Benchmarking Deep Learning for PROTAC Ternary Complex Prediction
Proteins: Structure, Function, and Bioinformatics · 2026
DOI: 10.1002/prot.70117 ↗At a glance
Journal article in Proteins: Structure, Function, and Bioinformatics, 2026. Written by Haoyu Chen and 10 co-authors. Institution: Key Laboratory of Marine Drugs, Chinese Ministry of Education, School of Medicine and Pharmacy, Ocean University of China, Qingdao, Shandong, China. Major MEDLINE topics: Ubiquitin-Protein Ligases, Deep Learning, Proteasome Endopeptidase Complex, Ubiquitin. Cited 1 times so far (Crossref); 32 references. Funded by: National Natural Science Foundation of China, Natural Science Foundation of Shandong Province, Qingdao Science and Technology Demonstration Project.
Abstract (original language)
Proteolysis Targeting Chimeras (PROTACs) represent a transformative approach to drug development by leveraging the intracellular ubiquitin‐proteasome system (UPS) for the selective degradation of target proteins. A PROTAC molecule comprises three essential components: a ligand that binds to the E3 ubiquitin ligase, a ligand that targets the protein of interest, and a flexible linker that connects the two. This distinctive structure enables the PROTAC to simultaneously engage with both the target protein and the E3 ligase, facilitating their interaction. Such proximity initiates the ubiquitination of the target protein, marking it for recognition and subsequent degradation. In this study, we benchmark ternary complexes based on PROTACs using four recently employed predictive tools: Chai‐1, AlphaFold2, AlphaFold3, and Protenix. Comparative analysis indicated that the ternary complexes predicted by the four prediction tools demonstrated satisfactory accuracy (Cα‐RMSD < 10 Å). Among the evaluated tools, three—Chai‐1, AlphaFold3, and Protenix—demonstrated superior performance in over half of the tests, while AlphaFold2 exhibited comparatively lower performance. However, significant challenges remained in accurately predicting the orientation of POI and the E3 ligase (Cα‐RMSD < 10 Å when POI or E3 ligase were used as reference), as well as the position of the small molecule PROTAC (RMSD < 5 Å). By benchmarking these tools, we underscore recent advancements in protein structure prediction, enhance our understanding of the mechanisms underpinning PROTAC complexes, and provide a valuable reference for evaluating the binding conformations of other ternary complexes, as well as for the development of future predictive tools.
Subjects
MeSH terms (MEDLINE)
Author keywords
Substances
Authors and institutions
- Key Laboratory of Marine Drugs, Chinese Ministry of Education, School of Medicine and Pharmacy, Ocean University of China, Qingdao, Shandong, China.
- Marine Biomedical Research Institute of Qingdao, Qingdao, Shandong, China.
ORCID profiles: Haoyu Chen, Fengjiao Wei, Jiajie Li, Zhuobin Shi, Shanshan Chen, Yu Fang, Shuxin Li, Xinru Gao, Lin Ju, Senbiao Fang, Ximing Xu
Funding
- National Natural Science Foundation of China
- Natural Science Foundation of Shandong Province
- Qingdao Science and Technology Demonstration Project
Cite
APA
Chen, H., Wei, F., Li, J., Shi, Z., Chen, S., Fang, Y., Li, S., Gao, X., Ju, L., Fang, S., & Xu, X. (2026). Benchmarking Deep Learning for PROTAC Ternary Complex Prediction. Proteins: Structure, Function, and Bioinformatics. https://doi.org/10.1002/prot.70117
Vancouver
Chen H, Wei F, Li J, Shi Z, Chen S, Fang Y, et al. Benchmarking Deep Learning for PROTAC Ternary Complex Prediction. Proteins: Structure, Function, and Bioinformatics. 2026. doi:10.1002/prot.70117
BibTeX
@article{Chen2026,
author = {Chen, Haoyu and Wei, Fengjiao and Li, Jiajie and Shi, Zhuobin and Chen, Shanshan and Fang, Yu and Li, Shuxin and Gao, Xinru and Ju, Lin and Fang, Senbiao and Xu, Ximing},
title = {Benchmarking Deep Learning for PROTAC Ternary Complex Prediction},
journal = {Proteins: Structure, Function, and Bioinformatics},
year = {2026},
doi = {10.1002/prot.70117}
}
EUVIMED