RA-PLA: Retrieval-augmented graph convolutional networks for protein-ligand binding affinity prediction
PLOS One · 2026
DOI: 10.1371/journal.pone.0357278 ↗Kurz gefasst
Fachartikel in der Zeitschrift PLOS One, 2026. Verfasst von Karim Abbasi und 3 weiteren Autor:innen. Beteiligte Einrichtung: Mosaheb Institute for Mathematical Research, Kharazmi University, Tehran, Iran. Hauptthemen laut MEDLINE: Proteins, Computational Biology, Drug Discovery. Die Arbeit nennt 65 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Protein-ligand binding affinity (PLA) prediction is essential for computational drug discovery, yet existing deep learning methods typically employ a single globally trained model that fails to adapt to individual query samples. In this paper, we propose a novel end-to-end framework that retrieves hard protein-ligand pairs—samples whose nearest neighbors have conflicting labels under manifold smoothness constraints—and integrates them via a semi-supervised graph convolutional network (GCN). For each query, we automatically construct a graph where nodes represent protein-ligand pairs and edges encode pairwise similarities. Our model jointly learns joint descriptors, graph topology, and the GCN predictor. During inference, we fine-tune the model per query using its retrieved hard neighbors.We evaluate on four benchmarks: PDBbind, Davis, KIBA, and BindingDB. Our method consistently outperforms state-of-the-art approaches. On Davis, we achieve a Concordance Index (CI) of 0.952 ± 0.005 (1.6% improvement over NerLTR-DTA) and AUPR of 0.815 ± 0.005 (7.6% improvement). On KIBA, we achieve CI of 0.916 ± 0.002 and AUPR of 0.871 ± 0.005, outperforming DeepCDA by 2.7% and 5.9%, respectively. On PDBbind, our CI of 0.894 ± 0.002 represents an 11.4% improvement over PLA-MoRe. On BindingDB, we achieve AUPR of 0.518 ± 0.009 (5.9% improvement over DeepCDA). In cold-target generalization across four unseen protein families, we achieve average AUPR improvements of 15.5%. Paired t-tests confirm statistical significance (p < 0.05), and ablation studies validate that both hard sample retrieval and end-to-end learning are essential for performance gains. Our framework demonstrates that query-specific adaptation significantly enhances both accuracy and generalization in PLA prediction.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Substanzen
Autor:innen und Institutionen
- Mosaheb Institute for Mathematical Research, Kharazmi University, Tehran, Iran.
- Computer Engineering and Information Technology Department, University of Qom, Qom, Iran.
- Department of Artificial Intelligence and Data Science, College of Science and Technology, University of Human Development, Sulaymaniyah, Kurdistan Region ofIraq.
ORCID-Profile: Karim Abbasi, Shima Rashidi
Zitieren
APA
Abbasi, K., Banadkuki, H., Sepahvand, R., & Rashidi, S. (2026). RA-PLA: Retrieval-augmented graph convolutional networks for protein-ligand binding affinity prediction. PLOS One. https://doi.org/10.1371/journal.pone.0357278
Vancouver
Abbasi K, Banadkuki H, Sepahvand R, Rashidi S. RA-PLA: Retrieval-augmented graph convolutional networks for protein-ligand binding affinity prediction. PLOS One. 2026. doi:10.1371/journal.pone.0357278
BibTeX
@article{Abbasi2026,
author = {Abbasi, Karim and Banadkuki, Hossein and Sepahvand, Reza and Rashidi, Shima},
title = {RA-PLA: Retrieval-augmented graph convolutional networks for protein-ligand binding affinity prediction},
journal = {PLOS One},
year = {2026},
doi = {10.1371/journal.pone.0357278}
}
EUVIMED