Margherita M De Carli1, Andrea A Baccarelli2, Letizia Trevisi3, Ivan Pantic3,4, Kasey Jm Brennan2, Michele R Hacker5,6, Holly Loudon7, Kelly J Brunst8, Robert O Wright1,9, Rosalind J Wright8,9, Allan C Just1,9. 1. Department of Environmental Medicine & Public Health, Icahn School of Medicine at Mount Sinai, New York, NY, USA. 2. Department of Environmental Health Sciences, Mailman School of Public Health, Columbia University, New York, NY, USA. 3. Department of Environmental Health, Harvard TH Chan School of Public Health, Boston, MA, USA. 4. Department of Developmental Neurobiology, National Institute of Perinatology, Mexico City, Mexico. 5. Department of Epidemiology, Harvard TH Chan School of Public Health, Boston, MA, USA. 6. Department of Obstetrics & Gynecology, Beth Israel Deaconess Medical Center, Harvard Medical School, Boston, MA, USA. 7. Department of Obstetrics & Gynecology, Icahn School of Medicine at Mount Sinai, New York, NY, USA. 8. Department of Pediatrics, Icahn School of Medicine at Mount Sinai, New York, NY, USA. 9. Mindich Child Health & Development Institute, Icahn School of Medicine at Mount Sinai, New York, NY, USA.
Abstract
AIM: We compared predictive modeling approaches to estimate placental methylation using cord blood methylation. MATERIALS & METHODS: We performed locus-specific methylation prediction using both linear regression and support vector machine models with 174 matched pairs of 450k arrays. RESULTS: 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. CONCLUSION: The present study indicates the need for caution in interpreting cross-tissue predictions. Few methylation sites can be predicted between cord blood and placenta.
AIM: We compared predictive modeling approaches to estimate placental methylation using cord blood methylation. MATERIALS & METHODS: We performed locus-specific methylation prediction using both linear regression and support vector machine models with 174 matched pairs of 450k arrays. RESULTS: 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. CONCLUSION: The present study indicates the need for caution in interpreting cross-tissue predictions. Few methylation sites can be predicted between cord blood and placenta.
Entities:
Keywords:
450k arrays; DNA methylation; cord blood; epigenetics; methylation prediction; placenta; support vector machine
Authors: Martin J Aryee; Andrew E Jaffe; Hector Corrada-Bravo; Christine Ladd-Acosta; Andrew P Feinberg; Kasper D Hansen; Rafael A Irizarry Journal: Bioinformatics Date: 2014-01-28 Impact factor: 6.937
Authors: Hyang-Min Byun; Kimberly D Siegmund; Fei Pan; Daniel J Weisenberger; Gary Kanel; Peter W Laird; Allen S Yang Journal: Hum Mol Genet Date: 2009-09-23 Impact factor: 6.150
Authors: Georgia Chalfun; Marcelo Martins Reis; Mariana Barros Genuíno de Oliveira; Aline de Araújo Brasil; Margarida Dos Santos Salú; Antônio José Ledo Alves da Cunha; Arnaldo Prata-Barbosa; Maria Clara de Magalhães-Barbosa Journal: Epigenetics Date: 2021-10-01 Impact factor: 4.861
Authors: Anne K Bozack; Elena Colicino; Allan C Just; Robert O Wright; Andrea A Baccarelli; Rosalind J Wright; Alison G Lee Journal: Epigenetics Date: 2021-10-22 Impact factor: 4.861
Authors: Kelly J Brunst; Marco Sanchez-Guerra; Yueh-Hsiu Mathilda Chiu; Ander Wilson; Brent A Coull; Itai Kloog; Joel Schwartz; Kasey J Brennan; Michelle Bosquet Enlow; Robert O Wright; Andrea A Baccarelli; Rosalind J Wright Journal: Environ Int Date: 2017-12-15 Impact factor: 9.621
Authors: Sarah Lyon-Caen; Valérie Siroux; Johanna Lepeule; Philippe Lorimier; Pierre Hainaut; Pascal Mossuz; Joane Quentin; Karine Supernant; David Meary; Laurence Chaperot; Sam Bayat; Flemming Cassee; Sarah Valentino; Anne Couturier-Tarrade; Delphine Rousseau-Ralliard; Pascale Chavatte-Palmer; Claire Philippat; Isabelle Pin; Rémy Slama; The Sepages Study Group Journal: Int J Environ Res Public Health Date: 2019-10-14 Impact factor: 3.390
Authors: Michelle Bosquet Enlow; Carter R Petty; Michele R Hacker; Heather H Burris Journal: Psychoneuroendocrinology Date: 2020-11-04 Impact factor: 4.905