Abstract
Whole-cell biosensors (WCBs) offer rapid, cost-effective monitoring of environmental contamination and human disease. Current WCB efforts to optimize detection of single target analytes under laboratory conditions have achieved vastly improved performance, setting the stage for WCB deployment in complex environments. We propose a framework that leverages the cross-specificity of single-target WCBs to quantify multiple targets using supervised machine learning. Specifically, we engineer six sensors for heavy metal contaminants in laboratory E. coli. We then evolve the strain to generate five chassis with improved growth in seawater conditions. We transform the chassis with the sensors, creating a set of 30 variants. The variant dynamic responses are characterized with microfluidics, revealing significant diversity. Leveraging this diversity, we construct a consortium to combinatorically quantify multiple analytes with machine learning, outperforming single-target biosensors in over 90% of our test samples. These results form a generalizable framework that facilitates WCB translation toward settings beyond the laboratory.