Ranking Protein-Protein Models with Large Language Models and Graph Neural Networks
Publication date
2025-08-03
Authors
Xu, Xiaotong
Bonvin, Alexandre M.J.J.
Editors
KC, Dukka B.
Advisors
Supervisors
Document Type
Part of book
Metadata
Show full item recordCollections
License
taverne
Abstract
Protein-protein interactions (PPIs) are associated with various diseases, including cancer, infections, and neurodegenerative disorders. Obtaining three-dimensional structural information on these PPIs serves as a foundation to interfere with those or to guide drug design. Various strategies can be followed to model those complexes, all typically resulting in a large number of models. A challenging step in this process is the identification of good models (near-native PPI conformations) from the large pool of generated models. To address this challenge, we previously developed DeepRank-GNN-esm, a graph-based deep learning algorithm for ranking modeled PPI structures harnessing the power of protein language models. In this chapter, we detail the use of our software with examples. DeepRank-GNN-esm is freely available at https://github.com/haddocking/DeepRank-GNN-esm .
Keywords
Algorithms, Computational Biology/methods, Deep Learning, Graph Neural Networks, Humans, Large Language Models, Models, Molecular, Neural Networks, Computer, Protein Conformation, Protein Interaction Mapping/methods, Protein Interaction Maps, Proteins/chemistry, Software, Taverne, SDG 3 - Good Health and Well-being
Citation
Xu, X & Bonvin, A M J J 2025, Ranking Protein-Protein Models with Large Language Models and Graph Neural Networks. in D B KC (ed.), Large Language Models (LLMs) in Protein Bioinformatics. 1 edn, Methods in Molecular Biology, vol. 2941, Humana Press, New York, pp. 71-83. https://doi.org/10.1007/978-1-0716-4623-6_4