CimpleG: Finding simple CpG methylation signatures

Abstract

DNA methylation (DNAm) at specific CG dinucleotides (CpG sites) in the genome provides powerful biomarkers for a wide range of applications, such as epigenetic clocks, cell type deconvolution, and stratification of cancer patients. Such epigenetic signatures are usually based on multivariate approaches that require hundreds of DNAm sites for predictions. In contrast, targeted assays for only a few selected CpGs may facilitate faster turnover, better standardisation, and reduced costs. Here, we propose a computational framework named CimpleG for the detection of small CpG methylation signatures, exemplarily used for cell type classification. We evaluate the performance of CimpleG and competing methods on two distinct datasets in regard to the cell-type classification of blood cells and of other somatic cells. Furthermore, we evaluate how well these classifiers perform cellular deconvolution of blood cell mixtures. We show that CimpleG is both time efficient and performs as well as Elastic Net, while basing its prediction on a single DNAm site per cell type. Altogether, CimpleG provides a complete computational framework for the delineation of DNAm signatures and cellular deconvolution.