DNA methylation-based classification of central nervous system tumours

• Published in: Nature (London) Vol. 555; no. 7697; pp. 469 - 474
• Main Authors: Capper, David, Jones, David T. W., Hovestadt, Volker, Schrimpf, Daniel, Sturm, Dominik, Kratz, Annekathrin, Huang, Kristin, Pajtler, Kristian W., Lindenberg, Kerstin, Harter, Patrick N., Braczynski, Anne K., Plate, Karl H., Dohmen, Hildegard, Garvalov, Boyan K., Hölsken, Annett, Hewer, Ekkehard, Bewerunge-Hudler, Melanie, Schick, Matthias, Schittenhelm, Jens, Wani, Khalida, Witt, Hendrik, Milde, Till, Witt, Olaf, Giangaspero, Felice, Geisenberger, Christoph, Rodriguez, Fausto J., Becker, Albert, Preusser, Matthias, Haberler, Christine, Cryan, Jane, Farrell, Michael, Deckert, Martina, Hench, Jürgen, Frank, Stephan, Serrano, Jonathan, Kannan, Kasthuri, Tsirigos, Aristotelis, Brück, Wolfgang, Hofer, Silvia, Brehmer, Stefanie, Seiz-Rosenhagen, Marcel, Hänggi, Daniel, Rozsnoki, Stephanie, Hansford, Jordan R., Kohlhof, Patricia, Kristensen, Bjarne W., Lechner, Matt, Lopes, Beatriz, Mawrin, Christian, Ketter, Ralf, Kulozik, Andreas, Heppner, Frank, Koch, Arend, Jouvet, Anne, Keohane, Catherine, Mühleisen, Helmut, Mueller, Wolf, Driever, Pablo Hernáiz, Kramm, Christof M., Müller, Hermann L., Rutkowski, Stefan, Frühwald, Michael C., Gnekow, Astrid, Fleischhack, Gudrun, Calaminus, Gabriele, Perry, Arie, Jones, Chris, Jacques, Thomas S., Radlwimmer, Bernhard, Gessi, Marco, Pietsch, Torsten, Schramm, Johannes, Schackert, Gabriele, Westphal, Manfred, Reifenberger, Guido, Wesseling, Pieter, Weller, Michael, Bendszus, Martin, Huang, Annie, Jabado, Nada, Northcott, Paul A., Paulus, Werner, Gajjar, Amar, Taylor, Michael D., Ryzhova, Marina, Platten, Michael, Unterberg, Andreas, Wick, Wolfgang, Acker, Till, Hartmann, Christian, Aldape, Kenneth, Buslei, Rolf, Lichter, Peter, Kool, Marcel, Herold-Mende, Christel, Ellison, David W., Hasselblatt, Martin, Snuderl, Matija, Korshunov, Andrey, Pfister, Stefan M.
• Format: Journal Article
• Language: English
• Published: London Nature Publishing Group UK 22.03.2018; Nature Publishing Group
• Subjects: 13/56; 45/61; 631/114/1386; 631/114/2407; 631/67/1922; 631/67/69; Adolescent; Adult; Aged; Aged, 80 and over; Bioinformatics; Brain cancer; Cancer; Cancer diagnosis; Central nervous system; Central Nervous System Neoplasms - classification; Central Nervous System Neoplasms - diagnosis; Central Nervous System Neoplasms - genetics; Central Nervous System Neoplasms - pathology; Child; Child, Preschool; Classification; Classifiers; Clinical trials; Cohort Studies; Data processing; Deoxyribonucleic acid; Diagnosis; Diagnostic software; Diagnostic systems; DNA; DNA Methylation; DNA sequencing; Female; Gene expression; Generalized linear models; Genetic aspects; Genomes; Humanities and Social Sciences; Humans; Identification and classification; Infant; Learning algorithms; Machine learning; Male; Medical examination; Methods; Methylation; Middle Aged; multidisciplinary; Nervous system; Observations; Probability; Reproducibility of Results; Science; Standardization; Tumors; Unsupervised Machine Learning; Young Adult; Germany
• ISSN: 0028-0836; 1476-4687; 1476-4687
• DOI: 10.1038/nature26000

Accurate pathological diagnosis is crucial for optimal management of patients with cancer. For the approximately 100 known tumour types of the central nervous system, standardization of the diagnostic process has been shown to be particularly challenging—with substantial inter-observer variability in the histopathological diagnosis of many tumour types. Here we present a comprehensive approach for the DNA methylation-based classification of central nervous system tumours across all entities and age groups, and demonstrate its application in a routine diagnostic setting. We show that the availability of this method may have a substantial impact on diagnostic precision compared to standard methods, resulting in a change of diagnosis in up to 12% of prospective cases. For broader accessibility, we have designed a free online classifier tool, the use of which does not require any additional onsite data processing. Our results provide a blueprint for the generation of machine-learning-based tumour classifiers across other cancer entities, with the potential to fundamentally transform tumour pathology. An online approach for the DNA methylation-based classification of central nervous system tumours across all entities and age groups has been developed to help to improve current diagnostic standards. Classifying tumour types for better diagnoses Precise cancer diagnoses are essential to ensure the best treatment plans for patients, but standardization of the diagnostic process has been challenging. The authors present a comprehensive approach for DNA-methylation-based classification of brain tumours. The tool improves diagnostic precision of standard methods, and is made available online for broad accessibility. The results illustrate the potential applications of molecular diagnosis tools.