A diversified consortium of engineered biosensors enables multi-target quantification.

Whole-cell biosensors (WCBs) offer rapid, cost-effective monitoring of environmental contamination. Efforts to optimize detection of isolated target analytes under laboratory conditions have achieved vastly improved performance and set the stage for WCB deployment in complex environments. We propose a framework that leverages cross-reactivity 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 and transform them with the sensors to create a set of 30 variants. The variant responses are characterized with microfluidics, revealing significant diversity. Leveraging this diversity, we combinatorially quantify multiple analytes with a machine learning model that takes an in silico consortium of response inputs and outperforms single-target WCBs in over 90% of test samples. These results form a generalizable framework that facilitates WCB translation toward settings beyond the laboratory. A record of this paper's transparent peer review process is included in the supplemental information.