A Novel Three-Stage Framework for Association Analysis Between SNPs and Brain Regions.

摘要: Motivation: At present, a number of correlation analysis methods between SNPs and ROIs have been devised to explore the pathogenic mechanism Alzheimer's disease. However, some deficiencies inherent in these methods, including lack statistical efficacy biological meaning. This study aims at addressing issues: insufficient by previous (relative high regression error) meaning association analysis. Results: In this paper, novel three-stage framework is proposed. Firstly, clustering algorithm applied remove potential linkage unbalanced structure two SNPs. Then, group sparse model used introduce prior information such as gene select feature After above steps, each SNP has weight vector corresponding ROI, importance can be judged according weights vector, then selected. Finally, for selected SNPS, support machine implement prediction phenotype values. The experimental results under multiple performance measures show that proposed method better accuracy than other methods.