Nucleosome positioning plays an important role in predicting the methylation status of CpG islands

CpG island methylation is highly correlated with epigenetic gene control during mammalian development. The majority of CpG islands are normally unmethylated, but in some specifically pathological situations some of the CpG islands are prone to become methylated. Current methods about prediction of DNA methylation utilized DNA sequence features, transcription factor binding site features and histone methylation mark features. In this study, we used SVM to predict the methylation status of CpG islands from human Chromosome 22 and improved the accuracy to 90.6%. We not only used 4 DNA sequence features such as sequence length, CG ratio, C+G% content, CpG frequency and 39 transcription factor binding sites features, but also added nucleosome position features. Our results support the view that nucleosomes are preferentially targeted by DNA methyltransferases and imply that nucleosome-bound DNA regions are more prone to become methylated than flanking regions. At last, we explain why the histone methylation marks can predict DNA methylation status.

[1]  Alexander E. Kel,et al.  TRANSFAC®: transcriptional regulation, from patterns to profiles , 2003, Nucleic Acids Res..

[2]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[3]  M. Ehrlich,et al.  Amount and distribution of 5-methylcytosine in human DNA from different types of tissues of cells. , 1982, Nucleic acids research.

[4]  A. Bird,et al.  Number of CpG islands and genes in human and mouse. , 1993, Proceedings of the National Academy of Sciences of the United States of America.

[5]  H. Prydz,et al.  CpG islands as gene markers in the human genome. , 1992, Genomics.

[6]  W. Doerfler,et al.  DNA methylation and gene activity. , 1983, Annual review of biochemistry.

[7]  Dustin E. Schones,et al.  Dynamic Regulation of Nucleosome Positioning in the Human Genome , 2008, Cell.

[8]  A. Bird.  CpG-rich islands and the function of DNA methylation , 1986, Nature.

[9]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[10]  Jun S. Song,et al.  Identifying Positioned Nucleosomes with Epigenetic Marks in Human from ChIP-Seq , 2008, BMC Genomics.

[11]  Michael Q. Zhang,et al.  Histone methylation marks play important roles in predicting the methylation status of CpG islands. , 2008, Biochemical and biophysical research communications.

[12]  Terrence S. Furey,et al.  The UCSC Genome Browser Database , 2003, Nucleic Acids Res..

[13]  P. Cochat,et al.  Et al , 2008, Archives de pediatrie : organe officiel de la Societe francaise de pediatrie.

[14]  Manoj Bhasin,et al.  Prediction of methylated CpGs in DNA sequences using a support vector machine , 2005, FEBS letters.

[15]  M. Frommer,et al.  CpG islands in vertebrate genomes. , 1987, Journal of molecular biology.

[16]  Antony V. Cox,et al.  Open access, freely available online PLoS BIOLOGY DNA Methylation Profiling of the Human Major Histocompatibility Complex: A Pilot Study , 2022 .

[17]  Thomas Lengauer,et al.  CpG Island Methylation in Human Lymphocytes Is Highly Correlated with DNA Sequence, Repeats, and Predicted DNA Structure , 2006, PLoS genetics.

[18]  Xavier Messeguer,et al.  PROMO: detection of known transcription regulatory elements using species-tailored searches , 2002, Bioinform..

[19]  J. Herman,et al.  Gene silencing in cancer in association with promoter hypermethylation. , 2003, The New England journal of medicine.

[20]  D. Hanahan,et al.  The Hallmarks of Cancer , 2000, Cell.

[21]  Éric Renault,et al.  MethDB - a public database for DNA methylation data , 2001, Nucleic Acids Res..

[22]  Peter A. Jones,et al.  The fundamental role of epigenetic events in cancer , 2002, Nature Reviews Genetics.