Resumen
Debido a sus propiedades catalíticas, las lacasas fúngicas tienen aplicación en diversos campos tecnológicos, desde la biorremediación hasta la producción de biocombustibles. Aquí reexaminamos la selección de modelos para la actividad de la lacasa extracelular en Trametes villosa mediante un diseño compuesto central (CCD), considerando factores como la temperatura, el pH inicial y el volumen de inóculo. Para abordar las preocupaciones sobre el sobreajuste y la “fuga” en la evaluación en estudios RSM de tamaño muestral pequeño (N pequeño), adoptamos un protocolo estricto de validación cruzada (CV) anidada (externa de 5 pliegues para la generalización e interna de 3 pliegues para el ajuste de hiperparámetros) y comparamos tres modelos de aprendizaje superficial: regresión de cresta cuadrática, regresión de vectores de soporte (SVR) de núcleo RBF y bosques aleatorios con dos perceptrones multicapa compactos (MLP). Para preservar la plausibilidad física, modelamos la respuesta como log(y + ε) con ε = 0,1 y reportamos el RMSE y el R² del CV externo de 5 pliegues en la escala retrotransformada. En los pliegues externos, la SVR (RBF) obtuvo el menor RMSE y la menor varianza entre pliegues; el bosque aleatorio fue competitivo; los MLP mostraron mayor variabilidad y la cresta se ajustó insuficientemente. Los análisis SHAP para el mejor modelo destacaron la temperatura como el principal factor determinante, y el pH y el inóculo como contribuciones secundarias no monótonas. Los resultados indican que los métodos no lineales superficiales se generalizan mejor en conjuntos de datos RSM pequeños y deberían preferirse para la optimización de procesos en etapas tempranas.
Referencias
Agrawal, K., Chaturvedi, V., Verma, P. (2018). Fungal laccase discovered but yet undiscovered. Bioresources & Bioprocessing, 5, 4. https://doi.org/10.1186/s40643-018-0190-z
Alazmi, M. (2024). Enzyme catalytic efficiency prediction: employing convolutional neural networks and XGBoost. Frontiers in Artificial Intelligence, 7, 1446063. https://doi.org/10.3389/frai.2024.1446063
Aragao, M. S., Menezes, D. B., Ramos, L. C., Oliveira, H. S., Bharagava, R. N., Ferreira, L. F. R., Teixeira, J. A., Ruzene, D., Silva, D. P. (2020). Mycoremediation of vinasse by surface response methodology and preliminary studies in air-lift bioreactors. Chemosphere, 244(2), 125432. https://doi.org/10.1016/j.chemosphere.2019.125432
Caballero, R. E., Jiménez, V., Miranda, M., Rovira, D., Branda, G., de Pérez, J. R. C. (2024). An optimal culture medium for laccase production and sugar cane vinasse biotreatment with Trametes villosa using Plackett–Burman and central composite designs. Applied Environmental Research, 46(1), 001. https://doi.org/10.35762/AER.2024001
Cao, Y., Qiu, B., Ning, X., Fan, L., Qin, Y., Yu, D., Yang, C., Ma, H., Liao, X., You, C. (2024). Enhancing machine-learning prediction of enzyme catalytic temperature optima through amino acid conservation analysis. International Journal of Molecular Sciences, 25(11), 6252. https://doi.org/10.3390/ijms25116252
Cheng, Y., Bi, X., Xu, Y., Liu, Y., Li, J., Du, G., Lv, X., Liu, L. (2022). Artificial intelligence technologies in bioprocess: Opportunities and challenges. Bioresource Technology, 369, 128451. https://doi.org/10.1016/j.biortech.2022.128451
Chenthamara, D., Sivaramakrishnan, M., Ramakrishnan, S., Esakkimuthu, S., Ko, R., Subramaniam, S. (2022). Improved laccase production from Pleurotus floridanus using deoiled microalgal biomass: statistical and hybrid swarm-based neural networks modeling approach. 3 Biotech, 12(12), 346. https://doi.org/10.1007/s13205-022-03404-y
da Silva Pereira, A., Pinheiro, Á. D. T., Rocha, M. V. P., Gonçalves, L. R. B., Cartaxo, S. J. M. (2021). Hybrid neural network modeling and particle swarm optimization for improved ethanol production from cashew apple juice. Bioprocess and Biosystems Engineering, 44(2), 329–342. https://doi.org/10.1007/s00449-020-02445-y
de Menezes, L. H. S., Pimentel, A. B., Oliveira, P. C., Tavares, I. M., Ruiz, H., Irfan, M., Bilal, M., das Chagas, T. P., da Silva, R. G. P., Salay, L. C., de Oliveira, J. R., Franco, M. (2023). The application of chemometric methods in the production of enzymes through solid state fermentation uses the artificial neural network—a review. Bioenergy Research, 16, 279–288. https://doi.org/10.1007/s12155-022-10462-w
Dhakar, K., & Pandey, A. (2013). Laccase production from a temperature and pH tolerant fungal strain of Trametes hirsuta (MTCC 11397). Enzyme Research, 2013, 869062. https://doi.org/10.1155/2013/869062
Dourado Fernandes, C., Nascimento, V., Menezes, D., Vilar, D., Torres, N., Leite, M., Veja-Baudrit, J., Bilal, M., Iqbal, H., Bharagava, R., Egues, S., Ferreira, L. F. (2020). Fungal biosynthesis of lignin-modifying enzymes from pulp wash and Luffa cylindrica for azo dye RB5 biodecolorization using modeling by response surface methodology and artificial neural network. Journal of Hazardous Materials, 399, 123094. https://doi.org/10.1016/j.jhazmat.2020.123094
Gado, J. E., Knotts, M., Shaw, A. Y., Marks, D., Gauthier, N. P., Sander, C., Beckham, G. T. (2025). Machine learning prediction of enzyme optimum pH. Nature Machine Intelligence, 7, 716–729. https://doi.org/10.1038/s42256-025-01026-6
Gutiérrez-Soto, G., Medina-González, G., Treviño-Ramírez, J., Hernández-Luna, C. (2015). Native macro fungi that produce lignin-modifying enzymes, cellulases and xylanases with potential biotechnological applications. BioResources, 10(4), 6676–6689. https://doi.org/10.15376/biores.10.4.6676-6689
Janusz, G., Pawlik, A., Świderska, U., Polak, J., Sokół, J., Jarosz-Wilkolazka, A., Paszczynski, A. (2020). Laccase properties, physiological functions, and evolution. International Journal of Molecular Sciences, 21, 966. https://doi.org/10.3390/ijms21030966
Junior, J. A., Vieira, Y. A., Cruz, I. A., Vilar, D., Aguiar, M. M., Torres, N. H., Bharagava, R. N., Lima, A. S., de Souza, R. L., Ferreira, L. F. R. (2020). Sequential degradation of raw vinasse by a laccase enzyme producing fungus Pleurotus sajor-caju and its ATPS purification. Biotechnology Reports, 25, e00411.
Karp, S., Faraco, V., Amore, A., Letti, L., Thomaz-Soccol, V., Soccol, C. (2015). Statistical optimization of laccase production and delignification of sugarcane bagasse by Pleurotus ostreatus in solid-state fermentation. BioMed Research International, 2015, 1–8. https://doi.org/10.1155/2015/181204
Loi, M., Glazunova, O., Fedorova, T., Logrieco, A. F., Mulè, G. (2021). Fungal laccases: The forefront of enzymes for sustainability. Journal of Fungi, 7, 1048. https://doi.org/10.3390/jof7121048
Lundberg, S. M., Lee, S.-I. (2017). A unified approach to interpreting model predictions. In U. von Luxburg (Ed.), Advances in Neural Information Processing Systems (NeurIPS) (pp. 4768–4777). Curran Associates Inc.
Mayolo-Deloisa, K., González-González, M., Rito-Palomares, M. (2020). Laccases in food industry: bioprocessing, potential industrial and biotechnological applications. Frontiers in Bioengineering and Biotechnology, 8, 222. https://doi.org/10.3389/fbioe.2020.00222
Mondal, P., Galodha, A., Verma, V., Singh, V., Show, P., Awasthi, M., Lall, B., Anees, S., Pollmann, K., Jain, R. (2023). Review on machine learning-based bioprocess optimization, monitoring, and control systems. Bioresource Technology, 370, 128523. https://doi.org/10.1016/j.biortech.2022.128523
Moore, D., Robson, G., Trinci, A. (2020). 21st century guidebook to fungi. Cambridge University Press. https://doi.org/10.1017/9781108776387
Palmieri, G., Giardina, P., Bianco, C., Scaloni, A., Capasso, A., Sannia, G. (1998). A novel white laccase from Pleurotus ostreatus. The Journal of Biological Chemistry, 272(50), 31301–31307. https://dx.doi.org/10.1074/jbc.272.50.31301
Paraschiv, G., Ferdes, M., Ionescu, M., Moiceanu, G., Zabava, B. S., Dinca, M. N. (2022). Laccases—versatile enzymes used to reduce environmental pollution. Energies, 15, 1835. https://doi.org/10.3390/en15051835
Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Prettenhofer, P., Weiss, R., Dubourg, V., VanderPlas, J., Passos, A., Cournapeau, D., Brucher, M., Perrot, M., Duchesnay, E. (2011). Scikit-learn: Machine learning in Python. Journal of Machine Learning Research, 12, 2825–2830.
Senthivelan, T., Kanagaraj, J., Panda, R. C., Narayani, T. (2019). Screening and production of a potential extracellular fungal laccase from Penicillium chrysogenum: media optimization by response surface methodology (RSM) and central composite rotatable design (CCRD). Biotechnology Reports, 23, 30–44. https://doi.org/10.1016/j.btre.2019.e00344
Van Rossum, G., & Drake, F. L. (2009). Python 3 Reference Manual. Python Software Foundation, CreateSpace.
Vilar, D., Dourado Fernandes, C., Nascimento, V., Torres, N., Leite, M., Bharagava, R., Bilal, M., Salazar, G., Eguiluz, K., Ferreira, L. F. (2021). Hyper-production optimization of fungal oxidative green enzymes using citrus low-cost byproduct. Journal of Environmental Chemical Engineering, 9, 105013. https://doi.org/10.1016/j.jece.2020.105013
Wadhwa, H., Singh, R., Chopra, C. (2023). Occurrence and applications of fungal laccases: a comprehensive biotechnological review. Biological Forum – An International Journal, 15(4), 463–469.
Wainaina, S., & Taherzadeh, M. (2023). Automation and artificial intelligence in filamentous fungi-based bioprocesses: a review. Bioresource Technology, 369, 128421. https://doi.org/10.1016/j.biortech.2022.128421
Zhang, L., Luo, K., Zhou, Z., Yu, Y., Jiang, F., Banghao, W., Li, M., Hong, L. (2025). A deep retrieval-enhanced meta-learning framework for enzyme optimum pH prediction. Journal of Chemical Information and Modeling, 65(7), 3761–3770. https://doi.org/10.1021/acs.jcim.4c02291
Esta obra está bajo una licencia internacional Creative Commons Atribución-NoComercial-SinDerivadas 4.0.
Derechos de autor 2026 Revista de la Academia Colombiana de Ciencias Exactas, Físicas y Naturales