Abstract
BackgroundThe rapid identification of Bacillus spores and bacterial identification are paramount because of their implications in food poisoning, pathogenesis and their use as potential biowarfare agents. Many automated analytical techniques such as Curie-point pyrolysis mass spectrometry (Py-MS) have been used to identify bacterial spores giving use to large amounts of analytical data. This high number of features makes interpretation of the data extremely difficult We analysed Py-MS data from 36 different strains of aerobic endospore-forming bacteria encompassing seven different species. These bacteria were grown axenically on nutrient agar and vegetative biomass and spores were analyzed by Curie-point Py-MS.ResultsWe develop a novel genetic algorithm-Bayesian network algorithm that accurately identifies sand selects a small subset of key relevant mass spectra (biomarkers) to be further analysed. Once identified, this subset of relevant biomarkers was then used to identify Bacillus spores successfully and to identify Bacillus species via a Bayesian network model specifically built for this reduced set of features.ConclusionsThis final compact Bayesian network classification model is parsimonious, computationally fast to run and its graphical visualization allows easy interpretation of the probabilistic relationships among selected biomarkers. In addition, we compare the features selected by the genetic algorithm-Bayesian network approach with the features selected by partial least squares-discriminant analysis (PLS-DA). The classification accuracy results show that the set of features selected by the GA-BN is far superior to PLS-DA.
Highlights
The rapid identification of Bacillus spores and bacterial identification are paramount because of their implications in food poisoning, pathogenesis and their use as potential biowarfare agents
Unlike most data sets which concentrate on a single or only a handful of Bacillus species, this data set investigates 36 different strains of aerobic endosporeforming bacteria encompassing seven different species: Bacillus amyloliquefaciens, Bacillus cereus, Bacillus licheniformis, Bacillus megaterium, Bacillus subtilis, Bacillus sphaericus, and Brevibacillus laterosporus. These bacteria were grown axenically on nutrient agar as detailed in [8,15] and vegetative biomass and spores were analyzed in triplicates by Curie-point pyrolysis mass spectrometry (Py-MS)
In this study Py-MS data from a diverse group of Bacillus species were analysed using a novel approach of combining variable selection from genetic algorithms (GA) with the probabilistic relationship inference from Bayesian network (BN)
Summary
The rapid identification of Bacillus spores and bacterial identification are paramount because of their implications in food poisoning, pathogenesis and their use as potential biowarfare agents. Many automated analytical techniques such as Curie-point pyrolysis mass spectrometry (Py-MS) have been used to identify bacterial spores giving use to large amounts of analytical data This high number of features makes interpretation of the data extremely difficult We analysed Py-MS data from 36 different strains of aerobic endospore-forming bacteria encompassing seven different species. The sporulation process in Bacillus species causes singular molecular and cellular changes in the cell which are not seen in the vegetative state [1] One of these changes is the Members of the genus Bacillus are widely distributed in the environment and because their spores are so resistant their control is of considerable importance in the food manufacture [2]. There is a need to have a generic characterisation method that allows rapid identification of spores and typing of bacteria
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
