PretiMeth: precise prediction models for DNA methylation based on single methylation mark
Open Access
- 15 May 2020
- journal article
- research article
- Published by Springer Science and Business Media LLC in BMC Genomics
- Vol. 21 (1), 1-15
- https://doi.org/10.1186/s12864-020-6768-9
Abstract
The computational prediction of methylation levels at single CpG resolution is promising to explore the methylation levels of CpGs uncovered by existing array techniques, especially for the 450 K beadchip array data with huge reserves. General prediction models concentrate on improving the overall prediction accuracy for the bulk of CpG loci while neglecting whether each locus is precisely predicted. This leads to the limited application of the prediction results, especially when performing downstream analysis with high precision requirements. Here we reported PretiMeth, a method for constructing precise prediction models for each single CpG locus. PretiMeth used a logistic regression algorithm to build a prediction model for each interested locus. Only one DNA methylation feature that shared the most similar methylation pattern with the CpG locus to be predicted was applied in the model. We found that PretiMeth outperformed other algorithms in the prediction accuracy, and kept robust across platforms and cell types. Furthermore, PretiMeth was applied to The Cancer Genome Atlas data (TCGA), the intensive analysis based on precise prediction results showed that several CpG loci and genes (differentially methylated between the tumor and normal samples) were worthy for further biological validation. The precise prediction of single CpG locus is important for both methylation array data expansion and downstream analysis of prediction results. PretiMeth achieved precise modeling for each CpG locus by using only one significant feature, which also suggested that our precise prediction models could be probably used for reference in the probe set design when the DNA methylation beadchip update. PretiMeth is provided as an open source tool via https://github.com/JxTang-bioinformatics/PretiMeth.Funding Information
- Sichuan Science and Technology Program (2018HH0149)
- The National Natural Science Foundation of China (61872063)
- Sichuan Province Youth Science and Technology Innovation Team (2015TD0018)
This publication has 56 references indexed in Scilit:
- CpGIMethPred: computational model for predicting methylation status of CpG islands in human genomeBMC Medical Genomics, 2013
- DNA methylation patterns associate with genetic and gene expression variation in HapMap cell linesGenome Biology, 2011
- Megakaryoblastic leukemia protein-1 (MKL1): Increasing evidence for an involvement in cancer progression and metastasisThe International Journal of Biochemistry & Cell Biology, 2010
- Genome-Wide Evolutionary Analysis of Eukaryotic DNA MethylationScience, 2010
- EpiGRAPH: user-friendly software for statistical analysis and prediction of (epi)genomic dataGenome Biology, 2009
- Histone methylation marks play important roles in predicting the methylation status of CpG islandsBiochemical and Biophysical Research Communications, 2008
- JunD is involved in the antiproliferative effect of Δ9-tetrahydrocannabinol on human breast cancer cellsOncogene, 2008
- DNA methylation profiling of human chromosomes 6, 20 and 22Nature Genetics, 2006
- Computational prediction of methylation status in human genomic sequencesProceedings of the National Academy of Sciences of the United States of America, 2006
- Loss of USF transcriptional activity in breast cancer cell linesOncogene, 1999