BERT-DomainAFP: Antifreeze protein recognition and classification model based on BERT and structural domain annotation
Shengzhen Chen,
Ping Zheng,
Lele Zheng,
Qinglong Yao,
Ziyu Meng,
Longshan Lin,
Xinhua Chen,
Ruoyu Liu
Affiliations
Shengzhen Chen
State Key Laboratory of Mariculture Breeding, Key Laboratory of Marine Biotechnology of Fujian Province, Institute of Oceanology, College of Marine Sciences, Haixia Institute of Science and Technology, Fujian Agriculture and Forestry University, Fuzhou 350002, China
Ping Zheng
State Key Laboratory of Mariculture Breeding, Key Laboratory of Marine Biotechnology of Fujian Province, Institute of Oceanology, College of Marine Sciences, Haixia Institute of Science and Technology, Fujian Agriculture and Forestry University, Fuzhou 350002, China
Lele Zheng
State Key Laboratory of Mariculture Breeding, Key Laboratory of Marine Biotechnology of Fujian Province, Institute of Oceanology, College of Marine Sciences, Haixia Institute of Science and Technology, Fujian Agriculture and Forestry University, Fuzhou 350002, China
Qinglong Yao
State Key Laboratory of Mariculture Breeding, Key Laboratory of Marine Biotechnology of Fujian Province, Institute of Oceanology, College of Marine Sciences, Haixia Institute of Science and Technology, Fujian Agriculture and Forestry University, Fuzhou 350002, China
Ziyu Meng
State Key Laboratory of Mariculture Breeding, Key Laboratory of Marine Biotechnology of Fujian Province, Institute of Oceanology, College of Marine Sciences, Haixia Institute of Science and Technology, Fujian Agriculture and Forestry University, Fuzhou 350002, China
Longshan Lin
Laboratory of Marine Biodiversity Research, Third Institute of Oceanography, Ministry of Natural Resources, Xiamen 361005, China
Xinhua Chen
State Key Laboratory of Mariculture Breeding, Key Laboratory of Marine Biotechnology of Fujian Province, Institute of Oceanology, College of Marine Sciences, Haixia Institute of Science and Technology, Fujian Agriculture and Forestry University, Fuzhou 350002, China; Corresponding author
Ruoyu Liu
State Key Laboratory of Mariculture Breeding, Key Laboratory of Marine Biotechnology of Fujian Province, Institute of Oceanology, College of Marine Sciences, Haixia Institute of Science and Technology, Fujian Agriculture and Forestry University, Fuzhou 350002, China; Corresponding author
Summary: Antifreeze proteins (AFPs) are crucial for organisms to adapt to low temperatures, with applications in medicine, food storage, aquaculture, and agriculture. Accurate AFP identification is challenging due to structural and sequence diversity. To improve prediction and classification, we propose BERT-DomainAFP, a deep learning model trained on the AntiFreezeDomains dataset created with a novel annotation strategy. The model uses pre-trained ProteinBERT and incorporates oversampling and undersampling techniques to handle unbalanced data, ensuring high predictive ability. BERT-DomainAFP achieves 98.48% accuracy, the highest among existing models, and can classify different AFP types based on structural domain features. This model outperforms current tools, offering a promising solution for AFP recognition and classification in research and applications.
