The promise of AlphaFold for gene structure annotation
Nucleic Acids Research · 2026
DOI: 10.1093/nar/gkag369 ↗Kurz gefasst
Fachartikel in der Zeitschrift Nucleic Acids Research, 2026. Verfasst von Helen R Davison und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Biochemistry, Cell and Systems Biology, Institute of Systems, Molecular and Integrative Biology, University of Liverpool, Liverpool, L6…. Hauptthemen laut MEDLINE: Molecular Sequence Annotation, Software, Proteins. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 51 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Wellcome Trust, University of Liverpool's.
Abstract (Originalsprache)
Most new genomes lack annotation, automated methods are error-prone, and few genomes are ever manually curated due to time and cost. Protein structure predictions may offer a new route to assess and improve gene models without requiring experimental data. Here, we explore whether scores from protein structure prediction can aid in scoring gene model quality. We chose three species (Fusarium graminearum, Toxoplasma gondii, and Aspergillus fumigatus) from the VEuPathDB database that have collectively undergone more than 1000 manual curation events. We modelled translations of the gene models with AlphaFold 3, before and after curation, collecting various scores. Then we carried out structure searching of the PDB with Foldseek and sequence-based domain identification using InterProScan. We profiled the scores produced by these methods to identify those best for gene model assessment. AlphaFold 3 scores strongly favoured manually improved over pre-improvement gene models, supporting 65–84% of manually-curated changes. Combining scores across multiple tools (AlphaFold 3, Foldseek and InterProScan) provided further improvements in model scoring. Overall, the most discriminative scores combined the outputs of AlphaFold 3 and Foldseek. Importantly, we find that scores from the much faster Protenix-Mini retain the same discriminatory power as those from AlphaFold 3. Our results, therefore, highlight the potential of scores derived from deep learning-based protein structure prediction for scoring gene models in the absence of experimental data.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Substanzen
Autor:innen und Institutionen
- Department of Biochemistry, Cell and Systems Biology, Institute of Systems, Molecular and Integrative Biology, University of Liverpool, Liverpool, L69 7ZB, United Kingdom.
- Computational Biology Facility, University of Liverpool, Liverpool, L69 7ZB, United Kingdom.
- Department of Biology, University of Pennsylvania, Philadelphia, PA 19104, United States.
Förderung
- Wellcome Trust
- University of Liverpool's
Zitieren
APA
Davison, H. R., Böhme, U., Mesdaghi, S., Wilkinson, P. A., Roos, D. S., Jones, A. R., & Rigden, D. J. (2026). The promise of AlphaFold for gene structure annotation. Nucleic Acids Research. https://doi.org/10.1093/nar/gkag369
Vancouver
Davison HR, Böhme U, Mesdaghi S, Wilkinson PA, Roos DS, Jones AR, et al. The promise of AlphaFold for gene structure annotation. Nucleic Acids Research. 2026. doi:10.1093/nar/gkag369
BibTeX
@article{Davison2026,
author = {Davison, Helen R and Böhme, Ulrike and Mesdaghi, Shahram and Wilkinson, Paul A and Roos, David S and Jones, Andrew R and Rigden, Daniel J},
title = {The promise of AlphaFold for gene structure annotation},
journal = {Nucleic Acids Research},
year = {2026},
doi = {10.1093/nar/gkag369}
}
EUVIMED