Machine learning-assisted global DNA methylation fingerprint analysis for differentiating early-stage lung cancer from benign lung diseases

DNA methylation plays a critical role in the development of human tumors. However, routine characterization of DNA methylation can be time-consuming and labor-intensive. We herein describe a sensitive, simple surface -enhanced Raman spectroscopy (SERS) approach for identifying the DNA methylation pattern in early-stage lung cancer (LC) patients. By comparing SERS spectra of methylated DNA bases or sequences with their coun-terparts, we identified a reliable spectral marker of cytosine methylation. To move toward clinical applications, we applied our SERS strategy to detect the methylation patterns of genomic DNA (gDNA) extracted from cell line models as well as formalin-fixed paraffin-embedded tissues of early-stage LC and benign lung diseases (BLD) patients. In a clinical cohort of 106 individuals, our results showed distinct methylation patterns in gDNA be-tween early-stage LC (n = 65) and BLD patients (n = 41), suggesting cancer-induced DNA methylation alter-ations. Combined with partial least square discriminant analysis, early-stage LC and BLD patients were differentiated with an area under the curve (AUC) value of 0.85. We believe that the SERS profiling of DNA methylation alterations, together with machine learning could potentially offer a promising new route toward the early detection of LC.