Graph_RG: Dominating CASP16 's Small Molecule Affinity Prediction Subcategory—A Pose‐Free Framework for Billion‐Scale Virtual Screening
Proteins: Structure, Function, and Bioinformatics · 2026-01 · 94 (1) · 286-294
DOI: 10.1002/prot.70010 ↗At a glance
Journal article in Proteins: Structure, Function, and Bioinformatics, published online on 2025-06-20. Written by Haiping Zhang. Institution: Faculty of Pharmaceutical Science, Shenzhen University of Advanced Technology, Shenzhen, China. Major MEDLINE topics: Graph Neural Networks, Drug Development, Drug Evaluation, Preclinical. Cited 2 times so far (Crossref); 17 references. Funded by: the SMART Major Project, Shenzhen Science and Technology Program, Shenzhen Key Projects.
Abstract (original language)
Protein–ligand interaction prediction is pivotal in early‐stage drug development, enabling large‐scale virtual screening, drug optimization, and reverse target searching. In this work, we present Graph_RG, our top‐performing model in the CASP16 small molecule track's protein–ligand affinity prediction category, achieving a N‐weighted Kendall's Tau of 0.42—significantly outperforming other submissions (second‐best: 0.36). Beyond accuracy, Graph_RG is noncomplex dependent, hence exhibits exceptional computational efficiency, operating > 100 000× faster than conformation‐search dependent prediction methods, thus enabling billion‐ to 10‐billion‐scale screening on standard servers. We further discuss the potential improvements for Graph_RG, including dataset optimization, atomic vector representation enhancements, and model architecture upgrades. We also introduce the potential broader applications in large‐scale drug screening, reverse target identification, and GPCR‐specific drug discovery. We also point out the development of an interactive web platform hosting Graph_RG and its derivative models to enhance accessibility. By integrating community feedback and iterative model refinement, this initiative bridges the gap between AI‐driven predictions and practical drug discovery, fostering advancements in both computational methodologies and biomedical applications.
Subjects
MeSH terms (MEDLINE)
Author keywords
Substances
Authors and institutions
- Faculty of Pharmaceutical Science, Shenzhen University of Advanced Technology, Shenzhen, China.
ORCID profiles: Haiping Zhang
Funding
- the SMART Major Project
- Shenzhen Science and Technology Program
- Shenzhen Key Projects
Cite
APA
Zhang, H. (2026). Graph_RG: Dominating CASP16 's Small Molecule Affinity Prediction Subcategory—A Pose‐Free Framework for Billion‐Scale Virtual Screening. Proteins: Structure, Function, and Bioinformatics, 94(1), 286-294. https://doi.org/10.1002/prot.70010
Vancouver
Zhang H. Graph_RG: Dominating CASP16 's Small Molecule Affinity Prediction Subcategory—A Pose‐Free Framework for Billion‐Scale Virtual Screening. Proteins: Structure, Function, and Bioinformatics. 2026;94(1):286-294. doi:10.1002/prot.70010
BibTeX
@article{Zhang2026,
author = {Zhang, Haiping},
title = {Graph_RG: Dominating CASP16 's Small Molecule Affinity Prediction Subcategory—A Pose‐Free Framework for Billion‐Scale Virtual Screening},
journal = {Proteins: Structure, Function, and Bioinformatics},
year = {2026},
volume = {94},
number = {1},
pages = {286--294},
doi = {10.1002/prot.70010}
}
EUVIMED