YeastMate

YeastMate detects and segments Saccharomyces cerevisiae cells in microscopy images and subclassifies mating and budding events to support quantitative analysis of cell cycle and developmental processes.

Key Features:

• Deep learning-based automation: Uses deep learning with an adaptation of Mask R-CNN and a custom segmentation head for automated detection and segmentation of cells from microscopy images.
• Lifecycle event detection: Identifies mating and budding events as dynamic cellular processes in microscopy data.
• Cell subclassification: Subclassifies cells to distinguish mother and daughter cells during lifecycle transitions.
• Microscopy image analysis: Operates on microscopy images of Saccharomyces cerevisiae to extract cellular structures and events.

Scientific Applications:

• Cell morphology analysis: Quantifies cellular morphology and structural features of S. cerevisiae from microscopy images.
• Cell cycle and reproductive studies: Detects mating and budding events for investigations of cell cycle dynamics and reproductive processes.
• Lineage and developmental analysis: Differentiates mother and daughter cells to support studies of cellular lineage and development.

Methodology:

Deep learning-based image analysis using an adapted Mask R-CNN architecture with a custom segmentation head for detection, segmentation, and subclassification of mating and budding events in microscopy images.