Person:

Hovestadt, Volker

Medulloblastoma is a malignant childhood cerebellar tumour comprised of distinct molecular subgroups. Whereas genomic characteristics of these subgroups are well defined, the extent to which cellular diversity underlies their divergent biology and clinical behaviour remains largely unexplored. We used single-cell transcriptomics to investigate intra- and inter-tumoural heterogeneity in twenty-five medulloblastomas spanning all molecular subgroups. WNT, SHH, and Group 3 tumours comprised subgroup-specific undifferentiated and differentiated neuronal-like malignant populations, whereas Group 4 tumours were exclusively comprised of differentiated neuronal-like neoplastic cells. SHH tumours closely resembled granule neurons of varying differentiation states that correlated with patient age. Group 3 and Group 4 tumours exhibited a developmental trajectory from primitive progenitor-like to more mature neuronal-like cells, whose relative proportions distinguished these subgroups. Cross-species transcriptomics defined distinct glutamatergic populations as putative cells-of-origin for SHH and Group 4 subtypes. Collectively, these data provide novel insights into the cellular and developmental states underlying subtype-specific medulloblastoma biology.

DNA methylation data-based personalized cancer diagnostics has emerged as the state-of-the-art in molecular pathology, still, we lack standards for choosing statistical methods with regard to well-calibrated probability estimates for these typically highly multiclass classification tasks. To support this choice, we evaluated well-established machine learning (ML) classifiers in combination with post-processing algorithms and developed ML-workflows that allow for unbiased class probability estimation including random forests (RF), elastic net (ELNET), support vector machines (SVM) and boosted trees. Calibrators included ridge penalized multinomial logistic regression (MR) and Platt scaling by fitting logistic regression (LR) and Firth’s penalized LR. We compared these workflows to the state-of-the-art on a recently published brain tumor 450k DNA methylation cohort of 2801 samples with 91 diagnoses using a 5 × 5-fold nested cross-validation scheme. Model fits were assessed with a comprehensive panel of performance metrics. ELNET was the top stand-alone classifier with best graphical calibration profiles. Best overall two-stage workflow was MR-calibrated SVM with linear kernels closely followed by ridge-calibrated tuned RF. For calibration MR was the most effective regardless of the primary classifier. This work provides valuable guidance on choosing ML-workflows, their tuning and hyperparameter settings with reproducible protocols in the open-source R language to generate well-calibrated class probability estimates for precision medicine using DNA methylation data. Computation times vary depending on the ML-algorithm from <15mins to 5d using multi-core desktop PCs. Detailed R scripts are freely available on GitHub.