High-throughput screening accelerated by machine learning for morphology of silica nanoparticles with high cell permeability

Abstract

Silica nanoparticles have garnered tremendous attention as drug delivery carriers in recent years. Then, the cell permeability of nanoparticles is a major obstacle that limits the delivery efficacy of drugs. People always regulate the low-dimensional characteristics of nanoparticles to promote their permeability, such as the charge and the size. In addition, the morphology of nanoparticles has also been proven to be a significant influence factor. However, it’s still a challenge to screen the high-dimensional characteristics of nanoparticles to optimize the cell permeability. Herein, we introduce a high-throughput screening framework accelerated by machine learning for the morphology of silica nanoparticles with high cell permeability. We find that icosahedral morphology, the common morphology of the virus, exhibits the best performance. The superior permeability of the icosahedral nanoparticles is attributed to their larger rotation freedom during the internalization process, which promotes the formation of pores in the cell membrane. These findings are expected to inspire the design of efficient drug-delivery nanocarriers.