These data represent the 2282 commercial clinical samples that were used in the initial study discovery.

These samples were collected between October 2014 and October 2016 and were genotyped based on ethnicity (77 for Cau; 75 for AA; 71 for His). The original commercial model incorporated the Gail model +PRS (for which 5 year and lifetime risk score can be found in column O and P; calculated per Dite, 2016). The Gail model risk scores alone can be found in columns M and N. The Streamlined model plus PRS risk scores are in columns Q and R. The polygenic risk scores are in column L were calculated per Mealiffe 2010. The clinical Gail model questions can be found in columns D-K, respectively: current age; age at menarche, age at 1st live birth; previous biopsy; number of previous biopsies; confirmed atypical hyperplasia; ethnicity. (XLSX)