Yi Chen1,Jingyu Wang1,Ben Hoar1,Shengtao Lu1,Chong Liu1
University of California, Los Angeles1
Yi Chen1,Jingyu Wang1,Ben Hoar1,Shengtao Lu1,Chong Liu1
University of California, Los Angeles1
A fundamental understanding of the extracellular microenvironments of O<sub>2</sub> and reactive oxygen species (ROS) such as H<sub>2</sub>O<sub>2</sub>, ubiquitous in microbiology, demands high-throughput methods of mimicking, controlling, and perturbing gradients of O<sub>2</sub> and H<sub>2</sub>O<sub>2</sub> at microscopic scale with high spatiotemporal precision. However, there is a paucity for a high-throughput strategy of microenvironment design and it remains challenging to achieve O<sub>2</sub> and H<sub>2</sub>O<sub>2</sub> heterogeneities with the microbiologically desirable spatiotemporal resolutions. Here we report the inverse design, based on machine learning (ML), of electrochemically generated microscopic O<sub>2</sub> and H<sub>2</sub>O<sub>2</sub> profiles relevant for microbiology. Microwire arrays with suitably designed electrochemical catalysts enable the independent control of O<sub>2</sub> and H<sub>2</sub>O<sub>2</sub> profiles with spatial resolution of ~10<sup>1</sup> μm and temporal resolution of ~10<sup>0</sup> sec. Neural networks aided by data augmentation inversely design the experimental conditions needed for targeted O<sub>2</sub> and H<sub>2</sub>O<sub>2</sub> microenvironments while being order-of-magnitude faster. Interfacing ML-based inverse design with electrochemically controlled concentration heterogeneity creates a viable fast-response platform towards better understanding the extracellular space with desirable spatiotemporal control.