pcnaDeep

pcnaDeep performs single-cell tracking and cell-cycle profiling in time-lapse microscopy by combining deep-learning PCNA (Proliferating Cell Nuclear Antigen) instance segmentation with mother-daughter lineage assignment using fluorescent cell-cycle biosensors.

Key Features:

• Automated Single-Cell Tracking: Automates tracking of individual cells across time-lapse sequences while maintaining cell identities over extended periods.
• Mother-Daughter Relationship Assignment: Assigns mother-daughter relationships at cell division events using fluorescent biosensors that report cell-cycle information.
• Deep-Learning PCNA Segmentation: Applies deep-learning-based instance segmentation to detect and quantify PCNA signals associated with cell-cycle phases.
• Cell Cycle Profiling: Resolves mitosis relationships and profiles cell-cycle stages over long-term observations using fluorescent cell-cycle reporters.

Scientific Applications:

• Molecular Control of Cellular Decisions: Enables analysis of single-cell behaviors to study molecular mechanisms that govern cellular decision-making processes.
• Biomedical Research Enhancement: Supports long-term lineage-aware single-cell analysis across cell divisions for diverse biomedical research contexts.

Methodology:

Integrates deep-learning algorithms with traditional cell tracking and cell-cycle-resolving pipelines to process time-lapse microscopy imaging data.