EUVIMEDOpdag EUVIMED
Open access

Protein‐Ligand Structure and Affinity Prediction in CASP16 Using a Geometric Deep Learning Ensemble and Flow Matching

Alex Morehead iD, Jian Liu iD, Pawan Neupane, Nabin Giri iD, Jianlin Cheng iD

Proteins: Structure, Function, and Bioinformatics · 2026

DOI: 10.1002/prot.26827 ↗

At a glance

Journal article in Proteins: Structure, Function, and Bioinformatics, 2026. Written by Alex Morehead and 4 co-authors. Institution: Department of Electrical Engineering & Computer Science, NextGen Precision Health, University of Missouri, Columbia, Missouri, USA. Major MEDLINE topics: Deep Learning, Proteins, Computational Biology, Software. Cited 6 times so far (Crossref); 29 references. The full text is freely available in PubMed Central. Funded by: NIGMS NIH HHS, National Science Foundation, NIH HHS.

AbstractSubjectsBibliografiske oplysningerCiteRelated studies

Abstract (original language)

Predicting the structure of ligands bound to proteins is a foundational problem in modern biotechnology and drug discovery, yet little is known about how to combine the predictions of protein‐ligand structure (poses) produced by the latest deep learning methods to identify the best poses and how to accurately estimate the binding affinity between a protein target and a list of ligand candidates. Further, a blind benchmarking and assessment of protein‐ligand structure and binding affinity prediction is necessary to ensure it generalizes well to new settings. Towards this end, we introduce MULTICOM_ ligand, a deep learning‐based protein‐ligand structure and binding affinity prediction ensemble featuring structural consensus ranking for unsupervised pose ranking and a new deep generative flow matching model for joint structure and binding affinity prediction. Notably, MULTICOM_ ligand ranked among the top‐5 ligand prediction methods in both protein‐ligand structure prediction and binding affinity prediction in the 16th Critical Assessment of Techniques for Structure Prediction (CASP16), demonstrating its efficacy and utility for real‐world drug discovery efforts. The source code for MULTI COM_ ligand is freely available on GitHub.

Subjects

MeSH terms (MEDLINE)

Deep LearningProteinsComputational BiologySoftwareLigandsProtein BindingProtein ConformationDrug DiscoveryBinding SitesDatabases, ProteinModels, MolecularAlgorithms

Author keywords

binding affinitydeep learningdiffusion modeldrug discoveryflow matchingpose predictionprotein‐ligand structure

Substances

LigandsProteins

Authors and institutions

  • Department of Electrical Engineering & Computer Science, NextGen Precision Health, University of Missouri, Columbia, Missouri, USA.

ORCID profiles: Alex Morehead, Jian Liu, Nabin Giri, Jianlin Cheng

Funding

  • NIGMS NIH HHS
  • National Science Foundation
  • NIH HHS
  • National Institutes of Health

Cite

APA

Morehead, A., Liu, J., Neupane, P., Giri, N., & Cheng, J. (2026). Protein‐Ligand Structure and Affinity Prediction in CASP16 Using a Geometric Deep Learning Ensemble and Flow Matching. Proteins: Structure, Function, and Bioinformatics. https://doi.org/10.1002/prot.26827

Vancouver

Morehead A, Liu J, Neupane P, Giri N, Cheng J. Protein‐Ligand Structure and Affinity Prediction in CASP16 Using a Geometric Deep Learning Ensemble and Flow Matching. Proteins: Structure, Function, and Bioinformatics. 2026. doi:10.1002/prot.26827

BibTeX
@article{Morehead2026,
  author = {Morehead, Alex and Liu, Jian and Neupane, Pawan and Giri, Nabin and Cheng, Jianlin},
  title = {Protein‐Ligand Structure and Affinity Prediction in CASP16 Using a Geometric Deep Learning Ensemble and Flow Matching},
  journal = {Proteins: Structure, Function, and Bioinformatics},
  year = {2026},
  doi = {10.1002/prot.26827}
}
Start for free →