EUVIMEDObjevte EUVIMED
Open access · CC BY 4.0

Assessment of Pharmaceutical Protein–Ligand Pose and Affinity Predictions in CASP16

Michael K Gilson iD, Jerome Eberhardt iD, Peter Škrinjar iD, Janani Durairaj iD, Xavier Robin iD, Andriy Kryshtafovych iD

Proteins: Structure, Function, and Bioinformatics · 2026

DOI: 10.1002/prot.70061 ↗

At a glance

Journal article in Proteins: Structure, Function, and Bioinformatics, 2026. Written by Michael K Gilson and 5 co-authors. Institution: Skaggs School of Pharmacy and Pharmaceutical Sciences, University of California San Diego, La Jolla, California, USA. Major MEDLINE topics: Proteins, Computational Biology, Drug Discovery. Cited 13 times so far (Crossref); 60 references. The full text is freely available (open access, CC BY 4.0). Funded by: NIGMS NIH HHS, US National Institute of General Medical Sciences (NIGMS/NIH), National Institutes of Health.

AbstraktSubjectsBibliografické údajeCiteRelated studies

Abstract (original language)

The protein–ligand component of the 16th Critical Assessment of Structure Prediction (CASP16) challenged participants to predict both binding poses and affinities of small molecules to protein targets, with a focus on drug‐like compounds from pharmaceutical discovery projects. Thirty research groups submitted predictions for 229 protein–ligand pose targets and 140 affinity targets across five protein systems. Among the submitted predictions, template‐based pose‐prediction methods did particularly well, with the best groups achieving mean LDDT‐PLI values of 0.69 (scale of 0–1 with 1 best). For comparison, we also ran a set of automated baseline pose‐prediction methods, including ones using deep neural networks. Of these, AlphaFold 3 did particularly well, with a mean LDDT‐PLI of 0.8, thus outscoring the best CASP16 predictor. The CASP affinity predictions showed modest correlation with experimental data (maximum Kendall's τ = 0.42), well below the theoretical maximum possible given experimental uncertainty (~0.73). As seen in prior challenges, providing experimental structures did not improve affinity predictions in the second stage of the challenge, suggesting that the scoring functions used here are a key limiting factor. Overall, the accuracy achieved by CASP participants is similar to that observed in the prior Drug Design Data Resource (D3R) blinded prediction challenges. The present results highlight the progress and persistent challenges in computational protein–ligand modeling and provide valuable benchmarks for the field of computer‐aided drug design.

Subjects

MeSH terms (MEDLINE)

ProteinsComputational BiologyDrug DiscoveryLigandsProtein BindingProtein ConformationSoftwareModels, MolecularBinding SitesHumansNeural Networks, ComputerDatabases, Protein

Author keywords

benchmarkingdrug designligandsneural networksproteins

Substances

LigandsProteins

Authors and institutions

  • Skaggs School of Pharmacy and Pharmaceutical Sciences, University of California San Diego, La Jolla, California, USA.
  • SIB Swiss Institute of Bioinformatics, Basel, Switzerland.
  • Biozentrum, University of Basel, Basel, Switzerland.
  • Genome Center, University of California, Davis, California, USA.

ORCID profiles: Michael K Gilson, Jerome Eberhardt, Peter Škrinjar, Janani Durairaj, Xavier Robin, Andriy Kryshtafovych

Funding

  • NIGMS NIH HHS
  • US National Institute of General Medical Sciences (NIGMS/NIH)
  • National Institutes of Health

Cite

APA

Gilson, M. K., Eberhardt, J., Škrinjar, P., Durairaj, J., Robin, X., & Kryshtafovych, A. (2026). Assessment of Pharmaceutical Protein–Ligand Pose and Affinity Predictions in CASP16. Proteins: Structure, Function, and Bioinformatics. https://doi.org/10.1002/prot.70061

Vancouver

Gilson MK, Eberhardt J, Škrinjar P, Durairaj J, Robin X, Kryshtafovych A. Assessment of Pharmaceutical Protein–Ligand Pose and Affinity Predictions in CASP16. Proteins: Structure, Function, and Bioinformatics. 2026. doi:10.1002/prot.70061

BibTeX
@article{Gilson2026,
  author = {Gilson, Michael K and Eberhardt, Jerome and Škrinjar, Peter and Durairaj, Janani and Robin, Xavier and Kryshtafovych, Andriy},
  title = {Assessment of Pharmaceutical Protein–Ligand Pose and Affinity Predictions in CASP16},
  journal = {Proteins: Structure, Function, and Bioinformatics},
  year = {2026},
  doi = {10.1002/prot.70061}
}
Start for free →