Computational prediction of methylation status in human genomic sequences

Rajdeep Das, Nevenka Dimitrova, Zhenyu Xuan, Robert A. Rollins, Fatemah Haghighi, John R. Edwards, Jingyue Ju, Timothy H. Bestor, Michael Q. Zhang

Research output: Contribution to journalArticle

112 Scopus citations

Abstract

Epigenetic effects in mammals depend largely on heritable genomic methylation patterns. We describe a computational pattern recognition method that is used to predict the methylation landscape of human brain DNA. This method can be applied both to CpG islands and to non-CpG island regions. It computes the methylation propensity for an 800-bp region centered on a CpG dinucleotide based on specific sequence features within the region. We tested several classifiers for classification performance, including K means clustering, linear discriminant analysis, logistic regression, and support vector machine. The best performing classifier used the support vector machine approach. Our program (called HDFINDER) presently has a prediction accuracy of 86%, as validated with CpG regions for which methylation status has been experimentally determined. Using HDFINDER, we have depicted the entire genomic methylation patterns for all 22 human autosomes.

Original languageEnglish
Pages (from-to)10713-10716
Number of pages4
JournalProceedings of the National Academy of Sciences of the United States of America
Volume103
Issue number28
DOIs
StatePublished - Jul 11 2006

Keywords

  • CpG islands
  • DNA methylation
  • Epigenomics
  • Methylation prediction

Fingerprint Dive into the research topics of 'Computational prediction of methylation status in human genomic sequences'. Together they form a unique fingerprint.

  • Cite this