APPLICATION OF PATTERN-RECOGNITION TO MONITORING FERMENTATIONS OF BACILLUS-AMYLOLIQUEFACIENS

Pattern recognition techniques were applied to analytical data to dist inguish abnormal from normal microbial fermentations using Bacillus am yloliquefaciens as a model system. Patterns of fermentation end produc ts during growth of B. amyloliquefaciens were obtained from HPLC analy sis of broth samples. Data were also obtained from fermentations using other bacterial species, strains, and environmental conditions, and w ere compared with the model data set. The bacterial species cultured i ncluded B. subtilus, B. licheniformis, and Escherichia coli. Environme ntal variables included aeration and temperature. The chromatographic patterns were compared by using hierarchical cluster and principal com ponent analysis to obtain a quantitative measure of their similarity a nd to establish the normal variability within a model data set. Statis tical analysis of the data indicated that individual fermentations can be assigned to distinct clusters on the basis of their divergence fro m the model system. Altered environments and other species can be iden tified as outliers from the model set. These results show that pattern recognition analysis has direct applicability to monitoring fermentat ion processes.