Computational prediction of eukaryotic phosphorylation sites

Area of Science:

• Biochemistry
• Bioinformatics
• Computational Biology

Background:

• Protein phosphorylation is a key post-translational modification regulating cellular functions.
• Dysregulated phosphorylation is implicated in diseases like cancer.
• Identifying phosphorylation sites is crucial for understanding signaling networks and disease mechanisms.

Purpose of the Study:

• To review and categorize computational methods for predicting protein phosphorylation sites.
• To compare existing prediction tools based on various criteria.
• To provide insights into challenges and solutions in phosphorylation site prediction.

Main Methods:

• Literature review and categorization of computational phosphorylation site prediction methods.
• Comparison of methods based on machine learning techniques, data sources, and use of sequence/structural information.
• Analysis of challenges in predictor design and their resolutions.

Main Results:

• Numerous web-accessible computational tools for phosphorylation site prediction exist.
• Methods vary in their approach, including machine learning algorithms and data utilization.
• The review categorizes and compares these diverse prediction strategies.

Conclusions:

• Computational prediction of phosphorylation sites offers significant value due to the resource-intensive nature of experimental methods.
• This review serves as a guide for selecting appropriate prediction tools for biological applications.
• It also aids researchers aiming to enhance existing phosphorylation site prediction techniques.