Open AccessOnePetri: Accelerating Common Bacteriophage Petri Dish Assays with Computer Vision
Author(s) -
Michael Shamash,
Corinne F. Maurice
Publication year - 2021
Publication title -
phage
Language(s) - English
Resource type - Journals
eISSN - 2641-6549
pISSN - 2641-6530
DOI - 10.1089/phage.2021.0012
Subject(s) - petri dish , enumeration , bacteriophage , computer science , petri net , throughput , artificial intelligence , mathematics , algorithm , biology , discrete mathematics , operating system , wireless , microbiology and biotechnology , biochemistry , escherichia coli , gene
Bacteriophage plaque enumeration is a critical step in a wide array of protocols. The current gold standard for plaque enumeration on Petri dishes is through manual counting. However, this approach is not only time-consuming and prone to human error but also limited to Petri dishes with countable number of plaques resulting in low throughput. Materials and Methods: We present OnePetri, a collection of trained machine learning models and open-source mobile application for the rapid enumeration of bacteriophage plaques on circular Petri dishes. Results: When compared against the current gold standard of manual counting, OnePetri was ∼30 × faster. Compared against other similar tools, OnePetri had lower relative error (∼13%) than Plaque Size Tool (PST) (∼86%) and CFU.AI (∼19%), while also having significantly reduced detection times over PST (1.7 × faster). Conclusions: The OnePetri application is a user-friendly platform that can rapidly enumerate phage plaques on circular Petri dishes with high precision and recall.