| Nome: | Descrição: | Tamanho: | Formato: | |
|---|---|---|---|---|
| 2.95 MB | Adobe PDF |
Orientador(es)
Resumo(s)
This concerns P. corcovadensis, an endemic plant of Brazil commonly used by the population due to its therapeutic properties. Optimizing chemical extraction conditions is critical for increasing the availability of bioactive compounds from plants. These compounds have antioxidant potential derived from a plant’s specialized metabolism and can exhibit a variety of biological actions. Therefore, statistical tools such as the Random Forest and Lazy KStar machine learning algorithms were used to determine the optimal condition for the extraction of phenolic compounds from P. corcovadensis leaves, with model evaluated by coefficient of determination (R2), mean square root of calibration error (RMSEC), and residual predictive deviation (RPD). The optimal extraction condition was obtained using a mixture of 80/20% (ethanol/water) at 70 °C for 120 min. For those extracts, there were 11.64 ± 0.04 mg GAE g-1 and antioxidant activity of 21.27 ± 0.53 mmol Trolox g-1, 33.15 ± 11.66 mmol Trolox g-1, and 13.47 ± 1.37 mmol Fe2+ by DPPH, ABTS and FRAP tests. With this study, we have shown that mathematical modelling can also be helpful in experimental sciences and can be used to develop predictive models. It was possible to develop predictive models for total phenolic compounds determination using the Random Forest and Lazy KStar machine learning algorithms. The Random Forest algorithm performed very well for DPPH modelling, giving us the confidence to use it to prediction antioxidant activity.
Descrição
Palavras-chave
Specialized metabolism Phenolic compounds Antioxidant activity Generalized linear model Machine learning
Contexto Educativo
Citação
Bruno Henrique Fontoura, Luciano de Souza Ramos, Lucas Vinícius Dallacorte, Michelle Fernanda Faita Rodrigues, José Abramo Marchese, Tiago Adriano Fernandes, Mário Antônio Alves da Cunha, Vanderlei Aparecido de Lima, Solange Teresinha Carpes, Optimization of extraction of bioactive compounds from Piper corcovadensis C.DC leaves using a generalized linear model, Journal of Food Science and Technology, July 2025, https://doi.org/10.1007/s13197-025-06433-6
Editora
Springer