Development and Validation of a Novel Placental DNA Methylation Biomarker of Maternal Smoking during Pregnancy in the ECHO Program.
Study Goal
The researchers aimed to develop placental DNA methylation-based biomarkers to classify maternal cigarette smoking during pregnancy (MSDP).
Results Summary
The study found that logistic LASSO regression performed best in classifying MSDP based on placental DNA methylation signatures, with high accuracy in external validation datasets. The placental smoking index (PSI) scores correlated with maternal smoking frequency but not with vitamin C supplementation.
Population
Pregnant women who smoked during pregnancy and their placentas.
Effective Dosage
Not mentioned
Duration
Not mentioned
Interactions
None mentioned
| Intervention | Direction | Endpoint | Population | Dosage | Impact | Claim # |
|---|---|---|---|---|---|---|
maternal cigarette smoking during pregnancy (MSDP) | neutral | health outcomes in infants and children | infants and children | numerous | associated with numerous adverse health outcomes | #1 |
maternal cigarette smoking during pregnancy (MSDP) | neutral | placental DNA methylation (DNAm), placental structure, and function | placentas | - | negative effects | #2 |
logistic LASSO regression | increase | performance in cross-validation testing | - | lowest number of input CpGs | demonstrated the highest performance | #3 |
models developed for the same platform | increase | accuracy in external datasets | external datasets | greatest | accuracy was greatest | #4 |
maternal cigarette smoking during pregnancy (MSDP) | increase | PSI scores | smokers only | - | PSI scores were positively correlated | #5 |
maternal cigarette smoking during pregnancy (MSDP) | increase | maternal plasma cotinine levels | smokers only | - | PSI scores were positively correlated | #6 |
maternal cigarette smoking during pregnancy (MSDP) | increase | self-reported cigarettes per day | smokers only | - | PSI scores were positively correlated | #7 |
placental DNAm-based biomarkers of MSDP | neutral | biomarkers of MSDP | studies of prenatal disease origins | first | developed | #8 |
BACKGROUND: Maternal cigarette smoking during pregnancy (MSDP) is associated with numerous adverse health outcomes in infants and children with potential lifelong consequences. Negative effects of MSDP on placental DNA methylation (DNAm), placental structure, and function are well established. OBJECTIVE: Our aim was to develop biomarkers of MSDP using DNAm measured in placentas ( METHODS: We compared the ability of four machine learning methods [logistic least absolute shrinkage and selection operator (LASSO) regression, logistic elastic net regression, random forest, and gradient boosting machine] to classify MSDP based on placental DNAm signatures. We developed separate models using the complete EPIC array dataset and on the subset of probes also found on the 450K array so that models exist for both platforms. For comparison, we developed a model using CpGs previously associated with MSDP in placenta. For each final model, we used model coefficients and normalized beta values to calculate placental smoking index (PSI) scores for each sample. Final models were validated in two external datasets: the Extremely Low Gestational Age Newborn observational study, RESULTS: Logistic LASSO regression demonstrated the highest performance in cross-validation testing with the lowest number of input CpGs. Accuracy was greatest in external datasets when using models developed for the same platform. PSI scores in smokers only ( DISCUSSION: To our knowledge, we have developed the first placental DNAm-based biomarkers of MSDP with broad utility to studies of prenatal disease origins. https://doi.org/10.1289/EHP13838.