To have precise prevention, diagnosis, and treatment for substance use disorders, phenotype refinement and etiology elucidation are needed. In this project, novel machine learning methods will be developed, enabling the integrative analysis of data from multiple available sources, including phenotype, environment, genotype, and functional genomics. The developed methods will be used to refine phenotypes of varying substance use disorders, followed by genome wide association studies to identify novel genetic risk factors of these disorders and to elucidate the functional impact of the associated genetic variants in order to produce potentially actionable targets for intervention.
