HNSPPI: a hybrid computational model combing network and sequence information for predicting protein-protein...

Area of Science:

• Molecular Biology
• Bioinformatics
• Computational Biology

Background:

• Protein-protein interactions (PPIs) regulate essential life activities and are crucial for understanding biological processes and drug discovery.
• Experimental methods for PPI detection are limited by cost, time, and inability to capture transient interactions.
• Existing computational methods for PPI prediction face challenges in efficiency and data complexity.

Purpose of the Study:

• To develop a novel computational framework, HNSPPI, for accurate prediction of protein-protein interactions.
• To overcome the limitations of current PPI prediction methods by integrating diverse biological data.
• To identify potential therapeutic targets through enhanced PPI prediction.

Main Methods:

• HNSPPI utilizes a hybrid supervised learning approach.
• It integrates amino acid sequence information and protein-protein interaction network properties.
• The model comprehensively characterizes the intrinsic relationship between proteins.

Main Results:

• HNSPPI demonstrated high performance on six benchmark datasets.
• The model significantly outperformed five existing PPI prediction algorithms.
• HNSPPI identified potential SARS-CoV-2-Human interactions, suggesting new regulatory mechanisms.

Conclusions:

• HNSPPI is a robust and effective model for predicting novel protein-protein interactions.
• The framework offers a promising approach for advancing PPI research and drug discovery.
• HNSPPI provides valuable insights into complex biological systems like SARS-CoV-2-Human interactions.