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

The coronavirus pathogenesis pathway, which consists of severe acute respiratory syndrome (SARS) coronavirus infection and signaling pathways, including the interferon pathway, the transforming growth factor beta pathway, the mitogen-activated protein kinase pathway, the apoptosis pathway, and the inflammation pathway, is activated upon coronaviral infection. An artificial intelligence approach based on machine learning was utilized to develop models with images of the coronavirus pathogenesis pathway to predict the activation states. Data on coronaviral infection held in a database were analyzed with Ingenuity Pathway Analysis (IPA), a network pathway analysis tool. Data related to SARS coronavirus 2 (SARS-CoV-2) were extracted from more than 100,000 analyses and datasets in the IPA database. A total of 27 analyses, including nine analyses of SARS-CoV-2-infected human-induced pluripotent stem cells (iPSCs) and iPSC-derived cardiomyocytes and fibroblasts, and a total of 22 analyses of SARS-CoV-2-infected lung adenocarcinoma (LUAD), were identified as being related to "human" and "SARS coronavirus 2" in the database. The coronavirus pathogenesis pathway was activated in SARS-CoV-2-infected iPSC-derived cells and LUAD cells. A prediction model was developed in Python 3.11 using images of the coronavirus pathogenesis pathway under different conditions. The prediction model of activation states of the coronavirus pathogenesis pathway may aid in treatment identification.