Optimization of Process Parameters for Cholesterol Oxidase Production by Streptomyces Olivaceus MTCC 6820

Shraddha Sahu1, Shailendra Singh Shera1, Rathindra Mohan Banik1, *
1 Bioprocess Technology Laboratory, School of Biochemical Engineering, Indian Institute of Technology (Banaras Hindu University), Varanasi, Uttar Pradesh, India

Article Metrics

CrossRef Citations:
Total Statistics:

Full-Text HTML Views: 1488
Abstract HTML Views: 1073
PDF Downloads: 395
ePub Downloads: 280
Total Views/Downloads: 3236
Unique Statistics:

Full-Text HTML Views: 802
Abstract HTML Views: 610
PDF Downloads: 269
ePub Downloads: 178
Total Views/Downloads: 1859

Creative Commons License
© 2019 Sahu et al.

open-access license: This is an open access article distributed under the terms of the Creative Commons Attribution 4.0 International Public License (CC-BY 4.0), a copy of which is available at: ( This license permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.

* Address correspondence to this author at the Bioprocess Technology Laboratory, School of Biochemical Engineering, Indian Institute of Technology (Banaras Hindu University), Varanasi, Uttar Pradesh, India;
Tel: +919415624727; E-mails:,



Streptomyces olivaceus MTCC 6820 is a potent microorganism for cholesterol oxidase (ChOx) production through the submerged fermentation process. Statistical optimization of the process parameters for submerged fermentation enhances the production of enzymes.


This work is aimed to optimize the culture conditions for the fermentative production of cholesterol oxidase by Streptomyces olivaceus MTCC 6820 using combined Response Surface Methodology (RSM) and Artificial Neural Network (ANN) techniques.


The ChOx production (U/ml) was modeled and optimized as a function of six independent variables (culture conditions) using RSM and ANN.


ChOx production enhanced 2.2 fold, i.e 1.9 ± 0.21 U/ml under unoptimized conditions to 4.2 ± 0.51 U/ml after the optimization of culture conditions. Higher coefficient of determination (R2 = 97.09 %) for RSM and lower values of MSE (0.039) and MAPE (3.46 %) for ANN proved the adequacy of both the models. The optimized culture conditions predicted by RSM vs. ANN were pH (7.5), inoculum age (48 h), inoculum size (11.25 % v/v), fermentation period (72 h), incubation temperature (30°C) and shaking speed (175 rpm).


The modeling, optimization and prediction abilities of both RSM and ANN methodologies were compared. The values of Pearson correlation coefficient (r) (ANN0.98 > RSM0.95), regression coefficient (R2) between experimental activity, RSM and ANN predicted ChOx activity, respectively (ANN0.96 > RSM0.90) and Absolute Average Deviation (AAD) for (ANN3.46% < RSM9.87%) substantiated better prediction ability of ANN than RSM. These statistical values indicated the superiority of ANN in capturing the non-linear behavior of the system.

Keywords: Artificial neural network, Cholesterol oxidase, Optimization, Response surface methodology, Streptomyces olivaceus, ChOx activity.