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

Abstract

<p>A unique approach to bioactivity and chemical data curation coupled with Random forest analyses has led to a series of target-specific and cross-validated Predictive Feature Fingerprints (PFF) that have high predictability across multiple therapeutic targets and disease stages involved in the SARS-CoV-2 induced COVID-19 pandemic, which include plasma kallikrein, HIV protease, NSP5, NSP12, JAK family and AT-1. The approach was highly accurate in determining the matched target for the different compound sets and suggests that the models could be used for virtual screening of target specific compound libraries. The curation-modeling process was successfully applied to a SARS-CoV-2 phenotypic screen and could be used for predictive bioactivity estimation and prioritization for clinical trial selection, virtual screening of drug libraries for repurposing of drug molecules, and analysis and direction of proprietary datasets.</p>

Resources and computational strategies to advance small molecule SARS-CoV-2 discovery: Lessons from the pandemic and preparing for future health crises

“…In modern days, many different in silico approaches can be used to assist the design of a drug candidate or drug, from data (e.g., text and image) mining (e.g., annotated drug databases, antiviral peptide databases, electronic health patient records…), genome analysis, comparative genomics, multiple sequence alignments, visualization tools for epidemiological studies, analysis of macromolecular interaction networks, structural predictions (e.g., comparative modeling, protein folding…), antibody-drug conjugate, analysis of point mutations, protein docking, various types of molecular simulation engines (e.g., for proteins, peptides, small molecules, cell membrane, DNA, RNA, glycans, and interactions among these molecules…), binding pocket predictions, PROTACs (e.g., degradation of viral protein capsids), transcriptomic profile analysis, virtual screening (from small collections of approved drugs as in drug repositioning or repurposing projects to the screening of ultra-large virtual libraries), hit to lead optimization, drug combination, computational polypharmacology and compound profiling, ADMET prediction, multiparameter optimization methods associated with novel data visualization approaches, systems biology, systems pharmacology, with or without the use of machine learning and artificial intelligence (AI) algorithms depending on the type of methods, available data and the stage of the projects [19] , [77] , [80] , [127] , [128] , [129] , [130] , [131] , [132] , [133] , [134] , [135] , [136] , [137] , [138] , [139] , [140] , [141] , [142] , [143] , [144] , [145] , [146] , [147] , [148] , [149] , [150] , [151] , [152] , [153] , [154] , [155] , [156] , [157] , [158] , [159] , [160] , [161] , [162] , [163] , [164] , [165] , [166] , [167] , [168] , [169] , …”