Geometric Hashing and ΑΙ-Quantum Deep Learning functional similarities
on Remdesivir, drug synergies to treat COVID-19 in Practice.
Abstract
Νovel SARS coronavirus 2 (SARS-CoV-2) of the family Coronaviridae
starting in China and spreading around the world is an enveloped,
positive-sense, single-stranded RNA of the genus betacoronavirus
encoding the SARS-COV-2 (2019-NCOV, Coronavirus Disease 2019. Remdesivir
drug, or GS-5734 lead compound, first described in 2016 as a potential
anti-viral agent for Ebola diseade and has also being researched as a
potential therapeutic agent against the severe acute respiratory
syndrome coronavirus 2 (SARS-CoV-2), the coronavirus that causes
coronavirus disease 2019 (COVID-19). Computer-aided drug design (CADD),
Structure and Ligand based Drug Repositioning strategies based on
parallel docking methodologies have been widely used for both modern
drug development and drug repurposing to find effective treatments
against this disease. Quantum mechanics, molecular mechanics, molecular
dynamics (MD), and combinations have shown superior performance to other
drug design approaches providing an unprecedented opportunity in the
rational drug development fields and for the developing of innovative
drug repositioning methods. We tested 18 phytochemical small molecule
libraries and predicted their synergies in COVID-19 (2019- NCOV), to
devise therapeutic strategies, repurpose existing ones in order to
counteract highly pathogenic SARS-CoV-2 infection. We anticipate that
our geometry hashing driven quantum deep learing similarity approaches
which is based on separated pairs of short consecutive matching
fragments, can be used for the development of anticoronaviral drug
combinations in large scale HTS screenings, and to maximize the safety
and efficacy of the Remdesivir, Colchicine and Ursolic acid drugs
already known to induce synergy with potential therapeutic value or drug
repositioning to COVID-19 patients.