Intelligent DNA methylation biomarker selection for colorectal cancer

DNA methylation plays an important role in the regulation of gene expression, and aberrant changes in epigenetic regulation can be detected in cancer development or progress. In this study, genome-wide DNA methylation profiles and electronic medical records were combined to identify effective DNA methylation biomarkers for colorectal cancer (CRC). Statistical analytics and deep learning approaches were integrated to explore associated novel biomarkers. These identified biomarkers could facilitate accurate diagnosis of CRC and monitor disease progression for a testing subject, and provide suggestions for appropriate medical treatments. Firstly, DNA methylation profiles were analyzed through a standard pipeline to discover significantly differential methylation biomarkers as primary biomarkers. Incorporating Taiwan's National Health Insurance Research Database (NHIRD), associated comorbidities of CRC were identified and associated disease genes were considered as secondary biomarkers. The intersection of primary and secondary biomarkers was performed to obtain CRC-relevant biomarker candidates, and gene ontology annotations were used to calculate candidate biomarker-to-biomarker distances. Based on the formulated gene-pair distance matrix for all candidate biomarkers, we applied clustering algorithms to categorize candidate biomarkers into different functional groups. Corresponding coefficients for each biomarker within a functional cluster were ranked through an attention-based recurrent neural network. The weighting coefficient for each biomarker was further taken as a reference for designing a practical testing toolkit. Finally, we obtained 11 important biomarkers from 5 functional clustered groups which were established by the 141 biomarker candidates screened from 450k DNA methylation probes.