AlphaFold 3: an unprecedent opportunity for fundamental research and drug development

Abstract

AlphaFold3 (AF3), as the latest generation of artificial intelligence model jointly developed by Google DeepMind and Isomorphic Labs, has been widely heralded in the scientific research community since its launch. With unprecedented accuracy, the AF3 model may successfully predict the structure and interactions of virtually all biomolecules, including proteins, ligands, nucleic acids, ions, etc. By accurately simulating the structural information and interactions of biomacromolecules, it has shown great potential in many aspects of structural prediction, mechanism research, drug design, protein engineering, vaccine development, and precision therapy. In order to further understand the characteristics of AF3 and accelerate its promotion, this article sets out to address the development process, working principle, and application in drugs and biomedicine, especially focusing on the intricate differences and some potential pitfalls compared to other deep learning models. We explain how a structure-prediction tool can impact many research fields, and in particular revolutionize the strategies for designing of effective next generation vaccines and chemical and biological drugs.

Keywords

AlphaFold3 / artificial intelligence / structure prediction / drug design / biomedical research

Acknowledgments

This work was supported by funds of the Key Research and Development Grant of MOST (grant No. 2023YFA095000), the Affiliated Xiangshan Hospital of Wenzhou Medical University, the National Science Foundation of China (grant No. 82470005), and Wenzhou Institute University of Chinese Academy of Sciences. We thank members of the laboratory for helpful discussion.

Author contributions

Ziqi Fang (Writing—original draft), Hongbiao Ran (Writing—original draft), Yonghan Zhang (Writing—original draft), Chensong Chen (Writing—review & editing), Ping Lin (Writing—review & editing), Xiang Zhang (Writing—review & editing), and Min Wu (Writing—review & editing).

Conflict of interest

None declared. The corresponding author M.W. as an Editorial Board Member of Precision Clinical Medicine was blinded from reviewing and making decisions on this manuscript.

References

[1] Callaway E. Chemistry Nobel goes to developers of AlphaFold AI that predicts protein structures. Nature 2024; 634: 525-6. https://doi.org/10.1038/d41586-024-03214-7

[2] Abramson J, Adler J, Dunger J et al. Accurate structure pre-diction of biomolecular interactions with AlphaFold 3. Nature 2024; 630: 493-500. https://doi.org/10.1038/s41586-024-07487-w

[3] Cramer P. AlphaFold2 and the future of structural biology. Nat Struct Mol Biol 2021; 28: 704-5. https://doi.org/10.1038/s41594-021-00650-1

[4] Akdel M, Pires DEV, Pardo EP et al. A structural biology commu-nity assessment of AlphaFold2 applications. Nat Struct Mol Biol 2022; 29: 1056-67. https://doi.org/10.1038/s41594-022-00849-w

[5] Bordin N, Dallago C, Heinzinger M et al. Novel machine learning approaches revolutionize protein knowledge. Trends Biochem Sci 2023; 48: 345-59. https://doi.org/10.1016/j.tibs.2022.11.001

[6] Dill KA, MacCallum JL. The protein-folding problem, 50 years on. Science 2012; 338: 1042-6. https://doi.org/10.1126/science.1219021

[7] Kendrew JC, Bodo G, Dintzis HM et al. A three-dimensional model of the myoglobin molecule obtained by x-ray analysis. Nature 1958; 181: 662-6. https://doi.org/10.1038/181662a0

[8] Shi Y. A glimpse of structural biology through X-ray crystallog-raphy. Cell 2014; 159: 995-1014. https://doi.org/10.1016/j.cell.2014.10.051

[9] Wüthrich K. Protein structure determination in solution by NMR spectroscopy. J Biol Chem 1990; 265: 22059-62. https://doi.org/10.1016/S0021-9258(18)45665-7

[10] Earl LA, Falconieri V, Milne JL et al. Cryo-EM: beyond the micro-scope. Curr Opin Struct Biol 2017; 46: 71-8. https://doi.org/10.1016/j.sbi.2017.06.002

[11] Thompson MC, Yeates TO, Rodriguez JA. Advances in meth-ods for atomic resolution macromolecular structure determi-nation. F1000Research 2020; 9: F1000 Faculty Rev-667. https://doi.org/10.12688/f1000research.25097.1

[12] Bai X-c, McMullan G, Scheres SHW. How cryo-EM is revolu-tionizing structural biology. Trends Biochem Sci 2015; 40: 49-57. https://doi.org/10.1016/j.tibs.2014.10.005

[13] Jaskolski M, Dauter Z, Wlodawer A. A brief history of macro-molecular crystallography, illustrated by a family tree and its Nobel fruits. FEBS J 2014; 281: 3985-4009. https://doi.org/10.1111/febs.12796

[14] Taylor WR, Orengo CA. Protein structure alignment. J Mol Biol 1989; 208: 1-22. https://doi.org/10.1016/0022-2836(89)90084-3

[15] Zhang Y, Skolnick J. TM-align: a protein structure alignment al-gorithm based on the TM-score. Nucleic Acids Res 2005; 33: 2302-9. https://doi.org/10.1093/nar/gki524

[16] Shindyalov IN, Bourne PE. Protein structure alignment by incre-mental combinatorial extension (CE) of the optimal path. Pro-tein Eng 1998; 11: 739-47. https://doi.org/10.1093/protein/11.9.739

[17] Wang S, Sun S, Li Z et al. Accurate de novo prediction of pro-tein contact map by ultra-deep learning model. PLoS Comput Biol 2017; 13: e1005324. https://doi.org/10.1371/journal.pcbi.1005324

[18] Pearce R, Zhang Y. Deep learning techniques have significantly impacted protein structure prediction and protein design. Curr Opin Struct Biol 2021; 68: 194-207. https://doi.org/10.1016/j.sbi.2021.01.007

[19] Kuhlman B, Bradley P. Advances in protein structure prediction and design. Nat Rev Mol Cell Biol 2019; 20: 681-97. https://doi.org/10.1038/s41580-019-0163-x

[20] Silver D, Huang A, Maddison CJ et al. Mastering the game of Go with deep neural networks and tree search. Nature 2016; 529: 484-9. https://doi.org/10.1038/nature16961

[21] Senior AW, Evans R, Jumper J et al. Improved protein structure prediction using potentials from deep learning. Nature 2020; 577: 706-10. https://doi.org/10.1038/s41586-019-1923-7

[22] Kryshtafovych A, Schwede T, Topf M et al. Critical assess-ment of methods of protein structure prediction (CASP)-Round XIII. Proteins 2019; 87: 1011-20. https://doi.org/10.1002/prot.25823

[23] Senior AW, Evans R, Jumper J et al. Protein structure predic-tion using multiple deep neural networks in the 13th Critical Assessment of Protein Structure Prediction (CASP13). Proteins 2019; 87: 1141-8. https://doi.org/10.1002/prot.25834

[24] Jumper J, Evans R, Pritzel A et al. Highly accurate protein struc-ture prediction with AlphaFold. Nature 2021; 596: 583-9. https://doi.org/10.1038/s41586-021-03819-2

[25] Kryshtafovych A, Schwede T, Topf M et al. Critical assessment of methods of protein structure prediction (CASP)—Round XIV. Proteins Struct Funct Bioinforma 2021; 89: 1607-17. https://doi.org/10.1002/prot.26237

[26] Varadi M, Anyango S, Deshpande M et al. AlphaFold Protein Structure Database: massively expanding the structural cov-erage of protein-sequence space with high-accuracy models. Nucleic Acids Res 2022; 50: D439-44. https://doi.org/10.1093/nar/gkab1061

[27] Marx V. Method of the year: protein structure prediction. Nat Methods 2022; 19: 5-10. https://doi.org/10.1038/s41592-021-01359-1

[28] Zhang Y, Vass M, Shi D et al. Benchmarking refined and unre-fined AlphaFold2 structures for Hit Discovery. J Chem Inf Model 2023; 63: 1656-67. https://doi.org/10.1021/acs.jcim.2c01219

[29] Kayastha K, Katsyv A, Himmrich C et al. Structure-based electron-confurcation mechanism of the Ldh-EtfAB complex. eLife 2022; 11: e77095. https://doi.org/10.7554/eLife.77095

[30] Liang M, Chen X, Zhu C et al. Identification of a novel substrate motif of yeast separase and deciphering the recognition speci-ficity using AlphaFold2 and molecular dynamics simulation. Biochem Biophys Res Commun 2022; 620: 173-9. https://doi.org/10.1016/j.bbrc.2022.06.056

[31] Lorenz P, Steinbeck F, Krause L et al. The KRAB domain of ZNF10 guides the identification of specific amino acids that trans-form the ancestral KRAB-A-related domain present in Human PRDM9 into a canonical modern KRAB-A domain. Int J Mol Sci 2022; 23: 1072. https://doi.org/10.3390/ijms23031072

[32] McMullen P, Fang L, Qiao Q et al. Impacts of a zwitterionic peptide on its fusion protein. Bioconjug Chem 2022; 33: 1485-93. https://doi.org/10.1021/acs.bioconjchem.2c00176

[33] Zhorov BS, Dong K. Pyrethroids in an AlphaFold2 model of the insect sodium channel. Insects 2022; 13: 745. https://doi.org/10.3390/insects13080745

[34] Pinheiro F, Santos J, Ventura S. AlphaFold and the amyloid landscape. J Mol Biol 2021; 433: 167059. https://doi.org/10.1016/j.jmb.2021.167059

[35] Goulet A, Joos R, Lavelle K et al. A structural discovery journey of streptococcal phages adhesion devices by AlphaFold2. Front Mol Biosci 2022; 9: 960325. https://doi.org/10.3389/fmolb.2022.960325

[36] Goulet A, Mahony J, Cambillau C et al. Exploring structural di-versity among adhesion devices encoded by lactococcal P335 phages with AlphaFold2. Microorganisms 2022; 10: 2278. https://doi.org/10.3390/microorganisms10112278

[37] Pasquadibisceglie A, Leccese A, Polticelli F. A computational study of the structure and function of human zrt and irt-like proteins metal transporters: an elevator-type transport mech-anism predicted by AlphaFold2. Front Chem 2022; 10: 1004815. https://doi.org/10.3389/fchem.2022.1004815

[38] Wee J, Wei GW. Benchmarking AlphaFold3’s protein-protein complex accuracy and machine learning prediction reliabil-ity for binding free energy changes upon mutation. ArXiv Pub-lished online June 6, 2024. https://doi.org/10.48550/arXiv.2406.03979

[39] Ma W, Zhang S, Li Z et al. Enhancing protein function pre-diction performance by utilizing AlphaFold-predicted protein structures. J Chem Inf Model 2022; 62: 4008-17. https://doi.org/10.1021/acs.jcim.2c00885

[40] Rappoport D, Jinich A. Enzyme substrate prediction from three-dimensional feature representations using space-filling curves. J Chem Inf Model 2023; 63: 1637-48. https://doi.org/10.1021/acs.jcim.3c00005

[41] Feng Y, Liu XC, Li L et al. Naturally occurring I81N mu-tation in Human cytochrome c regulates both inherent peroxidase activity and interactions with neuroglobin. ACS Omega 2022; 7: 11510-8. https://doi.org/10.1021/acsomega.2c01256

[42] Dawson JE, Smith IN, Martin W et al. Shape shifting: the mul-tiple conformational substates of the PTEN N-terminal PIP2 -binding domain. Protein Sci Publ Protein Soc 2022; 31: e4308. https://doi.org/10.1002/pro.4308

[43] Hu M, Yuan F, Yang KK et al. Exploring evolution-aware & -free protein language models as protein function predictors. ArXiv Published online October 16, 2022. https://doi.org/10.48550/arXiv.2206.06583

[44] Evans R, O’Neill M, Pritzel A et al. Protein complex prediction with AlphaFold-multimer. Biorxiv, 2022: 2021.10.04.463034. https://doi.org/10.1101/2021.10.04.463034

[45] Bernatavicius A, Šícho M, Janssen APA et al. AlphaFold meets de novo drug design: leveraging structural protein informa-tion in multitarget molecular generative models. J Chem Inf Model 2024; 64: 8113-22. https://doi.org/10.1021/acs.jcim.4c00309

[46] Deneke VE, Blaha A, Lu Y et al. A conserved fertilization com-plex bridges sperm and egg in vertebrates. Cell 2024; 187: 7066-7078. https://doi.org/10.1016/j.cell.2024.09.035

[47] He XH, You CZ, Jiang HL et al. AlphaFold2 versus experimen-tal structures: evaluation on G protein-coupled receptors. Acta Pharmacol Sin 2023; 44: 1-7. https://doi.org/10.1038/s41401-022-00938-y

[48] Graham F. Daily briefing: AlphaFold3 is now open source. Na-ture Published online November 12, 2024. https://doi.org/10.1038/d41586-024-03728-0

[49] Karras T, Aittala M, Aila T et al. Elucidating the design space of diffusion-based generative models. In 36th Conference on Neural Information Processing Systems, 2022, pp. 26565-77.

[50] Edgar RC, Batzoglou S. Multiple sequence alignment. Curr Opin Struct Biol 2006; 16: 368-73. https://doi.org/10.1016/j.sbi.2006.04.004

[51] Ji Z, Lee N, Frieske R et al. Survey of hallucination in natural language generation. ACM Comput Surv 2023; 55: 1-38. https://doi.org/10.1145/3571730

[52] Tade RS, Jain SN, Satyavijay JT et al. Artificial intelligence in the paradigm shift of pharmaceutical sciences: A review. Nano Biomed Eng 2024; 16: 64-77. https://doi.org/10.26599/NBE.2023.9290043

[53] Isert C, Atz K, Schneider G. Structure-based drug design with geometric deep learning. Curr Opin Struct Biol 2023; 79: 102548. https://doi.org/10.1016/j.sbi.2023.102548

[54] Wang F, Diao X, Chang S et al. Recent progress of deep learning in drug discovery. Curr Pharm Des 2021; 27: 2088-96. https://doi.org/10.2174/1381612827666210129123231

[55] Yang X, Wang Y, Byrne R et al. Concepts of artificial in-telligence for computer-assisted drug discovery. Chem Rev 2019; 119: 10520-94. https://doi.org/10.1021/acs.chemrev.8b00728

[56] Jiménez-Luna J, Grisoni F, Weskamp N et al. Artificial intelli-gence in drug discovery: recent advances and future perspec-tives. Expert Opin Drug Discov 2021; 16: 949-59. https://doi.org/10.1080/17460441.2021.1909567

[57] Sarkar C, Das B, Rawat VS et al. Artificial intelligence and ma-chine learning technology driven modern drug discovery and development. Int J Mol Sci 2023; 24: 2026. https://doi.org/10.3390/ijms24032026

[58] Hudson IL. Data integration using advances in machine learn-ing in drug discovery and molecular biology. Methods Mol Biol Clifton NJ 2021; 2190: 167-84. https://doi.org/10.1007/978-1-0716-0826-5_7

[59] Ren F, Ding X, Zheng M et al. AlphaFold accelerates artificial intelligence powered drug discovery: efficient discovery of a novel CDK20 small molecule inhibitor. Chem Sci 2023; 14: 1443-52. https://doi.org/10.1039/d2sc05709c

[60] Weng Y, Pan C, Shen Z et al. Identification of potential WSB1 in-hibitors by AlphaFold modeling, virtual screening, and Molec-ular dynamics simulation studies. Evid-Based Complement Al-tern Med ECAM 2022; 2022: 4629392. https://doi.org/10.1155/2022/4629392

[61] Yang Q, Jian X, Syed AAS et al. Structural comparison and drug screening of spike proteins of ten SARS-CoV-2 variants. Res Wash DC 2022; 2022: 9781758. https://doi.org/10.34133/2022/9781758

[62] Park HM, Park Y, Vankerschaver J et al. Rethinking protein drug design with highly accurate structure prediction of anti-CRISPR proteins. Pharm Basel Switz 2022; 15: 310. https://doi.org/10.3390/ph15030310

[63] Yang Q, Xia D, Syed AAS et al. Highly accurate protein struc-ture prediction and drug screen of monkeypox virus proteome. J Infect 2023; 86: 66-117. https://doi.org/10.1016/j.jinf.2022.08.006

[64] Buttenschoen M, Morris GM, Deane CM. PoseBusters: AI-based docking methods fail to generate physically valid poses or gen-eralise to novel sequences. Chem Sci 2024; 15: 3130-9. https://doi.org/10.1039/d3sc04185a

[65] Mirdita M, Schütze K, Moriwaki Y et al. ColabFold: making pro-tein folding accessible to all. Nat Methods 2022; 19: 679-82. https://doi.org/10.1038/s41592-022-01488-1

[66] Manshour N, Ren JZ, Esmaili F et al. Comprehensive evaluation of AlphaFold-multimer, AlphaFold3 and ColabFold, and scor-ing functions in predicting protein-peptide complex structures. Biorxiv, 2024: 2024.11.11.622992. https://doi.org/10.1101/2024.11.11.622992

[67] Medvedev KE, Schaeffer RD, Grishin NV. Leveraging AI to ex-plore structural contexts of post-translational modifications in drug binding. J Cheminformatics 2025; 17: 67. https://doi.org/10.1186/s13321-025-01019-y

[68] Schymkowitz J, Borg J, Stricher F et al. The FoldX web server: an online force field. Nucleic Acids Res 2005; 33: W382-388. https://doi.org/10.1093/nar/gki387

[69] Xiong P, Zhang C, Zheng W et al. BindProfX: assessing mutation-induced binding affinity change by protein interface profiles with pseudo-counts. J Mol Biol 2017; 429: 426-34. https://doi.org/10.1016/j.jmb.2016.11.022

[70] Lu W, Zhang J, Rao J et al. AlphaFold3, a secret sauce for predicting mutational effects on protein-protein interactions. Biorxiv, 2024: 2024.05.25.595871. https://doi.org/10.1101/2024.05.25.595871

[71] Wee J, Wei GW. Evaluation of AlphaFold 3’s protein-protein complexes for predicting binding free energy changes upon mutation. J Chem Inf Model 2024; 64: 6676-83. https://doi.org/10.1021/acs.jcim.4c00976

[72] Chen E, Pan E, Zhang S. Structure bioinformatics of six Hu-man integral transmembrane enzymes and their AlphaFold3 predicted water-soluble QTY analogs: insights into FACE1 and STEA4 binding mechanisms. Pharm Res 2025; 42: 291-305. https://doi.org/10.1007/s11095-025-03822-6

[73] Stanzione F, Giangreco I, Cole JC. Use of molecular dock-ing computational tools in drug discovery. Prog Med Chem 2021; 60: 273-343. https://doi.org/10.1016/bs.pmch.2021.01.004

[74] Zhao Z, Ukidve A, Kim J et al. Targeting strategies for tissue-specific drug delivery. Cell 2020; 181: 151-67. https://doi.org/10.1016/j.cell.2020.02.001

[75] Zhang X, Shen C, Zhang H et al. Advancing Ligand docking through deep learning: challenges and prospects in virtual screening. Acc Chem Res 2024; 57: 1500-9. https://doi.org/10.1021/acs.accounts.4c00093

[76] Wang ZY, Li MZ, Li WJ et al. Mechanism of action of Daqinjiao decoction in treating cerebral small vessel disease explored using network pharmacology and molecular docking technol-ogy. Phytomedicine Int J Phytother Phytopharm 2023; 108: 154538. https://doi.org/10.1016/j.phymed.2022.154538

[77] Li T, Guo R, Zong Q et al. Application of molecular docking in elaborating molecular mechanisms and inter-actions of supramolecular cyclodextrin. Carbohydr Polym 2022; 276: 118644. https://doi.org/10.1016/j.carbpol.2021.118644

[78] Dong Y, Tao B, Xue X et al. Molecular mechanism of Epicedium treatment for depression based on network phar-macology and molecular docking technology. BMC Complement Med Ther 2021; 21: 222. https://doi.org/10.1186/s12906-021-03389-w

[79] Sun Z, Wang Y, Pang X et al. Mechanisms of polydatin against spinal cord ischemia-reperfusion injury based on network pharmacology, molecular docking and molecular dynamics simulation. Bioorganic Chem 2023; 140: 106840. https://doi.org/10.1016/j.bioorg.2023.106840

[80] Krishna R, Wang J, Ahern W et al. Generalized biomolec-ular modeling and design with RoseTTAFold All-Atom. Science 2024; 384: eadl2528. https://doi.org/10.1126/science.adl2528

[81] Trott O, Olson AJ. AutoDock Vina: improving the speed and ac-curacy of docking with a new scoring function, efficient opti-mization, and multithreading. J Comput Chem 2010; 31: 455-61. https://doi.org/10.1002/jcc.21334

[82] Miller EB, Murphy RB, Sindhikara D et al. Reliable and accurate solution to the induced fit docking problem for protein-ligand binding. J Chem Theory Comput 2021; 17: 2630-9. https://doi.org/10.1021/acs.jctc.1c00136

[83] Solís KH, Romero-Ávila MT, Rincón-Heredia R et al. Multiple LPA3 receptor agonist binding sites evidenced under docking and functional studies. Int J Mol Sci 2025; 26: 4123. https://doi.org/10.3390/ijms26094123

[84] Li X, Zhou S, Tae HS et al. N-terminal capping of the αo-conotoxin analogue GeX-2 improves the serum stability and selectivity toward the Human α9 α10 nicotinic acetylcholine re-ceptor. J Med Chem 2024; 67: 18400-11. https://doi.org/10.1021/acs.jmedchem.4c01758

[85] Gadde N, Dodamani S, Altaf R et al. Leveraging AlphaFold 3 for structural modeling of neurological disorder-associated proteins: A pathway to precision medicine. Biorxiv, 2024: 2024.11.18.624211. https://doi.org/10.1101/2024.11.18.624211

[86] Yao M, Miller GW, Vardarajan BN et al. Deciphering proteins in Alzheimer’s disease: A new mendelian randomization method integrated with AlphaFold3 for 3D structure prediction. Cell Ge-nomics 2024; 4: 100700. https://doi.org/10.1016/j.xgen.2024.100700

[87] Domene-Serrano I, Cuadros R, García-Escudero V et al. Shapeshifter W-Tau peptide inhibits tau aggregation and disin-tegrates paired helical Filaments. Biochemistry 2025; 64: 1841-51. https://doi.org/10.1021/acs.biochem.4c00809

[88] Peng Z, Xu S, Wang H et al. Identification of GDP as a small inhibitory molecule in HepG2 cells by non-targeted metabolomics analysis. Oncol Lett 2025; 29: 178. https://doi.org/10.3892/ol.2025.14924

[89] Zhao S, Luo J, Xu P et al. Designed peptide binders and nanobod-ies as PROTAC starting points for targeted degradation of PCNA and BCL6. Int J Biol Macromol 2025; 308: 142667. https://doi.org/10.1016/j.ijbiomac.2025.142667

[90] Klußmann M, Reuter J, Werner C et al. Examining farnesyltrans-ferase interaction with cell-permeable CaaX peptides and the role of the CaaX motif in biological activity. J Pept Sci Off Publ Eur Pept Soc 2025; 31: e70009. https://doi.org/10.1002/psc.70009

[91] Wee J, Chen J, Wei GW. Preventing future zoonosis: SARS-CoV-2 mutations enhance human-animal cross-transmission. Com-put Biol Med 2024; 182: 109101. https://doi.org/10.1016/j.compbiomed.2024.109101

[92] Wang J, Xie J, Yu Y et al. Enhancing the understandings on SARS-CoV-2 main protease (Mpro) mutants from molecular dynam-ics and machine learning. Int J Biol Macromol 2025; 310: 143076. https://doi.org/10.1016/j.ijbiomac.2025.143076

[93] Liu N, Zhu Y, Chong H et al. Structural characterization of HIV fusion inhibitor LP-98: insights into antiviral and resistance mechanisms. Antiviral Res 2025; 239: 106190. https://doi.org/10.1016/j.antiviral.2025.106190

[94] Mosalanejad Z, Faraji SN, Rahbar MR et al. Designing an op-timized theta-defensin peptide for HIV therapy using in-silico approaches. J Integr Bioinforma Published online March 19, 2025. https://doi.org/10.1515/jib-2023-0053

[95] Su H, Wu G, Xiong M et al. Dynamic cap-mediated substrate access and potent inhibitor design of Monkeypox virus I7L pro-tease. Adv Sci Weinh Baden-Wurtt Ger Published online April 7, 2025:e2501625. https://doi.org/10.1002/advs.202501625

[96] Zhang L, Zheng Y, Shao M et al. AlphaFold-based AI docking reveals AMPK/SIRT1-TFEB pathway modulation by traditional Chinese medicine in metabolic-associated fatty liver disease. Pharmacol Res 2025; 212: 107617. https://doi.org/10.1016/j.phrs.2025.107617

[97] Claustre A, Malige M, Macheton M et al. Structure predictions of MuRF1-UBE2 complexes identify amino acid residues gov-erning interaction selectivity for each MuRF1-E2 pair. FEBS J 2025; 292: 2559-77. https://doi.org/10.1111/febs.70017

[98] Zhou H, Xu Z, Xiong Y et al. Structural insights into the binding of human TGIF1 with SMAD2 MH2 domain. FEBS Lett Published online May 21, 2025. https://doi.org/10.1002/1873-3468.70073

[99] Xiao L, Wu Z, Su J et al. Development of a potent neutraliz-ing nanobody against canine distemper virus hemagglutinin protein. Front Immunol 2025; 16: 1585793. https://doi.org/10.3389/fimmu.2025.1585793

[100] Lin Z, Akin H, Rao R et al. Evolutionary-scale prediction of atomic-level protein structure with a language model. Science 2023; 379: 1123-30. https://doi.org/10.1126/science.ade2574

[101] Baek M, DiMaio F, Anishchenko I et al. Accurate prediction of protein structures and interactions using a three-track neural network. Science 2021; 373: 871-6. https://doi.org/10.1126/science.abj8754

[102] Guo C, Liu X, Mei Z et al. AMBP protects against aortic valve calcification by inhibiting ERK1/2 and JNK pathways mediated by FHL3. Theranostics 2025; 15: 4398-415. https://doi.org/10.7150/thno.109182

[103] Madarász K, Mótyán JA, Chang Chien YC et al. BCOR-rearranged sarcomas: In silico insights into altered domains and BCOR in-teractions. Comput Biol Med 2025; 191: 110144. https://doi.org/10.1016/j.compbiomed.2025.110144

[104] Yue C, Shi S, Li Z et al. Studying the signaling mechanism of Neuropilin-1’s intracellular disorder region via conformational mining and dynamic interaction characterization. J Phys Chem B 2025; 129: 2392-401. https://doi.org/10.1021/acs.jpcb.4c07616

[105] Chu KY, Crawford AN, Krah BS et al. Cripto-1 acts as a molecu-lar bridge linking nodal to ALK4 via distinct structural domains. Protein Sci Publ Protein Soc 2025; 34: e70034. https://doi.org/10.1002/pro.70034

[106] Pan A, Liu X, Han H et al. Disruption of a potential disulfide bond of Cys65-Cys141 on the structure and stability of globin X from zebrafish. Phys Chem Chem Phys PCCP 2025; 27: 2828-33. https://doi.org/10.1039/d4cp04253k

[107] Zeng D, Xin J, Yang K et al. A hemagglutinin stem vaccine designed rationally by AlphaFold2 confers broad protection against influenza B infection. Viruses 2022; 14: 1305. https://doi.org/10.3390/v14061305

[108] Alnajran H, Awadalla M, Aldakheel FM et al. Design of a peptide-based vaccine against human respiratory syncytial virus using a reverse vaccinology approach: evaluation of immunogenicity, antigenicity, allergenicity, and toxicity. Front Immunol 2025; 16: 1546254. https://doi.org/10.3389/fimmu.2025.1546254

[109] Jiang K, Yan Z, Di Bernardo M et al. Rapid in silico directed evo-lution by a protein language model with EVOLVEpro. Science 2025; 387: eadr6006.https://doi.org/10.1126/science.adr6006

[110] Wei Y, Gao P, Pan D et al. Engineering eukaryotic transposon-encoded Fanzor2 system for genome editing in mammals. Nat Chem Biol Published online May 20, 2025. https://doi.org/10.1038/s41589-025-01902-7

[111] Johnsson F, Karagöl T, Karagöl A et al. Structural bioinfor-matic study of six human olfactory receptors and their Al-phaFold3 predicted water-soluble QTY variants and OR1A2 with an odorant octanoate and TAAR9 with spermidine. QRB Discov 2025; 6: e2. https://doi.org/10.1017/qrd.2024.18

[112] Chen E, Zhang S. Structural bioinformatic study of human mitochondrial respiratory integral membrane megacomplex and its AlphaFold3 predicted water-soluble QTY megacomplex analog. QRB Discov 2025; 6: e12. https://doi.org/10.1017/qrd.2025.2

[113] Gao H, Hamp T, Ede J et al. The landscape of tolerated genetic variation in humans and primates. Science 2023; 380: eabn8153. https://doi.org/10.1126/science.abn8197

[114] Iqbal S, Brünger T, Pérez-Palma E et al. Delineation of func-tionally essential protein regions for 242 neurodevelopmental genes. Brain 2023; 146: 519-33. https://doi.org/10.1093/brain/awac381

[115] Zhang Z, Li C, Li Q et al. Structure prediction of novel isoforms from uveal melanoma by AlphaFold. Sci Data 2023; 10: 513. https://doi.org/10.1038/s41597-023-02429-z

[116] Qie D, Zhai Y, Yang F et al. A de novo TNNI3K variant ag-gravates the pathogenicity of DMD-associated early-onset car-diomyopathy:a case report. Front Genet 2025; 16: 1525941. https://doi.org/10.3389/fgene.2025.1525941

[117] Chen J, Li Z, Wu Y et al. Identification of pathogenic missense mutations of NF1 using computational approaches. J Mol Neu-rosci MN 2024; 74: 94. https://doi.org/10.1007/s12031-024-02271-x

[118] Nosrati MSS, Doustmohammadi A, Severino M et al. Novel KIF26A variants associated with pediatric intestinal pseudo-obstruction (PIPO) and brain developmental defects. Clin Genet 2025; 107: 83-90. https://doi.org/10.1111/cge.14621

[119] Ding X, Chen H, Lu Y et al. Analysis of FBN1 gene mutations in six Chinese pedigrees affected with Marfan syndrome. Chin J Med Genet 2025; 42: 41-50. https://doi.org/10.3760/cma.j.cn511374-20240828-00459

[120] Liu Y, Yan L, Zhang Y et al. Genetic analysis of a fetus with Far-ber lipogranulomatosis caused by ASAH1 gene variant. Chin J Med Genet 2025; 42: 232-7. https://doi.org/10.3760/cma.j.cn511374-20240910-00482

[121] Furukawa S, Kushima I, Kato H et al. Whole-genome sequencing analysis of Japanese autism spectrum disorder trios. Psychiatry Clin Neurosci 2025; 79: 87-97. https://doi.org/10.1111/pcn.13767

[122] Homma F, Huang J, van der Hoorn RAL. AlphaFold-Multimer predicts cross-kingdom interactions at the plant-pathogen in-terface. Nat Commun 2023; 14: 6040. https://doi.org/10.1038/s41467-023-41721-9

[123] Jia X, Fu Q, Yang G et al. Genome-wide identification and expres-sion analysis of TONNEAU1 recruited motif (TRM) gene Family in tomato. Int J Mol Sci 2025; 26: 3676. https://doi.org/10.3390/ijms26083676

[124] Toghani A, Terauchi R, Kamoun S et al. Can AI modelling of pro-tein structures distinguish between sensor and helper NLR im-mune receptors? Biorxiv, 2024: 2024.11.24.625045. https://doi.org/10.1101/2024.11.24.625045

[125] Ye ZX, Gu GW, Ren PP et al. Identification and characterization of three novel iflaviruses in the cabbage Whitefly Aleyrodes proletella. Insects 2025; 16: 335. https://doi.org/10.3390/insects16040335

[126] Wen H, Wang L, Gong Y et al. Genome-wide identification and characterization of GRAS transcription factor Family in culti-vated hybrid sugarcane ZZ1 (Saccharum officinarum) and their role in development and stress. Int J Mol Sci 2024; 25: 13470. https://doi.org/10.3390/ijms252413470

[127] Yang T, Xu XT, Tang LJ et al. Genome-wide study of plant-specific PLATZ transcription factors and functional analysis of OsPLATZ1 in regulating caryopsis development of rice (Oryza sativa L.) Plants Basel Switz 2025; 14: 151. https://doi.org/10.3390/plants14020151

[128] Zhu X, Li Y, Gu N. Application of artificial intelligence in the ex-ploration and optimization of biomedical nanomaterials. Nano Biomed Eng 2023; 15: 342-53. https://doi.org/10.26599/NBE.2023.9290035

[129] Anusha ZZ, Li J, Zuo H et al. AlphaFold 3-Aided design of DNA motifs to assemble into triangles. J Am Chem Soc 2024; 146: 25422-5. https://doi.org/10.1021/jacs.4c08387

[130] Ye Q, Eves R, Vance TDR et al. Aeromonas hydrophila RTX adhesin has three ligand-binding domains that give the bac-terium the potential to adhere to and aggregate a wide vari-ety of cell types. mBio 2025; 16: e0315824. https://doi.org/10.1128/mbio.03158-24

[131] Gonzalez-Ordenes F, Herrera-Soto N, Muñoz SM et al. Glyco-gen metabolism in methanogens: A key pathway for metabolic response to nutrient availability. Biochem Biophys Res Commun 2024; 739: 150978. https://doi.org/10.1016/j.bbrc.2024.150978

[132] Yen IY, Whitfield GB, Rubinstein JL et al. Conformational changes in the motor ATPase CpaF facilitate a rotary mech-anism of Tad pilus assembly. Nat Commun 2025; 16: 3839. https://doi.org/10.1038/s41467-025-59009-5

[133] Bandeira PT, Chaves CR, Monteiro Torres PH et al. Immunolo-calization and 3D modeling of three unique proteins belonging to the costa of Tritrichomonas foetus. Parasitol Res 2025; 124: 30. https://doi.org/10.1007/s00436-025-08466-4

[134] Huang J, Peterson PP, Xu Z et al. Homeodomain protein Sxi1 αregulates cell-cell fusion during distinct sexual reproduc-tion modes in Cryptococcus deneoformans. BioRxiv, 2025: 2025.02.11.637763. https://doi.org/10.1101/2025.02.11.637763

[135] Liu S, Lei T, Tan Y et al. Discovery, structural characteristics and evolutionary analyses of functional domains in Acineto-bacter baumannii phage tail fiber/spike proteins. BMC Microbiol 2025; 25: 73. https://doi.org/10.1186/s12866-025-03790-2

[136] Shi Y. Drug development in the AI era: AlphaFold 3 is coming! Innov Camb Mass 2024; 5: 100685. https://doi.org/10.1016/j.xinn.2024.100685

[137] Watson ER, Novick S, Matyskiela ME et al. Molecular glue CELMoD compounds are regulators of cereblon conforma-tion. Science 2022; 378: 549-53. https://doi.org/10.1126/science.add7574

[138] Masters MR, Mahmoud AH, Lill MA. Do deep learning models for Co-folding learn the physics of protein-ligand interactions? Biorxiv, 2024: 2024.06.03.597219. https://doi.org/10.1101/2024.06.03.597219

[139] He XH, Li JR, Shen SY et al. AlphaFold3 versus experimen-tal structures: assessment of the accuracy in ligand-bound G protein-coupled receptors. Acta Pharmacol Sin Published online December 6, 2024. https://doi.org/10.1038/s41401-024-01429-y

[140] Eshak F, Goupil-Lamy A. AI driven approaches in nanobody epitope prediction: are we there yet? Biorxiv, 2024: 2024.10.07.616899. https://doi.org/10.1101/2024.10.07.616899

[141] Nam KH. Evaluation of AlphaFold3 for the fatty acids dock-ing to human fatty acid-binding proteins. J Mol Graph Model 2024; 133: 108872. https://doi.org/10.1016/j.jmgm.2024.108872

[142] Sieskind R, Missoury S, Madru C et al. Crystal structures of monomeric BsmI restriction endonuclease reveal coordi-nated sequential cleavage of two DNA strands. Commun Biol 2025; 8: 387. https://doi.org/10.1038/s42003-025-07612-z

[143] Mamun Y, Aguado A, Preza A et al. Substrate binding of human and bacterial type IA topoisomerase: an experimentation with AlphaFold 3.0. Comput Struct Biotechnol J 2025; 27: 1342-9. https://doi.org/10.1016/j.csbj.2025.03.041

[144] McDonnell RT, Henderson AN, Elcock AH. Structure prediction of large RNAs with AlphaFold3 highlights its capabilities and limitations. J Mol Biol 2024; 436: 168816. https://doi.org/10.1016/j.jmb.2024.168816

[145] Degenhardt MFS, Degenhardt HF, Bhandari YR et al. Determin-ing structures of RNA conformers using AFM and deep neural networks. Nature 2025; 637: 1234-43. https://doi.org/10.1038/s41586-024-07559-x

[146] Bernard C, Postic G, Ghannay S et al. Has AlphaFold 3 reached its success for RNAs? Biorxiv, 2024: 2024.06.13.598780. https://doi.org/10.1101/2024.06.13.598780

[147] Ji Z, Lee N, Frieske R et al. Survey of hallucination in natural language generation. ArXiv Published online July 14, 2024. https://doi.org/10.48550/arXiv.2202.03629

[148] Iebed D, Gökler T, van Ingen H et al. Phosphorylation of the HMGN1 nucleosome binding domain decreases helicity and in-teractions with the acidic patch. Chembiochem Eur J Chem Biol 2024; 25: e202400589. https://doi.org/10.1002/cbic.202400589

[149] Meng L, Wei L, Wu R. MVGNN-PPIS: A novel multi-view graph neural network for protein-protein interaction sites prediction based on Alphafold3-predicted structures and transfer learn-ing. Int J Biol Macromol 2025; 300: 140096. https://doi.org/10.1016/j.ijbiomac.2025.140096

[150] Jabeen A, Oakeshott JG, Lee SF et al. Template-based modeling of insect odorant receptors outperforms AlphaFold3 for ligand binding predictions. Sci Rep 2024; 14: 29084. https://doi.org/10.1038/s41598-024-80094-x

[151] Cheng J, Liu J, Neupane P. Accurate prediction of protein complex stoichiometry by integrating AlphaFold3 and tem-plate information. Research Square Published online February 6, 2025:rs.3.rs-5855710. https://doi.org/10.21203/rs.3.rs-5855710/v1

[152] Majila K, Ullanat V, Viswanath S. A deep learning method for predicting interactions for intrinsically disordered regions of proteins. BioRxiv 2025: 2024.12.19.629373. https://doi.org/10.1101/2024.12.19.629373

[153] Gomes DEB, Yang B, Vanella R et al. Integrating dynamic net-work analysis with AI for enhanced epitope prediction in PD-L1:affibody interactions. J Am Chem Soc 2024; 146: 23842-53. https://doi.org/10.1021/jacs.4c05869

[154] Song B, Wang K, Na S et al. Cmai: predicting antigen-antibody interactions from massive sequencing data. BioRxiv, 2024.06.27.601035. https://doi.org/10.1101/2024.06.27.601035

[155] Li Q, Zhao Y, Chordia MD et al. Enhanced prediction of antigen and antibody binding interface using ESM-2 and Bi-LSTM. Hum Immunol 2025; 86: 111304. https://doi.org/10.1016/j.humimm.2025.111304

[156] Olenyi T, Marquet C, Grekova A et al. TMVisDB: anno-tation and 3D-visualization of transmembrane proteins. J Mol Biol 2025; 437: 168997. https://doi.org/10.1016/j.jmb.2025.168997

[157] Tikhonov DB, Korkosh VS, Zhorov BS. 3D-aligned tetrameric ion channels with universal residue labels for comparative struc-tural analysis. Biophys J 2025; 124: 458-70. https://doi.org/10.1016/j.bpj.2024.12.019

[158] Zhang O, Naik SA, Liu ZH et al. A curated rotamer library for common post-translational modifications of proteins. Bioin-forma Oxf Engl 2024; 40: btae444. https://doi.org/10.1093/bioinformatics/btae444

[159] Medvedev KE, Schaeffer RD, Grishin NV. DrugDomain: the evo-lutionary context of drugs and small molecules bound to do-mains. Protein Sci Publ Protein Soc 2024; 33: e5116. https://doi.org/10.1002/pro.5116

[160] Döpner P, Kemnitz S, Doerr M et al. af3cli: Streamlining Al-phaFold3 input preparation. J Chem Inf Model 2025; 65: 3886-91. https://doi.org/10.1021/acs.jcim.5c00276

[161] Liu J, Neupane P, Cheng J. Improving AlphaFold2 and 3-based protein complex structure prediction with MULTICOM4 in CASP16. BioRxiv 2025: 2025.03.06.641913. https://doi.org/10.1101/2025.03.06.641913

[162] Nogales E, Mahamid J. Bridging structural and cell biology with cryo-electron microscopy. Nature 2024; 628: 47-56. https://doi.org/10.1038/s41586-024-07198-2

[163] Bartas M, Slychko K, Brázda V et al. Searching for new Z-DNA/Z-RNA binding proteins based on structural similarity to experi-mentally validated z αdomain. Int J Mol Sci 2022; 23: 768. https://doi.org/10.3390/ijms23020768