Automated Machine Learning in Flow Cytometry

The primary objective of our study was to accurately identify and distinguish the unique flowcytometric phenotypic fingerprints of bacterial cells from defined cultures, reducing subjective bias through the use of autogating and AutoML techniques. Notes: bs: Bacillus subtilis subsp. spizizenii bt: Burkholderia thailandensis cg: Corynebacterium glutamicum ec: Escherichia coli pp: Pseudomonas putida ps: pseudomonas stutzeri