Artificial Intelligence Approach in Machine Learning-Based Modeling and Networking of the Coronavirus Pathogenesis...

Area of Science:

• Virology
• Computational Biology
• Bioinformatics

Background:

• The coronavirus pathogenesis pathway, involving signaling cascades like interferon and apoptosis, is activated during severe acute respiratory syndrome (SARS) coronavirus infection.
• Understanding these pathways is crucial for developing targeted therapies against coronaviruses, including SARS-CoV-2.

Purpose of the Study:

• To develop and validate machine learning models for predicting the activation states of the coronavirus pathogenesis pathway.
• To analyze SARS-CoV-2 infection data using Ingenuity Pathway Analysis (IPA) to identify relevant pathways and cell types.

Main Methods:

• Utilized artificial intelligence and machine learning on images of the coronavirus pathogenesis pathway.
• Analyzed over 100,000 SARS-CoV-2 related datasets from the IPA database.
• Developed a prediction model in Python 3.11 using pathway images from infected human-induced pluripotent stem cells (iPSCs) and lung adenocarcinoma (LUAD) cells.

Main Results:

• The coronavirus pathogenesis pathway was found to be activated in SARS-CoV-2-infected iPSC-derived cells and LUAD cells.
• Machine learning models were successfully developed to predict pathway activation states.
• Identified 27 relevant analyses, including those involving iPSC-derived cells and LUAD.

Conclusions:

• The developed prediction model for coronavirus pathogenesis pathway activation states shows potential for aiding in treatment identification for SARS-CoV-2 infections.
• This AI-driven approach offers a novel method for analyzing complex viral pathogenesis pathways.