Academic Journal of Computing & Information Science, 2025, 8(7); doi: 10.25236/AJCIS.2025.080701.
Ziqin He1, Hexin Tan2
1School of Health Science and Engineering, University of Shanghai for Science and Technology, Shanghai, China
2Department Chinese Medicine Authentication, College of Pharmacy, Naval Medical University (Second Military Medical University), Shanghai, China
Protein structure prediction represents a fundamental challenge in biochemistry. Conventional experimental approaches remain constrained by complex sample preparation requirements, substantial costs, and limited capacity for capturing dynamic structural information. These methodological limitations in experimental techniques have motivated the advancement of AI-assisted computational approaches. This review systematically examines the technological evolution of the AlphaFold system across three successive generations, from AlphaFold1's integration of deep learning with evolutionary covariance analysis, to AlphaFold2's revolutionary attention-based Evoformer architecture, culminating in AlphaFold3's diffusion model for multi-molecular complex prediction. Key advancements encompass the diversification of input modalities, expansion of predictive scope, and optimization of computational efficiency. Furthermore, we critically evaluate core application domains spanning fundamental biological research, pharmaceutical discovery and design, biotechnology and synthetic biology applications, and the structural bioinformatics tool ecosystem. Finally, we delineate persistent technical challenges within the field.
AlphaFold, Protein Structure Prediction, Artificial Intelligence
Ziqin He, Hexin Tan. AlphaFold: Evolution, Applications, and Challenges. Academic Journal of Computing & Information Science (2025), Vol. 8, Issue 7: 1-10. https://doi.org/10.25236/AJCIS.2025.080701.
[1] Senior, Andrew W., et al. "Improved protein structure prediction using potentials from deep learning." Nature 577.7792 (2020): 706-710.
[2] Jumper, John, et al. "Highly accurate protein structure prediction with AlphaFold." nature 596.7873 (2021): 583-589.
[3] Abramson, Josh, et al. "Accurate structure prediction of biomolecular interactions with AlphaFold 3." Nature 630.8016 (2024): 493-500.
[4] Tunyasuvunakool, Kathryn, et al. "Highly accurate protein structure prediction for the human proteome." Nature 596.7873 (2021): 590-596.
[5] Sommer, Markus J., et al. "Structure-guided isoform identification for the human transcriptome." Elife 11 (2022): e82556.
[6] Bordin, Nicola, et al. "AlphaFold2 reveals commonalities and novelties in protein structure space for 21 model organisms." Communications biology 6.1 (2023): 160.
[7] Hu, Liya, et al. "Novel fold of rotavirus glycan-binding domain predicted by AlphaFold2 and determined by X-ray crystallography." Communications Biology 5.1 (2022): 419.
[8] Nomburg, Jason, et al. "Birth of protein folds and functions in the virome." Nature 633.8030 (2024): 710-717.
[9] Xiao, Qingjie, et al. "Utilization of AlphaFold2 to predict MFS protein conformations after selective mutation." International Journal of Molecular Sciences 23.13 (2022): 7235.
[10] Wayment-Steele, Hannah K., et al. "Predicting multiple conformations via sequence clustering and AlphaFold2." Nature 625.7996 (2024): 832-839.
[11] Varadi, Mihaly, et al. "AlphaFold Protein Structure Database: massively expanding the structural coverage of protein-sequence space with high-accuracy models." Nucleic acids research 50.D1 (2022): D439-D444.
[12] Sim, Jiho, Sohee Kwon, and Chaok Seok. "HProteome-BSite: predicted binding sites and ligands in human 3D proteome." Nucleic Acids Research 51.D1 (2023): D403-D408.
[13] Wong, Felix, et al. "Benchmarking AlphaFold‐enabled molecular docking predictions for antibiotic discovery." Molecular systems biology 18.9 (2022): e11081.
[14] Yang, Qiangzhen, et al. "Structural comparison and drug screening of spike proteins of ten SARS-CoV-2 variants." Research (2022).
[15] Zeng, Dian, et al. "A hemagglutinin stem vaccine designed rationally by AlphaFold2 confers broad protection against influenza B infection." Viruses 14.6 (2022): 1305.
[16] Ibrahim, Tarhan, et al. "AlphaFold2-multimer guided high-accuracy prediction of typical and atypical ATG8-binding motifs." PLoS biology 21.2 (2023): e3001962.
[17] Wayment-Steele, Hannah K., et al. "Predicting multiple conformations via sequence clustering and AlphaFold2." Nature 625.7996 (2024): 832-839.
[18] Jendrusch, Michael, Jan O. Korbel, and S. Kashif Sadiq. "AlphaDesign: A de novo protein design framework based on AlphaFold." Biorxiv (2021): 2021-10.
[19] Goverde, Casper A., et al. "De novo protein design by inversion of the AlphaFold structure prediction network." Protein Science 32.6 (2023): e4653.
[20] Van Kempen, Michel, et al. "Fast and accurate protein structure search with Foldseek." Nature biotechnology 42.2 (2024): 243-246.
[21] Barrio-Hernandez, Inigo, et al. "Clustering predicted structures at the scale of the known protein universe." Nature 622.7983 (2023): 637-645.
[22] Ma, Wenjian, et al. "Enhancing protein function prediction performance by utilizing AlphaFold-predicted protein structures." Journal of Chemical Information and Modeling 62.17 (2022): 4008-4017.
[23] Hu, Mingyang, et al. "Exploring evolution-aware &-free protein language models as protein function predictors." Advances in Neural Information Processing Systems 35 (2022): 38873-38884.