Abstract
Liquid biopsy approaches offer a promising technology for early and minimally invasive cancer detection. Tumor-educated platelets (TEPs) have emerged as a promising liquid biopsy biosource for the detection of various cancer types. In this study, we processed and analyzed the TEPs collected from 466 Non-small Cell Lung Carcinoma (NSCLC) patients and 410 asymptomatic individuals (controls) using the previously established thromboSeq protocol. We developed a novel particle-swarm optimization machine learning algorithm which enabled the selection of an 881 RNA biomarker panel (AUC 0.88). Herein we propose and validate in an independent cohort of samples (n = 558) two approaches for blood samples testing: one with high sensitivity (95% NSCLC detected) and another with high specificity (94% controls detected). Our data explain how TEP-derived spliced RNAs may serve as a biomarker for minimally-invasive clinical blood tests, complement existing imaging tests, and assist the detection and management of lung cancer patients.
Original language | English |
---|---|
Article number | 9359 |
Number of pages | 12 |
Journal | Scientific Reports |
Volume | 13 |
Issue number | 1 |
DOIs | |
Publication status | Published - 8 Jun 2023 |
Keywords
- LIQUID BIOPSY
- GENE-EXPRESSION
- RNA-SEQ
- DIAGNOSIS
- IDENTIFICATION
- BIOMARKERS
- VALIDATION
- SEQUESTER