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

[Image: see text] 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...

Descripción completa

Detalles Bibliográficos
Autores principales: Tran-Nguyen, Viet-Khoa, Ballester, Pedro J.
Formato: Online Artículo Texto
Lenguaje:English
Publicado: American Chemical Society 2023
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10015451/
https://www.ncbi.nlm.nih.gov/pubmed/36848585
http://dx.doi.org/10.1021/acs.jcim.3c00218
_version_ 1784907211101700096
author Tran-Nguyen, Viet-Khoa
Ballester, Pedro J.
author_facet Tran-Nguyen, Viet-Khoa
Ballester, Pedro J.
author_sort Tran-Nguyen, Viet-Khoa
collection PubMed
description [Image: see text] 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.
format Online
Article
Text
id pubmed-10015451
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher American Chemical Society
record_format MEDLINE/PubMed
spelling pubmed-100154512023-03-16 Beware of Simple Methods for Structure-Based Virtual Screening: The Critical Importance of Broader Comparisons Tran-Nguyen, Viet-Khoa Ballester, Pedro J. J Chem Inf Model [Image: see text] 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. American Chemical Society 2023-02-27 /pmc/articles/PMC10015451/ /pubmed/36848585 http://dx.doi.org/10.1021/acs.jcim.3c00218 Text en © 2023 The Authors. Published by American Chemical Society https://creativecommons.org/licenses/by/4.0/Permits the broadest form of re-use including for commercial purposes, provided that author attribution and integrity are maintained (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Tran-Nguyen, Viet-Khoa
Ballester, Pedro J.
Beware of Simple Methods for Structure-Based Virtual Screening: The Critical Importance of Broader Comparisons
title Beware of Simple Methods for Structure-Based Virtual Screening: The Critical Importance of Broader Comparisons
title_full Beware of Simple Methods for Structure-Based Virtual Screening: The Critical Importance of Broader Comparisons
title_fullStr Beware of Simple Methods for Structure-Based Virtual Screening: The Critical Importance of Broader Comparisons
title_full_unstemmed Beware of Simple Methods for Structure-Based Virtual Screening: The Critical Importance of Broader Comparisons
title_short Beware of Simple Methods for Structure-Based Virtual Screening: The Critical Importance of Broader Comparisons
title_sort beware of simple methods for structure-based virtual screening: the critical importance of broader comparisons
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10015451/
https://www.ncbi.nlm.nih.gov/pubmed/36848585
http://dx.doi.org/10.1021/acs.jcim.3c00218
work_keys_str_mv AT trannguyenvietkhoa bewareofsimplemethodsforstructurebasedvirtualscreeningthecriticalimportanceofbroadercomparisons
AT ballesterpedroj bewareofsimplemethodsforstructurebasedvirtualscreeningthecriticalimportanceofbroadercomparisons

Ejemplares similares