Candida species Identification
Disciplines
Bacterial Infections and Mycoses | Medical Microbiology
Abstract (300 words maximum)
The genus Candida is a vast collection of more than 200 species of yeast. Some of these are commensals that live in harmony with the human body, while others are pathogenic. Discovered in 2009, C. auris is a pathogenic species of Candida which has a deleterious effect on patients in acute healthcare settings. This is a yeast of interest as it is hard to differentiate from other species in the Candida genus, and it has the highest morbidity rate of all the Candida spp. Many existing diagnostic platforms have a very high misidentification rate with C. auris, a challenge that is in need of an effective solution. This project is focused on developing a diagnostic platform which will allow for identifying for C. auris with routine laboratory equipment. The approach involves taking microscope images of cell cultures of Candida spp. and processing the micrographs by a machine learning algorithm to find any morphological differences in the species, allowing for adaptive identification.
Academic department under which the project should be listed
Science and Mathematics
Primary Investigator (PI) Name
Dr. Chris Cornelison
Candida species Identification
The genus Candida is a vast collection of more than 200 species of yeast. Some of these are commensals that live in harmony with the human body, while others are pathogenic. Discovered in 2009, C. auris is a pathogenic species of Candida which has a deleterious effect on patients in acute healthcare settings. This is a yeast of interest as it is hard to differentiate from other species in the Candida genus, and it has the highest morbidity rate of all the Candida spp. Many existing diagnostic platforms have a very high misidentification rate with C. auris, a challenge that is in need of an effective solution. This project is focused on developing a diagnostic platform which will allow for identifying for C. auris with routine laboratory equipment. The approach involves taking microscope images of cell cultures of Candida spp. and processing the micrographs by a machine learning algorithm to find any morphological differences in the species, allowing for adaptive identification.