[PSI]-CIC: A Deep-Learning Pipeline for the Annotation of Sectored Saccharomyces cerevisiae Colonies
Bulletin of Mathematical Biology · 2025
DOI: 10.1007/s11538-024-01379-w ↗Kurz gefasst
Fachartikel in der Zeitschrift Bulletin of Mathematical Biology, 2025. Verfasst von Jordan Collignon und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Applied Mathematics, University of California, Merced, 5200 N Lake Drive, Merced, CA, 95343, USA. Hauptthemen laut MEDLINE: Saccharomyces cerevisiae, Deep Learning, Prions, Phenotype. Die Arbeit nennt 66 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NIGMS NIH HHS, National Science Foundation, National Institute of General Medical Sciences.
Abstract (Originalsprache)
The $$[PSI^+]$$ [ P S I + ] prion phenotype in yeast manifests as a white, pink, or red color pigment. Experimental manipulations destabilize prion phenotypes, and allow colonies to exhibit $$[psi^-]$$ [ p s i - ] (red) sectored phenotypes within otherwise completely white colonies. Further investigation of the size and frequency of sectors that emerge as a result of experimental manipulation is capable of providing critical information on mechanisms of prion curing, but we lack a way to reliably extract this information. Images of experimental colonies exhibiting sectored phenotypes offer an abundance of data to help uncover molecular mechanisms of sectoring, yet the structure of sectored colonies is ignored in traditional biological pipelines. In this study, we present [ PSI ]-CIC, the first computational pipeline designed to identify and characterize features of sectored yeast colonies. To overcome the barrier of a lack of manually annotated data of colonies, we develop a neural network architecture that we train on synthetic images of colonies and apply to real images of $$[PSI^+]$$ [ P S I + ] , $$[psi^-]$$ [ p s i - ] , and sectored colonies. In hand-annotated experimental images, our pipeline correctly predicts the state of approximately 95% of colonies detected and frequency of sectors in approximately 89.5% of colonies detected. The scope of our pipeline could be extended to categorizing colonies grown under different experimental conditions, allowing for more meaningful and detailed comparisons between experiments. Our approach streamlines the analysis of sectored yeast colonies providing a rich set of quantitative metrics and provides insight into mechanisms driving the curing of prion phenotypes.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Department of Applied Mathematics, University of California, Merced, 5200 N Lake Drive, Merced, CA, 95343, USA.
- Department of Biochemistry and Molecular Biology, University of Massachusetts, Amherst, 240 Thatcher Rd, Amherst, MA, 01003, USA.
- Department of Chemistry and Biochemistry, University of Washington, 109 Bagley Hall, Seattle, WA, 98195, USA.
- Department of Applied Mathematics, University of California, Merced, 5200 N Lake Drive, Merced, CA, 95343, USA. ssindi@ucmerced.edu.
Förderung
- NIGMS NIH HHS
- National Science Foundation
- National Institute of General Medical Sciences
Zitieren
APA
Collignon, J., Naeimi, W., Serio, T. R., & Sindi, S. (2025). [PSI]-CIC: A Deep-Learning Pipeline for the Annotation of Sectored Saccharomyces cerevisiae Colonies. Bulletin of Mathematical Biology. https://doi.org/10.1007/s11538-024-01379-w
Vancouver
Collignon J, Naeimi W, Serio TR, Sindi S. [PSI]-CIC: A Deep-Learning Pipeline for the Annotation of Sectored Saccharomyces cerevisiae Colonies. Bulletin of Mathematical Biology. 2025. doi:10.1007/s11538-024-01379-w
BibTeX
@article{Collignon2025,
author = {Collignon, Jordan and Naeimi, Wesley and Serio, Tricia R and Sindi, Suzanne},
title = {[PSI]-CIC: A Deep-Learning Pipeline for the Annotation of Sectored Saccharomyces cerevisiae Colonies},
journal = {Bulletin of Mathematical Biology},
year = {2025},
doi = {10.1007/s11538-024-01379-w}
}
EUVIMED