Prediction of porcine interferon α antiviral activity in fermentation by Pichia pastoris based on multivariable regression and artificial neural network
One of the most important methods to produce porcine interferon α is microbial fermentation. In the present study, recombinant Pichia pastoriswas used. Broth’s antiviral activity is the key index of the expression level of porcine interferon α. Measurement of antiviral activity is a time-co...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Association of the Chemical Engineers of Serbia
2014-01-01
|
| Series: | Chemical Industry and Chemical Engineering Quarterly |
| Subjects: | |
| Online Access: | http://www.doiserbia.nb.rs/img/doi/1451-9372/2014/1451-93721200097D.pdf |
| _version_ | 1828498920559345664 |
|---|---|
| author | Ding Jian Wang Huihui Dai Keke Zi Yuhua Shi Zhongping |
| author_facet | Ding Jian Wang Huihui Dai Keke Zi Yuhua Shi Zhongping |
| author_sort | Ding Jian |
| collection | DOAJ |
| description | One of the most important methods to produce porcine interferon α is
microbial fermentation. In the present study, recombinant Pichia pastoriswas
used. Broth’s antiviral activity is the key index of the expression level of
porcine interferon α. Measurement of antiviral activity is a time-consuming
and difficult task, which makes the research and production work inconvenient
and uncertain. To solve this problem, multivariable regression and artificial
neural network were applied to predict the antiviral activity based on five
on-line variables (induction time, temperature, dissolve doxygen, O2uptake
rate and CO2 evolution rate) and two off-line variables (methanol consumption
rate and total protein concentration).Parameters of the multivariable
quadratic polynomial regression equation were estimate dusing least square
methods. Optimization of artificial neural network(ANN)was achieved by
back-propagation and genetic algorithm. Verified by test set, the
ANN optimized by genetic algorithm had the best predictive performance and
generalization. The sensitivity analysis showed that CO2evolution rate,
O2 uptake rate and methanol consumption rate were the most relevant factors
for model’s output, except for the antiviral activity’s own previous value. |
| first_indexed | 2024-12-11T13:15:50Z |
| format | Article |
| id | doaj.art-f1ea72e0c6a449e0b806768aa762ca02 |
| institution | Directory Open Access Journal |
| issn | 1451-9372 2217-7434 |
| language | English |
| last_indexed | 2024-12-11T13:15:50Z |
| publishDate | 2014-01-01 |
| publisher | Association of the Chemical Engineers of Serbia |
| record_format | Article |
| series | Chemical Industry and Chemical Engineering Quarterly |
| spelling | doaj.art-f1ea72e0c6a449e0b806768aa762ca022022-12-22T01:06:04ZengAssociation of the Chemical Engineers of SerbiaChemical Industry and Chemical Engineering Quarterly1451-93722217-74342014-01-01201293810.2298/CICEQ120704097D1451-93721200097DPrediction of porcine interferon α antiviral activity in fermentation by Pichia pastoris based on multivariable regression and artificial neural networkDing Jian0Wang Huihui1Dai Keke2Zi Yuhua3Shi Zhongping4Key Laboratory of Industrial Biotechnology, Ministry of Education, Jiangnan University, Wuxi, ChinaKey Laboratory of Industrial Biotechnology, Ministry of Education, Jiangnan University, Wuxi, ChinaKey Laboratory of Industrial Biotechnology, Ministry of Education, Jiangnan University, Wuxi, ChinaKey Laboratory of Industrial Biotechnology, Ministry of Education, Jiangnan University, Wuxi, ChinaKey Laboratory of Industrial Biotechnology, Ministry of Education, Jiangnan University, Wuxi, ChinaOne of the most important methods to produce porcine interferon α is microbial fermentation. In the present study, recombinant Pichia pastoriswas used. Broth’s antiviral activity is the key index of the expression level of porcine interferon α. Measurement of antiviral activity is a time-consuming and difficult task, which makes the research and production work inconvenient and uncertain. To solve this problem, multivariable regression and artificial neural network were applied to predict the antiviral activity based on five on-line variables (induction time, temperature, dissolve doxygen, O2uptake rate and CO2 evolution rate) and two off-line variables (methanol consumption rate and total protein concentration).Parameters of the multivariable quadratic polynomial regression equation were estimate dusing least square methods. Optimization of artificial neural network(ANN)was achieved by back-propagation and genetic algorithm. Verified by test set, the ANN optimized by genetic algorithm had the best predictive performance and generalization. The sensitivity analysis showed that CO2evolution rate, O2 uptake rate and methanol consumption rate were the most relevant factors for model’s output, except for the antiviral activity’s own previous value.http://www.doiserbia.nb.rs/img/doi/1451-9372/2014/1451-93721200097D.pdfporcine interferon αantiviral activitymultivariable regressionartificial neural networkback-propagation algorithmgenetic algorithm |
| spellingShingle | Ding Jian Wang Huihui Dai Keke Zi Yuhua Shi Zhongping Prediction of porcine interferon α antiviral activity in fermentation by Pichia pastoris based on multivariable regression and artificial neural network Chemical Industry and Chemical Engineering Quarterly porcine interferon α antiviral activity multivariable regression artificial neural network back-propagation algorithm genetic algorithm |
| title | Prediction of porcine interferon α antiviral activity in fermentation by Pichia pastoris based on multivariable regression and artificial neural network |
| title_full | Prediction of porcine interferon α antiviral activity in fermentation by Pichia pastoris based on multivariable regression and artificial neural network |
| title_fullStr | Prediction of porcine interferon α antiviral activity in fermentation by Pichia pastoris based on multivariable regression and artificial neural network |
| title_full_unstemmed | Prediction of porcine interferon α antiviral activity in fermentation by Pichia pastoris based on multivariable regression and artificial neural network |
| title_short | Prediction of porcine interferon α antiviral activity in fermentation by Pichia pastoris based on multivariable regression and artificial neural network |
| title_sort | prediction of porcine interferon α antiviral activity in fermentation by pichia pastoris based on multivariable regression and artificial neural network |
| topic | porcine interferon α antiviral activity multivariable regression artificial neural network back-propagation algorithm genetic algorithm |
| url | http://www.doiserbia.nb.rs/img/doi/1451-9372/2014/1451-93721200097D.pdf |
| work_keys_str_mv | AT dingjian predictionofporcineinterferonaantiviralactivityinfermentationbypichiapastorisbasedonmultivariableregressionandartificialneuralnetwork AT wanghuihui predictionofporcineinterferonaantiviralactivityinfermentationbypichiapastorisbasedonmultivariableregressionandartificialneuralnetwork AT daikeke predictionofporcineinterferonaantiviralactivityinfermentationbypichiapastorisbasedonmultivariableregressionandartificialneuralnetwork AT ziyuhua predictionofporcineinterferonaantiviralactivityinfermentationbypichiapastorisbasedonmultivariableregressionandartificialneuralnetwork AT shizhongping predictionofporcineinterferonaantiviralactivityinfermentationbypichiapastorisbasedonmultivariableregressionandartificialneuralnetwork |