Detecting PCOS susceptibility loci from genome-wide association studies via iterative trend correlation based feature screening.

ABSTRACT:

Background

Feature screening plays a critical role in handling ultrahigh dimensional data analyses when the number of features exponentially exceeds the number of observations. It is increasingly common in biomedical research to have case-control (binary) response and an extremely large-scale categorical features. However, the approach considering such data types is limited in extant literature. In this article, we propose a new feature screening approach based on the iterative trend correlation (ITC-SIS, for short) to detect important susceptibility loci that are associated with the polycystic ovary syndrome (PCOS) affection status by screening 731,442 SNP features that were collected from the genome-wide association studies.

Results

We prove that the trend correlation base

SUBMITTER: Dai X 

PROVIDER: S-EPMC7199379 | biostudies-literature | 2020 May

REPOSITORIES: biostudies-literature