PROSPECT: A web server for predicting protein histidine phosphorylation sites.

Area of Science:

• Biochemistry
• Computational Biology
• Proteomics

Background:

• Histidine phosphorylation is vital for bacterial signaling and metabolism.
• Its role in mammalian cells is understudied, highlighting the need for predictive tools.
• Identifying histidine phosphorylation sites is essential for understanding cellular processes.

Purpose of the Study:

• To develop a computational tool for predicting histidine phosphorylation substrates and sites.
• To provide a user-friendly web server for researchers.

Main Methods:

• PROSPECT utilizes a hybrid approach integrating two convolutional neural network (CNN) classifiers and a random forest classifier.
• Input features include one-of-K coding, enhanced grouped amino acids content (EGAAC), and composition of k-spaced amino acid group pairs (CKSAAGP).

Main Results:

• PROSPECT accurately predicts histidine phosphorylation sites using only protein sequence information.
• The tool demonstrates high accuracy and speed in proteome-wide predictions.
• A user-friendly web server is publicly available.

Conclusions:

• PROSPECT outperforms existing phosphohistidine (pHis) predictors in speed and accuracy.
• The PROSPECT web server is expected to be a valuable resource for identifying pHis sites, particularly in bacteria.