High dimensional data modeling

Eunice Kennedy Shriver National Institute Of Child Health & Human Development

Investigators

Abstract

The overarching goal of the proposed study is to employ emerging high throughput omics technology to investigate the metabolomic antecedents of GDM and fetal overgrowth to advance the understanding of etiology and to construct effective prediction models that can inform early prediction of GDM and fetal overgrowth. In addressing this goal, the proposed study also explores methodological developments that can identify sparse and interpretable metabolite features and facilitate mediation analysis with high dimensional exposures.