Protein Quantification and Imaging by Surface-Enhanced Raman Spectroscopy and Similarity Analysis.

Protein quantification techniques such as immunoassays have been improved considerably, but they have several limitations, including time-consuming procedures, low sensitivity, and extrinsic detection. Because direct surface-enhanced Raman spectroscopy (SERS) can detect intrinsic signals of proteins, it can be used as an effective detection method. However, owing to the complexity and reliability of SERS signals, SERS is rarely adopted for quantification without a purified target protein. This study reports an efficient and effective direct SERS-based immunoassay (SERSIA) technique for protein quantification and imaging. SERSIA relies on the uniform coating of gold nanoparticles (GNPs) on a target-protein-immobilized substrate by simple centrifugation. As centrifugation induces close contact between the GNPs and target proteins, the intrinsic signals of the target protein can be detected. For quantification, the protein levels in a cell lysate are estimated using similarity analysis between antibody-only and protein-conjugated samples. This method reliably estimates the protein level at a sub-picomolar detection limit. Furthermore, this method enables quantitative imaging of immobilized protein at a micrometer range. Because this technique is fast, sensitive, and requires only one type of antibody, this approach can be a useful method to detect proteins in biological samples.

Early-Stage Lung Cancer Diagnosis by Deep Learning-Based Spectroscopic Analysis of Circulating Exosomes.

Lung cancer has a high mortality rate, but an early diagnosis can contribute to a favorable prognosis. A liquid biopsy that captures and detects tumor-related biomarkers in body fluids has great potential for early-stage diagnosis. Exosomes, nanosized extracellular vesicles found in blood, have been proposed as promising biomarkers for liquid biopsy. Here, we demonstrate an accurate diagnosis of early-stage lung cancer, using deep learning-based surface-enhanced Raman spectroscopy (SERS) of the exosomes. Our approach was to explore the features of cell exosomes through deep learning and figure out the similarity in human plasma exosomes, without learning insufficient human data. The deep learning model was trained with SERS signals of exosomes derived from normal and lung cancer cell lines and could classify them with an accuracy of 95%. In 43 patients, including stage I and II cancer patients, the deep learning model predicted that plasma exosomes of 90.7% patients had higher similarity to lung cancer cell exosomes than the average of the healthy controls. Such similarity was proportional to the progression of cancer. Notably, the model predicted lung cancer with an area under the curve (AUC) of 0.912 for the whole cohort and stage I patients with an AUC of 0.910. These results suggest the great potential of the combination of exosome analysis and deep learning as a method for early-stage liquid biopsy of lung cancer.