ABSTRACT Crohn’s disease (CD) is a chronic immune-mediated gastrointestinal disease characterized by significant clinical and molecular heterogeneity. The clinical heterogeneity is evidenced by the wide variation in disease location, severity, and behavior. The molecular heterogeneity is evidenced by the numerous genetic risk loci which have been identified to date. Fortunately, there are an increasing number of therapeutic options for the treatment of CD including blockade of tumor necrosis factor and blockade of IL-12/23 signaling. Unfortunately, patients rapidly cycle through medications, often due to lack of response, further increasing morbidity and healthcare costs. Therefore, there is an urgent need for data matching the mechanism of the disease to the treatment target to guide treatment selection. Our long-term goal is to improve first-line therapy selection in CD as more therapies become available at biosimilar prices. In this career development proposal, I will focus on acquiring data which provides a deeper understanding of the clinical and molecular attributes which associate with response to anti-IL-12/23 therapy to improve drug positioning and first-line therapy selection for this class of therapy in CD. We have shown that CD patients with autoimmune skin disease preferentially respond to anti-IL-12/23 therapy. We will utilize machine learning to identify additional clinical patterns which associate with preferential response to therapy, then develop a decision tool to aid clinicians in selection of patients for first-line anti-IL-12/23 therapy. Then, we will investigate genomic predictors of response using both a targeted and genome wide approach. Finally, we will identify transcriptional modules which associate with drug response which will yield insight into the tissue cell signatures which associate with differential response. The scientific and training objectives outlined will provide me with the expertise needed to pursue independent investigation in the field of precision medicine, with a specific emphasis on the utilization of large scale clinical and genomic datasets to predict prognostic and therapeutic outcomes in CD.