Artificial Neural Network - Multi-Objective Genetic Algorithm based optimization for the enhanced pigment...

Area of Science:

• Biotechnology
• Phycology
• Biochemistry

Background:

• Cyanobacteria, such as Synechocystis sp. PCC 6803, naturally produce valuable pigments like carotenoids, chlorophyll a, and phycocyanin.
• Abiotic stresses (low temperature, high light) and nutritional stresses (nitrogen sources) influence pigment accumulation.

Purpose of the Study:

• To investigate the effects of abiotic and nutritional stresses on pigment accumulation in Synechocystis sp. PCC 6803.
• To optimize pigment production using Response Surface Methodology (RSM) and Artificial Neural Network-Multi-Objective Genetic Algorithm (ANN-MOGA).

Main Methods:

• Cultivation of Synechocystis sp. PCC 6803 under varying abiotic conditions (temperature, light).
• Assessment of pigment production with different nitrogen sources (urea, ammonium chloride, sodium nitrate).
• Application of RSM and ANN-MOGA for optimizing pigment synthesis and predicting enzyme activity.

Main Results:

• Combined nitrogen sources (urea/nitrate, ammonium chloride/nitrate) enhanced pigment accumulation.
• ANN-MOGA model predicted and achieved significant increases in chlorophyll a (21.93 µg/mL), carotenoids (9.78 µg/mL), and phycocyanin (0.05 µg/mL).
• Pigments exhibited significant scavenging activity (IC50: 7.66 ± 0.001) and high correlation with antioxidant enzyme activities (APX, CAT, GPX; R² > 0.92).

Conclusions:

• RSM and machine learning (ANN-MOGA) are effective tools for optimizing cyanobacterial pigment production.
• Optimized pigments from Synechocystis sp. PCC 6803 possess valuable antioxidant properties.
• These methods can be applied to enhance the yield of other microbial metabolites for commercial viability.