Deciphering the Interactions of SARS-CoV-2 Proteins with Human Ion Channels Using Machine-Learning-Based Methods

Area of Science:

• Virology
• Computational Biology
• Drug Discovery

Background:

• Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) causes the COVID-19 pandemic.
• Ion channels play a crucial role in the molecular pathogenesis of SARS-CoV-2 infection.
• Machine learning (ML) enhances the accuracy of predicting host-pathogen protein-protein interactions (PPIs).

Purpose of the Study:

• To investigate SARS-CoV-2 protein interactions with human ion channels (HICs).
• To identify potential drug targets for COVID-19 treatment.
• To explore host pathways affected by SARS-CoV-2.

Main Methods:

• Utilized the PPI-MetaGO algorithm to train and predict PPIs between SARS-CoV-2 proteins and HICs.
• Generated protein-protein interaction networks (PPINs) and signaling pathway maps.
• Identified U.S. Food and Drug Administration (FDA)-approved drugs targeting relevant HICs.

Main Results:

• Achieved high prediction accuracy for PPIs (82.71%) with strong precision and sensitivity.
• Identified altered host pathways, including calcium signaling and taste transduction.
• Highlighted potential HICs as targets for experimental validation and drug repurposing.

Conclusions:

• The study provides valuable insights into host-pathogen interactions, specifically involving ion channels in SARS-CoV-2 infection.
• Identified potential HICs and FDA-approved drugs offer a promising avenue for developing host-directed antiviral therapies.
• Reinforces drug repurposing as a strategy for effective COVID-19 therapeutic management.