DeepUMQA-Global is a deep learning framework designed for protein model accuracy estimation (EMA). DeepUMQA-Global quantifies the bidirectional compatibility between sequences and predicted 3D structures. This enables the server to provide a comprehensive and highly accurate characterization of protein fold accuracy. (More about DeepUMQAGlobal...)
News
- 2025/04/23, MviewEMA was accepted for publication by Cell Reports Methods.
- 2025/04/23, DeepUMQA-X was accepted for publication by Nucleic Acids Research.
-
2024/11/30, Breaking news
Ranking of DeepUMQA-X (Group name: GuijunLab-QA) in
CASP16 EMA:
- Local accuracy estimation: Third in complex local interface; Third in residue identification.
- Global accuracy estimation: Third in overall interface; Fifth in overall fold accuracy.
- 2024/06/01, GraphCPLMQA ranked first in the 1-year blind test of CAMEO-QE.
- 2023/11/28, GraphCPLMQA was accepted for publication by Briefings in Bioinformatics.
- 2023/09/22, DeepUMQA3 was accepted for publication by Bioinformatics.
- 2022/12/13, Breaking news DeepUMQA3 ranked first in CASP15 complex interface assessment.
References
-
Dong Liu, Xuanfeng Zhao, et al. Efficient gIobal accuracy estimation for protein complex structural models using multi-view representation learning.
Cell Reports Methods, 2026, 6(2): 101312 -
Dong Liu, Jun Liu, et al. DeepUMQA-X: Comprehensive and insightful estimation of model accuracy for protein single-chain and complex.
Nucleic Acids Research, 2025, https://doi.org/10.1093/nar/gkaf380 -
Jun Liu, Dong Liu, Guijun Zhang*. DeepUMQA3: a web server for accurate assessment of interface residue accuracy in protein complexes.
Bioinformatics, 2023, 39(10): btad591. -
Saisai Guo, Jun Liu, Guijun Zhang*. DeepUMQA: Ultrafast Shape Recognition-based Protein Model Quality Assessment using Deep Learning.
Bioinformatics, 2022, 38(7): 1895-1903.