BIOPROCESS OPTIMIZATION OF MICROBIAL OIL YIELD FROM Aspergillus niger USING MACHINE LEARNING MODELS AND SHEA BUTTER KERNEL EXTRACT AS CARBON SOURCE

Abstract

The optimization of biological processes involving Aspergillus niger is necessary and vital for improving its industrial applications, especially in valuable metabolites production. This study burrow into the utilization of Machine Learning (ML) models to maximize the metabolite production and growth of Aspergillus niger using Shea Butter Kernel Extract (SBKE) as a carbon source. This research involves sample isolation, serial dilution, preparation of Potato Dextrose Agar (PDA), Fungi isolation, identification of fungi isolate macroscopically, preparation of stock culture, screening of oleaginous fungi using Congo red Agar, medium of fermentation for the preparation of microbial oil using SBKE as a carbon source and also using glucose as a carbon source, identification of fungi microscopically, lipid extraction from oleaginous isolate and optimization of microbial oil yield using ML models. The result shows that five (5) fungal isolates were obtained on PDA plates after being incubated, the morphological characteristics, the oleaginous activities and lipopolytic activities of fungi isolates, the result of the wet biomass with glucose compared to SBKE and the result of the dry biomass with glucose compared to SBKE. Incubation day 13 has the highest fungal biomass while incubation day 3 has the lowest fungal biomass while using SBKE. . Incubation day 9 has the highest fungal biomass while incubation day 13 has the lowest fungal biomass. From the result on the graph, glucose yielded better than SBKE except on day 13 (2.63g) and 15 (2.23). This research adds to sustainable biological processing by using a renewable carbon source and illustrates the importance of ML to transform the applications of biotechnology.