Investigation of blueberry juice fermentation by mixed probiotic strains: Regression modeling, machine learning optimization and comparison with fermentation by single strain in the phenolic and volatile profiles

Abstract

Three strains, including L. fermentum, L. plantarum and S. thermophilus, were combined to ferment blueberry juice. Through the sequential simplex lattice mixture design, regression modeling and genetic algorithm optimization, it was found that the combination of S. thermophilus with either L. fermentum or L. plantarum weakened the capacity of Lactobacillus strains to enrich phenolics, and the combinations of these strains had no synergistic effect of synthesizing lactic acid. The resulting optimal inoculation proportion to enrich phenolics was the mixed L. fermentum and L. plantarum at 0.5:0.5. After fermentation for 48 h, total phenolic, ferulic acid, rutin, and quercetin-3-rhamnoside of mixed fermented samples were 82.19 %, 15.22 %, 79.08 % and 98.59 % higher than the unfermented juice, and their contents were all highest among the fermented samples. Moreover, the samples fermented by mixed strains possessed higher amounts of 3-methyl-1-butanol, 2-methyl-1-propanol, 2-heptanone and 2-pentanone than samples fermented by L. fermentum, S. thermophilus and unfermented samples.

Keywords: Blueberry juice; Genetic algorithm; Lactic acid bacteria; Mixed fermentation; Simplex lattice mixture design; Volatile compound.