ABSTRACT Warfarin remains one of the most commonly prescribed drugs and a leading cause of emergencyhospitalizations. Warfarin use is especially common in medically underserved patients such as AfricanAmericans (AAs) and Latinos which is particularly concerning since AAs and Latinos suffer worse outcomesdue to suboptimal warfarin therapy. Thus AAs and Latinos can derive a distinct benefit from warfarinpharmacogenomic (PGx) algorithms which maximize safety and efficacy by predicting individualized warfarindose. However currently available PGx algorithms have critical limitations including a lack of generalizability tonon-white populations and a failure to account for 50 percent of variability in warfarin dose. Under-representationin clinical studies the propensity to cause adverse events and a lack of consideration of admixed populationsin clinical PGx guidelines are all factors that contribute to limited utility of warfarin PGx algorithms in diversepopulations. Many potential sources of warfarin stable dose variability remain critically unexplored including therole of vitamin K biosynthesizing bacterial species the influence of local ancestry at warfarin pharmacogenesand the potential for machine learning techniques to enable accurate warfarin dosing algorithms in diversepopulations. This proposal addresses the overarching hypothesis that warfarin stable dose prediction can beimproved by incorporation of gut microbiome data measures of local ancestry and machine learning in diversepopulations. We will pursue three Specific Aims (SAs) to test this hypothesis: (SA1) Determine the impact ofabundance of vitamin K biosynthesizing bacteria from the gut microbiome on warfarin stable dose and; (SA2)Determine the influence of local admixture on warfarin stable dose in admixed populations; (SA3) Optimizewarfarin PGx algorithms for diverse populations using machine learning. In SA#1 we will conduct a clinical studywith fecal sample collection at anticoagulation clinic visits and perform whole genome bacterial sequencing toidentify the effect of vitamin K biosynthesizing bacterial species on warfarin stable dose. In SA#2 we will estimateAfrican European and Native American local ancestry in warfarin pharmacogenes in a large admixedpopulation (n=1194) and determine its effects on warfarin stable dose. In SA#3 a large diverse population ofwarfarin treated patients (n=7366) will be used to develop machine learning models and test improved predictionof warfarin stable dose over existing linear regression models. Our studies overcome major limitations ofprevious warfarin PGx studies by leveraging gut microbiome data local ancestry machine learning and diverseadmixed populations. The outcomes of this work will provide a framework for local ancestry investigation withother PGx drug-gene pairs enabling use of clinical PGx guidelines in admixed populations. This research hasthe potential to identify new sources of variability in warfarin dose improve the safety and efficacy of warfarintreatment and reduce disparities in PGx research for medically underserved patients.