OBJECTIVES/GOALS: To assemble publicly-available, proprietary, and geocoded datasets about social, environmental, behavioral, and psychological exposures experienced by children with asthma, to provide a technical overview of data aggregation, management, and integration processes utilized, and to build predictive models using sociome and clinical data. METHODS/STUDY POPULATION: Publicly-available data involving census information, crime, green space, building permits, vacant and abandoned buildings, traffic (City of Chicago data portal), pollution and weather (National Oceanic and Atmospheric Administration), and noise (Array of Things project) were assembled. We placed a local instance of the Pelias geocoder on the UChicago Center for Research Informatics HIPAA-compliant infrastructure. The UChicago Clinical Research Data Warehouse will be leveraged to obtain clinical information for children diagnosed with asthma at UChicago Medicine between 2007 and 2021. The address of each child will be subjected to geocoding, and this information will be aligned with imported sociome data. A model will be built to account for each sociome elements contribution to asthma outcomes. RESULTS/ANTICIPATED RESULTS: Here we are creating sustainable and scalable ways for collecting, standardizing, and sharing real-world sociome data, simultaneously linking those data back to patient information. With this work, we aim to demonstrate feasibility of a data-commons-as-a-service for clinical and sociome data and to provide technical specifications and descriptions of processes employed. Creating generalizable and scalable infrastructure to support research of social and environmental impacts on clinical outcomes is critical, and our work will provide a framework to be used in other disease states. Further, this infrastructure will facilitate the application of advanced analytical tools and visualization platforms to accelerate the study of diseases and lead to new insights into factors influencing outcomes. DISCUSSION/SIGNIFICANCE: Beyond focusing on and treating biological mechanisms of disease, advancing health also requires addressing adverse consequences of sociome factors on clinical outcomes. We describe an innovative process to comprehensively codify and quantify such information in a way suitable for large scale co-analysis with biological and clinical data.