Sarcoma classification by DNA methylation profiling.
- Koelsche C
- Schrimpf D
- Stichel D
- Sill M
- Sahm F
- Reuss DE
- Blattner M
- Worst B
- Heilig CE
- Beck K
- Horak P
- Kreutzfeldt S
- Paff E
- Stark S
- Johann P
- Selt F
- Ecker J
- Sturm D
- Pajtler KW
- Reinhardt A
- Wefers AK
- Sievers P
- Ebrahimi A
- Suwala A
- Fernandez-Klett F
- Casalini B
- Korshunov A
- Hovestadt V
- Kommoss FKF
- Kriegsmann M
- Schick M
- Bewerunge-Hudler M
- Milde T
- Witt O
- Kulozik AE
- Kool M
- Romero-Perez L
- Grunewald TGP
- Kirchner T
- Wick W
- Platten M
- Unterberg A
- Uhl M
- Abdollahi A
- Debus J
- Lehner B
- Thomas C
- Hasselblatt M
- Paulus W
- Hartmann C
- Staszewski O
- Prinz M
- Hench J
- Frank S
- Versleijen-Jonkers YMH
- Weidema ME
- Mentzel T
- Griewank K
- de Alava E
- Martin JD
- Gastearena MAI
- Chang KT
- Low SYY
- Cuevas-Bourdier A
- Mittelbronn M
- Mynarek M
- Rutkowski S
- Schuller U
- Mautner VF
- Schittenhelm J
- Serrano J
- Snuderl M
- Buttner R
- Klingebiel T
- Buslei R
- Gessler M
- Wesseling P
- Dinjens WNM
- Brandner S
- Jaunmuktane Z
- Lyskjaer I
- Schirmacher P
- Stenzinger A
- Brors B
- Glimm H
- Heining C
- Tirado OM
- Sainz-Jaspeado M
- Mora J
- Alonso J
- Del Muro XG
- Moran S
- Esteller M
- Benhamida JK
- Ladanyi M
- Wardelmann E
- Antonescu C
- Flanagan A
- Dirksen U
- Hohenberger P
- Baumhoer D
- Hartmann W
- Vokuhl C
- Flucke U
- Petersen I
- Mechtersheimer G
- Capper D
- Jones DTW
- Frohling S
- Pfister SM
- von Deimling A.
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.