Machine learning driven forward-reverse design of Ag–ZnO–PEEK nanocomposites for sustainable biomass and lipid enhancement in Chlorella vulgaris AK_123 with integrated anti-bacterial activity
摘要
At present, the realm of nanobionics has garnered significant attention for its potential applications in microalgal systems, offering innovative strategies to augment growth, productivity, and metabolic performance. Present study influences nanotechnology to explore the multifaceted effects of novel biocompatible nanocomposite Ag–ZnO–PEEK (silver-zinc oxide- Polyether Ether Ketone) on isolated microalgae Chlorella vulgaris_AK, with a focus on improving the biomass production, mitigating oxidative stress, and enhancing the lipid biosynthesis. The morphometric demonstrations of Ag–ZnO–PEEK nanocomposite were characterized by Scanning electron microscopy, energy-dispersive X-ray spectroscopy, X-ray diffraction, and Fourier-transform infrared spectroscopy. Different concentrations of Ag–ZnO–PEEK (10, 20, 40, 80, and 160 ppm) were applied to the microalgae for observing the biomass enhancement and lipid yield. Among all the applied concentrations, 40 ppm exhibited the suitable one for high biomass and lipid yield of 4.25 g/L and 3.31 g/L respectively. Machine learning integrating forward prediction and E-UCB-based inverse design was employed to optimize microalgal growth conditions. Gradient boosting achieved the highest R2 of 0.9794, while ensemble uncertainty enabled reliable identification of high-performing unsampled conditions. Additionally, the effect of the as synthesized nanocomposite was also investigated as a potential antibacterial candidate against Bacillus sp. Hence, these advancements not only elevate the microalgae biomass production but also support the sustainable generation of biofuels and bioproducts from microalgae. Therefore, this study provides a scalable framework for integrating nanotechnology into renewable energy by maintaining circular bio-economy.