Feature-Optimized LightGBM Ensemble Framework for Interpretable and High-Accuracy Antifreeze Protein Prediction

Muhammad Allah Razi; Laiba Saeed; Usman Shafeeq; Asma Batool; Nasir Ali

doi:10.5281/zenodo.19686139

المؤلفون

Muhammad Allah Razi Department of Computer and Software Engineering, Khwaja Fareed University of Engineering and Information Technology (KFUEIT), Rahim Yar Khan, Punjab, Pakistan المؤلف
Laiba Saeed Lecturer at Department of Data Science and AI, Khwaja Fareed University of Engineering and Information Technology (KFUEIT), Rahim Yar Khan, Punjab, Pakistan المؤلف
Usman Shafeeq Lecturer at Department of Data Science and AI, Khwaja Fareed University of Engineering and Information Technology (KFUEIT), Rahim Yar Khan, Punjab, Pakistan المؤلف
Asma Batool Assistant Professor at Department of Optometry Vision Sciences, AHS Bakhtawar Amin Medical & Dental College, Multan, Punjab, Pakistan المؤلف
Nasir Ali Departments of Physics, Government Degree College Saleh Pat, Sukkur, Pakistan المؤلف

DOI:

https://doi.org/10.5281/zenodo.19686139

الملخص

Antifreeze proteins (AFPs) are known to occur universally in different species of plants, insects, and fish. These antifreeze proteins are capable of inhibiting the growth of ice crystals, helping the species survive under severely low-temperature conditions. Because of the unique properties of these proteins, their applications are diversifying into metabolic engineering, food processing like yogurt production, and cryopreservation. Various researchers have developed different computer-aided approaches to identify antifreeze proteins. However, the current available predictors are limited by low levels of accuracy and lack of strong predictive potential. This necessitates the development of more accurate predictive methods to identify antifreeze proteins. In this paper, a comprehensive study of the different methods available for predicting antifreeze proteins is conducted. A comparative study of different machine models for the identification of antifreeze proteins is presented. The study reveals that the proposed LightGBM classifier with the help of pentamer feature representations surpasses all the other machine learning models. The proposed model reflected a sensitivity of 97.50%, a recall of 98.30%, and an F1-score of 99.10%.

السير الشخصية للمؤلفين

Muhammad Allah Razi، Department of Computer and Software Engineering, Khwaja Fareed University of Engineering and Information Technology (KFUEIT), Rahim Yar Khan, Punjab, Pakistan

Department of Computer and Software Engineering, Khwaja Fareed University of Engineering and Information Technology (KFUEIT), Rahim Yar Khan, Punjab, Pakistan
Laiba Saeed، Lecturer at Department of Data Science and AI, Khwaja Fareed University of Engineering and Information Technology (KFUEIT), Rahim Yar Khan, Punjab, Pakistan

Lecturer at Department of Data Science and AI, Khwaja Fareed University of Engineering and Information Technology (KFUEIT), Rahim Yar Khan, Punjab, Pakistan
Usman Shafeeq، Lecturer at Department of Data Science and AI, Khwaja Fareed University of Engineering and Information Technology (KFUEIT), Rahim Yar Khan, Punjab, Pakistan

Lecturer at Department of Data Science and AI, Khwaja Fareed University of Engineering and Information Technology (KFUEIT), Rahim Yar Khan, Punjab, Pakistan
Asma Batool، Assistant Professor at Department of Optometry Vision Sciences, AHS Bakhtawar Amin Medical & Dental College, Multan, Punjab, Pakistan

Assistant Professor at Department of Optometry Vision Sciences, AHS Bakhtawar Amin Medical & Dental College, Multan, Punjab, Pakistan
Nasir Ali، Departments of Physics, Government Degree College Saleh Pat, Sukkur, Pakistan

Departments of Physics, Government Degree College Saleh Pat, Sukkur, Pakistan

المراجع

[1] Ali, F., Akbar, S., Ghulam, A., Maher, Z. A., Unar, A., & Talpur, D. B. (2021). AFPCMBPred: Computational identification of antifreeze proteins by extending consensus sequences into multi-blocks evolutionary information. Computers in Biology and Medicine, 139, 105006.

[2] Cham: Springer International Publishing. Cheng, C. H. C., & Zhuang, X. (2020). Molecular origins and mechanisms of fish antifreeze evolution. Antifreeze proteins volume 1: environment, systematics and evolution, 275-313.

[3] Chen, S., Zheng, P., Zheng, L., Yao, Q., Meng, Z., Lin, L., & Liu, R. (2025). BERT-DomainAFP: Antifreeze protein recognition and classification model based on BERT and structural domain annotation. iScience, 28(4). Fuller, B. J. (2004). Cryoprotectants: the essential antifreezes to protect life in the frozen state. CryoLetters, 25(6), 375-388.

[4] Chi Fai Cheung, R., Bun Ng, T., & Ho Wong, J. (2017). Antifreeze proteins from diverse organisms and their applications: an overview. Current Protein and Peptide Science, 18(3), 262-283.

[5] Dhandapani, K., Sivarajan, K., Ravindhiran, R., & Sekar, J. N. (2022). Fungal infections as an uprising threat to human health: Chemosensitization of fungal pathogens with afp from aspergillus giganteus. Frontiers in Cellular and Infection Microbiology, 12, 887971.

[6] Ding, X., Zhang, H., Chen, H., Wang, L., Qian, H., & Qi, X. (2015). Extraction, purification and identification of antifreeze proteins from cold acclimated malting barley (Hordeum vulgare L.). Food chemistry, 175, 74-81.

[7] Drori, R., Davies, P. L., & Braslavsky, I. (2015). Experimental correlation between thermal hysteresis activity and the distance between antifreeze proteins on an ice surface. RSC Advances, 5(11), 7848-7853.

[8] Estudillo, E., Jiménez, A., Bustamante-Nieves, P. E., Palacios-Reyes, C., Velasco, I., & López-Ornelas, A. (2021). Cryopreservation of gametes and embryos and their molecular changes. International journal of molecular sciences, 22(19), 10864.

[9] Feng, C., Wei, H., Li, X., Feng, B., Xu, C., Zhu, X., & Liu, R. (2024). A stackingbased algorithm for antifreeze protein identification using combined physicochemical, pseudo amino acid composition, and reduction property features. Computers in Biology and Medicine, 176, 108534.

[10] Gilbert, J. A., Davies, P. L., & Laybourn-Parry, J. (2005). A hyperactive, Ca2+- dependent antifreeze protein in an Antarctic bacterium. FEMS Microbiology Letters, 245(1), 67-72.

[11] Jiang, Y., Tong, G., Yin, H., & Xiong, N. (2019). A pedestrian detection method based on genetic algorithm for optimize XGBoost training parameters. IEEE Access, 7, 118310-118321.

[12] Ju, Y., Yang, Y., Tang, Q., Wang, M., Zeng, Y., Zhang, Z., ... & Li, L. (2023). Fluorometric detection of alpha-fetoprotein based on the use of a novel organic compound with AIE activity and aptamer-modified magnetic microparticles. Analytica Chimica Acta, 1278, 341692.

[13] Jung, W., Kim, Y. P., & Jin, E. (2020). Antifreeze protein-covered surfaces. In Antifreeze Proteins Volume 2: Biochemistry, Molecular Biology and Applications (pp. 307-326).

[14] Khan, A., Uddin, J., Ali, F., Banjar, A., & Daud, A. (2023). Comparative analysis of the existing methods for prediction of antifreeze proteins. Chemometrics and Intelligent Laboratory Systems, 232, 104729.

[15] Libbrecht, K. G. (2017). Physical dynamics of ice crystal growth. Annual Review of Materials Research, 47(1), 271-295. Deng, G. (1997). Isolation and characterization of a new type of antifreeze protein, from the longhorn sculpin myoxocephalus octodecimspinosis. Boston University.

Liu, X., Peng, H., Xie, J., Hu, Y., Liu, F., Wang, X., & Tan, S. (2021). Methods in biosynthesis and characterization of the antifreeze protein (AFP) for potential blood cryopreservation. Journal of Nanomaterials, 2021(1), 9932538.

[16] Lopes, J. C., Kinasz, C. T., Luiz, A. M. C., Kreusch, M. G., & Duarte, R. T. D. (2024). Frost fighters: unveiling the potential of microbial antifreeze proteins in biotech innovation. Journal of Applied Microbiology, 135(6), lxae140.

[17] Mehra, R., Kumar, H., Rafiq, S., Kumar, N., Buttar, H. S., Leicht, K., & Korzeniowska, M. 2022 . Enhancing yogurt products’ ingredients: preservation strategies, processing conditions, analytical detection methods, and therapeutic delivery an overview. PeerJ, 10, e14177.

[18] Naing, A. H., & Kim, C. K. (2019). A brief review of applications of antifreeze proteins in cryopreservation and metabolic genetic engineering. 3 Biotech, 9(9), 329.

[19] Rives, N., Lamba, V., Cheng, C. C., & Zhuang, X. (2024). Diverse origins of nearidentical antifreeze proteins in unrelated fish lineages provide insights into evolutionary mechanisms of new gene birth and protein sequence convergence. Molecular biology and evolution, 41(9), msae182.

[20] Robles, V., G. Valcarce, D., & F. Riesco, M. (2019). The use of antifreeze proteins in the cryopreservation of gametes and embryos. Biomolecules, 9(5), 181.

[21] Tas, R. P., Hendrix, M. M., & Voets, I. K. (2022). Direct evidence for pinning of single, ice-bound antifreeze proteins by subzero nanoscopy. bioRxiv, 2022-04.

[22] Wanigasekara, C., Oromiehie, E., Swain, A., Prusty, B. G., & Nguang, S. K. (2021). Machine learning-based inverse predictive model for AFP based thermoplastic composites. Journal of Industrial Information Integration, 22, 100197.

[23] Xu, X., Liu, X., Yu, S., Wang, T., Li, R., Zhang, Y., & Liu, Y. (2024). Medicinal and edible polysaccharides from ancient plants: extraction, isolation, purification, structure, biological activity and market trends of sea buckthorn polysaccharides. Food & Function, 15(9), 4703-4723.

[24] Zhang, D., & Gong, Y. (2020). The comparison of LightGBM and XGBoost coupling factor analysis and prediagnosis of acute liver failure. Ieee Access, 8, 220990- 221003

[25] Abbas, M. A., Khan, M. Z., Atif, H. M., Shahzad, A., & Mahar, J. (2025). Computer-Aided Analysis of Oxino-bis-Pyrazolederivative as a Potential Breast Cancer Drug Based on DFT, Molecular Docking, and Pharmacokinetic Studies: Compared with the Standard Drug Tamoxifen. Indus Journal of Bioscience Research, 3(6), 535-537

[26] Abbas, M. A., Mahar, J., Hameed, N., & Rasool, M. S. (2025). DFT-Guided Design of a Low-Band-Gap Pyrazoline Scaffold: The Critical Role of a Para-Nitro Substituent. Multidisciplinary Surgical Research Annals, 3(3), 461-503.

[27] Abbas, M. A., Mahar, J., Khan, M. J., Rasool, M. S., & Khan, M. Z. (2025). IN SILICO INVESTIGATION OF 3, 6-DIPHENYL-[1, 2, 4] TRIAZOLO [3, 4-B][1, 3, 4] THIADIAZOLE DERIVATIVES AS EGFR MODULATORS FOR LUNG CANCER TREATMENT. The Cancer Research Review, 4(2), 243-308.

[28] Abbas, M. A., Mahar, J., Rasool, M. S., Khan, M. J., & Khan, M. Z. (2025). The Dual Therapeutic Promise of Quinoa: Exploring Antidiabetic and Antioxidant Effects through Experimental and Computational Models. Multidisciplinary Surgical Research Annals, 3(3), 504-544.

[29] Abbas, M. A., Junaid, M. J. M., Rasool, M. S., & Mahar, J. (2025). Structural and NLO Properties of Novel Organic 4-Bromo-4-Nitrostilbene Crystal: Experimental and DFT Study. International Research Journal of Management and Social Sciences, 6(4), 1-20.

[30] Abbas, M. A., & Rasool, M. S. (2026). Eco-Friendly Synthesis of Ag–Co3O4 Nanoparticles for Visible-Light Photocatalysis and DFT-Based Nonlinear Optical Investigation. Chemical Technology and Engineering Applications, 1(1), 23-34.

[31] Junaid, M., Rasool, M. S., Abbas, M. A., & Mahar, J. (2024). Formulation Development and Evaluation of a Bilayered Tablet Containing Dapagliflozin and Metformin. Global Research Journal of Natural Science and Technology, 2(3).

[32] Akram, S., Abbas, M. A., Mahar, J., Rasool, M. S., & Junaid, M. INTERFACIAL DEFECT PASSIVATION AND PHOTOPHYSICAL ENGINEERING OF CSPBCL₃ QUANTUM DOTS VIA BISBENZIMIDAZOLIUM LIGANDS FOR ADVANCED ELECTRONIC DEVICES.

[33] Abbas, M. A., Khan, M. Z., Atif, H. M., Shahzad, A., & Mahar, J. (2025). Computer-Aided Analysis of Oxino-bis-Pyrazolederivative as a Potential Breast Cancer Drug Based on DFT, Molecular Docking, and Pharmacokinetic Studies: Compared with the Standard Drug Tamoxifen. Indus Journal of Bioscience Research, 3(6), 535-537.