Title: Data integration to improve prediction of human complex traits and diseases
Authors: Bingxin Zhao - Purdue University (United States) [presenting]
Hongtu Zhu - University of Texas MD Anderson Cancer Center (United States)
Abstract: One ultimate goal in biomedical studies is to develop prediction models for complex traits and diseases. We use large-scale datasets to showcase some recent real data applications to predict complex traits and diseases (such as fluid intelligence and heart diseases). We integrate multiple data resources, including the common genetic variants from high-dimensional genotyping data, gene expression data, exome data, biomarkers, and multi-modality imaging traits. We illustrate the clinical achievements of current data integration methods and also highlight the existing challenges and opportunities.