SProtP: a web server to recognize those short-lived proteins based on sequence-derived features in human cells

Area of Science:

• Biochemistry and Molecular Biology
• Computational Biology
• Cell Biology

Background:

• Protein turnover is crucial for cellular processes like cell cycle progression and signal transduction.
• Short-lived proteins are key regulators, but their half-lives are difficult to measure experimentally.
• Understanding sequence-derived factors influencing short-lived protein degradation is vital for cell biology research.

Purpose of the Study:

• To develop a computational method for recognizing short-lived proteins in human cells using sequence-derived features.
• To identify molecular determinants that affect the degradation of short-lived proteins.
• To provide a more accurate and accessible tool for short-lived protein identification.

Main Methods:

• Systematic analysis of sequence-derived features correlated with protein degradation.
• Development of a Support Vector Machine (SVM)-based classifier for short-lived protein recognition.
• Validation of the SVM model on multiple independent human datasets.

Main Results:

• Proteins with signal peptides and transmembrane regions were found to have predominantly short half-lives.
• The SVM classifier achieved high performance, with average sensitivity of 80.8% and specificity of 79.8% on testing datasets.
• Excellent accuracy was obtained on independent validation datasets (up to 99%).

Conclusions:

• The proposed computational approach effectively recognizes short-lived proteins based on sequence features.
• This method offers a significant improvement in accuracy over traditional techniques like the N-end rule.
• A web server, SProtP, has been developed for public access to this valuable tool.