Label‐Free Prediction of Tumor Metastatic Potential via Ramanome

Abstract

Assessing metastatic potential is crucial for cancer treatment strategies. However, current methods are time‐consuming, labor‐intensive, and have limited sample accessibility. Therefore, this study aims to investigate the urgent need for rapid and accurate approaches by proposing a Ramanome‐based metastasis index (RMI) using machine learning of single‐cell Raman spectra to rapidly and accurately assess tumor cell metastatic potential. Validation with various cultured tumor cells and a mouse orthotopic model of pancreatic ductal adenocarcinoma show a Kendall rank correlation coefficient of 1 compared to Transwell experiments and histopathological assessments. Significantly, lipid‐related Raman peaks are most influential in determining RMI. The lipidomic analysis confirmed strong correlations between metastatic potential and phosphatidylcholine, phosphatidylethanolamine, cholesteryl ester, ceramide, and bis(monoacylglycero)phosphate, crucial in cell membrane composition or signal transduction. Therefore, RMI is a valuable tool for predicting tumor metastatic potential and providing insights into metastasis mechanisms.