Abstract
Abstract Early detection of clear cell renal cell carcinoma (ccRCC) and accurate differentiation between malignant and benign lesions pose clinical challenges. Profiling the epigenetic pattern of patients through liquid biopsy offers a promising strategy for non-invasive cancer identification. This study utilizes the methylation characteristics of urinary cell-free DNA to enhance the precise diagnosis of ccRCC. In this study, 32 patients with malignant RCC, 20 patients with benign kidney lesions, and 28 age- and sex-matched healthy donors were enrolled. Urine samples were collected and applied by PredicineEPIC assay to analyze the whole genome methylation profiles. We assessed the methylation differences on cancer-specific altered regions and constructed a machine learning model for malignant and benign classification. Beta values were calculated for differentially methylated regions identified through literature mining and our current work. These features carry methylation signals that are recognized by gradient boosting machine and used for classification training. The leave-one-out cross-validation method compensated for the shotage of sample size. The sensitivity and specificity of the optimal model in the training set are both greater than 0.97, and it can achieve an accuracy of 0.95 on the validation set. This performance surpasses traditional diagnostic methods such as contrast-enhanced CT and MRI. This study demonstrated the technical feasibility of leveraging epigenetics profiles to discriminate malignant from benign lesions, suggesting a promising liquid biopsy-based approach for the precise detection of renal cell carcinoma. Citation Format: Wen Kong, Hang Dong, Haoran Tang, Pan Du, Shidong Jia, Jin Zhang. Precise detection of benign and malignant renal tumor via epigenetic characteristics of urinary cell-free DNA [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2024; Part 1 (Regular Abstracts); 2024 Apr 5-10; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2024;84(6_Suppl):Abstract nr 1738.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
