AI-based Protein 3D Prediction using AlphaFold
Article Sidebar
Main Article Content
Abstract
Three-dimensional protein prediction with a high approximation to the actual conformation is conceptually possible using mathematical models according to the Anfinsen dogma. Still, it is impractical due to the multiple conformations that add complexity due to the Levinthal paradox. One way to solve this puzzle is by using machine learning models based on structures that have already been elucidated using artificial intelligence. The AlphaFold program allows de novo predictions by using machine learning algorithms. This paper explains the tool’s components and the metrics used to interpret the results. It provides optional ways to access the program, along with a practical example to learn how to execute a prediction. It concludes with the principles of use and ethics of the tool.
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
Los autores conservan los derechos de autor y ceden a la revista el derecho de la primera publicación y pueda editarlo, reproducirlo, distribuirlo, exhibirlo y comunicarlo en el país y en el extranjero mediante medios impresos y electrónicos. Asimismo, asumen el compromiso sobre cualquier litigio o reclamación relacionada con derechos de propiedad intelectual, exonerando de responsabilidad a la Editorial Tecnológica de Costa Rica. Además, se establece que los autores pueden realizar otros acuerdos contractuales independientes y adicionales para la distribución no exclusiva de la versión del artículo publicado en esta revista (p. ej., incluirlo en un repositorio institucional o publicarlo en un libro) siempre que indiquen claramente que el trabajo se publicó por primera vez en esta revista.
References
[1] C. B. Anfinsen, “Principles that govern the folding of protein chains,” Science, vol. 181, no. 4096, pp. 223–230, 1973, doi: 10.1126/science.181.4096.223.
[2] R. Zwanzig, A. Szabo, and B. Bagchi, “Levinthal’s paradox,” Proc. Natl. Acad. Sci. USA, vol. 89, no. 1, pp. 20–22, 1992, doi: 10.1073/pnas.89.1.20.
[3] J. Jumper et al., “Highly accurate protein structure prediction with AlphaFold,” Nature, vol. 596, no. 7873, pp. 583-589, 2021, doi: 10.1038/s41586-021-03819-2.
[4] J. Abramson et al., “Accurate structure prediction of biomolecular interactions with AlphaFold 3,” Nature, vol. 630, no. 8016, pp. 493–500, 2024, doi: 10.1038/s41586-024-07487-w.
[5] U. Göbel, C. Sander, R. Schneider, and A. Valencia, “Correlated mutations and residue contacts in proteins,” Proteins, vol. 18, no. 4, pp. 309–317, 1994, doi: 10.1002/prot.340180402.
[6] S. A. Benner and D. Gerloff, “Patterns of divergence in homologous proteins as indicators of secondary and tertiary structure,” Adv. Enzyme Regul., vol. 31, pp. 121–181, 1991, doi: 10.1016/0065-2571(91)90012-B.
[7] W. R. Taylor and K. Hatrick, “Compensating changes in protein multiple sequence alignments,” Protein Eng. Des. Sel., vol. 7, no. 3, pp. 341–348, 1994, doi: 10.1093/protein/7.3.341.
[8] V. Mariani, M. Biasini, A. Barbato, and T. Schwede, “lDDT: A local superposition-free score for comparing protein structures and models,” Bioinformatics, vol. 29, no. 21, pp. 2722–2728, 2013, doi: 10.1093/bioinformatics/btt473.
[9] H.-B. Guo et al., “AlphaFold2 models indicate that protein sequence determines both structure and dynamics,” Sci. Rep., vol. 12, p. 10696, 2022, doi: 10.1038/s41598-022-14382-9.
[10] G. Kim et al., “Easy and accurate protein structure prediction using ColabFold,” 2023. [Online]. Available: https://colabfold.mmseqs.com
[11] R. Krishna et al., “Generalized biomolecular modeling and design with RoseTTAFold All-Atom,” Science, vol. 384, no. 6693, p. eadl2528, 2024, doi: 10.1126/science.adl2528.
[12] M. van Kempen et al., “Fast and accurate protein structure search with Foldseek,” Nat. Biotechnol., vol. 42, no. 2, pp. 243–246, 2024, doi: 10.1038/s41587-023-01773-0.
[13] M. Varadi et al., “AlphaFold Protein Structure Database in 2024: providing structure coverage for over 214 million protein sequences,” Nucleic Acids Res., vol. 52, no. D1, pp. D368–D375, 2024, doi: 10.1093/nar/gkad1011.
[14] B. T. Bajar et al., “Improving brightness and photostability of green and red fluorescent proteins for live cell imaging,” Sci. Rep., vol. 6, p. 20889, 2016, doi: 10.1038/srep20889.
[15] S. Papadaki et al., “Dual-expression system for blue fluorescent protein optimization,” Sci. Rep., vol. 12, p. 13214, 2022, doi: 10.1038/s41598-022-13214-0.
[16] T. M. Wannier et al., “Monomerization of far-red fluorescent proteins,” Proc. Natl. Acad. Sci. USA, vol. 115, no. 48, pp. E11294–E11301, 2018, doi: 10.1073/pnas.1807449115.
[17] J. Lee et al., “Versatile phenotype-activated cell sorting,” Sci. Adv., vol. 6, no. 43, p. eabb7438, 2020, doi: 10.1126/sciadv.abb7438.
[18] J. L. Watson et al., “De novo design of protein structure and function with RFdiffusion,” Nature, vol. 620, no. 7976, pp. 1089–1100, 2023, doi: 10.1038/s41586-023-06415-8.
[19] S. Vázquez Torres et al., “De novo designed proteins neutralize lethal snake venom toxins,” Nature, vol. 639, no. 8053, pp. 225–231, 2025, doi: 10.1038/s41586-024-08393-x.
[20] S. Tang et al., “De novo gene synthesis by an antiviral reverse transcriptase,” Science, vol. 386, no. 6717, pp. 1–41, 2024, doi: 10.1126/science.adq0876.