A deep neural network based regression model for triglyceride concentrations prediction using epigenome-wide DNA methylation profiles

Thumbnail Image
Islam, Md. M
Tian, Ye
Cheng, Yan
Wang, Yang
Hu, Pingzhao
Journal Title
Journal ISSN
Volume Title
Abstract Background Epigenetic modification has an effect on gene expression under the environmental alteration, but it does not change corresponding genome sequence. DNA methylation (DNAm) is one of the important epigenetic mechanisms. DNAm variations could be used as epigenetic markers to predict and account for the change of many human phenotypic traits, such as cancer, diabetes, and high blood pressure. In this study, we built deep neural network (DNN) regression models to account for interindividual variation in triglyceride concentrations measured at different visits of peripheral blood samples using epigenome-wide DNAm profiles. Results We used epigenome-wide DNAm profiles of before and after medication interventions (called pretreatment and posttreatment, respectively) to predict triglyceride concentrations for peripheral blood draws at visit 2 (using pretreatment data) and at visit 4 (using both pretreatment and posttreatment data). Our experimental results showed that DNN models can predict triglyceride concentrations for blood draws at visit 4 using pretreatment and posttreatment DNAm data more accurately than for blood draws at visit 2 using pretreatment DNAm data. Furthermore, we got the best prediction results when we used pretreatment DNAm data to predict triglyceride concentrations for blood draws at visit 4, which suggests a long-term epigenetic effect on phenotypic traits. We compared the prediction performances of our proposed DNN models with that of support vector machine (SVM). This comparison showed that our DNN models achieved better prediction performance than did SVM. Conclusions We demonstrated the superiority of our proposed DNN models over the SVM model for predicting triglyceride concentrations. This study also suggests that the DNN approach has advantages over other traditional machine-learning methods to model high-dimensional epigenome-wide DNAm data and other genomic data.
BMC Proceedings. 2018 Sep 17;12(Suppl 9):21