{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,17]],"date-time":"2026-10-17T00:40:37Z","timestamp":1792197637264,"version":"4.4.0"},"reference-count":26,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,10,16]],"date-time":"2026-10-16T00:00:00Z","timestamp":1792108800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,10,16]],"date-time":"2026-10-16T00:00:00Z","timestamp":1792108800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["npj Precis. Onc."],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Missed genetic deletions can prevent cancer patients from receiving effective targeted therapy. Standard pipelines, such as TSO500, use bin count averaging for copy number variation detection but often overlook focal events. To address this, we developed a machine learning (ML) pipeline for deletion detection and zygosity evaluation within the MASTERsg precision oncology program. We focused on the tumor suppressor gene PTEN, whose loss confers sensitivity to mTOR\/Akt inhibition. An Extreme Gradient Boosting model trained on PTEN-deleted and wild-type tumor samples identified focal deletions missed by the TSO500 pipeline and CNVkit that were associated with concordant PTEN protein loss by immunohistochemistry. Importantly, the model detected PTEN deletions in 33\/204 profiled samples that were classified as PTEN wild-type by TSO500; 75% (15\/20) of stainable cases showed absent or reduced PTEN protein expression. These findings demonstrate the potential of ML to enhance panel sequencing, uncovering therapeutically relevant alterations missed by established diagnostic methods.<\/jats:p>","DOI":"10.1038\/s41698-026-01756-9","type":"journal-article","created":{"date-parts":[[2026,10,16]],"date-time":"2026-10-16T22:48:13Z","timestamp":1792190893000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Machine learning uncovers previously undetectable genetic deletions in cancer panel sequencing"],"prefix":"10.1038","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3650-488X","authenticated-orcid":false,"given":"Irina A.","family":"Kerle","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Oleksandr","family":"Husak","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Thomas","family":"Gross","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andreas","family":"Hartig","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rebecca","family":"Prause","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Daniela","family":"Richter","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sascha","family":"Br\u00fcckmann","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Maximilian","family":"Werner","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anja","family":"K\u00f6gler","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dorothea","family":"Hanf","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lino","family":"M\u00f6hrmann","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7824-5073","authenticated-orcid":false,"given":"Doreen","family":"William","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Karsten","family":"Wendt","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5977-5375","authenticated-orcid":false,"given":"Nicole","family":"Pfarr","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3400-7254","authenticated-orcid":false,"given":"Carolin","family":"Mogler","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Daniela E.","family":"Aust","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Evelin","family":"Schr\u00f6ck","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Christoph","family":"Heining","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hanno","family":"Glimm","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,10,16]]},"reference":[{"key":"1756_CR1","doi-asserted-by":"publisher","first-page":"2525","DOI":"10.1158\/2159-8290.CD-23-1194","volume":"13","author":"YR Murciano-Goroff","year":"2023","unstructured":"Murciano-Goroff, Y. R., Suehnholz, S. P., Drilon, A. & Chakravarty, D. Precision oncology: 2023 in review. Cancer Discov. 13, 2525\u20132531 (2023).","journal-title":"Cancer Discov."},{"key":"1756_CR2","doi-asserted-by":"publisher","first-page":"588","DOI":"10.1016\/j.annonc.2024.04.005","volume":"35","author":"MF Mosele","year":"2024","unstructured":"Mosele, M. F. et al. Recommendations for the use of next-generation sequencing (NGS) for patients with advanced cancer in 2024: a report from the ESMO Precision Medicine Working Group. Ann. Oncol. 35, 588\u2013606 (2024).","journal-title":"Ann. Oncol."},{"key":"1756_CR3","doi-asserted-by":"publisher","first-page":"292","DOI":"10.1016\/j.jmoldx.2025.01.002","volume":"27","author":"H Al-Kateb","year":"2025","unstructured":"Al-Kateb, H. et al. Clinical validation of the trusight oncology 500 assay for the detection and reporting of pan-cancer biomarkers. J. Mol. Diagn. 27, 292\u2013305 (2025).","journal-title":"J. Mol. Diagn."},{"key":"1756_CR4","doi-asserted-by":"publisher","first-page":"6152","DOI":"10.3390\/cancers14246152","volume":"14","author":"L Giac\u00f2","year":"2022","unstructured":"Giac\u00f2, L. et al. A computational framework for comprehensive genomic profiling in solid cancers: the analytical performance of a high-throughput assay for small and copy number variants. Cancers 14, 6152 (2022).","journal-title":"Cancers"},{"key":"1756_CR5","doi-asserted-by":"publisher","first-page":"bbae645","DOI":"10.1093\/bib\/bbae645","volume":"26","author":"E Munt\u00e9","year":"2025","unstructured":"Munt\u00e9, E. et al. Detection of germline CNVs from gene panel data: benchmarking the state of the art. Brief. Bioinform. 26, bbae645 (2025).","journal-title":"Brief. Bioinform."},{"key":"1756_CR6","doi-asserted-by":"publisher","first-page":"2342","DOI":"10.3390\/cells9112342","volume":"9","author":"DJ Turnham","year":"2020","unstructured":"Turnham, D. J., Bullock, N., Dass, M. S., Staffurth, J. N. & Pearson, H. B. The PTEN conundrum: how to target PTEN-deficient prostate cancer. Cells 9, 2342 (2020).","journal-title":"Cells"},{"key":"1756_CR7","doi-asserted-by":"publisher","first-page":"10","DOI":"10.1007\/s44257-024-00017-y","volume":"2","author":"M Frasca","year":"2024","unstructured":"Frasca, M. et al. Artificial intelligence applications to genomic data in cancer research: a review of recent trends and emerging areas. Discov. Anal. 2, 10 (2024).","journal-title":"Discov. Anal."},{"key":"1756_CR8","doi-asserted-by":"publisher","unstructured":"Chen, T. & Guestrin, C. XGBoost: a scalable tree boosting system. In Proc. 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining 785\u2013794 https:\/\/doi.org\/10.1145\/2939672.2939785 (ACM, 2016).","DOI":"10.1145\/2939672.2939785"},{"key":"1756_CR9","doi-asserted-by":"publisher","first-page":"e1004873","DOI":"10.1371\/journal.pcbi.1004873","volume":"12","author":"E Talevich","year":"2016","unstructured":"Talevich, E., Shain, A. H., Botton, T. & Bastian, B. C. CNVkit: genome-wide copy number detection and visualization from targeted DNA sequencing. PLoS Comput. Biol. 12, e1004873 (2016).","journal-title":"PLoS Comput. Biol."},{"key":"1756_CR10","unstructured":"Ensembl genome browser 115. https:\/\/www.ensembl.org\/index.html."},{"key":"1756_CR11","doi-asserted-by":"publisher","first-page":"2780","DOI":"10.1158\/2159-8290.CD-21-0126","volume":"11","author":"P Horak","year":"2021","unstructured":"Horak, P. et al. Comprehensive genomic and transcriptomic analysis for guiding therapeutic decisions in patients with rare cancers. Cancer Discov. 11, 2780\u20132795 (2021).","journal-title":"Cancer Discov."},{"key":"1756_CR12","doi-asserted-by":"publisher","first-page":"e0260089","DOI":"10.1371\/journal.pone.0260089","volume":"16","author":"JM Conroy","year":"2021","unstructured":"Conroy, J. M. et al. A scalable high-throughput targeted next-generation sequencing assay for comprehensive genomic profiling of solid tumors. PLoS ONE 16, e0260089 (2021).","journal-title":"PLoS ONE"},{"key":"1756_CR13","doi-asserted-by":"publisher","first-page":"386","DOI":"10.1016\/j.cels.2017.08.013","volume":"5","author":"E Gon\u00e7alves","year":"2017","unstructured":"Gon\u00e7alves, E. et al. Widespread post-transcriptional attenuation of genomic copy-number variation in cancer. Cell Syst. 5, 386\u2013398.e4 (2017).","journal-title":"Cell Syst."},{"key":"1756_CR14","doi-asserted-by":"publisher","first-page":"93","DOI":"10.1126\/science.ade3925","volume":"380","author":"J Zecha","year":"2023","unstructured":"Zecha, J. et al. Decrypting drug actions and protein modifications by dose- and time-resolved proteomics. Science 380, 93\u2013101 (2023).","journal-title":"Science"},{"key":"1756_CR15","doi-asserted-by":"publisher","first-page":"595","DOI":"10.1016\/j.cell.2018.03.043","volume":"173","author":"S Turajlic","year":"2018","unstructured":"Turajlic, S. et al. Deterministic evolutionary trajectories influence primary tumor growth: TRACERx renal. Cell 173, 595\u2013610.e11 (2018).","journal-title":"Cell"},{"key":"1756_CR16","doi-asserted-by":"publisher","first-page":"144","DOI":"10.1038\/s41592-020-01013-2","volume":"18","author":"M Tarabichi","year":"2021","unstructured":"Tarabichi, M. et al. A practical guide to cancer subclonal reconstruction from DNA sequencing. Nat. Methods 18, 144\u2013155 (2021).","journal-title":"Nat. Methods"},{"key":"1756_CR17","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-021-26698-7","volume":"12","author":"G Tanner","year":"2021","unstructured":"Tanner, G., Westhead, D. R., Droop, A. & Stead, L. F. Benchmarking pipelines for subclonal deconvolution of bulk tumour sequencing data. Nat. Commun. 12, 6396 (2021).","journal-title":"Nat. Commun."},{"key":"1756_CR18","doi-asserted-by":"publisher","first-page":"bbae442","DOI":"10.1093\/bib\/bbae442","volume":"25","author":"X Cheng","year":"2024","unstructured":"Cheng, X. et al. Enhancing clinical genomic accuracy with panelGC: a novel metric and tool for quantifying and monitoring GC biases in hybridization capture panel sequencing. Brief. Bioinform. 25, bbae442 (2024).","journal-title":"Brief. Bioinform."},{"key":"1756_CR19","doi-asserted-by":"publisher","first-page":"229","DOI":"10.31557\/apjcb.2025.10.1.229-238","volume":"10","author":"MH Lucky","year":"2025","unstructured":"Lucky, M. H., Baig, S., Hanif, M. & Asghar, A. H. Systematic review: comprehensive methods for detecting BRCA1 and BRCA2 mutations in breast and ovarian cancer. Asian Pac. J. Cancer Biol. 10, 229\u2013238 (2025).","journal-title":"Asian Pac. J. Cancer Biol."},{"key":"1756_CR20","doi-asserted-by":"publisher","DOI":"10.1186\/s12920-021-01059-x","volume":"14","author":"AK Singh","year":"2021","unstructured":"Singh, A. K. et al. Detecting copy number variation in next generation sequencing data from diagnostic gene panels. BMC Med. Genom. 14, 214 (2021).","journal-title":"BMC Med. Genom."},{"key":"1756_CR21","doi-asserted-by":"publisher","unstructured":"Wick, W. et al. Molecularly matched targeted therapies plus radiotherapy in glioblastoma: the phase 1\/2a N2M2 umbrella trial. Nat. Med. 1\u20138. https:\/\/doi.org\/10.1038\/s41591-025-03928-9 (2025).","DOI":"10.1038\/s41591-025-03928-9"},{"key":"1756_CR22","doi-asserted-by":"publisher","first-page":"2661","DOI":"10.3390\/cancers13112661","volume":"13","author":"A Starzy\u0144ska","year":"2021","unstructured":"Starzy\u0144ska, A. et al. ZNF-281 as the potential diagnostic marker of oral squamous cell carcinoma. Cancers 13, 2661 (2021).","journal-title":"Cancers"},{"key":"1756_CR23","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1080\/00313020123290","volume":"33","author":"AA Thike","year":"2001","unstructured":"Thike, A. A., Chng, M. J., Fook-Chong, S. & Tan, P. H. Immunohistochemical expression of hormone receptors in invasive breast carcinoma: correlation of results of H-score with pathological parameters. Pathology 33, 21\u201325 (2001).","journal-title":"Pathology"},{"key":"1756_CR24","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0118432","volume":"10","author":"T Saito","year":"2015","unstructured":"Saito, T. & Rehmsmeier, M. The precision-recall plot is more informative than the ROC plot when evaluating binary classifiers on imbalanced datasets. PLoS ONE 10, e0118432 (2015).","journal-title":"PLoS ONE"},{"key":"1756_CR25","doi-asserted-by":"publisher","DOI":"10.1186\/s12864-019-6413-7","volume":"21","author":"D Chicco","year":"2020","unstructured":"Chicco, D. & Jurman, G. The advantages of the Matthews correlation coefficient (MCC) over F1 score and accuracy in binary classification evaluation. BMC Genom. 21, 6 (2020).","journal-title":"BMC Genom."},{"key":"1756_CR26","unstructured":"Lundberg, S. M. & Lee, S.-I. A unified approach to interpreting model predictions. In Proc. 31st International Conference on Neural Information Processing Systems, 4768\u20134777 (Curran Associates Inc., 2017)."}],"container-title":["npj Precision Oncology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41698-026-01756-9","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41698-026-01756-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41698-026-01756-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,16]],"date-time":"2026-10-16T23:55:18Z","timestamp":1792194918000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41698-026-01756-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10,16]]},"references-count":26,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["1756"],"URL":"https:\/\/doi.org\/10.1038\/s41698-026-01756-9","relation":{},"ISSN":["2397-768X"],"issn-type":[{"value":"2397-768X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10,16]]},"assertion":[{"value":"22 October 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 September 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 October 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"I.A.K. reports personal fees from Bayer and stock ownership in BioNTech, CureVac, Valneva, and Novavax but declares no non-financial competing interests. C.H. received research funding and honoraria for advisory board participation from Boehringer Ingelheim and honoraria for speaking engagements from Roche and Novartis. O.H. received intramural funding through the research project \u201cDECISIONS\u201d. M.W. was supported by the clinician scientist program \u201cForwarDD\u201d sponsored by the medical faculty of the Technical University Dresden. L.M. was supported by the German Research Foundation (DFG) through a Walter Benjamin Fellowship (grant numbers 551924272 and 574708936), and his wife is an employee of Pfizer Pharma GmbH.","order":1,"name":"Ethics","label":"Competing interests","group":{"name":"EthicsHeading","label":"Declarations"}}],"article-number":"397"}}