Predicting in situ nanoparticle behavior using multiple particle tracking and artificial neural networks.

Predictive models of nanoparticle transport can drive design of nanotherapeutic platforms to overcome biological barriers and achieve localized delivery. In this paper, we demonstrate the ability of artificial neural networks to predict both nanoparticle properties, such as size and protein adsorption, and aspects of the brain microenvironment, such as cell internalization, viscosity, and brain region by using large (>100 000) trajectory datasets collected via multiple particle tracking in in vitro gel models of the brain and cultured organotypic brain slices. Our neural network achieved a 0.75 recall score when predicting gel viscosity based on trajectory datasets, compared to 0.49 using an obstruction scaling model. When predicting in situ nanoparticle size based on trajectory datasets, neural networks achieved a 0.90 recall score compared to 0.83 using an optimized Stokes-Einstein predictor. To distinguish between nanoparticles of different sizes in more complex nanoparticle mixtures, our neural network achieved up to a recall score of 0.85. Even in cases of more nuanced output variables where mathematical models are not available, such as protein adhesion, neural networks retained the ability to distinguish between particle populations (recall score of 0.89). These findings demonstrate how trajectory datasets in combination with machine learning techniques can be used to characterize the particle-microenvironment interaction space.

Colloidal stability as a determinant of nanoparticle behavior in the brain.

Drug delivery to the brain is challenging due to a highly regulated blood-brain barrier (BBB) and a complex brain microenvironment. Nanoparticles, due to their tailorability, provide promising platforms to enhance therapeutic delivery and achieve controlled release and disease-specific localization in the brain. However, we have yet to fully understand the complex interactions between nanoparticles and the biological environments in which they operate. It is important to perform a systematic study to characterize nanoparticle behavior as a function of ion composition, concentration, and pH in cerebrospinal fluid (CSF). These could alter nanoparticle biological identity and influence diffusive capability and cellular uptake. In this study, poly(ethylene glycol) (PEG)-coated and carboxyl-coated polystyrene (PS-PEG and PS-COOH respectively) nanoparticles (NPs) were used to evaluate the aggregation kinetics, colloidal stability, and diffusive capability of nanoparticles in conditions relevant to the brain microenvironment. Size, surface charge, and surface coating were varied in a range of CSF ion concentrations and compositions, pH conditions, and temperatures. Small changes in calcium concentration and pH destabilize nanoparticles in CSF. However, PS-PEG NPs remain stable over a wider variety of conditions than PS-COOH NPs, and have higher diffusion capabilities in both agarose gels, an in vitro model of the brain microenvironment, and an organotypic brain tissue slice model. These results demonstrate the need for steric stabilization to maintain nanoparticle colloidal stability in a wide range of conditions. Importantly, colloidal stabilization allows for increased diffusive capability and can be used to predict diffusive behavior in the brain microenvironment.