Abstract 1914: Highly accurate detection of early-stage colorectal cancer using tumor and immune extracellular vesicles biomarkers

Colorectal cancer (CRC) is one of the most common cancers worldwide, and early detection is critical for treatment and improved survival rates. Precancerous and early-stage CRC present significant diagnostic challenges due to the small size of lesions and the very low expression of tumor-specific biomarkers in plasma. Current genomics-based diagnostic methods struggle to detect these lesions, making it imperative to develop more sensitive and specific approaches. Circulating extracellular vesicles (EVs) are emerging as a promising solution for early-stage CRC detection, since EVs are produced by tumor, microenviroment and host cells. Plasma EVs may offer a novel means to detect and monitor small early-stage tumors through detection of tumor-associated biomarkers, tumor specific host response, and microenvironment biomarkers To identify novel early-stage CRC specific biomarkers, we performed proteomic analysis on EVs purified from patient plasma using size exclusion chromatography and a proprietary buffer system that enhances EV and corona protein recovery. TrueDiscovery™ Data-independent acquisition (DIA) mass spectrometry (MS) analysis was conducted on 24 pre-cancer/stage 0 and 25 stage 1 CRC and 75 normal patient plasma samples. An in-house machine learning (ML) pipeline was developed to identify differentially expressed proteins and model multiplexes to identify those with extremely high diagnostic accuracy (> 0.99).An average of ∼2,500 QCed proteins were identified per sample and included in bioinformatics analysis. Comparative analysis of control patient EVs and either pre-cancerous/Stage 0, or Stage 1 colon cancer EVs using our ML pipeline identified 336 and 493 differentially expressed proteins for each group respectively (absolute Log2FC>0.5; FDR adjusted p-value <0.001; AUC>0.5). The 17 best pre/stage 0 proteins and 53 stage 1 proteins were trained and tested using Support Vector Machine to assess all potential 3-plexes to identify those with mean diagnostic accuracy > 99%. Our analysis yielded five 3-plexes in precancer/stage 0 and thirty-four 3-plexes in stage 1 with near perfect diagnostic accuracy in the discovery cohort. 3-Plexes were translated to ELISAs and initial testing retained very high accuracy (0.953), sensitivity (0.948) and specificity (0.958) classifying cancer vs control samples. The performance of highly accurate ELISA multiplexes is currently being assessed on an independent intended use case/control cohorts. Key biomarkers from CRC patient EVs indicate the potential to detect and diagnose early-stage and low tumor burden cancers using our methods. Interestingly, the most accurate 3-plexes consist of proteins from immune, inflammatory and metabolic processes, suggesting that for the detection of early-stage cancer it may be critical to include both tumor and host specific biomarkers. Citation Format: Poorva Mudgal, Zack Opheim, Cheryl Bandoski, Valesca Anschau, Martin Mehnert, Issa Isaac, Alan Ezrin, Todd A. Hembrough. Highly accurate detection of early-stage colorectal cancer using tumor and immune extracellular vesicles biomarkers [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2025; Part 1 (Regular Abstracts); 2025 Apr 25-30; Chicago, IL. Philadelphia (PA): AACR; Cancer Res 2025;85(8_Suppl_1):Abstract nr 1914.