PROJECT SUMMARY/ABSTRACT of Project 1 Colorectal cancer (CRC) rates vary across population groups. Given this and the rising rates of early-onset CRC, we need new approaches to identify individuals at higher risk who could benefit from precise screening strategies. Currently, screening relies on family history, yet over 80% of CRC cases occur in people without family history highlighting the need for more tailored and risk-based screening strategies. Using polygenic risk scores (PRS), which aggregate all CRC-associated genetic variants into a single score, we can identify high risk subgroups from the general population who are currently considered average-risk but who would likely benefit from targeted prevention and screening. One of the most critical challenges related to this is the fact that the predictive performance of the current PRS are substantially more effective in predicting risk in individuals of European ancestry compared with other population groups due to the fact that most genetic research has been done in European individuals. A promising strategy to address this is the use of functional genomic data to guide PRS development, which we propose in Aim 1. We will derive functional genomic scores from single cell data for open chromatin and RNA profiling for each cell type and state relevant to CRC (Aim 1a). In Aim 1b we will use machine learning to incorporate the functional genomic scores to build and validate PRS based on data from the largest CRC genetic epidemiologic consortium (123,000 CRC cases and 228,000 controls,). As an increasing number of companies are offering PRS direct to consumers, we urgently need to evaluate the clinical value of PRS for CRC screening. Therefore, we will use the microsimulation model MISCAN to measure the distributional cost-effectiveness of PRS for risk stratification and estimate the optimal screening strategy in terms of balanced access and efficiency based on the PRS across different population groups (Aim 2). Our team is ideally positioned to lead this effort given we discovered most of the common genetic risk factors for CRC, have single cell multi-omic data analyses expertise, developed comprehensive risk prediction models using cutting edge machine learning approaches. To enhance the clinical application of a novel PRS will make data and our models publicly available. Our findings aim to guide personalized interventions that reduce CRC burden across ancestral groups.