Project Summary Biofilms are intrinsically drug-resistant. While the signaling pathways mediating resistance in biofilms are documented, only recently has the importance of electrophysiology in modifying gentamicin resistance come to light. However, the role of electrophysiology in biofilm formation and maturation is unknown. Furthermore, we currently lack high throughput screening techniques for assessing the bactericidal potential of treatment strategies against clinical biofilms. During my K99 training, I will investigate how mechanically-stimulated calcium fluctuations modify the c-di-GMP pools (Aim 1.1) and bacterial swarming (Aim 1.2) leading to biofilm formation. Concomitantly, I will deploy an assay for measur- ing biofilm viability in high throughput to screen for antibiotic adjuvants against biofilms (Aim 2.1). During this phase, my training will focus on the culture of biofilms, analysis of non-optical electrophysiology data, and building machine learning models subsequently applied during my R00 phase. Following my K99 phase, I will investigate the electrophysiology of mature biofilms using both optical and non-optical techniques and correlate changes in antibiotic tolerance across the biofilm life-cycle with changes in electrophysiology (Aim 1.3). Concomitantly, I will build and train deep learning models to predict gentamicin adjuvants against slow-growing cells based on viability data collected in my K99 phase (Aim 2.2). The product of my project will enrich our understanding of biofilm electrophysiology and enable methods for mitigating their formation or promoting their retention as is desirable for probiotics. Additionally, this work will deliver new machine learning technologies for finding antibiotic adjuvants to combat drug-resistant clinical biofilms.