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.

Pediatric low-grade gliomas (pLGG) show heterogeneous responses to MAPK inhibitors (MAPKi) in clinical trials. Thus, more complex stratification biomarkers are needed to identify patients likely to benefit from MAPKi therapy. Here, we identify MAPK-related genes enriched in MAPKi-sensitive cell lines using the GDSC dataset and apply them to calculate class-specific MAPKi sensitivity scores (MSSs) via single-sample gene set enrichment analysis. The MSSs discriminate MAPKi-sensitive and non-sensitive cells in the GDSC dataset and significantly correlate with response to MAPKi in an independent PDX dataset. The MSSs discern gliomas with varying MAPK alterations and are higher in pLGG compared to other pediatric CNS tumors. Heterogenous MSSs within pLGGs with the same MAPK alteration identify proportions of potentially sensitive patients. The MEKi MSS predicts treatment response in a small set of pLGG patients treated with trametinib. High MSSs correlate with a higher immune cell infiltration, with high expression in the microglia compartment in single-cell RNA sequencing data, while low MSSs correlate with low immune infiltration and increased neuronal score. The MSSs represent predictive tools for the stratification of pLGG patients and should be prospectively validated in clinical trials. Our data supports a role for microglia in the response to MAPKi.

The diagnosis of sinonasal tumors is challenging due to a heterogeneous spectrum of various differential diagnoses as well as poorly defined, disputed entities such as sinonasal undifferentiated carcinomas (SNUCs). In this study, we apply a machine learning algorithm based on DNA methylation patterns to classify sinonasal tumors with clinical-grade reliability. We further show that sinonasal tumors with SNUC morphology are not as undifferentiated as their current terminology suggests but rather reassigned to four distinct molecular classes defined by epigenetic, mutational and proteomic profiles. This includes two classes with neuroendocrine differentiation, characterized by IDH2 or SMARCA4/ARID1A mutations with an overall favorable clinical course, one class composed of highly aggressive SMARCB1-deficient carcinomas and another class with tumors that represent potentially previously misclassified adenoid cystic carcinomas. Our findings can aid in improving the diagnostic classification of sinonasal tumors and could help to change the current perception of SNUCs.