Statistical and Artificial Neural Network Approaches to Modeling and Optimization of Fermentation Conditions for Production of a Surface/Bioactive Glyco-lipo-peptide

Abstract

A freshwater alkaliphilic strain of Pseudomonas aeruginosa, grown on waste frying oil-basal medium, produced a surface-active metabolite identified as glycolipopeptide. Bioprocess conditions namely temperature, pH, agitation and duration were comparatively modeled using statistical and artificial neural network (ANN) methods to predict and optimize product yield using the matrix of a central composite rotatable design (CCRD). Response surface methodology (RSM) was the statistical approach while a feed-forward neural network, trained with Levenberg–Marquardt back-propagation algorithm, was the neural network method. Glycolipopeptide model was predicted by a significant ( P < 0.001, R 2 of 0.9923) quadratic function of the RSM with a mean squared error (MSE) of 3.6661. The neural network model, on the other hand, returned an R 2 value of 0.9964 with an MSE of 1.7844. From all error metrics considered, ANN glycolipopeptide model significantly ( P < 0.01) outperformed RSM counterpart in predictive modeling capability. Optimization of factor levels for maximum glycolipopeptide concentration produced bioprocess conditions of 32 °C for temperature, 7.6 for pH, agitation speed of 130 rpm and a fermentation time of 66 h, at a combined desirability function of 0.872. The glycosylated lipid-tailed peptide demonstrated significant anti-bacterial activity (MIC = 8.125 µg/mL) against Proteus vulgaris , dose-dependent anti-biofilm activities against Escherichia coli (83%) and Candida dubliniensis (90%) in 24 h and an equally dose-dependent cytotoxic activity against human breast (MCF-7: IC50 = 65.12 µg/mL) and cervical (HeLa: IC50 = 16.44 µg/mL) cancer cell lines. The glycolipopeptide compound is recommended for further studies and trials for application in human cancer therapy.

Bioprocess Optimization of Nutritional Parameters for Enhanced Anti-leukemic L-Asparaginase Production by Aspergillus candidus UCCM 00117: A Sequential Statistical Approach

“…To select most suitable inoculum size (spore density) for the fermentation, inoculum sizes were screened by the OFAT approach by inoculating 3% (v/v) spore suspension of different inoculum sizes ranging from 10 3 to 10 9 spore-forming units per milliliter (sfu/mL) into minimal medium containing selected extraneous carbon and nitrogen substrates. Working spore concentrations were prepared by the spectrophotometric method as described in Ekpenyong et al ( 2020a ) and experimental set up, incubations, harvest, determinations of enzyme activity and statistical analyses were as described under carbon screening section.…”

“…Enzyme dosages were two-fold dilutions from enzyme stock solution ranging from 1.148 to 1174.898 µg/mL. Mycoplasma sterility tests, viability and subsequent cytotoxicity studies using the sulforhodamine B (SRB) assay were as described in Asitok and Ekpenyong ( 2019 ) and Ekpenyong et al ( 2020a ). Experiments were conducted in triplicates and results, expressed as % cell viability, were presented as means of triplicate determinations.…”

A Novel Strain of Stenotrophomonas Acidaminiphila Produces Super-active Alkaline Protease During Cassava Effluent Fermentation: Process Optimization, Kinetic Modeling and Scale-up

“…Like every other value-added microbial product, the natural or baseline yield is usually low and costeffectiveness very poor (Ekpenyong et al 2021a). To improve production economics, biosynthesis of one or more value-added metabolite during bioconversion of agro-industrial waste on a large scale has been suggested (Ekpenyong et al 2017a).…”

“…To improve production economics, biosynthesis of one or more value-added metabolite during bioconversion of agro-industrial waste on a large scale has been suggested (Ekpenyong et al 2017a). To improve yield and/or activity, a number of nutritional and environmental requirements of high-yielding microbial strains need to be optimized (Ekpenyong et al 2017a, b;2021a). Response surface methodology (RSM) and artificial neural network (ANN) methods have become gold standards for bioprocess optimizations for the dual purposes of improving yield and cost-effectiveness (Kanno et al 2020;Ekpenyong et al 2021a;Dwibedi et al 2021).…”

“…To improve yield and/or activity, a number of nutritional and environmental requirements of high-yielding microbial strains need to be optimized (Ekpenyong et al 2017a, b;2021a). Response surface methodology (RSM) and artificial neural network (ANN) methods have become gold standards for bioprocess optimizations for the dual purposes of improving yield and cost-effectiveness (Kanno et al 2020;Ekpenyong et al 2021a;Dwibedi et al 2021). Response surface methodology typically has a limitation in its handling of non-linear relationships, if at all.…”