{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,26]],"date-time":"2026-10-26T19:24:08Z","timestamp":1793042648078,"version":"4.5.0"},"reference-count":36,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2024,3,21]],"date-time":"2024-03-21T00:00:00Z","timestamp":1710979200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2024,3,21]],"date-time":"2024-03-21T00:00:00Z","timestamp":1710979200000},"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":["Sci Rep"],"abstract":"<jats:title>Abstract<\/jats:title><jats:p>The heterogeneous pathogenesis and treatment response of non-small cell lung cancer (NSCLC) has led clinical treatment decisions to be guided by NSCLC subtypes, with lung adenocarcinoma and lung squamous cell carcinoma being the most common subtypes. While histology-based subtyping remains challenging, NSCLC subtypes were found to be distinct at the transcriptomic level. However, unlike genomic alterations, gene expression is generally not assessed in clinical routine. Since subtyping of NSCLC has remained elusive using mutational data, we aimed at developing a neural network model that simultaneously learns from adenocarcinoma and squamous cell carcinoma samples of other tissue types and is regularized using a neural network model trained from gene expression data. While substructures of the expression-based manifold were captured in the mutation-based manifold, NSCLC classification accuracy did not significantly improve. However, performance was increased when rejecting inconclusive samples using an ensemble-based approach capturing prediction uncertainty. Importantly, SHAP analysis of misclassified samples identified co-occurring mutations indicative of both NSCLC subtypes, questioning the current NSCLC subtype classification to adequately represent inherent mutational heterogeneity. Since our model captures mutational patterns linked to clinical heterogeneity, we anticipate it to be suited as foundational model of genomic data for clinically relevant prognostic or predictive downstream tasks.<\/jats:p>","DOI":"10.1038\/s41598-024-57057-3","type":"journal-article","created":{"date-parts":[[2024,3,21]],"date-time":"2024-03-21T10:02:05Z","timestamp":1711015325000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Prediction uncertainty estimates elucidate the limitation of current NSCLC subtype classification in representing mutational heterogeneity"],"prefix":"10.1038","volume":"14","author":[{"given":"Andrei","family":"Puiu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Carlos","family":"G\u00f3mez Tapia","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Maximilian E. R.","family":"Weiss","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vivek","family":"Singh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ali","family":"Kamen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Matthias","family":"Siebert","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,3,21]]},"reference":[{"key":"57057_CR1","doi-asserted-by":"publisher","first-page":"017","DOI":"10.1093\/narcan\/zcab017","volume":"3","author":"AB Gussow","year":"2021","unstructured":"Gussow, A. B., Koonin, E. V. & Auslander, N. Identification of combinations of somatic mutations that predict cancer survival and immunotherapy benefit. NAR Cancer 3, 017 (2021).","journal-title":"NAR Cancer"},{"key":"57057_CR2","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1186\/s13073-022-01024-y","volume":"14","author":"J Long","year":"2022","unstructured":"Long, J. et al. A mutation-based gene set predicts survival benefit after immunotherapy across multiple cancers and reveals the immune response landscape. Genome Med. 14, 20 (2022).","journal-title":"Genome Med."},{"key":"57057_CR3","doi-asserted-by":"publisher","first-page":"37","DOI":"10.1038\/nrc2294","volume":"8","author":"R Clarke","year":"2008","unstructured":"Clarke, R. et al. The properties of high-dimensional data spaces: Implications for exploring gene and protein expression data. Nat. Rev. Cancer 8, 37\u201349 (2008).","journal-title":"Nat. Rev. Cancer"},{"key":"57057_CR4","doi-asserted-by":"publisher","first-page":"100561","DOI":"10.1016\/j.mcpro.2023.100561","volume":"22","author":"M Babu","year":"2023","unstructured":"Babu, M. & Snyder, M. Multi-omics profiling for health. Mol. Cell. Proteom. 22, 100561 (2023).","journal-title":"Mol. Cell. Proteom."},{"key":"57057_CR5","doi-asserted-by":"publisher","first-page":"e004415","DOI":"10.1136\/bmjgh-2020-004415","volume":"6","author":"KA Phillips","year":"2021","unstructured":"Phillips, K. A., Douglas, M. P., Wordsworth, S., Buchanan, J. & Marshall, D. A. Availability and funding of clinical genomic sequencing globally. BMJ Glob. Health 6, e004415 (2021).","journal-title":"BMJ Glob. Health"},{"key":"57057_CR6","doi-asserted-by":"publisher","first-page":"934","DOI":"10.1016\/j.annonc.2023.06.011","volume":"34","author":"A Bayle","year":"2023","unstructured":"Bayle, A. et al. ESMO study on the availability and accessibility of biomolecular technologies in oncology in Europe. Ann. Oncol. 34, 934\u2013945 (2023).","journal-title":"Ann. Oncol."},{"key":"57057_CR7","doi-asserted-by":"publisher","first-page":"168","DOI":"10.1111\/imcb.12404","volume":"99","author":"GL D\u2019Adamo","year":"2020","unstructured":"D\u2019Adamo, G. L., Widdop, J. T. & Giles, E. M. The future is now? Clinical and translational aspects of \u201comics\u2019\u2019 technologies. Immunol. Cell Biol. 99, 168\u2013176 (2020).","journal-title":"Immunol. Cell Biol."},{"key":"57057_CR8","doi-asserted-by":"publisher","first-page":"585","DOI":"10.1016\/j.molmed.2019.04.012","volume":"25","author":"V Relli","year":"2019","unstructured":"Relli, V., Trerotola, M., Guerra, E. & Alberti, S. Abandoning the notion of non-small cell lung cancer. Trends Mol. Med. 25, 585\u2013594 (2019).","journal-title":"Trends Mol. Med."},{"key":"57057_CR9","doi-asserted-by":"publisher","first-page":"291","DOI":"10.1016\/j.cell.2018.03.022","volume":"173","author":"KA Hoadley","year":"2018","unstructured":"Hoadley, K. A. et al. Cell-of-origin patterns dominate the molecular classification of 10,000 tumors from 33 types of cancer. Cell 173, 291-304.e6 (2018).","journal-title":"Cell"},{"key":"57057_CR10","doi-asserted-by":"publisher","first-page":"35528","DOI":"10.18632\/oncotarget.26217","volume":"9","author":"V Relli","year":"2018","unstructured":"Relli, V., Trerotola, M., Guerra, E. & Alberti, S. Distinct lung cancer subtypes associate to distinct drivers of tumor progression. Oncotarget 9, 35528\u201335540 (2018).","journal-title":"Oncotarget"},{"key":"57057_CR11","doi-asserted-by":"publisher","first-page":"2067","DOI":"10.1002\/cam4.4570","volume":"11","author":"S-H Hsiao","year":"2022","unstructured":"Hsiao, S.-H. et al. Comparative survival analysis of platinum-based adjuvant chemotherapy for early-stage squamous cell carcinoma and adenocarcinoma of the lung. Cancer Med. 11, 2067\u20132078 (2022).","journal-title":"Cancer Med."},{"key":"57057_CR12","doi-asserted-by":"publisher","first-page":"64","DOI":"10.1097\/JTO.0b013e3181f7c6d4","volume":"6","author":"G Scagliotti","year":"2011","unstructured":"Scagliotti, G. et al. Treatment-by-histology interaction analyses in three phase III trials show superiority of pemetrexed in nonsquamous non-small cell lung cancer. J. Thorac. Oncol. 6, 64\u201370 (2011).","journal-title":"J. Thorac. Oncol."},{"key":"57057_CR13","doi-asserted-by":"publisher","first-page":"3310","DOI":"10.1200\/JCO.22.00824","volume":"40","author":"N Singh","year":"2022","unstructured":"Singh, N. et al. Therapy for stage IV non-small-cell lung cancer with driver alterations: ASCO living guideline. J. Clin. Oncol. 40, 3310\u20133322 (2022).","journal-title":"J. Clin. Oncol."},{"key":"57057_CR14","doi-asserted-by":"publisher","first-page":"3323","DOI":"10.1200\/JCO.22.00825","volume":"40","author":"N Singh","year":"2022","unstructured":"Singh, N. et al. Therapy for stage IV non-small-cell lung cancer without driver alterations: ASCO living guideline. J. Clin. Oncol. 40, 3323\u20133343 (2022).","journal-title":"J. Clin. Oncol."},{"key":"57057_CR15","doi-asserted-by":"publisher","first-page":"860","DOI":"10.1038\/s43018-023-00578-z","volume":"4","author":"C Zhou","year":"2023","unstructured":"Zhou, C. et al. Interim survival analysis of the randomized phase III GEMSTONE-302 trial: Sugemalimab or placebo plus chemotherapy as first-line treatment for metastatic NSCLC. Nat Cancer 4, 860\u2013871 (2023).","journal-title":"Nat Cancer"},{"key":"57057_CR16","doi-asserted-by":"publisher","first-page":"510","DOI":"10.1016\/j.jtho.2016.11.002","volume":"12","author":"NM Woody","year":"2016","unstructured":"Woody, N. M. et al. A histologic basis for the efficacy of SBRT to the lung. J. Thorac. Oncol. 12, 510\u2013519 (2016).","journal-title":"J. Thorac. Oncol."},{"key":"57057_CR17","doi-asserted-by":"publisher","first-page":"887","DOI":"10.3390\/cancers15030887","volume":"15","author":"N Kita","year":"2023","unstructured":"Kita, N. et al. Comparison of recurrence patterns between adenocarcinoma and squamous cell carcinoma after stereotactic body radiotherapy for early-stage lung cancer. Cancers 15, 887 (2023).","journal-title":"Cancers"},{"key":"57057_CR18","doi-asserted-by":"publisher","first-page":"812","DOI":"10.1016\/j.immuni.2018.03.023","volume":"48","author":"V Thorsson","year":"2018","unstructured":"Thorsson, V. et al. The immune landscape of cancer. Immunity 48, 812\u2013830 (2018).","journal-title":"Immunity"},{"key":"57057_CR19","unstructured":"Lundberg, S.\u00a0M. & Lee, S.-I. A unified approach to interpreting model predictions. In Proc. 31st International Conference on Neural Information Processing Systems, NIPS\u201917 4768\u20134777 (Curran Associates Inc., 2017)"},{"key":"57057_CR20","doi-asserted-by":"crossref","unstructured":"Cho, J.\u00a0H. & Hariharan, B. On the efficacy of knowledge distillation. In 2019 IEEE\/CVF International Conference on Computer Vision (ICCV) 4793\u20134801 (2019).","DOI":"10.1109\/ICCV.2019.00489"},{"key":"57057_CR21","doi-asserted-by":"publisher","first-page":"495","DOI":"10.1038\/s41568-019-0179-8","volume":"19","author":"F Skoulidis","year":"2019","unstructured":"Skoulidis, F. & Heymach, J. V. Co-occurring genomic alterations in non-small-cell lung cancer biology and therapy. Nat. Rev. Cancer 19, 495\u2013509 (2019).","journal-title":"Nat. Rev. Cancer"},{"key":"57057_CR22","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1038\/s41698-021-00243-7","volume":"6","author":"F Zhang","year":"2022","unstructured":"Zhang, F. et al. Co-occurring genomic alterations and immunotherapy efficacy in NSCLC. NPJ Precis. Oncol. 6, 4 (2022).","journal-title":"NPJ Precis. Oncol."},{"key":"57057_CR23","doi-asserted-by":"publisher","first-page":"3676","DOI":"10.1038\/s41467-023-39400-w","volume":"14","author":"XG Luo","year":"2023","unstructured":"Luo, X. G., Kuipers, J. & Beerenwinkel, N. Joint inference of exclusivity patterns and recurrent trajectories from tumor mutation trees. Nat. Commun. 14, 3676 (2023).","journal-title":"Nat. Commun."},{"key":"57057_CR24","doi-asserted-by":"publisher","first-page":"23","DOI":"10.1016\/j.lungcan.2017.06.014","volume":"111","author":"C Labb\u00e9","year":"2017","unstructured":"Labb\u00e9, C. et al. Prognostic and predictive effects of TP53 co-mutation in patients with EGFR-mutated non-small cell lung cancer (NSCLC). Lung Cancer 111, 23\u201329 (2017).","journal-title":"Lung Cancer"},{"key":"57057_CR25","doi-asserted-by":"publisher","first-page":"3012","DOI":"10.1158\/1078-0432.CCR-16-2554","volume":"23","author":"Z-Y Dong","year":"2016","unstructured":"Dong, Z.-Y. et al. Potential predictive value of TP53 and KRAS mutation status for response to PD-1 blockade immunotherapy in lung adenocarcinoma. Clin. Cancer Res. 23, 3012\u20133024 (2016).","journal-title":"Clin. Cancer Res."},{"key":"57057_CR26","doi-asserted-by":"publisher","first-page":"1559","DOI":"10.1038\/s41591-018-0177-5","volume":"24","author":"N Coudray","year":"2018","unstructured":"Coudray, N. et al. Classification and mutation prediction from non-small cell lung cancer histopathology images using deep learning. Nat. Med. 24, 1559\u20131567 (2018).","journal-title":"Nat. Med."},{"key":"57057_CR27","doi-asserted-by":"publisher","first-page":"122","DOI":"10.1186\/s13059-016-0974-4","volume":"17","author":"W McLaren","year":"2016","unstructured":"McLaren, W. et al. The ensembl variant effect predictor. Genome Biol. 17, 122 (2016).","journal-title":"Genome Biol."},{"key":"57057_CR28","first-page":"29287","volume-title":"Advances in Neural Information Processing Systems","author":"J Meier","year":"2021","unstructured":"Meier, J. et al. Language models enable zero-shot prediction of the effects of mutations on protein function. In Advances in Neural Information Processing Systems Vol. 34 (eds Ranzato, M. et al.) 29287\u201329303 (Curran Associates Inc, 2021)."},{"key":"57057_CR29","first-page":"100019","volume":"1","author":"L Zhang","year":"2021","unstructured":"Zhang, L. et al. AutoGGN: A gene graph network AutoML tool for multi-omics research. Artif. Intell. Life Sci. 1, 100019 (2021).","journal-title":"Artif. Intell. Life Sci."},{"key":"57057_CR30","doi-asserted-by":"publisher","first-page":"348","DOI":"10.1038\/s41586-021-03922-4","volume":"598","author":"HA Elmarakeby","year":"2021","unstructured":"Elmarakeby, H. A. et al. Biologically informed deep neural network for prostate cancer discovery. Nature 598, 348\u2013352 (2021).","journal-title":"Nature"},{"key":"57057_CR31","doi-asserted-by":"publisher","first-page":"85","DOI":"10.1038\/nrg3868","volume":"16","author":"MD Ritchie","year":"2015","unstructured":"Ritchie, M. D., Holzinger, E. R., Li, R., Pendergrass, S. A. & Kim, D. Methods of integrating data to uncover genotype\u2013phenotype interactions. Nat. Rev. Genet. 16, 85\u201397 (2015).","journal-title":"Nat. Rev. Genet."},{"key":"57057_CR32","doi-asserted-by":"publisher","first-page":"401","DOI":"10.1158\/2159-8290.CD-12-0095","volume":"2","author":"E Cerami","year":"2012","unstructured":"Cerami, E. et al. The cbio cancer genomics portal: An open platform for exploring multidimensional cancer genomics data. Cancer Discov. 2, 401\u2013404 (2012).","journal-title":"Cancer Discov."},{"key":"57057_CR33","doi-asserted-by":"publisher","first-page":"D941","DOI":"10.1093\/nar\/gky1015","volume":"47","author":"JG Tate","year":"2019","unstructured":"Tate, J. G. et al. COSMIC: The catalogue of somatic mutations in cancer. Nucleic Acids Res. 47, D941\u2013D947 (2019).","journal-title":"Nucleic Acids Res."},{"key":"57057_CR34","doi-asserted-by":"publisher","first-page":"181","DOI":"10.1016\/j.ipl.2005.11.003","volume":"97","author":"PS Efraimidis","year":"2006","unstructured":"Efraimidis, P. S. & Spirakis, P. G. Weighted random sampling with a reservoir. Inf. Process. Lett. 97, 181\u2013185 (2006).","journal-title":"Inf. Process. Lett."},{"key":"57057_CR35","doi-asserted-by":"publisher","unstructured":"McInnes, L., Healy, J. & Melville, J. UMAP: Uniform manifold approximation and projection for dimension reduction. arXiv. https:\/\/doi.org\/10.48550\/arXiv.1802.03426 (2020).","DOI":"10.48550\/arXiv.1802.03426"},{"key":"57057_CR36","doi-asserted-by":"publisher","first-page":"371","DOI":"10.1016\/j.cell.2018.02.060","volume":"173","author":"MH Bailey","year":"2018","unstructured":"Bailey, M. H. et al. Comprehensive characterization of cancer driver genes and mutations. Cell 173, 371\u2013385 (2018).","journal-title":"Cell"}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-024-57057-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-024-57057-3","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-024-57057-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,21]],"date-time":"2024-03-21T10:10:39Z","timestamp":1711015839000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-024-57057-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,3,21]]},"references-count":36,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2024,12]]}},"alternative-id":["57057"],"URL":"https:\/\/doi.org\/10.1038\/s41598-024-57057-3","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,3,21]]},"assertion":[{"value":"22 November 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 March 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 March 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"A.P. is employed by Siemens SRL. C.G.T. was previously employed by Siemens Healthineers. M.E.R.W., V.S., A.K., and M.S. are employed by Siemens Healthineers.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"6779"}}