AI-Powered Surface Light Microscopy for In Situ Profiling of Cell Adhesions and Membrane Protein Binding Kinetics

Area of Science:

• Biophysics
• Cell Biology
• Biosensing

Background:

• Membrane proteins are crucial drug targets, but studying their interactions in situ is challenging.
• Surface plasmon resonance (SPR) imaging offers label-free observation but suffers from background interference.
• Quantitative analysis of molecular interactions at the cell membrane requires overcoming background noise.

Purpose of the Study:

• To develop an AI-powered platform for accurate, label-free quantification of ligand binding to membrane proteins.
• To overcome the limitations of traditional SPR imaging by reducing background noise.
• To enable precise kinetic analysis of molecular interactions at the single live-cell level.

Main Methods:

• Development of an artificial intelligence (AI)-powered surface light microscopy platform.
• Integration of a waveguide sensor chip for dual-channel (scattering and fluorescence) imaging.
• Training an AI model to recognize membrane-associated adhesions in scattering images for signal isolation.

Main Results:

• The AI model achieved an area under the curve of approximately 0.85 in recognizing membrane-associated adhesions.
• The platform successfully isolated real-time ligand-binding signals from nonspecific background.
• Robust in situ binding kinetic analysis at the single live-cell level was enabled.

Conclusions:

• The AI-powered platform transforms label-free biosensing from qualitative to quantitative.
• This method decouples measurement sensitivity from biological interpretation specificity.
• The technology enables molecularly precise analysis directly on live cells, advancing drug development and biological studies.