{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T03:03:03Z","timestamp":1787022183800,"version":"build-2736575974"},"reference-count":34,"publisher":"Public Library of Science (PLoS)","issue":"12","license":[{"start":{"date-parts":[[2025,12,4]],"date-time":"2025-12-04T00:00:00Z","timestamp":1764806400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Korean government","award":["RS-2023-00268071"],"award-info":[{"award-number":["RS-2023-00268071"]}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:p>Accurate identification of cancer tissue\/cell of origin (TOO\/COO) is critical for diagnosis and treatment; yet existing whole-genome approaches demand extensive computation and often struggle with sparse mutation signals. Here, we introduce an informative regional subset framework that selects a small number of biologically and statistically significant 1Mbp genomic intervals to train a CatBoost prediction model. On a benchmark of 137 whole-genome samples across six cancer types, our method achieved a 4% gain in melanoma accuracy (from 88.0% using all 2,128 regions to 92.0% with 300 regions), a 4.4% gain in multiple myeloma (87.0% with 600 regions), and perfect (100%) accuracy in high-mutation cancers such as esophageal adenocarcinoma and glioblastoma with as few as 50 informative regions. When extended to 934 PCAWG samples spanning 14 cancer lineages, the same limited regional subsets matched or improved whole-genome performance, reaching up to 100% accuracy in gastrointestinal, skin, and brain cancers, demonstrating exceptional scalability. Our approach not only reduces computational burden and enhances interpretability but also provides a robust, generalizable tool for precision oncology and the diagnosis of cancers of unknown primary.<\/jats:p>","DOI":"10.1371\/journal.pone.0337106","type":"journal-article","created":{"date-parts":[[2025,12,4]],"date-time":"2025-12-04T18:52:42Z","timestamp":1764874362000},"page":"e0337106","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":1,"title":["Biologically-informed regional subset analysis with CatBoost for robust tissue-of-origin prediction"],"prefix":"10.1371","volume":"20","author":[{"given":"Sungmin","family":"Yang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2610-4321","authenticated-orcid":true,"given":"Hong-Gee","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2025,12,4]]},"reference":[{"issue":"1","key":"pone.0337106.ref001","doi-asserted-by":"crossref","first-page":"31","DOI":"10.1038\/nrg2626","article-title":"Sequencing technologies - the next generation","volume":"11","author":"ML Metzker","year":"2010","journal-title":"Nat Rev Genet."},{"issue":"7463","key":"pone.0337106.ref002","doi-asserted-by":"crossref","first-page":"415","DOI":"10.1038\/nature12477","article-title":"Signatures of mutational processes in human cancer","volume":"500","author":"LB Alexandrov","year":"2013","journal-title":"Nature."},{"issue":"8","key":"pone.0337106.ref003","doi-asserted-by":"crossref","first-page":"757","DOI":"10.1056\/NEJMra1303917","article-title":"Cancer of unknown primary site","volume":"371","author":"GR Varadhachary","year":"2014","journal-title":"N Engl J Med."},{"issue":"12","key":"pone.0337106.ref004","first-page":"1712","article-title":"Epigenomic analysis of cancers of unknown primary","volume":"30","author":"JW Rhee","year":"2020","journal-title":"Genome Research."},{"issue":"1","key":"pone.0337106.ref005","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random Forests","volume":"45","author":"L Breiman","year":"2001","journal-title":"Machine Learning."},{"key":"pone.0337106.ref006","doi-asserted-by":"crossref","unstructured":"Chen T, Guestrin C. XGBoost: a scalable tree boosting system. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 2016. p. 785\u201394.","DOI":"10.1145\/2939672.2939785"},{"issue":"2","key":"pone.0337106.ref007","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0311250","article-title":"Enhancing machine learning performance in cardiac surgery ICU: hyperparameter optimization with metaheuristic algorithm","volume":"20","author":"A Bahrami","year":"2025","journal-title":"PLoS One."},{"key":"pone.0337106.ref008","doi-asserted-by":"crossref","first-page":"108005","DOI":"10.1016\/j.cmpb.2023.108005","article-title":"A machine learning model for predicting acute exacerbation of in-home chronic obstructive pulmonary disease patients","volume":"246","author":"H Yin","year":"2024","journal-title":"Comput Methods Programs Biomed."},{"issue":"1","key":"pone.0337106.ref009","doi-asserted-by":"crossref","first-page":"4013","DOI":"10.1038\/s41467-022-31666-w","article-title":"Machine learning-based tissue of origin classification for cancer of unknown primary diagnostics using genome-wide mutation features","volume":"13","author":"L Nguyen","year":"2022","journal-title":"Nat Commun."},{"issue":"5","key":"pone.0337106.ref010","doi-asserted-by":"crossref","first-page":"1185","DOI":"10.3390\/cancers14051185","article-title":"Deep learning-based pan-cancer classification model reveals tissue-of-origin specific gene expression signatures","volume":"14","author":"M Divate","year":"2022","journal-title":"Cancers (Basel)."},{"key":"pone.0337106.ref011","article-title":"Tumor origin identification through machine learning and gene expression profiling.","volume":"42","author":"X Wang","year":"2024","journal-title":"JCO."},{"key":"pone.0337106.ref012","article-title":"Abstract 4331 : machine learning-based classification of tissue origin of cancer using methylation profiles","author":"M De Velasco","year":"2024","journal-title":"Cancer Research."},{"key":"pone.0337106.ref013","doi-asserted-by":"crossref","DOI":"10.1158\/1557-3265.LIQBIOP24-PR019","article-title":"Abstract PR019: transfer learning for accurate tissue of origin classification from cfDNA methylation","volume":"30","author":"S Farashahi","year":"2024","journal-title":"Clinical Cancer Research."},{"issue":"1","key":"pone.0337106.ref014","doi-asserted-by":"crossref","DOI":"10.1093\/jncics\/pkac080","article-title":"Prediction of tissue-of-origin of early stage cancers using serum miRNomes","volume":"7","author":"J Matsuzaki","year":"2023","journal-title":"JNCI Cancer Spectr."},{"key":"pone.0337106.ref015","doi-asserted-by":"crossref","first-page":"101","DOI":"10.1200\/JCO.2024.42.23_suppl.101","article-title":"Machine learning-based noninvasive diagnostic classifiers for the prediction of cancer tissue of origin using serum microRNAs.","volume":"42","author":"A Zhang","year":"2024","journal-title":"JCO."},{"key":"pone.0337106.ref016","doi-asserted-by":"crossref","DOI":"10.1158\/1538-7445.METASTASIS22-PR005","article-title":"Abstract PR005: Deep learning-based multimodal integration of histology and genomics improves cancer origin prediction","volume":"83","author":"M Shaban","year":"2023","journal-title":"Cancer Research."},{"issue":"5","key":"pone.0337106.ref017","doi-asserted-by":"crossref","first-page":"1309","DOI":"10.1038\/s41591-024-02915-w","article-title":"Prediction of tumor origin in cancers of unknown primary origin with cytology-based deep learning","volume":"30","author":"F Tian","year":"2024","journal-title":"Nat Med."},{"issue":"1","key":"pone.0337106.ref018","first-page":"71","article-title":"COOBoostR: an extreme gradient boosting-based tool for robust tissue or cell-of-origin prediction of tumors","volume":"13","author":"S Yang","year":"2022","journal-title":"Life (Basel)."},{"issue":"7412","key":"pone.0337106.ref019","doi-asserted-by":"crossref","first-page":"504","DOI":"10.1038\/nature11273","article-title":"Chromatin organization is a major influence on regional mutation rates in human cancer cells","volume":"488","author":"B Schuster-B\u00f6ckler","year":"2012","journal-title":"Nature."},{"issue":"7539","key":"pone.0337106.ref020","doi-asserted-by":"crossref","first-page":"360","DOI":"10.1038\/nature14221","article-title":"Cell-of-origin chromatin organization shapes the mutational landscape of cancer","volume":"518","author":"P Polak","year":"2015","journal-title":"Nature."},{"key":"pone.0337106.ref021","doi-asserted-by":"crossref","first-page":"11383","DOI":"10.1038\/ncomms11383","article-title":"The topography of mutational processes in breast cancer genomes","volume":"7","author":"S Morganella","year":"2016","journal-title":"Nat Commun."},{"issue":"7399","key":"pone.0337106.ref022","doi-asserted-by":"crossref","first-page":"502","DOI":"10.1038\/nature11071","article-title":"Melanoma genome sequencing reveals frequent PREX2 mutations","volume":"485","author":"MF Berger","year":"2012","journal-title":"Nature."},{"issue":"7339","key":"pone.0337106.ref023","doi-asserted-by":"crossref","first-page":"467","DOI":"10.1038\/nature09837","article-title":"Initial genome sequencing and analysis of multiple myeloma","volume":"471","author":"MA Chapman","year":"2011","journal-title":"Nature."},{"issue":"5","key":"pone.0337106.ref024","doi-asserted-by":"crossref","first-page":"464","DOI":"10.1038\/ng.804","article-title":"High-resolution characterization of a hepatocellular carcinoma genome","volume":"43","author":"Y Totoki","year":"2011","journal-title":"Nat Genet."},{"issue":"10","key":"pone.0337106.ref025","doi-asserted-by":"crossref","first-page":"964","DOI":"10.1038\/ng.936","article-title":"Genomic sequencing of colorectal adenocarcinomas identifies a recurrent VTI1A-TCF7L2 fusion","volume":"43","author":"AJ Bass","year":"2011","journal-title":"Nat Genet."},{"issue":"2","key":"pone.0337106.ref026","doi-asserted-by":"crossref","first-page":"462","DOI":"10.1016\/j.cell.2013.09.034","article-title":"The somatic genomic landscape of glioblastoma","volume":"155","author":"CW Brennan","year":"2013","journal-title":"Cell."},{"issue":"5","key":"pone.0337106.ref027","doi-asserted-by":"crossref","first-page":"478","DOI":"10.1038\/ng.2591","article-title":"Exome and whole-genome sequencing of esophageal adenocarcinoma identifies recurrent driver events and mutational complexity","volume":"45","author":"AM Dulak","year":"2013","journal-title":"Nat Genet."},{"issue":"7","key":"pone.0337106.ref028","doi-asserted-by":"crossref","first-page":"1006","DOI":"10.1093\/bioinformatics\/btt730","article-title":"CrossMap: a versatile tool for coordinate conversion between genome assemblies","volume":"30","author":"H Zhao","year":"2014","journal-title":"Bioinformatics."},{"issue":"7793","key":"pone.0337106.ref029","doi-asserted-by":"crossref","first-page":"82","DOI":"10.1038\/s41586-020-1969-6","article-title":"Pan cancer analysis of whole genomes","volume":"578","author":"International Cancer Genome Consortium, Pan-Cancer Analysis of Whole Genomes Consortium","year":"2020","journal-title":"Nature."},{"issue":"14","key":"pone.0337106.ref030","doi-asserted-by":"crossref","first-page":"1919","DOI":"10.1093\/bioinformatics\/bts277","article-title":"BEDOPS: high-performance genomic feature operations","volume":"28","author":"S Neph","year":"2012","journal-title":"Bioinformatics."},{"issue":"7414","key":"pone.0337106.ref031","doi-asserted-by":"crossref","first-page":"57","DOI":"10.1038\/nature11247","article-title":"An integrated encyclopedia of DNA elements in the human genome","volume":"489","year":"2012","journal-title":"Nature."},{"issue":"7","key":"pone.0337106.ref032","doi-asserted-by":"crossref","first-page":"1897","DOI":"10.1016\/j.cell.2016.12.002","article-title":"The international human epigenome consortium: a blueprint for scientific collaboration and discovery","volume":"167","author":"HG Stunnenberg","year":"2016","journal-title":"Cell."},{"issue":"7539","key":"pone.0337106.ref033","doi-asserted-by":"crossref","first-page":"317","DOI":"10.1038\/nature14248","article-title":"Integrative analysis of 111 reference human epigenomes","volume":"518","author":"Consortium Roadmap Epigenomics","year":"2015","journal-title":"Nature."},{"key":"pone.0337106.ref034","unstructured":"Dorogush AV, Ershov V, Gulin A. CatBoost: gradient boosting with categorical features support. arXiv prerprint 2018. https:\/\/arxiv.org\/abs\/1810.11363"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0337106","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,4]],"date-time":"2025-12-04T18:52:50Z","timestamp":1764874370000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0337106"}},"subtitle":[],"editor":[{"given":"Yogendra Kumar","family":"Prajapati","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2025,12,4]]},"references-count":34,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2025,12,4]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0337106","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,4]]}}}