A Novel Metaheuristic Approach Inspired by Trees Social Relationships and Models for Fermentation Medium
Keywords:
Trees social relationship algorithm, Neural network modeling, Fermentation process optimization, Empirical model building, Hybrid optimization approachAbstract
The Trees Social Relationships (TSR) metaheuristic algorithm is employed to model and optimise a fermentation medium for producing the enzyme hydantoinase by Agrobacterium radiobacter. Leveraging experimental data from the literature, we developed two neural network models. The neural network models utilised the concentrations of four medium components as inputs and provided either hydantoinase or cell concentration as a single output. The TSR algorithm was then applied to optimise the input space of the neural network models, identifying the optimal settings for maximising enzyme and cell production. This approach showcases the effective integration of neural networks with the TSR algorithm, resulting in a robust process modeling and optimisation tool.
References
[1] Hemraj S. Nandanwar, R. P., & Hoondal, G. S. (2013). (D)-p-hydroxyphenylglycine production by thermostable D-hydantoinase from Brevibacillus parabrevis-PHG1. Biocatalysis and biotransformation, 31(1), 22–32. DOI:10.3109/10242422.2012.755962
[2] Alimoradi, M., Azgomi, H., & Asghari, A. (2022). Trees social relations optimization algorithm: A new swarm-based metaheuristic technique to solve continuous and discrete optimization problems. Mathematics and computers in simulation, 194(C), 629–664. DOI:10.1016/j.matcom.2021.12.010
[3] Sharon Mano Pappu, J., Gummadi, S. N., & Jayabalan, T. (2022). Modeling and optimization of microbial production of xylitol. Role of microbes in industrial products and processes, 223–254. DOI:10.1002/9781119901198.ch9
[4] Wari, E., Zhu, W., & Liu, X. (2015). Genetic algorithms applications in the food process industry. In IIE annual conference. Proceedings. Institute of industrial and systems engineers (IISE), (pp. 288-297). https://www.proquest.com/openview/885118ef4fbd523f7d708ce84b146e0b/1?pq-origsite=gscholar&cbl=51908
[5] Daliri, A., Asghari, A., Azgomi, H., & Alimoradi, M. (2022). The water optimization algorithm: A novel metaheuristic for solving optimization problems. Applied intelligence, 52(15), 17990–18029. DOI:10.1007/s10489-022-03397-4
[6] Daliri, A., Alimoradi, M., Zabihimayvan, M., & Sadeghi, R. (2024). World hyper-heuristic: A novel reinforcement learning approach for dynamic exploration and exploitation. Expert systems with applications, 244(10), 122931. DOI:10.1016/j.eswa.2023.122931
[7] Herring, R., & Paarlberg, R. (2016). The political economy of biotechnology. Annual review of resource economics, 8(8), 397–416. DOI:10.1146/annurev-resource-100815-095506
[8] Brinc, M., & Belič, A. (2019). Optimization of process conditions for mammalian fed-batch cell culture in automated micro-bioreactor system using genetic algorithm. Journal of biotechnology, 20(300), 40–47. DOI:10.1016/j.jbiotec.2019.05.001
[9] Zhou, T., Reji, R., Kairon, R. S., & Chiam, K. H. (2023). A review of algorithmic approaches for cell culture media optimization. Frontiers in bioengineering and biotechnology, 11, 1195294. DOI:10.3389/fbioe.2023.1195294
[10] Pham, P. V. (2018). Medical biotechnology: techniques and applications. In Omics technologies and bio-engineering (pp. 449–469). Elsevier. DOI:10.1016/B978-0-12-804659-3.00019-1
[11] Yamaji, H. (2014). Suitability and perspectives on using recombinant insect cells for the production of virus-like particles. Applied microbiology and biotechnology, 98(5), 1963–1970. DOI:10.1007/s00253-013-5474-9
[12] Kim, G. B., Kim, W. J., Kim, H. U., & Lee, S. Y. (2020). Machine learning applications in systems metabolic engineering. Current opinion in biotechnology, 64, 1–9. DOI:10.1016/j.copbio.2019.08.010
[13] Alimoradi, M., Zabihimayvan, M., Daliri, A., Sledzik, R., & Sadeghi, R. (2022). Deep neural classification of darknet traffic. In Artificial intelligence research and development (pp. 105–114). IOS Press. DOI:10.3233/FAIA220323
[14] Riordon, J., Sovilj, D., Sanner, S., Sinton, D., & Young, E. W. K. (2019). Deep learning with microfluidics for biotechnology. Trends in biotechnology, 37(3), 310–324. DOI:10.1016/j.tibtech.2018.08.005
[15] Chen, W. H., Uribe, M. C., Kwon, E. E., Lin, K. Y. A., Park, Y. K., Ding, L., & Saw, L. H. (2022). A comprehensive review of thermoelectric generation optimization by statistical approach: Taguchi method, analysis of variance (ANOVA), and response surface methodology (RSM). Renewable and sustainable energy reviews, 169(C), 112917. DOI:10.1016/j.rser.2022.112917
[16] Aziz, K., Mamouni, R., Kaya, S., & Aziz, F. (2024). Low-cost materials as vehicles for pesticides in aquatic media: A review of the current status of different biosorbents employed, optimization by RSM approach. Environmental science and pollution research, 31(28), 39907–39944. DOI:10.1007/s11356-023-27640-8
[17] Andoh, A., Imaeda, H., Aomatsu, T., Inatomi, O., Bamba, S., Sasaki, M., … Fujiyama, Y. (2011). Comparison of the fecal microbiota profiles between ulcerative colitis and Crohn’s disease using terminal restriction fragment length polymorphism analysis. Journal of gastroenterology, 46(4), 479–486. DOI:10.1007/s00535-010-0368-4
[18] Khajehkhasan, S., & Fakheri, S. (2020). A new method based on operational strategies for early detection of breast cancers. Innovation management and operational strategies, 1(2), 187–201. DOI:10.22105/imos.2021.266543.1027
Metrics
