Particle tracking (PT) is a biophysical tool for elucidating molecular interactions, transport phenomena of diverse species, and rheological properties of complex materials. PT experiments involve first obtaining high resolution videos that capture time-resolved increments of particles, followed by extraction of traces of entities of interest from videos in the form of spatial locations over time, a process we refer to as path conversion. Finally, quantitative analysis of the traces will yield diffusivities, viscoelasticity, etc. Lung diseases, such as cystic fibrosis and COPD, are characterized by a highly viscoelastic mucus layer that is incapable of being cleared by mucociliary clearance. Not surprisingly, the viscoelasticity of mucus often directly reflects disease progression. A variety of mucolytics are being investigated, but due to the variable composition and properties of mucus between patients, effective mucolytics treatment will likely be different between individuals; too little/inappropriate mucolytics will not be effective in restoring mucus clearance, whereas too much may result in bronchorrhea. Although microbeads-based rheology has been performed on a variety of mucus specimens in basic research, the capacity for high throughput characterization of rheological properties of biological specimens in a clinical setting is currently not available. This limitation can be attributed to inefficiencies of path conversion: current PT software requires extensive human supervision/intervention to achieve accurate path conversion, not only resulting in poor reproducibility and throughput but also restricting its use to only expert labs. Our vision is to make PT as objective and easy to use as a simple plate reader that can be readily utilized by clinicians (diagnostics, disease progression, therapy effectiveness), pharma (preclinical/clinical drug screening), and research professionals. Towards this goal, we have created a neural network tracker (NNT) that automatically determines the location of all particles in each frame with zero user-input (i.e. no parameter for users to change), and retains the identity of all particles from frame to frame. The innovation is that NNT can robustly, reproducibly, and accurately track a wide range of 2D/3D videos with virtually no need for human intervention, achieving unparalleled time savings. We have already successfully deployed NNT over the Google cloud, which offers exceptional scalability. Nevertheless, for time-sensitive applications, such as an automated PT rheometer, the transfer of large video data files is likely prohibitive. Therefore, in this Phase I STTR, we seek to enable real-time NNT-based PT analysis on the local machine while video microscopy data is being acquired by the microscope, and allow data from PT analysis to drive the operation of the microscope.
In Aim 1, we will integrate our NNT with a single objective fluorescence microscope system called Monoptes.
Aim 2 will evaluate the performance of our NNT- Monoptes system. If successful, our technology would form the basis of a fully automated PT system capable of measuring rheological properties of fluids/materials or distribution of particle sizes in a 96-well plate format.
Particle tracking is a powerful biophysical tool in life and physical sciences, but unfortunately, its application has been strongly limited by inefficiencies in accurately extracting particle traces from raw movies. Unlike conventional particle tracking methods, we have combined artificial intelligence and machine learning to create a software that can consistently provide superior and truly automated tracking performance compared to current alternatives. In this proposal, we will integrate this latest advance with sophisticated instrumentation to develop a microscope system capable of fully automated particle tracking microscopy in a 96-well plate format. If successful, the instrument will likely be utilized by clinicians (diagnostics, disease progression, therapy effectiveness), pharma (preclinical/clinical drug screening of patients), and research professionals.
