BoostMe accurately predicts DNA methylation values in whole-genome bisulfite sequencing of multiple human tissues

Luli S Zou; Michael R Erdos; D Leland Taylor; Peter S Chines; Arushi Varshney; McDonnell Genome Institute; Stephen C J Parker; Francis S Collins; John P Didion

doi:10.1186/s12864-018-4766-y

BoostMe accurately predicts DNA methylation values in whole-genome bisulfite sequencing of multiple human tissues

BMC Genomics. 2018 May 23;19(1):390. doi: 10.1186/s12864-018-4766-y.

Authors

Luli S Zou¹, Michael R Erdos¹, D Leland Taylor^{1

2}, Peter S Chines¹, Arushi Varshney³; McDonnell Genome Institute; Stephen C J Parker^{3

4}, Francis S Collins⁵, John P Didion¹

Affiliations

¹ National Human Genome Research Institute, National Institutes of Health, Bethesda, MD, 20892, USA.
² European Molecular Biology Laboratory, European Bioinformatics Institute, Wellcome Genome Campus, Hinxton, Cambridgeshire, UK.
³ Department of Human Genetics, University of Michigan, Ann Arbor, MI, 48109, USA.
⁴ Department of Computational Medicine and Bioinformatics, University of Michigan, Ann Arbor, MI, 48109, USA.
⁵ National Human Genome Research Institute, National Institutes of Health, Bethesda, MD, 20892, USA. collinsf@od.nih.gov.

Abstract

Background: Bisulfite sequencing is widely employed to study the role of DNA methylation in disease; however, the data suffer from biases due to coverage depth variability. Imputation of methylation values at low-coverage sites may mitigate these biases while also identifying important genomic features associated with predictive power.

Results: Here we describe BoostMe, a method for imputing low-quality DNA methylation estimates within whole-genome bisulfite sequencing (WGBS) data. BoostMe uses a gradient boosting algorithm, XGBoost, and leverages information from multiple samples for prediction. We find that BoostMe outperforms existing algorithms in speed and accuracy when applied to WGBS of human tissues. Furthermore, we show that imputation improves concordance between WGBS and the MethylationEPIC array at low WGBS depth, suggesting improved WGBS accuracy after imputation.

Conclusions: Our findings support the use of BoostMe as a preprocessing step for WGBS analysis.

Keywords: Adipose; DNA methylation; EPIC; Imputation; Pancreatic islets; Skeletal muscle; Whole-genome bisulfite sequencing (WGBS); XGBoost.

MeSH terms

Algorithms
Computational Biology / methods*
DNA Methylation / drug effects*
High-Throughput Nucleotide Sequencing
Humans
Sulfites / pharmacology*
Whole Genome Sequencing*

Substances

Sulfites
hydrogen sulfite

Abstract

MeSH terms

Substances

Grants and funding