EpiGe: A cytosine methyl-genotyping PCR-based machine-learning tool for rapid classification of medulloblastoma

Molecular classification of medulloblastoma is critical for the correct treatment of this malignant paediatric brain tumour. The analysis of genome-wide DNA methylation patterns has profoundly improved diagnostic precision and classification of brain tumours. However, the implementation of DNA methylation microarrays in daily clinical practice can be time-consuming, costly and inaccessible for many centres worldwide. We aimed to develop a machine-learning decision support system for rapid and cost-effective prediction of medulloblastoma methylation class directly from quantitative PCR data. Bisulphite converted DNA from 74 samples was hybridized to the Illumina InfiniumMethylation Epic array