id	author	title	date	pages	extension	mime	words	sentences	flesch	summary	cache	txt
cord-329318-eo8auo1f	Gusarov, Sergey	COSMO-RS-Based Descriptors for the Machine Learning-Enabled Screening of Nucleotide Analogue Drugs against SARS-CoV-2	2020-10-26		.txt	text/plain	3971	217	46	[Image: see text] Chemical similarity-based approaches employed to repurpose or develop new treatments for emerging diseases, such as COVID-19, correlates molecular structure-based descriptors of drugs with those of a physiological counterpart or clinical phenotype. In this study, we propose a novel set of drug screening descriptors based on COSMO-RS σ-profiles, augmented by dipole moment and induced charge of the phosphorus atom, to evaluate the chemical similarity of the drugs with nucleotides, as RNA replication transcription initiation activators. A novel set of descriptors based on COSMO-RS σ-profiles and chemical thermodynamics is proposed and evaluated using PCA for the initial screening of a series of nucleotides and nucleotide-analog RdRp replication inhibitor drugs to help accelerate the discovery of COVID-19 treatments. The PCA results show that the novel σ-profile-based descriptor set I clearly correlates the leading COVID-19 drugs remdesivir and EIDD-2801 in monophosphate forms and highlights weaker correlations with drugs that have been reported to exhibit anti-SARS-CoV-2 activity.	./cache/cord-329318-eo8auo1f.txt	./txt/cord-329318-eo8auo1f.txt