AlphaFold illuminates half of the dark human proteins

Jessica L Binder; Joel Berendzen; Amy O Stevens; Yi He; Jian Wang; Nikolay V Dokholyan; Tudor I Oprea

doi:10.1016/j.sbi.2022.102372

AlphaFold illuminates half of the dark human proteins

Curr Opin Struct Biol. 2022 Jun:74:102372. doi: 10.1016/j.sbi.2022.102372. Epub 2022 Apr 16.

Authors

Jessica L Binder¹, Joel Berendzen², Amy O Stevens³, Yi He⁴, Jian Wang⁵, Nikolay V Dokholyan⁶, Tudor I Oprea⁷

Affiliations

¹ Translational Informatics Division, Department of Internal Medicine, University of New Mexico, Albuquerque, NM 87131, USA. Electronic address: https://twitter.com/@jessicamaine.
² Translational Informatics Division, Department of Internal Medicine, University of New Mexico, Albuquerque, NM 87131, USA.
³ Department of Chemistry and Chemical Biology, University of New Mexico, Albuquerque, NM 87131, USA.
⁴ Translational Informatics Division, Department of Internal Medicine, University of New Mexico, Albuquerque, NM 87131, USA; Department of Chemistry and Chemical Biology, University of New Mexico, Albuquerque, NM 87131, USA.
⁵ Department of Pharmacology, Department of Biochemistry and Molecular Biology, Penn State University College of Medicine, Hershey, PA 17033, USA.
⁶ Department of Pharmacology, Department of Biochemistry and Molecular Biology, Penn State University College of Medicine, Hershey, PA 17033, USA; Department of Chemistry and Department of Biomedical Engineering, Pennsylvania State University, University Park, PA 16802, United States.
⁷ Translational Informatics Division, Department of Internal Medicine, University of New Mexico, Albuquerque, NM 87131, USA; UNM Comprehensive Cancer Center, Albuquerque, NM, USA; Department of Rheumatology and Inflammation Research, Institute of Medicine, Sahlgrenska Academy at the University of Gothenburg, Gothenburg, Sweden; Novo Nordisk Foundation Center for Protein Research, Faculty of Health and Medical Sciences, University of Copenhagen, Copenhagen, Denmark. Electronic address: toprea@salud.unm.edu.

Abstract

We investigate the use of confidence scores to evaluate the accuracy of a given AlphaFold (AF2) protein model for drug discovery. Prediction of accuracy is improved by not considering confidence scores below 80 due to the effects of disorder. On a set of recent crystal structures, 95% are likely to have accurate folds. Conformational discordance in the training set has a much more significant effect on accuracy than sequence divergence. We propose criteria for models and residues that are possibly useful for virtual screening. Based on these criteria, AF2 provides models for half of understudied (dark) human proteins and two-thirds of residues in those models.

Keywords: Artificial intelligence; Drug discovery; Model evaluation; Protein folding; Understudied proteins; Virtual screening.

Publication types

Review
Research Support, U.S. Gov't, Non-P.H.S.
Research Support, N.I.H., Extramural

MeSH terms

Drug Discovery
Furylfuramide*
Humans
Protein Folding
Proteins* / chemistry

Substances

Proteins
Furylfuramide

Abstract

Publication types

MeSH terms

Substances

Grants and funding