MBD-isolated Genome Sequencing provides a high-throughput and comprehensive survey of DNA methylation in the human genome

Abstract

DNA methylation is an epigenetic modification involved in both normal developmental processes and disease states through the modulation of gene expression and the maintenance of genomic organization. Conventional methods of DNA methylation analysis, such as bisulfite sequencing, methylation sensitive restriction enzyme digestion and array-based detection techniques, have major limitations that impede high-throughput genome-wide analysis. We describe a novel technique, MBD-isolated Genome Sequencing (MiGS), which combines precipitation of methylated DNA by recombinant methyl-CpG binding domain of MBD2 protein and sequencing of the isolated DNA by a massively parallel sequencer. We utilized MiGS to study three isogenic cancer cell lines with varying degrees of DNA methylation. We successfully detected previously known methylated regions in these cells and identified hundreds of novel methylated regions. This technique is highly specific and sensitive and can be applied to any biological settings to identify differentially methylated regions at the genomic scale.

Figure 1.

Bisulfite sequencing of newly identified methylated regions. Bisulfite sequencing was performed on (A) peri-centromeric CpG island on chromosome 16, (B) promoter CpG island of PTCHD1 and (C) ZEB1 intronic CpG island in HCT116, DICER^ex5 and DKO cells. Genomic coordinates (NCBI Build 36.1) for the bisulfite sequencing amplicon of chromosome 16 peri-centromeric CpG island are shown. Positions relative to the transcription start site are indicated for the amplicons of PTCHD1 and ZEB1. Each circle represents a CpG dinucleotide with black circles representing methylated cytosines and white ones representing unmethylated cytosines. Each row represents one individual allele sequenced. Rectangles above each cell line represent the non-overlapping 100-bp windows covered by each amplicon. Methylated windows identified by MiGS are shaded in gray while unmethylated windows are in white.

Figure 2.

Sampling curves for HCT116 and DICER^ex5. The curves show the number of 100-bp windows identified as being methylated (y-axis) for a given number of sequences randomly drawn from the entire dataset (x-axis). Blue lines represent sampling curves for HCT116, and red lines correspond to data for DICER^ex5. The solid lines show the results obtained when considering all significantly methylated windows (≥4 reads), while the dash lines represent the results for highly methylated loci (≥10 reads) only. The vertical black line shows the number of reads used in this study.