Machine Learning-Assisted Dual-Marker Detection in Serum Small Extracellular Vesicles for the Diagnosis and Prognosis Prediction of Non-Small Cell Lung Cancer.

Wenzhe Li,Jianchao Xue,Huayi Wang,Chen Wang,Siyuan Ye,Kaidi Li,Naixin Liang,Yadong Wang,Ling Zhu,Shanqing Li,Yanlian Yang

doi:10.3390/nano12050809

Abstract

Small extracellular vesicles (sEVs) carry molecular information from their source cells and are desired biomarkers for cancer diagnosis. We establish a machine learning-assisted dual-marker detection method to analyze the expression of epidermal growth factor receptor (EGFR) and C-X-C chemokine receptor 4 (CXCR4) in serum sEVs for the diagnosis and prognosis prediction of non-small cell lung cancer (NSCLC). We find that the serum sEV EGFR and CXCR4 are significantly higher in advanced stage NSCLC (A/NSCLC) patients compared to early stage NSCLC (E/NSCLC) patients and the healthy donors (HDs). A receiver operating characteristic curve (ROC) analysis demonstrates that the combination of EGFR and CXCR4 in serum sEVs as an efficient diagnostic index and malignant degree indicator for NSCLC. Machine learning further shows a diagnostic accuracy of 97.4% for the training cohort and 91.7% for the validation cohort based on the combinational marker. Moreover, this machine leaning-assisted serum sEV analysis successfully predicts the possibility of tumor relapse in three NSCLC patients by comparing their serum sEVs before and three days after surgery. This study provides an intelligent serum sEV-based assay for the diagnosis and prognosis prediction of NSCLC, and will benefit the precision management of NSCLC.

Highlights

epidermal growth factor receptor (EGFR)+ or CXCR4+ Small extracellular vesicles (sEVs) were further labeled with anti-EGFR or anti-CXCR4 microbead enrichment followed by dual staining for signal amplification
We established a dual-marker detection method to analyze the expression of EGFR and CXCR4 on serum sEVs for the diagnosis and prognosis prediction of NSCLS. sEVs were enriched on microbeads and stained with fluorescent antibodies against EGFR and CXCR4 to facilitate signal amplification of these two proteins on the sEVs in flow cytometry analysis, overcoming the problem whereby the nano-scaled size of the sEVs exceeds the detection limit of the traditional flow cytometry
We demonstrated that the expression levels of EGFR and CXCR4 on the sEVs well represented the ones in the source lung cancer cells

Summary

Introduction

Lung cancer is the leading cause of cancer-related death worldwide, and non-small cell lung cancer (NSCLC) constitutes approximately 85% of lung cancer [1,2]. Accurate non-invasive diagnosis and early prognosis prediction based on biomarker detection help with precision medicine and prolong the survival of NSCLC. Traditional investigation of biomarkers in NSCLC is mainly based on immunohistochemistry (IHC) and fluorescent in situ hybridization (FISH) analysis of the tumor tissue. The difficulties in collecting tissue biopsies for repeated detection and the single biopsy bias due to intratumoral heterogeneity limit the application of the tissue-based assessment for accurate diagnosis, Nanomaterials 2022, 12, 809.

Methods

Results

Conclusion