Machine Learning Establishes Single-Cell Calcium Dynamics as an Early Indicator of Antibiotic Response

Changes in bacterial physiology necessarily precede cell death in response to antibiotics. Herein we investigate the early disruption of Ca(2+) homeostasis as a marker for antibiotic response. Using a machine learning framework, we quantify the temporal information encoded in single-cell Ca(2+) dynamics. We find Ca(2+) dynamics distinguish kanamycin sensitive and resistant cells before changes in gross cell phenotypes such as cell growth or protein stability. The onset time (pharmacokinetics) and probability (pharmacodynamics) of these aberrant Ca(2+) dynamics are dose and time-dependent, even at the resolution of single-cells. Of the compounds profiled, we find Ca(2+) dynamics are also an indicator of Polymyxin B activity. In Polymyxin B treated cells, we find aberrant Ca(2+) dynamics precedes the entry of propidium iodide marking membrane permeabilization. Additionally, we find modifying membrane voltage and external Ca(2+) concentration alters the time between these aberrant dynamics and membrane breakdown suggesting a previously unappreciated role of Ca(2+) in the membrane destabilization during Polymyxin B treatment. In conclusion, leveraging live, single-cell, Ca(2+) imaging coupled with machine learning, we have demonstrated the discriminative capacity of Ca(2+) dynamics in identifying antibiotic-resistant bacteria.