Novel Development of Predictive Feature Fingerprints to Identify Chemistry-Based Features for the Effective Drug Design of SARS-CoV-2 Target Antagonists and Inhibitors Using Machine Learning

A unique approach to bioactivity and chemical data curation coupled with random forest analyses has led a series of target-specific cross-validated predictive feature fingerprints (PFF) that have high predictability across multiple therapeutic targets disease stages involved in the severe acute respiratory syndrome due coronavirus 2 (SARS-CoV-2)-induced COVID-19 pandemic, which include plasma kallikrein, human immunodeficiency virus (HIV)-protease, nonstructural protein (NSP)5, NSP12, Janus kinase (JAK) family, AT-1. The was highly accurate determining matched target for different compound sets suggests models could be used virtual screening libraries. curation-modeling process successfully applied SARS-CoV-2 phenotypic screen estimation prioritization clinical trial selection; drug libraries repurposing molecules; analysis direction proprietary sets.