Litcius/Paper detail

Beware of Simple Methods for Structure-Based Virtual Screening: The Critical Importance of Broader Comparisons

Viet‐Khoa Tran‐Nguyen, Pedro J. Ballester

2023Journal of Chemical Information and Modeling23 citationsDOIOpen Access PDF

Abstract

We discuss how data unbiasing and simple methods such as protein-ligand Interaction FingerPrint (IFP) can overestimate virtual screening performance. We also show that IFP is strongly outperformed by target-specific machine-learning scoring functions, which were not considered in a recent report concluding that simple methods were better than machine-learning scoring functions at virtual screening.

Topics & Concepts

Virtual screeningSimple (philosophy)Computer scienceMachine learningArtificial intelligenceFingerprint (computing)Data miningDrug discoveryBioinformaticsBiologyEpistemologyPhilosophyComputational Drug Discovery MethodsBioinformatics and Genomic NetworksProtein Structure and Dynamics