Sarcoma classification by DNA methylation profiling

Christian Koelsche, Daniel Schrimpf, Damian Stichel, Martin Sill, Felix Sahm, David E. Reuss, Mirjam Blattner, Barbara Worst, Christoph E. Heilig, Katja Beck, Peter Horak, Simon Kreutzfeldt, Elke Paff, Sebastian Stark, Pascal Johann, Florian Selt, Jonas Ecker, Dominik Sturm, Kristian W. Pajtler, Annekathrin ReinhardtAnnika K. Wefers, Philipp Sievers, Azadeh Ebrahimi, Abigail Suwala, Francisco Fernández-Klett, Belén Casalini, Andrey Korshunov, Volker Hovestadt, Felix K. F. Kommoss, Mark Kriegsmann, Matthias Schick, Melanie Bewerunge-Hudler, Till Milde, Olaf Witt, Andreas E. Kulozik, Marcel Kool, Laura Romero-Pérez, Thomas G. P. Grünewald, Thomas Kirchner, Wolfgang Wick, Michael Platten, Andreas Unterberg, Matthias Uhl, Amir Abdollahi, J. rgen Debus, Burkhard Lehner, Christian Thomas, Martin Hasselblatt, Werner Paulus, Christian Hartmann, Ori Staszewski, Marco Prinz, J. rgen Hench, Stephan Frank, Yvonne M. H. Versleijen-Jonkers, Marije E. Weidema, Thomas Mentzel, Klaus Griewank, Enrique de Álava, Juan D. az Martín, Miguel A. Idoate Gastearena, Kenneth Tou-En Chang, Sharon Yin Yee Low, Adrian Cuevas-Bourdier, Michel Mittelbronn, Martin Mynarek, Stefan Rutkowski, Ulrich Schüller, Viktor F. Mautner, Jens Schittenhelm, Jonathan Serrano, Matija Snuderl, Reinhard Büttner, Thomas Klingebiel, Rolf Buslei, Manfred Gessler, Pieter Wesseling, Winand N. M. Dinjens, Sebastian Brandner, Zane Jaunmuktane, Iben Lyskjær, Peter Schirmacher, Albrecht Stenzinger, Benedikt Brors, Hanno Glimm, Christoph Heining, Oscar M. Tirado, Miguel Sáinz-Jaspeado, Jaume Mora, Javier Alonso, Xavier Garcia del Muro, Sebastian Moran, Manel Esteller, Jamal K. Benhamida, Marc Ladanyi, Eva Wardelmann, Cristina Antonescu, Adrienne Flanagan, Uta Dirksen, Peter Hohenberger, Daniel Baumhoer, Wolfgang Hartmann, Christian Vokuhl, Uta Flucke, Iver Petersen, Gunhild Mechtersheimer, David Capper, David T. W. Jones, Stefan Fröhling, Stefan M. Pfister, Andreas von Deimling*

*Corresponding author for this work

Research output: Contribution to journalArticleAcademicpeer-review

Abstract

Sarcomas are malignant soft tissue and bone tumours affecting adults, adolescents and children. They represent a morphologically heterogeneous class of tumours and some entities lack defining histopathological features. Therefore, the diagnosis of sarcomas is burdened with a high inter-observer variability and misclassification rate. Here, we demonstrate classification of soft tissue and bone tumours using a machine learning classifier algorithm based on array-generated DNA methylation data. This sarcoma classifier is trained using a dataset of 1077 methylation profiles from comprehensively pre-characterized cases comprising 62 tumour methylation classes constituting a broad range of soft tissue and bone sarcoma subtypes across the entire age spectrum. The performance is validated in a cohort of 428 sarcomatous tumours, of which 322 cases were classified by the sarcoma classifier. Our results demonstrate the potential of the DNA methylation-based sarcoma classification for research and future diagnostic applications.
Original languageEnglish
Article number498
JournalNature Communications
Volume12
Issue number1
DOIs
Publication statusPublished - 1 Dec 2021

Cite this