Plasma Exosome Analysis for Protein Mutation Identification Using a Combination of Raman Spectroscopy and Deep Learning

초록

Protein mutation detection using liquid biopsy can besimply performedperiodically, making it easy to detect the occurrence of newly emergingmutations rapidly. However, it has low diagnostic accuracy since thereare more normal proteins than mutated proteins in body fluids. Toincrease the diagnostic accuracy, we analyzed plasma exosomes usingnanoplasmonic spectra and deep learning. Exosomes, a promising biomarker,are abundant in plasma and stably carry intact proteins originatingfrom mother cells. However, the mutated exosomal proteins cannot bedetected sensitively because of the subtle changes in their structure.Therefore, we obtained Raman spectra that provide molecular informationabout structural changes in mutated proteins. To extract the uniquefeatures of the protein from complex Raman spectra, we developed adeep-learning classification algorithm with two deep-learning models.Consequently, controls with wild-type proteins and patients with mutatedproteins were classified with high accuracy. As a proof of concept,we discriminated the lung cancer patients with mutations in the epidermalgrowth factor receptor (EGFR), L858R, E19del, L858R + T790M,and E19del + T790M, from controls with an accuracy of0.93. Moreover, the protein mutation status of the patients with primary(E19del, L858R) and secondary (+T790M) mutations was clearly monitored.Overall, our technique is expected to be applied as a novel methodfor companion diagnostic and treatment monitoring.

키워드