isGP-DRLF

isGP-DRLF identifies sub-Golgi protein localization using deep representation learning features to characterize protein distribution across Golgi sub-compartments.

Key Features:

• Deep representation learning (107-dimensional features): Extracts deep representation learning features from protein sequences represented as a 107-dimensional feature vector.
• Single-type feature representation: Uses a single type of feature representation rather than multi-type sequence feature fusion to improve identification accuracy of sub-Golgi proteins.
• Benchmark-tested performance: Demonstrates general, reliable, and robust performance in predicting sub-Golgi protein localization on benchmark datasets.

Scientific Applications:

• Sub-Golgi localization mapping: Predicts localization of proteins within Golgi sub-compartments to support spatial proteomics analyses.
• Cell biology and bioinformatics studies: Supports investigation of Golgi apparatus functions and protein sorting mechanisms.
• Neurodegenerative disease research: Provides localization data relevant to studies of Golgi-related mechanisms in neurodegenerative disorders.
• Molecular mechanism and therapeutic insight: Informs studies of molecular mechanisms and potential therapeutic strategies related to Golgi dysfunction.

Methodology:

Extracts deep representation learning features as a 107-dimensional vector from protein sequences, employs a single-type feature representation rather than multi-type sequence feature fusion, and evaluates performance on benchmark datasets.