Article

Profile analysis and prediction of tissue-specific CpG island methylation classes

Department of Molecular Biophysics, DKFZ, German Cancer Research Center, Heidelberg, Germany.
BMC Bioinformatics (Impact Factor: 2.67). 05/2009; 10(1):116. DOI: 10.1186/1471-2105-10-116
Source: PubMed

ABSTRACT The computational prediction of DNA methylation has become an important topic in the recent years due to its role in the epigenetic control of normal and cancer-related processes. While previous prediction approaches focused merely on differences between methylated and unmethylated DNA sequences, recent experimental results have shown the presence of much more complex patterns of methylation across tissues and time in the human genome. These patterns are only partially described by a binary model of DNA methylation. In this work we propose a novel approach, based on profile analysis of tissue-specific methylation that uncovers significant differences in the sequences of CpG islands (CGIs) that predispose them to a tissue- specific methylation pattern.
We defined CGI methylation profiles that separate not only between constitutively methylated and unmethylated CGIs, but also identify CGIs showing a differential degree of methylation across tissues and cell-types or a lack of methylation exclusively in sperm. These profiles are clearly distinguished by a number of CGI attributes including their evolutionary conservation, their significance, as well as the evolutionary evidence of prior methylation. Additionally, we assess profile functionality with respect to the different compartments of protein coding genes and their possible use in the prediction of DNA methylation.
Our approach provides new insights into the biological features that determine if a CGI has a functional role in the epigenetic control of gene expression and the features associated with CGI methylation susceptibility. Moreover, we show that the ability to predict CGI methylation is based primarily on the quality of the biological information used and the relationships uncovered between different sources of knowledge. The strategy presented here is able to predict, besides the constitutively methylated and unmethylated classes, two more tissue specific methylation classes conserving the accuracy provided by leading binary methylation classification methods.

Download full-text

Full-text

Available from: Coral del Val, Sep 03, 2015
0 Followers
 · 
198 Views
 · 
59 Downloads
  • Source
    • "It has been shown that the CpG island methylation status is correlated with the following features: CpG island specific attributes (e.g. length, GC content, GC observed/expected ratio) [14,21,3], patterns of DNA sequence composition [4,21,10], patterns of predicted DNA structure [14,10], patterns of conserved TFBS's and conserved elements [14], as well as the methylation status of nearby histones [13]. Computational prediction of CpG island methylation status based on the statistical properties of these features could render fairly reasonable accuracy (e.g., ~89% [4,13]). "
    Hao Zheng · Hongwei Wu · Jinping Li · Shi-Wen Jiang
    [Show abstract] [Hide abstract]
    ABSTRACT: DNA methylation is an inheritable chemical modification of cytosine, and represents one of the most important epigenetic events. Computational prediction of the DNA methylation status can be employed to speed up the genome-wide methylation profiling, and to identify the key features that are correlated with various methylation patterns. Here, we develop CpGIMethPred, the support vector machine-based models to predict the methylation status of the CpG islands in the human genome under normal conditions. The features for prediction include those that have been previously demonstrated effective (CpG island specific attributes, DNA sequence composition patterns, DNA structure patterns, distribution patterns of conserved transcription factor binding sites and conserved elements, and histone methylation status) as well as those that have not been extensively explored but are likely to contribute additional information from a biological point of view (nucleosome positioning propensities, gene functions, and histone acetylation status). Statistical tests are performed to identify the features that are significantly correlated with the methylation status of the CpG islands, and principal component analysis is then performed to decorrelate the selected features. Data from the Human Epigenome Project (HEP) are used to train, validate and test the predictive models. Specifically, the models are trained and validated by using the DNA methylation data obtained in the CD4 lymphocytes, and are then tested for generalizability using the DNA methylation data obtained in the other 11 normal tissues and cell types. Our experiments have shown that (1) an eight-dimensional feature space that is selected via the principal component analysis and that combines all categories of information is effective for predicting the CpG island methylation status, (2) by incorporating the information regarding the nucleosome positioning, gene functions, and histone acetylation, the models can achieve higher specificity and accuracy than the existing models while maintaining a comparable sensitivity measure, (3) the histone modification (methylation and acetylation) information contributes significantly to the prediction, without which the performance of the models deteriorate, and, (4) the predictive models generalize well to different tissues and cell types. The developed program CpGIMethPred is freely available at http://users.ece.gatech.edu/~hzheng7/CGIMetPred.zip.
    BMC Medical Genomics 01/2013; 6(1). DOI:10.1186/1755-8794-6-S1-S13 · 3.91 Impact Factor
  • Source
    • "By using "ultradeep" sequencing data from Taylor et al [19], we demonstrated that CpG flanking sequences can be used to model methylation susceptible CpG sites [20]. Finally, Previti et al analyzed tissue-specific CpG island methylation status, in terms of profiles created by probabilistically combining two sources of independent clusters (clusters from methylation data in 12 tissues and clusters from CGIs attributes) to demonstrate the predictive power of their method with a decision tree classifier [21]. Those investigators categorized profiles into four classes: constitutive unmethylated, constitutive methylated, unmethylated in sperm, and differentially methylated [21]. "
    [Show abstract] [Hide abstract]
    ABSTRACT: DNA methylation is essential for normal development and differentiation and plays a crucial role in the development of nearly all types of cancer. Aberrant DNA methylation patterns, including genome-wide hypomethylation and region-specific hypermethylation, are frequently observed and contribute to the malignant phenotype. A number of studies have recently identified distinct features of genomic sequences that can be used for modeling specific DNA sequences that may be susceptible to aberrant CpG methylation in both cancer and normal cells. Although it is now possible, using next generation sequencing technologies, to assess human methylomes at base resolution, no reports currently exist on modeling cell type-specific DNA methylation susceptibility. Thus, we conducted a comprehensive modeling study of cell type-specific DNA methylation susceptibility at three different resolutions: CpG dinucleotides, CpG segments, and individual gene promoter regions. Using a k-mer mixture logistic regression model, we effectively modeled DNA methylation susceptibility across five different cell types. Further, at the segment level, we achieved up to 0.75 in AUC prediction accuracy in a 10-fold cross validation study using a mixture of k-mers. The significance of these results is three fold: 1) this is the first report to indicate that CpG methylation susceptible "segments" exist; 2) our model demonstrates the significance of certain k-mers for the mixture model, potentially highlighting DNA sequence features (k-mers) of differentially methylated, promoter CpG island sequences across different tissue types; 3) as only 3 or 4 bp patterns had previously been used for modeling DNA methylation susceptibility, ours is the first demonstration that 6-mer modeling can be performed without loss of accuracy.
    BMC Bioinformatics 03/2012; 13 Suppl 3(Suppl 3):S15. DOI:10.1186/1471-2105-13-S3-S15 · 2.67 Impact Factor
  • Source
    • "Note, however, that CpGcluster strict set reaches the highest specificity but the lowest sensitivity. Interestingly, a recent study [29] also emphasizes that the CpGcluster p-value is a key attribute for distinguishing between constitutively methylated and unmethylated CGIs. "
    [Show abstract] [Hide abstract]
    ABSTRACT: Unmethylated stretches of CpG dinucleotides (CpG islands) are an outstanding property of mammal genomes. Conventionally, these regions are detected by sliding window approaches using %G + C, CpG observed/expected ratio and length thresholds as main parameters. Recently, clustering methods directly detect clusters of CpG dinucleotides as a statistical property of the genome sequence. We compare sliding-window to clustering (i.e. CpGcluster) predictions by applying new ways to detect putative functionality of CpG islands. Analyzing the co-localization with several genomic regions as a function of window size vs. statistical significance (p-value), CpGcluster shows a higher overlap with promoter regions and highly conserved elements, at the same time showing less overlap with Alu retrotransposons. The major difference in the prediction was found for short islands (CpG islets), often exclusively predicted by CpGcluster. Many of these islets seem to be functional, as they are unmethylated, highly conserved and/or located within the promoter region. Finally, we show that window-based islands can spuriously overlap several, differentially regulated promoters as well as different methylation domains, which might indicate a wrong merge of several CpG islands into a single, very long island. The shorter CpGcluster islands seem to be much more specific when concerning the overlap with alternative transcription start sites or the detection of homogenous methylation domains. The main difference between sliding-window approaches and clustering methods is the length of the predicted islands. Short islands, often differentially methylated, are almost exclusively predicted by CpGcluster. This suggests that CpGcluster may be the algorithm of choice to explore the function of these short, but putatively functional CpG islands.
    BMC Genomics 05/2010; 11(1, article 327):327. DOI:10.1186/1471-2164-11-327 · 4.04 Impact Factor
Show more