RESUMEN
This paper presents an inverse design methodology that utilizes artificial intelligence (AI)-driven experiments to optimize the chemoenzymatic epoxidation of soyabean oil using hydrogen peroxide and lipase (Novozym 435). First, experiments are conducted using a systematic 3-level, 5-factor Box-Behnken design to explore the effect of input parameters on oxirane oxygen content (OOC (%)). Based on these experiments, various AI models are trained, with the support vector regression (SVR) model being found to be the most accurate. SVR is then used as a fitness function in particle swarm optimization, and the suggested optimal conditions, upon experimental validation, resulted in a maximum OOC of 7.19 % (â¼98.5 % relative conversion of oil to epoxy). The results demonstrate the superiority of the proposed approach over existing methods. This framework offers a general intensified process optimization strategy with minimal resource utilization that can be applied to any other process.
Asunto(s)
Inteligencia Artificial , Compuestos Epoxi , Lipasa , Lipasa/metabolismo , Compuestos Epoxi/química , Aceite de Soja/química , Peróxido de Hidrógeno/química , Enzimas Inmovilizadas/metabolismo , Enzimas Inmovilizadas/química , Proteínas Fúngicas/metabolismoRESUMEN
A hybrid machine learning (ML) aided experimental approach was proposed in this study to evaluate the growth kinetics of Candida antarctica for lipase production. Different ML models were trained and optimized to predict the growth curves at various substrate concentrations. Results on comparison demonstrate the superior performance of the Gradient boosting regression (GBR) model in growth curves prediction. GBR-based growth kinetics was found to be matching well with the results of the conventional experimental approach while significantly reducing the experimental effort, time, and resources by â¼ 50%. Further, the activity and enzyme kinetics of lipase produced in this study was investigated on hydrolysis of p-nitrophenyl butyrate resulting in a maximum lipase activity of 24.07 U at 44 h. The robustness and significance of developed kinetic models were ensured through detailed statistical analysis. The application of the proposed hybrid approach can be extended to any other microbial process.
Asunto(s)
Candida , Lipasa , Basidiomycota , Candida/metabolismo , Enzimas Inmovilizadas/metabolismo , Proteínas Fúngicas , Cinética , Lipasa/metabolismo , Aprendizaje AutomáticoRESUMEN
Lipases are the industrially important biocatalysts, which are envisioned to have tremendous applications in the manufacture of a wide range of products. Their unique properties such as better stability, selectivity and substrate specificity position them as the most expansively used industrial enzymes. The research on production and applications of lipases is ever growing and there exists a need to have a latest review on the research findings of lipases. The present review aims at giving the latest and broadest overall picture of research and development on lipases by including the current studies and progressions not only in the diverse industrial application fields of lipases, but also with regard to its structure, classification and sources. Also, a special emphasis has been made on the aspects such as process optimization, modeling, and design that are very critical for further scale-up and industrial implementation. The detailed tabulations provided in each section, which are prepared by the exhaustive review of current literature covering the various aspects of lipase including its production and applications along with example case studies, will serve as the comprehensive source of current advancements in lipase research. This review will be very useful for the researchers from both industry as well as academia in promoting lipolysis as the most promising approaches to intensified, greener and sustainable processes. © 2017 American Institute of Chemical Engineers Biotechnol. Prog., 34:5-28, 2018.