Test performance of a DNA methylation–based liquid biopsy biomarker for detection and classification of pleural mesothelioma (PM).

Abstract

8082 Background: Circulating tumor DNA (ctDNA) profiling in pleural mesothelioma (PM) is challenging due to its molecular heterogeneity and lack of mesothelioma-specific mutations. Diagnosis can be challenging and may require repeat biopsies. Cell-free methylated DNA immunoprecipitation sequencing (cfMeDIP-seq) of plasma cell-free DNA (cfDNA) offers a non-invasive approach to analyzing differentially methylated regions (DMRs), providing insights into epigenetic changes that could serve as potential biomarkers for diagnosis, histological differentiation, and prognosis in PM. Methods: cfMeDIP-seq was performed on plasma samples from 55 PM patients and 24 asbestos-exposed non-cancer controls (NCC). Libraries were sequenced to an average depth of 70 million reads, and chromosomes 1-22 were binned into 300 bp windows for read tallying. For NCCs, bins with a mean beta-value <0.3 and CG density >2 (n = 3,537,691 windows) were analyzed. DMR analysis and pathway enrichment were conducted using R packages (limma, clusterProfiler), and machine learning models were developed with Python modules (pandas, numpy, sklearn). Results: Among the 55 PM patients (72% epithelioid, 13% biphasic, 15% sarcomatoid), the median age was 70 years, 85% were male, and 78% had prior asbestos exposure. Using a stringent filter (mean beta-value <0.1; CG density >5), a random forest classifier was developed with 141 windows, distinguishing PM from NCC with 91% accuracy, 88% precision (or positive predictive value, PPV), and an area under the ROC curve (AUC) of 0.94 across 5-fold cross-validation cohorts. DMR analysis of epithelioid vs. sarcomatoid PM revealed 1,585 significantly different windows (adjusted p < 0.05), achieving 83% accuracy, 74% precision, and an AUC of 0.98. Gene ontology analysis indicated significant enrichment in RNA processing pathways. Among epithelioid PM patients, distinct DMRs were identified between those with overall survival (OS) ≤ 6 months and >6 months (n = 1,824 windows, adjusted p < 0.05). Patients with OS ≥ 36 months and <36 months showed 37 significantly differential windows (adjusted p < 0.05), though test performance assessment was limited by the small sample size. Conclusions: If validated, global methylome profiling of ctDNA via cfMeDIP-seq offers a novel, non-invasive method that may enhance accurate diagnosis and histological differentiation. Additionally, identifying epigenetic biomarkers could provide deeper insights into PM biology, paving the way for personalized medicine and improved patient outcomes.