Abstract 2391: Computation of a user-friendly composite score from three prostate cancer biomarkers

Abstract

Abstract Summary: Prostate cancer (PCa) is the most commonly diagnosed solid organ cancer in men worldwide. Current diagnosis of PCa includes use of initial prostate specific antigen assay which has a high false positive rate, low specificity, and low sensitivity. Consequently, it results in overdiagnosis and overtreatment, leaving patients with unintended health complications from the side effects of unnecessary prostate biopsies and treatment. PCa biomarkers are being discovered to address this unmet need. Here, we report creation of a composite score based on three PCa biomarkers, plasmacytoma variant translocation 1 exon 4A, exon 4B, and exon 9. Statistical analysis of copy numbers derived from a real-time quantitative polymerase chain reaction - based assay showed these PCa biomarkers to be linearly separable. We trained a supervised learning algorithm using support vector classifiers to generate a classification hyperplane from which a composite score is developed. Our aggregate score when applied to test data from non-cancerous prostate epithelial cells and PCa cells accurately classified 100% PCa cells. Creation of this 3-biomarker based composite score lays the groundwork for clinical trial of its use in PCa diagnosis. Citation Format: Gargi Pal, Emmanuel Asante-Asamani, Leslie Liu, Olorunseun O. Ogunwobi. Computation of a user-friendly composite score from three prostate cancer biomarkers [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2021; 2021 Apr 10-15 and May 17-21. Philadelphia (PA): AACR; Cancer Res 2021;81(13_Suppl):Abstract nr 2391.