Protein‐Ligand Structure and Affinity Prediction in CASP16 Using a Geometric Deep Learning Ensemble and Flow Matching
- 8 April 2025
- journal article
- Published by Wiley in Proteins: Structure, Function, and Bioinformatics
- Vol. 94 (1) , 295-301
Abstract
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.Keywords
All Related Versions
Funding Information
- National Science Foundation (DBI2308699)
- National Institutes of Health (R01GM093123)
This publication has 11 references indexed in Scilit:
- Accurate structure prediction of biomolecular interactions with AlphaFold 3Nature, 2024
- State-specific protein–ligand complex structure prediction with a multiscale deep generative modelNature Machine Intelligence, 2024
- DynamicBind: predicting ligand-specific protein-ligand complex structure with a deep equivariant generative modelNature Communications, 2024
- PoseBusters: AI-based docking methods fail to generate physically valid poses or generalise to novel sequencesChemical Science, 2023
- Diffusion models in bioinformatics and computational biologyNature Reviews Bioengineering, 2023
- Assessment of protein–ligand complexes in CASP15Proteins: Structure, Function, and Bioinformatics, 2023
- Combining pairwise structural similarity and deep learning interface contact prediction to estimate protein complex model accuracy in CASP15Proteins: Structure, Function, and Bioinformatics, 2023
- Evolutionary-scale prediction of atomic-level protein structure with a language modelScience, 2023
- PDB-wide collection of binding data: current status of the PDBbind databaseBioinformatics, 2014
- Virtual screening strategies in drug discoveryCurrent Opinion in Chemical Biology, 2007