HPiP

HPiP uses an ensemble learning algorithm to predict host-pathogen protein-protein interactions (HP-PPIs) from structural and physicochemical descriptors computed from amino acid composition of host and pathogen proteins.

Key Features:

• Ensemble learning algorithm: Predicts HP-PPIs by integrating multiple learning approaches.
• Structural and physicochemical descriptors: Computes descriptors from amino acid composition of host and pathogen proteins for interaction prediction.
• Data shortage handling: Addresses data shortages and data unavailability for HP-PPI network reconstructions.
• Target prioritization: Narrows down candidate ranges for subsequent wet-lab experimental validations by suggesting potential HP-PPI targets.

Scientific Applications:

• Infectious disease mechanism elucidation: Reveals mechanistic insights into infectious diseases through computational framework establishment.
• HP-PPI network reconstruction: Reconstructs host-pathogen protein-protein interaction networks under conditions of limited available data.
• Target identification for experimental validation: Identifies potential HP-PPI targets to guide wet-lab experimental validation efforts.

Methodology:

HPiP employs an ensemble learning algorithm with structural and physicochemical descriptors computed from amino acid composition of host and pathogen proteins.