Novel approaches to the prediction of CpG islands and their methylation status

ABSTRACT

A DNA sequence can be described as a string composed of four symbols: A, T, C and G, each representing a chemically distinct nucleotide molecule. Combinations of two nucleotides are called dinucleotides and CpG islands represent regions of a DNA sequence, certain substrings, which are enriched in CpG dinucleotides (C followed by G). CpG islands represent an enigmatic feature of vertebrate genomes. They a critical target for transcriptional control, since methylation of these CpG islands leads to structural changes in the DNA that stops the expression of any associated gene. The factors that provoke or impede methylation are currently unknown. In general, the maintenance of a particular pattern of methylated CpG dinucleotides represents a critical regulatory system during a host of normal developmental processes, but the erroneous methylation of CpG islands and the resulting gene-silencing can lead to the development of cancer. We present here a novel unsupervised machine learning method that is capable of distinguishing biologically significant classes of CpG islands, including the separation of methylated and unmethylated CpG islands. This method represents an important novel approach that will aid in the computational prediction of methylation, which is commonly used in the preselection of worthwhile sequences for methylation experiments.

REFERENCES

• 1: F. Antequera, J. Boyes, and A. Bird, "High levels of de novo methylation and altered chromatin structure at CpG islands in cell lines," Cell, vol. 62, pp. 503--14, 1990.
• 2: A. P. Bird, "DNA methylation patterns and epigenetic memory," Genes Dev, vol. 16, pp. 6--21, 2002.
• 3: A. P. Bird, "CpG-rich islands and the function of DNA methylation," Nature, vol. 321, pp. 209--13, 1986.
• 4: J. Sved and A. Bird, "The expected equilibrium of the CpG dinucleotide in vertebrate genomes under a mutation model," Proc Natl Acad Sci USA, vol. 87, pp. 4692--6, 1990.
• 5: R. Jaenisch and A. Bird, "Epigenetic regulation of gene expression: how the genome integrates intrinsic and environmental signals," Nat Genet, vol. 33 Suppl, pp. 245--54, Mar 2003.
• 6: F. Antequera, "Structure, function and evolution of CpG island promoters," Cell Mol Life Sci, vol. 60, pp. 1647--58, 2003.
• 7: S. Saxonov, P. Berg, and D. L. Brutlag, "A genome-wide analysis of CpG dinucleotides in the human genome distinguishes two distinct classes of promoters," Proc Natl Acad Sci USA, vol. 103, pp. 1412--7, 2006.
• 8: K. L. Arney and A. G. Fisher, "Epigenetic aspects of differentiation," J Cell Sci, vol. 117, pp. 4355--63, Sep 1 2004.
• 9: W. Reik, W. Dean, and J. Walter, "Epigenetic reprogramming in mammalian development," Science, vol. 293, pp. 1089--93, Aug 10 2001.
• 10: E. Heard, "Recent advances in X-chromosome inactivation," Current Opinion in Cell Biology, vol. 16, pp. 247--255, 2004.
• 11: J. A. Yoder, C. P. Walsh, and T. H. Bestor, "Cytosine methylation and the ecology of intragenomic parasites," Trends in Genetics, vol. 13, pp. 335--340, 1997.
• 12: S. B. Baylin, M. Esteller, M. R. Rountree, K. E. Bachman, K. Schuebel, and J. G. Herman, "Aberrant patterns of DNA methylation, chromatin formation and gene expression in cancer," Hum Mol Genet, vol. 10, pp. 687--92, 2001.
• 13: M. Esteller, P. G. Corn, S. B. Baylin, and J. G. Herman, "A gene hypermethylation profile of human cancer," Cancer Res, vol. 61, pp. 3225--9, 2001.
• 14: J. P. Issa, "CpG island methylator phenotype in cancer," Nat Rev Cancer, vol. 4, pp. 988--93, Dec 2004.
• 15: Fang Fang , Shicai Fan , Xuegong Zhang , Michael Q. Zhang, Predicting methylation status of CpG islands in the human brain, Bioinformatics, v.22 n.18, p.2204-2209, September 2006 [doi>10.1093/bioinformatics/btl377]
• 16: Y. Yamada, H. Watanabe, F. Miura, H. Soejima, M. Uchiyama, T. Iwasaka, T. Mukai, Y. Sakaki, and T. Ito, "A comprehensive analysis of allelic methylation status of CpG islands on human chromosome 21q," Genome Res, vol. 14, pp. 247--66, Feb 2004.
• 17: C. Bock, M. Paulsen, S. Tierling, T. Mikeska, T. Lengauer, and J. Walter, "CpG island methylation in human lymphocytes is highly correlated with DNA sequence, repeats, and predicted DNA structure," PLoS Genet, vol. 2, p. e26, Mar 2006.
• 18: R. Das, N. Dimitrova, Z. Xuan, R. A. Rollins, F. Haghighi, J. R. Edwards, J. Ju, T. H. Bestor, and M. Q. Zhang, "Computational prediction of methylation status in human genomic sequences," Proc Natl Acad Sci U S A, vol. 103, pp. 10713--6, Jul 11 2006.
• 19: M. Hackenberg, C. Previti, P. Luque-Escamilla, P. Carpena, J. Martinez-Aroza, and J. Oliver, "CpGcluster: a distance-based algorithm for CpG-island detection," BMC Bioinformatics, vol. 7, p. 446, 2006.
• 20: V. K. Rakyan, T. Hildmann, K. L. Novik, J. Lewin, J. Tost, A. V. Cox, T. D. Andrews, K. L. Howe, T. Otto, A. Olek, J. Fischer, I. G. Gut, K. Berlin, and S. Beck, "DNA methylation profiling of the human major histocompatibility complex: a pilot study for the human epigenome project," PLoS Biol, vol. 2, p. e405, Dec 2004.
• 21: D. R. Maglott, K. S. Katz, H. Sicotte, and K. D. Pruitt, "NCBI's LocusLink and RefSeq {http://www.ncbi.nih.gov/RefSeq}," Nucleic Acids Res, vol. 28, pp. 126--8, Jan 1 2000.
• 22: D. Karolchik, A. S. Hinrichs, T. S. Furey, K. M. Roskin, C. W. Sugnet, D. Haussler, and W. J. Kent, "The UCSC Table Browser data retrieval tool {http://genome.ucsc.edu}" Nucleic Acids Res, vol. 32, pp. D493--6, Jan 1 2004.
• 23: L. Ponger, L. Duret, and D. Mouchiroud, "Determinants of CpG islands: expression in early embryo and isochore structure," Genome Res, vol. 11, pp. 1854--60, Nov 2001.
• 24: A. Siepel, G. Bejerano, J. S. Pedersen, A. S. Hinrichs, M. Hou, K. Rosenbloom, H. Clawson, J. Spieth, L. W. Hillier, S. Richards, G. M. Weinstock, R. K. Wilson, R. A. Gibbs, W. J. Kent, W. Miller, and D. Haussler, "Evolutionarily conserved elements in vertebrate, insect, worm, and yeast genomes," Genome Res, vol. 15, pp. 1034--50, 2005.
• 25: J. C. Bezdek, "Pattern Analysis," in Handbook of Fuzzy Computation, W. Pedrycz, P. P. Bonissone, and E. H. Ruspini, Eds. Bristol: Institute of Physics, 1998, pp. F6.1.1--F6.6.20.
• 26: A. P. Gasch and M. B. Eisen, "Exploring the conditional coregulation of yeast gene expression through fuzzy k-means clustering," Genome Biol, vol. 3, p. RESEARCH0059, Oct 10 2002.
• 27: Thomas M. Mitchell, Machine Learning, McGraw-Hill Higher Education, 1997
• 28: S. Tavazoie, J. D. Hughes, M. J. Campbell, R. J. Cho, and G. M. Church, "Systematic determination of genetic network architecture," Nat Genet, vol. 22, pp. 281--5, Jul 1999.
• 29: G. Saporta, "Probabilits, analyse des donnes et statistiques," Technip, 1996.
• 30: C. L. Wilkins, "Data mining with Spotfire Pro 4.0," Analytical Chemistry, vol. 72, pp. 550a--550a, AUG 1 2000.
• 31: P. Baldi, S. Brunak, Y. Chauvin, C. A. Andersen, and H. Nielsen, "Assessing the accuracy of prediction algorithms for classification: an overview," Bioinformatics, vol. 16, pp. 412--24, May 2000.
• 32: P. Carninci, A. Sandelin, B. Lenhard, S. Katayama, K. Shimokawa, J. Ponjavic, C. A. Semple, M. S. Taylor, P. G. Engstrom, M. C. Frith, A. R. Forrest, W. B. Alkema, S. L. Tan, C. Plessy, R. Kodzius, T. Ravasi, T. Kasukawa, S. Fukuda, M. Kanamori-Katayama, Y. Kitazume, H. Kawaji, C. Kai, M. Nakamura, H. Konno, K. Nakano, S. Mottagui-Tabar, P. Arner, A. Chesi, S. Gustincich, F. Persichetti, H. Suzuki, S. M. Grimmond, C. A. Wells, V. Orlando, C. Wahlestedt, E. T. Liu, M. Harbers, J. Kawai, V. B. Bajic, D. A. Hume, and Y. Hayashizaki, "Genome-wide analysis of mammalian promoter architecture and evolution," Nat Genet, vol. 38, pp. 626--35, 2006.

INDEX TERMS

Keywords:
CpG islands, classification, data mining, methylation, unsupervised learning