Project description: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 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, whereas tumors that are driven by SMARCB1-deficiency and tumors that represent previously misclassified adenoid cystic carcinomas are highly aggressive. Our findings have the potential to dramatically improve the diagnostic classification of sinonasal tumors and will fundamentally change the current perception of SNUCs.
Project description:The histopathological diagnosis of sinonasal tumors is challenging as it encompasses a heterogeneous spectrum of various differential diagnoses as well as poorly defined, disputed entities such as sinonasal undifferentiated carcinomas (SNUCs). In this study, we show that a machine learning algorithm based on DNA methylation is able to classify sinonasal tumors with clinical-grade reliability. We further show that tumors with SNUC morphology are not as undifferentiated as their current terminology suggests, but can be assigned to four molecular classes defined by distinct epigenic, mutational and proteomic profiles. This includes two classes with neuroendocrine differentiation, characterized by IDH2 or SWI/SNF chromatin remodeling complex mutations and overall favorable clinical course, highly aggressive tumors that are driven by SMARCB1-deficiency and tumors that represent previously misclassified adenoid-cystic carcinomas. Our findings have the potential to dramatically improve the diagnostic of challenging sinonasal tumors and could fundamentally change the current perception of SNUCs.
Project description:Cerebrospinal fluid (CSF) liquid biopsies serve as a rich source of tumor-derived cell-free DNA (cfDNA) for evaluating patients with central nervous system (CNS) tumors. However, challenges stemming from trace cfDNA yields and low mutational burden have hindered sensitivity, whereas first-generation clinical assays have relied on genetic alterations as biomarkers. Leveraging the diagnostic utility of DNA methylation classification in CNS tumors, we developed M-PACT (Methylation-based Predictive Algorithm for CNS Tumors), a robust deep neural network that accurately classifies tumors from sub-nanogram input cfDNA methylomes acquired through enzymatic methylation sequencing. In addition to tumor classification, this workflow enables methylation-based cellular deconvolution and sensitive copy number variation (CNV) detection. We benchmark our methodology in pediatric CNS embryonal tumors and further demonstrate accurate classification of intra-operative CSF, balanced tumor genomes, and secondary malignancies. Altogether, we provide a blueprint for CNS tumor classification from low input cfDNA methylomes, motivating prospective validation for future clinical implementation.
