Background: The plasma proteome holds promise as a future diagnostic and prognostic tool that can accurately reflect complex human traits and disease processes. We assessed the ability of plasma proteins to predict incident atherosclerotic cardiovascular disease (ASCVD). Methods: We assessed the relative ability of clinical, genetic, and high-throughput proteomic data to associate with ASCVD in a cohort of 41650 UK Biobank participants (figure). Selected features for analysis included clinical variables such as a cardiovascular risk score (QRISK3) and lipid levels, Olink protein expression data, and 36 polygenic risk scores (PRS). We used LASSO to select features and compare AUC statistics between data types. Stability selection with randomized LASSO identified the most robustly associated proteins. The benefit of the selected proteomic signature over the QRISK3 score was evaluated through the derivation of a Δ AUC value. Results: In this cohort, the mean age was 56 years, 60.2% were female, and 9.6% developed incident ASCVD over a median follow-up of 9.33 years. A protein-only LASSO model selected 252 proteins and returned an AUC of 0.723 (95% CI 0.708, 0.737). A clinical and genetic LASSO model which selected 4 clinical variables and 20 PRS achieved an AUC of 0.726 (95% CI 0.712, 0.741). Fifteen proteins selected by a stability selection algorithm offered improvement in ASCVD prediction over the QRISK3 score [Δ AUC: 0.011 (95% CI 0.002, 0.019)]. Conclusion: A plasma proteomic signature modestly improves the prediction of incident ASCVD over clinical and genetic factors. Further studies are warranted to better elucidate the clinical utility of this signature in predicting the risk of ASCVD over the standard practice of using the QRISK3 score.