High-Content Screening and Analysis of Stem Cell-Derived Neural Interfaces Using a Combinatorial Nanotechnology and Machine Learning Approach

Abstract

A systematic investigation of stem cell-derived neural interfaces can facilitate the discovery of the molecular mechanisms behind cell behavior in neurological disorders and accelerate the development of stem cell-based therapies. Nevertheless, high-throughput investigation of the cell-type-specific biophysical cues associated with stem cell-derived neural interfaces continues to be a significant obstacle to overcome. To this end, we developed a combinatorial nanoarray-based method for high-throughput investigation of neural interface micro-/nanostructures (physical cues comprising geometrical, topographical, and mechanical aspects) and the effects of these complex physical cues on stem cell fate decisions. Furthermore, by applying a machine learning (ML)-based analytical approach to a large number of stem cell-derived neural interfaces, we comprehensively mapped stem cell adhesion, differentiation, and proliferation, which allowed for the cell-type-specific design of biomaterials for neural interfacing, including both adult and human-induced pluripotent stem cells (hiPSCs) with varying genetic backgrounds. In short, we successfully demonstrated how an innovative combinatorial nanoarray and ML-based platform technology can aid with the rational design of stem cell-derived neural interfaces, potentially facilitating precision, and personalized tissue engineering applications.