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

• Published in: BMC genomics Vol. 19; no. 1; p. 390
• Main Authors: Zou, Luli S, Erdos, Michael R, Taylor, D Leland, Chines, Peter S, Varshney, Arushi, Parker, Stephen C J, Collins, Francis S, Didion, John P
• Format: Journal Article
• Language: English
• Published: England BioMed Central Ltd 23-05-2018; BioMed Central; BMC
• Subjects: Accuracy; Adipose; Algorithms; Analysis; Bisulfite; Computational Biology - methods; Deoxyribonucleic acid; Diabetes; Disease; DNA; DNA methylation; DNA Methylation - drug effects; DNA sequencing; EPIC; Epigenetic inheritance; Epigenetics; Gene expression; Genetic aspects; Genomes; Genomics; High-Throughput Nucleotide Sequencing; Human tissues; Humans; Imputation; Methodology; Methylation; Musculoskeletal system; Neural networks; Nucleotide sequencing; Predictions; Preprocessing; Stem cells; Sulfites; Sulfites - pharmacology; Tissue engineering; Transcription factors; Whole Genome Sequencing; Whole-genome bisulfite sequencing (WGBS); XGBoost; Adipose; Whole-genome bisulfite sequencing (WGBS); EPIC; XGBoost; DNA methylation; Imputation; Pancreatic islets; Skeletal muscle
• ISSN: 1471-2164; 1471-2164
• DOI: 10.1186/s12864-018-4766-y

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