Dataset Information

Predicting the impact of non-coding variants on DNA methylation.

ABSTRACT: DNA methylation plays a crucial role in the establishment of tissue-specific gene expression and the regulation of key biological processes. However, our present inability to predict the effect of genome sequence variation on DNA methylation precludes a comprehensive assessment of the consequences of non-coding variation. We introduce CpGenie, a sequence-based framework that learns a regulatory code of DNA methylation using a deep convolutional neural network and uses this network to predict the impact of sequence variation on proximal CpG site DNA methylation. CpGenie produces allele-specific DNA methylation prediction with single-nucleotide sensitivity that enables accurate prediction of methylation quantitative trait loci (meQTL). We demonstrate that CpGenie prioritizes validated GWAS SNPs, and contributes to the prediction of functional non-coding variants, including expression quantitative trait loci (eQTL) and disease-associated mutations. CpGenie is publicly available to assist in identifying and interpreting regulatory non-coding variants.

SUBMITTER: Zeng H

PROVIDER: S-EPMC5499808 | biostudies-literature | 2017 Jun

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Predicting the impact of non-coding variants on DNA methylation.

Zeng Haoyang H Gifford David K DK

Nucleic acids research 20170601 11

DNA methylation plays a crucial role in the establishment of tissue-specific gene expression and the regulation of key biological processes. However, our present inability to predict the effect of genome sequence variation on DNA methylation precludes a comprehensive assessment of the consequences of non-coding variation. We introduce CpGenie, a sequence-based framework that learns a regulatory code of DNA methylation using a deep convolutional neural network and uses this network to predict the ...[more]

PMID: 28334830

Similar Datasets

Project description:SummaryInterpreting genetic variants of unknown significance (VUS) is essential in clinical applications of genome sequencing for diagnosis and personalized care. Non-coding variants remain particularly difficult to interpret, despite making up a large majority of trait associations identified in genome-wide association studies (GWAS) analyses. Predicting the regulatory effects of non-coding variants on candidate genes is a key step in evaluating their clinical significance. Here, we develop a machine-learning algorithm, Inference of Connected expression quantitative trait loci (eQTLs) (IRT), to predict the regulatory targets of non-coding variants identified in studies of eQTLs. We assemble datasets using eQTL results from the Genotype-Tissue Expression (GTEx) project and learn to separate positive and negative pairs based on annotations characterizing the variant, gene and the intermediate sequence. IRT achieves an area under the receiver operating characteristic curve (ROC-AUC) of 0.799 using random cross-validation, and 0.700 for a more stringent position-based cross-validation. Further evaluation on rare variants and experimentally validated regulatory variants shows a significant enrichment in IRT identifying the true target genes versus negative controls. In gene-ranking experiments, IRT achieves a top-1 accuracy of 50% and top-3 accuracy of 90%. Salient features, including GC-content, histone modifications and Hi-C interactions are further analyzed and visualized to illustrate their influences on predictions. IRT can be applied to any VUS of interest and each candidate nearby gene to output a score reflecting the likelihood of regulatory effect on the expression level. These scores can be used to prioritize variants and genes to assist in patient diagnosis and GWAS follow-up studies.Availability and implementationCodes and data used in this work are available at https://github.com/miaecle/eQTL_Trees.Supplementary informationSupplementary data are available at Bioinformatics online.

Project description:Deregulated DNA methylation leading to transcriptional inactivation of certain genes occurs frequently in non-small-cell lung cancers (NSCLCs). As well as protein-coding genes, microRNA (miRNA)-coding genes may be targets for methylation in NSCLCs; however, the number of known methylated miRNA genes is still small. Thus, we investigated methylation of miRNA genes in primary tumour (TU) samples and corresponding non-malignant lung tissue (NL) samples of 50 NSCLC patients by using methylated DNA immunoprecipitation followed by custom-designed tiling microarray analyses (MeDIP-chip), and 252 differentially methylated probes between TU samples and NL samples were identified. These probes were annotated, which resulted in the identification of 34 miRNA genes with increased methylation in TU samples. Some of these miRNA genes were already known to be methylated in NSCLCs (e.g. those encoding miR-9-3 and miR-124), but methylation of the vast majority of them was previously unknown. We selected six miRNA genes (those encoding miR-10b, miR-1179, miR-137, miR-572, miR-3150b, and miR-129-2) for gene-specific methylation analyses in TU samples and corresponding NL samples of 104 NSCLC patients, and observed a statistically significant increase in methylation of these genes in TU samples (p?<?0.0001). In silico target prediction of the six miRNAs identified several oncogenic/cell proliferation-promoting factors (e.g. CCNE1 as an miR-1179 target). To investigate whether miR-1179 indeed targets CCNE1, we transfected miR-1179 gene mimics into CCNE1-expressing NSCLC cells, and observed downregulated CCNE1 mRNA expression in these cells as compared with control cells. Similar effects on cyclin E1 expression were seen in western blot analyses. In addition, we found a statistically significant reduction in the growth of NSCLC cells transfected with miR-1179 mimics as compared with control cells. In conclusion, we identified many methylated miRNA genes in NSCLC patients, and found that the miR-1179 gene is a potential tumour cell growth suppressor in NSCLCs. Overall, our findings emphasize the impact of miRNA gene methylation on the pathogenesis of NSCLCs. © 2018 The Authors. The Journal of Pathology published by John Wiley & Sons Ltd on behalf of Pathological Society of Great Britain and Ireland.

Dataset Information

Predicting the impact of non-coding variants on DNA methylation.

Publications

Predicting the impact of non-coding variants on DNA methylation.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets