TCGA cancer subtypes Ellrott et al. provide a means to assign patient samples from clinical trials and other cancer genome studies to published TCGA molecular subtypes. Applying machine learning to data from five different molecular platforms for 8,791 TCGA tumor samples, they contribute a public resource of 737 top classifier models, which can form the foundation for clinical assay development.","journal":"Cancer Cell","year":2025,"id":509610,"datarank":0.8034037928069588,"base_score":3.4011973816621555,"endowment":3.4011973816621555,"self_citation_contribution":0.5101796072493234,"citation_network_contribution":0.29322418555763546,"self_endowment_contribution":0.5101796072493234,"citer_contribution":0.29322418555763546,"corpus_percentile":null,"corpus_rank":null,"citation_count":29,"citer_count":26,"citers_with_citation_signal":12,"citers_with_endowment":12,"datacite_reuse_total":0,"is_dataset":false,"is_dataset_confidence":0.954,"is_data_producer":false,"deposit_databanks":null,"is_oa":true,"file_count":0,"downloads":0,"has_version_chain":false,"published_date":"2025-01-01","fair_score":null,"fair_percentile":null,"algorithm_id":"datarank_citation_only_1hop_v6","ranking_scope":"data_only","authors":[{"id":52032,"name":"Christopher K. Wong","orcid":null,"position":1,"is_corresponding":false},{"id":14257,"name":"Christina Yau","orcid":"0000-0002-1937-0859","position":2,"is_corresponding":false},{"id":1364565,"name":"Mauro A.A. Castro","orcid":null,"position":3,"is_corresponding":false},{"id":1288751,"name":"Jordan Lee","orcid":"0000-0002-0983-0495","position":4,"is_corresponding":false},{"id":1288750,"name":"Brian Karlberg","orcid":"0000-0002-7587-7849","position":5,"is_corresponding":false},{"id":1363808,"name":"Jasleen Grewal","orcid":"0000-0001-7213-5930","position":6,"is_corresponding":false},{"id":863006,"name":"Vincenzo Lagani","orcid":"0000-0002-6552-6076","position":7,"is_corresponding":false},{"id":626014,"name":"Bahar Tercan","orcid":"0000-0002-5332-264X","position":8,"is_corresponding":false},{"id":693877,"name":"Verena Friedl","orcid":"0000-0002-7247-6038","position":9,"is_corresponding":false},{"id":69739,"name":"Toshinori Hinoue","orcid":"0000-0002-5078-5016","position":10,"is_corresponding":false},{"id":1363809,"name":"Vladislav Uzunangelov","orcid":"0000-0002-1962-0977","position":11,"is_corresponding":false},{"id":926186,"name":"Lindsay Westlake","orcid":null,"position":12,"is_corresponding":false},{"id":566545,"name":"Xavier Loinaz","orcid":null,"position":13,"is_corresponding":false},{"id":593593,"name":"Ina Felau","orcid":"0000-0002-9005-0700","position":14,"is_corresponding":false},{"id":1363810,"name":"Peggy I. Wang","orcid":"0000-0003-1504-6370","position":15,"is_corresponding":false},{"id":52034,"name":"Anab Kemal","orcid":null,"position":16,"is_corresponding":false},{"id":11760,"name":"Todd A. Johnson","orcid":"0000-0003-4607-2782","position":17,"is_corresponding":false},{"id":237257,"name":"Ilya Shmulevich","orcid":"0000-0002-4410-8780","position":18,"is_corresponding":false},{"id":13708,"name":"Alexander J. Lazar","orcid":"0000-0002-6395-4499","position":19,"is_corresponding":false},{"id":1363811,"name":"Ioannis Tsamardinos","orcid":"0000-0002-2492-959X","position":20,"is_corresponding":false},{"id":1870,"name":"Katherine A. Hoadley","orcid":"0000-0002-1216-477X","position":21,"is_corresponding":false},{"id":13971,"name":"A. Gordon Robertson","orcid":"0000-0002-2839-596X","position":22,"is_corresponding":false},{"id":52038,"name":"Theo Knijnenburg","orcid":"0000-0001-6397-4222","position":23,"is_corresponding":false},{"id":1907,"name":"Christopher C. Benz","orcid":"0000-0001-5479-4641","position":24,"is_corresponding":false},{"id":266953,"name":"Joshua M. Stuart","orcid":"0000-0002-2171-565X","position":25,"is_corresponding":false},{"id":14273,"name":"Jean C. Zenklusen","orcid":"0000-0002-9489-1873","position":26,"is_corresponding":false},{"id":13344,"name":"Andrew D. Cherniack","orcid":"0000-0003-0470-0111","position":27,"is_corresponding":false},{"id":279356,"name":"Peter W. Laird","orcid":"0000-0001-9117-3641","position":28,"is_corresponding":false},{"id":251187,"name":"Kyle Ellrott","orcid":"0000-0002-6573-5900","position":0,"is_corresponding":true}],"reference_count":103,"raw_metadata":{"citation_network_status":"fetched"},"created_at":"2026-07-19T02:47:24.513904Z","pmid":"39753139","pmcid":null,"fwci":null,"citation_percentile":null,"influential_citations":0,"oa_status":null,"license":null,"views":0,"total_file_size_bytes":0,"version_count":0,"fair_f":null,"fair_a":null,"fair_i":null,"fair_r":null,"fair_zscore":null,"fair_rationale":null,"fair_model":null,"fair_agent_version":null,"fair_fulltext_source":null,"fair_has_llm":null,"fair_computed_at":null,"clinical_trials":[],"software_tools":[],"db_accessions":[],"linked_datasets":[],"topics":[]}