MethPriorGCN: a deep learning tool for inferring DNA methylation prior knowledge and guiding personalized medicine

Abstract

DNA methylation plays a crucial role in human diseases pathogenesis. Substantial experimental evidence from clinical and biological studies has confirmed numerous methylation-disease associations, which provide valuable prior knowledge for advancing precision medicine through biomarker discovery and disease subtyping. To systematically mine reliable methylation prior knowledge from known DNA methylation-disease associations and develop robust computational methods for precision medicine applications, we propose MethPriorGCN. By integrating layer attention mechanisms and feature weighting mechanisms, MethPriorGCN not only identified reliable methylation digital biomarkers but also achieved superior disease subtype classification accuracy.

Keywords: DNA methylation; biomarker discovery; disease classification; feature weighting; graph convolutional network.

Figure 1

The flowchart of MethPriorGCN.

Figure 2

AUC values for different training steps and learning rates.

Figure 3

ROC curves of PIGCN and four comparison algorithms.

Figure 4

Top 10 potential associated methylations for esophageal carcinoma.

Figure 5

Impact of feature weighting on classification accuracy.

Figure 6

Performance of MethPriorGCN under different values of hyperparameter δ. The dashed lines represent the results of GCN (classification model without feature weighting method).