Affinity capture of DNA methylation combined with high-throughput sequencing strikes a good balancebetween the high cost of whole genome bisulfite sequencing and the low coverage of methylationarrays. We present BayMeth, an empirical Bayes approach that uses a fully methylated control sampleto transform observed read counts into regional methylation levels. In our model, inefficient capturecan readily be distinguished from low methylation levels. BayMeth improves on existing methods,allows explicit modeling of copy number variation, and offers computationally-efficient analyticalmean and variance estimators. BayMeth is available in the Repitools Bioconductor package.