Support Vector Regression Approach to Predict the Design Space for the Extraction Process of Pueraria lobata
A support vector regression (SVR) method was introduced to improve the robustness and predictability of the design space in the implementation of quality by design (QbD), taking the extraction process of Pueraria lobata as a case study. In this paper, extraction time, number of extraction cycles, an...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2018-09-01
|
| Series: | Molecules |
| Subjects: | |
| Online Access: | http://www.mdpi.com/1420-3049/23/10/2405 |
| _version_ | 1811212889149669376 |
|---|---|
| author | Yaqi Wang Yuanzhen Yang Jiaojiao Jiao Zhenfeng Wu Ming Yang |
| author_facet | Yaqi Wang Yuanzhen Yang Jiaojiao Jiao Zhenfeng Wu Ming Yang |
| author_sort | Yaqi Wang |
| collection | DOAJ |
| description | A support vector regression (SVR) method was introduced to improve the robustness and predictability of the design space in the implementation of quality by design (QbD), taking the extraction process of Pueraria lobata as a case study. In this paper, extraction time, number of extraction cycles, and liquid–solid ratio were identified as critical process parameters (CPPs), and the yield of puerarin, total isoflavonoids, and extracta sicca were the critical quality attributes (CQAs). Models between CQAs and CPPs were constructed using both a conventional quadratic polynomial model (QPM) and the SVR algorithm. The results of the two models indicated that the SVR model had better performance, with a higher R2 and lower root-mean-square error (RMSE) and mean absolute deviation (MAD) than those of the QPM. Furthermore, the design space was predicted using a grid search technique. The operational range was extraction time, 24–51 min; number of extraction cycles, 3; and liquid–solid ratio, 14–18 mL/g. This study is the first reported work optimizing the design space of the extraction process of P. lobata based on an SVR model. SVR modeling, with its better prediction accuracy and generalization ability, could be a reliable tool for predicting the design space and shows great potential for the quality control of QbD. |
| first_indexed | 2024-04-12T05:36:56Z |
| format | Article |
| id | doaj.art-abeb2246a01642c9bed08dd14a0f617c |
| institution | Directory Open Access Journal |
| issn | 1420-3049 |
| language | English |
| last_indexed | 2024-04-12T05:36:56Z |
| publishDate | 2018-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Molecules |
| spelling | doaj.art-abeb2246a01642c9bed08dd14a0f617c2022-12-22T03:45:48ZengMDPI AGMolecules1420-30492018-09-012310240510.3390/molecules23102405molecules23102405Support Vector Regression Approach to Predict the Design Space for the Extraction Process of Pueraria lobataYaqi Wang0Yuanzhen Yang1Jiaojiao Jiao2Zhenfeng Wu3Ming Yang4College of Pharmacy, Chengdu University of Traditional Chinese Medicine, Chengdu 610072, ChinaKey Laboratory of Modern Preparation of Traditional Chinese Medicine, Ministry of Education, Jiangxi University of Traditional Chinese Medicine, Nanchang 330004, ChinaCollege of Pharmacy, Chengdu University of Traditional Chinese Medicine, Chengdu 610072, ChinaKey Laboratory of Modern Preparation of Traditional Chinese Medicine, Ministry of Education, Jiangxi University of Traditional Chinese Medicine, Nanchang 330004, ChinaCollege of Pharmacy, Chengdu University of Traditional Chinese Medicine, Chengdu 610072, ChinaA support vector regression (SVR) method was introduced to improve the robustness and predictability of the design space in the implementation of quality by design (QbD), taking the extraction process of Pueraria lobata as a case study. In this paper, extraction time, number of extraction cycles, and liquid–solid ratio were identified as critical process parameters (CPPs), and the yield of puerarin, total isoflavonoids, and extracta sicca were the critical quality attributes (CQAs). Models between CQAs and CPPs were constructed using both a conventional quadratic polynomial model (QPM) and the SVR algorithm. The results of the two models indicated that the SVR model had better performance, with a higher R2 and lower root-mean-square error (RMSE) and mean absolute deviation (MAD) than those of the QPM. Furthermore, the design space was predicted using a grid search technique. The operational range was extraction time, 24–51 min; number of extraction cycles, 3; and liquid–solid ratio, 14–18 mL/g. This study is the first reported work optimizing the design space of the extraction process of P. lobata based on an SVR model. SVR modeling, with its better prediction accuracy and generalization ability, could be a reliable tool for predicting the design space and shows great potential for the quality control of QbD.http://www.mdpi.com/1420-3049/23/10/2405Pueraria lobataSVRQPMextraction processQbDdesign space |
| spellingShingle | Yaqi Wang Yuanzhen Yang Jiaojiao Jiao Zhenfeng Wu Ming Yang Support Vector Regression Approach to Predict the Design Space for the Extraction Process of Pueraria lobata Molecules Pueraria lobata SVR QPM extraction process QbD design space |
| title | Support Vector Regression Approach to Predict the Design Space for the Extraction Process of Pueraria lobata |
| title_full | Support Vector Regression Approach to Predict the Design Space for the Extraction Process of Pueraria lobata |
| title_fullStr | Support Vector Regression Approach to Predict the Design Space for the Extraction Process of Pueraria lobata |
| title_full_unstemmed | Support Vector Regression Approach to Predict the Design Space for the Extraction Process of Pueraria lobata |
| title_short | Support Vector Regression Approach to Predict the Design Space for the Extraction Process of Pueraria lobata |
| title_sort | support vector regression approach to predict the design space for the extraction process of pueraria lobata |
| topic | Pueraria lobata SVR QPM extraction process QbD design space |
| url | http://www.mdpi.com/1420-3049/23/10/2405 |
| work_keys_str_mv | AT yaqiwang supportvectorregressionapproachtopredictthedesignspacefortheextractionprocessofpuerarialobata AT yuanzhenyang supportvectorregressionapproachtopredictthedesignspacefortheextractionprocessofpuerarialobata AT jiaojiaojiao supportvectorregressionapproachtopredictthedesignspacefortheextractionprocessofpuerarialobata AT zhenfengwu supportvectorregressionapproachtopredictthedesignspacefortheextractionprocessofpuerarialobata AT mingyang supportvectorregressionapproachtopredictthedesignspacefortheextractionprocessofpuerarialobata |