Accurate enzyme function prediction is important for protein functional annotation, drug discovery, metabolic-pathway analysis, and synthetic biology. Although recent structure-based methods have improved Enzyme Commission (EC) number prediction, they still have several limitations. First, predicted protein structures may contain unreliable regions, but residue-level structural confidence is often not fully exploited. Second, most methods extract features from the whole protein structure while paying insufficient attention to catalytic residues and active-site regions. Third, the hierarchical dependency among EC-level labels is not always explicitly modeled, which may lead to inconsistent predictions across EC levels. To address these issues, this paper proposes a hierarchical enzyme function prediction framework based on structural confidence and active-site-aware attention. Enzyme structures are represented as residue-level point-cloud representations constructed from Cα coordinates. A structural-confidence-aware geometric encoder incorporates residuelevel confidence values, such as AlphaFold pLDDT, into local geometric aggregation to reduce the influence of unreliable regions. An active-site-aware attention mechanism is further introduced to emphasize function-determining residues and their local catalytic microenvironments. In addition, a hierarchical EC decoder enforces parent-child consistency among EC labels. Experiments on the RCSB and HECNet datasets show that the proposed method outperforms representative sequence-based and structurebased baselines. The proposed model achieves Macro-F1 scores of 96.48% and 95.37% on the RCSB and HECNet datasets, respectively. Ablation and interpretability analyses further demonstrate the effectiveness of the proposed components.
- Open Access
- Article
Hierarchical Enzyme Function Prediction Based on Structural Confidence and Active-Site-Aware Attention
- Qiuhao Wang 1,
- Yuexiao Wang 1,
- Aohan Mei 2,
- Tian Zhang 3,
- Nan Li 4,*
Author Information
Received: 16 Jun 2026 | Revised: 19 Jul 2026 | Accepted: 24 Jul 2026 | Published: 11 Aug 2026
Abstract
Keywords
enzyme function prediction | EC number prediction | protein structure analysis | structure confidence | active-site-aware attention | hierarchical classification
References
- 1.
McDonald, A.G.; Tipton, K.F. Enzyme nomenclature and classification: The state of the art. FEBS J. 2023, 290, 2214–2231.
- 2.
The UniProt Consortium. UniProt: The Universal Protein Knowledgebase in 2023. Nucleic Acids Res. 2023, 51, D523–D531.
- 3.
Li, Y.;Wang, S.; Umarov, R.; et al. DEEPre: Sequence-based enzyme EC number prediction by deep learning. Bioinformatics 2018, 34, 760–769.
- 4.
Memon, S.A.; Khan, K.A.; Naveed, H. HECNet: A hierarchical approach to enzyme function classification using a Siamese Triplet Network. Bioinformatics 2020, 36, 4583–4589.
- 5.
Thornton, J.M.; Todd, A.E.; Milburn, D.; et al. From structure to function: Approaches and limitations. Nat. Struct. Biol. 2000, 7, 991–994.
- 6.
Rose, P.W.; Bi, C.; Bluhm, W.F.; et al. The RCSB Protein Data Bank: New resources for research and education. Nucleic Acids Res. 2013, 41, D475–D482.
- 7.
Jumper, J.; Evans, R.; Pritzel, A.; et al. Highly accurate protein structure prediction with AlphaFold. Nature 2021, 596, 583–589.
- 8.
Varadi, M.; Anyango, S.; Deshpande, M.; et al. AlphaFold Protein Structure Database in 2024: Providing structure coverage for over 214 million protein sequences. Nucleic Acids Res. 2024, 52, D368–D375.
- 9.
Amidi, A.; Amidi, S.; Vlachakis, D.; et al. EnzyNet: Enzyme classification using 3D convolutional neural networks on spatial representation. PeerJ 2018, 6, e4750.
- 10.
Gligorijevi´c, V.; Renfrew, P.D.; Kosciolek, T.; et al. Structure-based protein function prediction using graph convolutional networks. Nat. Commun. 2021, 12, 3168.
- 11.
Zhang, Z.; Yu, G.; Deng, Z.; et al. SEFP: Structure-Based Enzyme Function Prediction. IEEE Trans. Comput. Biol. Bioinform. 2025, 22, 1211–1221.
- 12.
Ribeiro, A.J.M.; Holliday, G.L.; Furnham, N.; et al. Mechanism and Catalytic Site Atlas (M-CSA): A database of enzyme reaction mechanisms and active sites. Nucleic Acids Res. 2018, 46, D618–D623.
- 13.
Petrova, N.V.; Wu, C.H. Prediction of catalytic residues using Support Vector Machine with selected protein sequence and structural properties. BMC Bioinform. 2006, 7, 312.
- 14.
Wang, F.; Liu, D.; Wang, H.; et al. CRHunter: Integrating multifaceted information to predict catalytic residues in enzymes. Sci. Rep. 2016, 6, 34044.
- 15.
Huang, Y.; Lin, Y.; Lan, W.; et al. GloEC: A hierarchical-aware global model for predicting enzyme function. Briefings Bioinform. 2024, 25, bbae365.
- 16.
Qu, F.; Zhao, Y.; Huang, T.; et al. HiPHD: Hierarchical Classification for Protein Remote Homology Detection by Incorporating Protein Sequential and Structural Information. IEEE/ACM Trans. Comput. Biol. Bioinform. 2025, 22, 2872–2881. https://doi.org/10.1109/TCBBIO.2025.3604441.
- 17.
Claudel-Renard, C.; Chevalet, C.; Faraut, T.; et al. Enzyme-specific profiles for genome annotation: PRIAM. Nucleic Acids Res. 2003, 31, 6633–6639.
- 18.
Tian, W.; Arakaki, A.K.; Skolnick, J. EFICAz: A comprehensive approach for accurate genome-scale enzyme function inference. Nucleic Acids Res. 2004, 32, 6226–6239.
- 19.
Arakaki, A.K.; Huang, Y.; Skolnick, J. EFICAz2: Enzyme function inference by a combined approach enhanced by machine learning. BMC Bioinform. 2009, 10, 107.
- 20.
Kumar, N.; Skolnick, J. EFICAz2.5: Application of a high-precision enzyme function predictor to 396 proteomes. Bioinformatics 2012, 28, 2687–2688.
- 21.
Yu, C.; Zavaljevski, N.; Desai, V.; et al. Genome-wide enzyme annotation with precision control: Catalytic families (CatFam) databases. Proteins Struct. Funct. Bioinform. 2009, 74, 449–460.
- 22.
Shen, H.B.; Chou, K.C. EzyPred: A top-down approach for predicting enzyme functional classes and subclasses. Biochem. Biophys. Res. Commun. 2007, 364, 53–59.
- 23.
Nagao, C.; Nagano, N.; Mizuguchi, K. Prediction of detailed enzyme functions and identification of specificity determining residues by random forests. PLoS ONE 2014, 9, e84623.
- 24.
Dalkiran, A.; Rifaioglu, A.S.; Martin, M.J.; et al. ECPred: A tool for the prediction of the enzymatic functions of protein sequences based on the EC nomenclature. BMC Bioinform. 2018, 19, 334.
- 25.
Nursimulu, N.; Xu, L.L.; Wasmuth, J.D.; et al. Improved enzyme annotation with EC-specific cutoffs using DETECT v2. Bioinformatics 2018, 34, 3393–3395.
- 26.
Ryu, J.Y.; Kim, H.U.; Lee, S.Y. Deep learning enables high-quality and high-throughput prediction of enzyme commission numbers. Proc. Natl. Acad. Sci. USA 2019, 116, 13996–14001.
- 27.
Watanabe, N.; Yamamoto, M.; Murata, M.; et al. EnzymeNet: Residual neural networks model for Enzyme Commission number prediction. Bioinform. Adv. 2023, 3, vbad173.
- 28.
Yu, T.; Cui, H.; Li, J.C.; et al. Enzyme function prediction using contrastive learning. Science 2023, 379, 1358–1363.
- 29.
Kulmanov, M.; Khan, M.A.; Hoehndorf, R. DeepGO: Predicting protein functions from sequence and interactions using a deep ontology-aware classifier. Bioinformatics 2018, 34, 660–668.
- 30.
Kulmanov, M.; Hoehndorf, R. DeepGOPlus: Improved protein function prediction from sequence. Bioinformatics 2020, 36, 422–429.
- 31.
Bileschi, M.L.; Belanger, D.; Bryant, D.; et al. Using deep learning to annotate the protein universe. Nat. Biotechnol. 2022, 40, 932–937.
- 32.
Song, Y.; Yuan, Q.; Chen, S.; et al. Accurately predicting enzyme functions through geometric graph learning on ESMFold-predicted structures. Nat. Commun. 2024, 15, 8180.
- 33.
Zhu, Z.; Lu, S.Y.; Huang, T.; et al. LKA: Large Kernel Adapter for Enhanced Medical Image Classification. In Proceedings of the International Conference on Medical Image Computing and Computer Assisted Intervention, Daejeon, Republic of Korea, 23 September 2025; pp. 394–404.
- 34.
Zhu, Z.; Zhu, H.; Lu, S.Y.; et al. Dual-Kernel Adapter: Expanding Spatial Horizons for Data-Constrained Medical Image Analysis. arXiv 2026, arXiv:2602.18888. https://arxiv.org/abs/2602.18888.
- 35.
Zhu, Z.; Jin, G.; Zhu, H.; et al. Confusion-Aware Spectral Regularizer for Long-Tailed Recognition. arXiv 2026, arXiv:2603.16732. https://arxiv.org/abs/2603.16732.
- 36.
Zhu, Z.; Liu, L.; Free, R.C.; et al. OPT-CO: Optimizing Pre-Trained Transformer Models for Efficient COVID-19 Classification with Stochastic Configuration Networks. Inf. Sci. 2024, 680, 121141. https://doi.org/10.1016/j.ins.2024.121141.
- 37.
Qi, C.R.; Su, H.; Mo, K.; et al. PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA, 21–26 July 2017; pp. 652–660.
- 38.
Qi, C.R.; Yi, L.; Su, H.; et al. PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space. In Proceedings of the Advances in Neural Information Processing Systems, Long Beach, CA, USA, 4–9 December 2017; Volume 30.
- 39.
Woo, S.; Park, J.; Lee, J.Y.; et al. CBAM: Convolutional Block Attention Module. In Proceedings of the European Conference on Computer Vision, Munich, Germany, 8–14 September 2018; pp. 3–19.
- 40.
Silla, C.N.; Freitas, A.A. A Survey of Hierarchical Classification Across Different Application Domains. Data Min. Knowl. Discov. 2011, 22, 31–72.
- 41.
Lin, T.Y.; Goyal, P.; Girshick, R.; et al. Focal Loss for Dense Object Detection. IEEE Trans. Pattern Anal. Mach. Intell. 2020, 42, 318–327.
This work is licensed under a Creative Commons Attribution 4.0 International License.
Suite 4002 Level 4, 447 Collins Street, Melbourne, Victoria 3000, Australia
General Inquiries: info@sciltp.com