Skip Navigation

Publication Detail

Title: Epigenome-wide cross-tissue predictive modeling and comparison of cord blood and placental methylation in a birth cohort.

Authors: De Carli, Margherita M; Baccarelli, Andrea A; Trevisi, Letizia; Pantic, Ivan; Brennan, Kasey Jm; Hacker, Michele R; Loudon, Holly; Brunst, Kelly J; Wright, Robert O; Wright, Rosalind J; Just, Allan C

Published In Epigenomics, (2017 Mar)

Abstract: We compared predictive modeling approaches to estimate placental methylation using cord blood methylation.We performed locus-specific methylation prediction using both linear regression and support vector machine models with 174 matched pairs of 450k arrays.At most CpG sites, both approaches gave poor predictions in spite of a misleading improvement in array-wide correlation. CpG islands and gene promoters, but not enhancers, were the genomic contexts where the correlation between measured and predicted placental methylation levels achieved higher values. We provide a list of 714 sites where both models achieved an R2 ≥0.75.The present study indicates the need for caution in interpreting cross-tissue predictions. Few methylation sites can be predicted between cord blood and placenta.

PubMed ID: 28234020 Exiting the NIEHS site

MeSH Terms: CpG Islands; DNA Methylation*; Enhancer Elements, Genetic; Epigenesis, Genetic*; Female; Fetal Blood/metabolism*; Genome, Human*; Humans; Models, Genetic*; Placenta/metabolism*; Pregnancy; Promoter Regions, Genetic; Support Vector Machine

Back
to Top