Incorporating genetic networks into case-control association studies with high-dimensional DNA methylation data.
Kipoong KimHokeun SunPublished in: BMC bioinformatics (2019)
The proposed variable selection approach can utilize prior biological network information for analysis of high-dimensional DNA methylation array data. It first captures gene level signals from multiple CpG sites using data a dimension reduction technique and then performs network-based regularization based on biological network graph information. It can select potentially cancer-related genes and genetic pathways that were missed by the existing methods.
Keyphrases
- dna methylation
- genome wide
- case control
- electronic health record
- copy number
- big data
- gene expression
- high resolution
- healthcare
- health information
- machine learning
- papillary thyroid
- squamous cell carcinoma
- single cell
- young adults
- data analysis
- high density
- convolutional neural network
- social media
- lymph node metastasis
- genome wide analysis