Localizatome

Localizatome captures stress-induced protein localization dynamics in living cells through high-throughput microscopy and machine learning analysis, providing open access to protein localization pattern data under oxidative stress.

Key Features:

• Stress-Induced Localization Database: Documents protein localization changes specifically under oxidative stress conditions, complementing existing steady-state localization databases.
• High-Throughput Microscopy Data: Contains localization patterns for 10,287 fluorescent protein-fused human proteins in HeLa cells analyzed before and after oxidative stress exposure.
• Machine Learning Analysis: Employs machine learning algorithms to analyze and classify protein localization patterns from microscopy data.
• Stress-Dependent Localization Change Identification: Identifies 1,910 proteins exhibiting oxidative stress-dependent localization changes, particularly distinct foci formation.
• Motif and Domain Analysis: Identifies specific amino acid motifs and intrinsically disordered regions associated with stress-induced protein redistribution.

Scientific Applications:

• Cellular Stress Response Research: Supports studies on cellular stress response mechanisms by providing dynamic localization data for stress granule assembly factors, autophagy-related proteins, and components of various signalling pathways.
• Disease Mechanism Investigation: Facilitates research on disease mechanisms involving protein mislocalization under stress conditions.
• Protein Redistribution Pattern Analysis: Enables analysis of stress-induced protein redistribution patterns and their association with specific sequence features.

Methodology:

Proteins were analyzed using an original high-throughput microscopy system and machine learning algorithms to determine localization patterns of fluorescent protein-fused human proteins in HeLa cells before and after exposure to oxidative stress.