Machine learning-based inverse design for electrochemically controlled microscopic gradients of O2 and H2O2

Abstract

A fundamental understanding of extracellular microenvironments of O2 and reactive oxygen species (ROS) such as H2O2, ubiquitous in microbiology, demands highthroughput methods of mimicking, controlling, and perturbing gradients of O2 and H2O2 at microscopic scale with high spatiotemporal precision. However, there is a paucity of high-throughput strategies of microenvironment design, and it remains challenging to achieve O2 and H2O2 heterogeneities with microbiologically desirable spatiotemporal resolutions. Here, we report the inverse design, based on machine learning (ML), of electrochemically generated microscopic O2 and H2O2 profiles relevant for microbiology. Microwire arrays with suitably designed electrochemical catalysts enable the independent control of O2 and H2O2 profiles with spatial resolution of ∼101 μm and temporal resolution of ∼10° s. Neural networks aided by data augmentation inversely design the experimental conditions needed for targeted O2 and H2O2 microenvironments while being two orders of magnitude faster than experimental explorations. Interfacing ML-based inverse design with electrochemically controlled concentration heterogeneity creates a viable fast-response platform toward better understanding the extracellular space with desirable spatiotemporal control.