A major challenge in cancer prognostics is finding early biomarkers that can accurately identify cancer. Circulating tumor cells are rare and circulating tumor DNA can not provide information about the originating cell. Extracellular vesicles (EVs) contain cell specific information, are abundant in fluids, and have unique properties between cancerous and non-cancerous. Fluorescence measurements have limitations from intrinsic fluorescent background signals, photobleaching, non-specific labelling, and EV structural modifications. Here, we demonstrate a label-free approach to classification of 3 different EVs, derived from non-malignant, non-invasive cancerous, and invasive cancerous cell lines. Using double nanohole optical tweezers, the scattering from single trapped EVs is measured, and using a 1D convolutional neural network, we are able to classify the time series optical signal into its respective EV class with greater than 90% accuracy.
Extracellular vesicles (EVs) are easily accessible in biological fluids and carry the molecular "fingerprints" of their parent cells, making them compelling candidates for minimally invasive cancer diagnostics. For future translation into clinical settings, greater sensitivity and specificity are desired. Here weachieve near-perfect classification for cancerous (2 types) and non-cancerous cell-derived EVs by using nanoaperture optical tweezers (NOTs) and deep learning. The NOT approach is label-free and has single-EV sensitivity -- the signal acquired is simply the laser tweezer scattered light. The high level of specificity is achieved by custom design of a four-layer convolution and Kolmogorov-Arnold linear layer deep learning model. Several other models are compared with this approach. Beyond diagnostics, this platform opens avenues for real-time EV profiling, deepening our biological understanding and advancing the development of minimally invasive personalized medicine.
Nanoaperture optical tweezers (NOTs) were used to analyze conalbumin in various forms. By analyzing the power spectrum of the NOT-transmitted laser signal, differences between iron and iron-free conalbumin were observed; the corner frequency extrapolated to zero-laser power was significantly larger in magnitude for conalbumin with iron, which was interpreted as coming from the enhanced electrostatic interactions close to the surface of the nanoaperture. Conalbumin in a diluted, but otherwise unprocessed, egg white sample showed the same behavior as purified iron-free conalbumin. Dynamic two-state transitions in the NOT signal were observed for iron-free conalbumin and conalbumin in egg white samples. We used this to determine the dominant state as a function of temperature, with one state showing a maximum occupancy around 30.4 °C. Deconvolution of the probability distribution function was used to find the energy landscape associated with this two-state transition. This work shows the potential of NOTs to see variations with metal ion binding, including conformational dynamics related to the binding at timescales not accessible to other methods.