Colorimetric aptasensor coupled with a deep-learning-powered smartphone app for programmed death ligand-1 expressing...

Area of Science:

• Biomedical Engineering
• Nanotechnology
• Cancer Diagnostics

Background:

• Lung cancer is a leading cause of cancer mortality, necessitating advanced non-invasive detection methods.
• Extracellular vesicles expressing programmed death ligand-1 (PD-L1@EVs) are potential biomarkers for lung cancer and immunotherapy response.

Purpose of the Study:

• To develop a sensitive and specific colorimetric aptasensor for detecting PD-L1@EVs.
• To create a smartphone-based quantitative analysis tool for improved accessibility.

Main Methods:

• Utilized a (Fe3O4)-SiO2-TiO2 nanocomposite for efficient EV capture.
• Employed a PD-L1 aptamer-triggered enzyme-linked hybridization chain reaction (HCR) for signal amplification.
• Developed a convolutional neural network (CNN)-powered smartphone app (ExoP) for quantitative chromaticity analysis.

Main Results:

• The aptasensor detected PD-L1@EVs with a limit of detection as low as 3.6x10^2 EVs/mL.
• Achieved a wide linear detection range from 10^3 to 10^10 EVs/mL with high specificity.
• Successfully differentiated serum samples from lung cancer patients and healthy volunteers.

Conclusions:

• The developed colorimetric aptasensor combined with a CNN-powered smartphone app provides a simple, sensitive, and specific method for lung cancer detection.
• This approach enhances accessibility, particularly in low-resource settings, by eliminating the need for specialized equipment.