PROJECT SUMMARY/ABSTRACT Lifetime Alcohol Use Disorder (AUD) has an estimated US lifetime prevalence of 29.1%. Major Depressive Disorder (MDD) is often comorbid with AUD, with an estimated lifetime AUD prevalence of 40.8% among those with lifetime MDD. This comorbidity was unequally distributed by sex globally, with prevalence nearly twice as high in men as in women. AUD and MDD are moderately heritable, with and a substantial proportion of the underlying genetic liability between AUD and MDD is shared, (rg = 0.56). The temporal order of the disorders is complex and likely differs by sex. This project proposes to leverage data from 10 existing collections from longitudinal, diverse ancestry cohorts to analyze the interacting sex, genetic, and co-morbid MDD effects on the trajectory of AUD. These analyses represent modeling approaches not previously applied in these datasets and successful completion of the proposed research will elucidate biological mechanisms of alcohol etiology by investigating sex-specific and time-varying genetic influences on item-level measures of AUD. Importantly, this proposal also includes development of novel machine learning (ML) approaches for predicting missing and/or unmeasured AUD outcomes from existing, biobank-scale data to improve power for genetic analyses. This K award will provide the structured training and mentorship in molecular genetics for complex traits and ancestrally diverse samples as well as psychiatric nosology and epidemiology necessary for the candidate to develop the expertise needed to support her goal of becoming an independent and innovative researcher in alcohol epidemiology. Combined with her background in biostatistics and analytical methods, the proposed training and research activities will develop her capacity posit the kinds of research hypothesis, comprehensive plans, and wholistic, innovative approaches which are most relevant to advancing science and medicine in alcohol research. In sum, with dedicated mentoring, the planned training and research will equip the candidate to establish a strong line of competitive research supporting a long-term goal of an independent research plan that integrates novel statistical and computational approaches to elucidate the genetic and environmental factors and interactions contributing to AUD.