DNA methylation in repetitive elements (RE) suppresses their mobility and maintains genomic stability, and decreases in it are frequently observed in tumor and/or surrogate tissues. Averaging methylation across RE in the genome is widely used to quantify global methylation. Methylation of RE in humans is considered a surrogate for global DNA methylation. Previous studies of RE methylation and cancer risk are inconsistent. Methylation may vary in specific RE loci and play diverse roles in disease development. Averaging methylation across RE, though offers a bird’s eye view of global methylomic status, may lose significant biological information. We seek an approach that can profile methylation in locus-specific RE. Ambiguous mapping of short reads by and the high cost of current bisulfite sequencing platforms make them impractical for quantifying locus-specific RE methylation, particularly in population studies and clinical trials. Although microarray-based approaches (e.g., Illumina’s Infinium methylation arrays) provide cost-effective and robust genome-wide methylation quantification, the number of interrogated CpGs in RE remains limited. We then developed a random forest-based algorithm (and corresponding R package, REMP) that can accurately predict genome-wide locus-specific RE methylation based on Infinium array profiling data. We validated its prediction performance using alternative sequencing and microarray data. Testing its clinical utility with The Cancer Genome Atlas data demonstrated that our algorithm offers more comprehensively extended locus-specific RE methylation information that can be readily applied to large human studies in a cost-effective manner. Furthermore, regulatory element enrichment and KEGG enrichment analyses revealed that hypomethylated RE in cancer may play a role in transcription activation, potentially impair chromatin stability, and regulate key cancer-related pathways. In addition, we observed a significant positive correlation between intronic locus-specific RE methylation and the host gene expression. Our work reveals the spatial dynamics of DNA methylation in RE across the human genome and its relations to cancer. Our findings may 1) promote RE methylation research in large human population and clinical studies; and 2) drive further investigations on the biological and pathological effects of RE methylation and improve our understanding of the role of global methylation in human diseases, especially cancer.

Last modified

• 04/26/2018

Creator

• Yinan Zheng

DOI

• https://doi.org/10.21985/N29D6Q

Subject

• Health Sciences Integrated PhD Program

Keyword

• Repetitive elements
• Cancer
• Machine learning
• DNA methylation

Date created

• 2017-01-01

Resource type

• Dissertation

Rights statement

• In Copyright