Pixelated high-Q metasurfaces for in-situ biospectroscopy and AI-enabled classification of lipid membrane photoswitching dynamics

TL;DR

This paper introduces an integrated platform combining pixelated dielectric metasurfaces, optofluidics, and deep learning for real-time, in-situ biospectroscopy of lipid membrane dynamics in aqueous environments, achieving high accuracy in classifying membrane conformations.

Contribution

It presents a novel in-situ biospectroscopy method using high-Q metasurfaces combined with deep learning for dynamic biological system analysis.

Findings

Achieved 98% accuracy in classifying membrane conformations.

Enabled real-time, time-resolved biospectroscopy in aqueous environments.

Demonstrated potential for studying complex biological processes.

Abstract

Nanophotonic devices excel at confining light into intense hot spots of the electromagnetic near fields, creating unprecedented opportunities for light-matter coupling and surface-enhanced sensing. Recently, all-dielectric metasurfaces with ultrasharp resonances enabled by photonic bound states in the continuum have unlocked new functionalities for surface-enhanced biospectroscopy by precisely targeting and reading out molecular absorption signatures of diverse molecular systems. However, BIC-driven molecular spectroscopy has so far focused on endpoint measurements in dry conditions, neglecting the crucial interaction dynamics of biological systems. Here, we combine the advantages of pixelated all-dielectric metasurfaces with deep learning-enabled feature extraction and prediction to realize an integrated optofluidic platform for time-resolved in-situ biospectroscopy. Our approach harnesses high-Q metasurfaces specifically designed for operation in a lossy aqueous environment together with advanced spectral sampling techniques to temporally resolve the dynamic behavior of photoswitchable lipid membranes. Enabled by a software convolutional neural network, we further demonstrate the real-time classification of the characteristic cis and trans membrane conformations with 98% accuracy. Our synergistic sensing platform incorporating metasurfaces, optofluidics, and deep learning opens exciting possibilities for studying multi-molecular biological systems, ranging from the behavior of transmembrane proteins to the dynamic processes associated with cellular communication.