VisINet — trained SARS-CoV-2 Mpro model

Le résumé fourni par la source

This is the trained VisINet model used for the prospective SARS-CoV-2 main protease (Mpro)virtual screening reported in: > Yasuo, N.; Yoda, H.; Yamamoto, K. Z.; Sekijima, M. *VisINet: Prospective> Structure-Based Virtual Screening Identifies SARS-CoV-2 Main Protease Hit Compounds.* VisINet is an image-based virtual screening method: compounds are scored from renderedimages of their protein–ligand docking poses, without molecular descriptors or dockingscores as network inputs. This checkpoint is the model that reranked the top 100,000Glide SP poses and produced the 1,100-compound selection from which five hits withquantifiable IC50 values were confirmed. See README.md for further information.

Ce résumé expose les affirmations des auteurs. BNTIC ne l’interprète pas comme une validation indépendante des résultats.