Advancing CNS tumor diagnostics with expanded DNA methylation-based classification
Martin Sill, Daniel Schrimpf, Areeba Patel, Dominik Sturm, Natalie Jäger, Philipp Sievers, Leonille Schweizer, Rouzbeh Banan, David L. Reuss, Abigail K. Suwala, Andrey Korshunov, Damian Stichel, Annika K. Wefers, Ann‐Christin Hau, Henning B. Boldt, Patrick N. Harter, Zied Abdullaev, Jamal Benhamida, Daniel Teichmann, Arend Koch, Jürgen Hench, Frank Stephan, Martin Hasselblatt, Sheila Mansouri, Theresita Díaz de Ståhl, Jonathan Serrano, Jonas Ecker, Florian Selt, Michael V. Taylor, Vijay Ramaswamy, Florence M.G. Cavalli, Anna S. Berghoff, Brigitte Bison, Mirjam Blattner-Johnson, Ivo Buchhalter, Rolf Buslei, Gabriele Calaminus, Nicola Dikow, Hildegard Dohmen, Philipp Euskirchen, Gudrun Fleischhack, Amar Gajjar, Nicolas U. Gerber, Marco Gessi, Gerrit H. Gielen, Astrid Gnekow, Nicholas G. Gottardo, Christine Haberler, Stefan Hamelmann, Volkmar Hans, Jordan R. Hansford, Christian Hartmann, Frank L. Heppner, Pablo Hernáiz Driever, Katja von Hoff, Ulrich W. Thomale, Stephan Tippelt, Michael C. Frühwald, Christof M. Kramm, Ulrich Schüller, Jens Schittenhelm, Martin U. Schuhmann, Marco Stein, Petra Ketteler, Marc Ladanyi, Nada Jabado, Barbara C. Jones, Chris Jones, Matthias A. Karajannis, Ralf Ketter, Patricia Kohlhof, Uwe Kordes, Annekathrin Reinhardt, Christian Kölsche, Katrin Lamszus, Péter Lichter, Sybren L. N. Maas, Christian Mawrin, Till Milde, Michel Mittelbronn, Camelia‐Maria Monoranu, Wolf Mueller, Martin Mynarek, Paul A. Northcott, Kristian W. Pajtler, Werner Paulus, Arie Perry, Ingmar Blümcke, Karl H. Plate, Michael Platten, Matthias Preusser, Torsten Pietsch, Marco Prinz, Guido Reifenberger, Bjarne Winther Kristensen, Marcel Kool, Volker Hovestadt, David W. Ellison, Thomas S. Jacques, Pascale Varlet
Abstract
DNA methylation-based classification is now central to contemporary neuro-oncology, as highlighted by the World Health Organization (WHO) classification of central nervous system (CNS) tumors. We present the Heidelberg CNS Tumor Methylation Classifier version 12.8 (v12.8), trained on 7,495 methylation profiles, which expands recognized entities from 91 classes in version 11 (v11) to 184 subclasses. This expansion is a result of newly identified tumor types discovered through our large online repository and global collaborations, underscoring CNS tumor heterogeneity. The random forest-based classifier achieves 95% subclass-level accuracy, with its well-calibrated probabilistic scores providing a reliable measure of confidence for each classification. Its hierarchical output structure enables interpretation across subclass, class, family, and superfamily levels, thereby supporting clinical decisions at multiple granularities. Comparative analyses demonstrate that v12.8 surpasses previous versions and conventional WHO-based approaches. These advances highlight the improved precision and practical utility of the updated classifier in personalized neuro-oncology.