Open AccessReliable and Rapid Identification of Listeria monocytogenes and Listeria Species by Artificial Neural Network-Based Fourier Transform Infrared Spectroscopy
Author(s) -
Cecilia A. Rebuffo,
Jürgen Schmitt,
Mareike Wenning,
Felix von Stetten,
Siegfried Scherer
Publication year - 2006
Publication title -
applied and environmental microbiology
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.552
H-Index - 324
eISSN - 1070-6291
pISSN - 0099-2240
DOI - 10.1128/aem.72.2.994-1000.2006
Subject(s) - listeria monocytogenes , listeria , identification (biology) , fourier transform infrared spectroscopy , artificial neural network , microbiology and biotechnology , biology , fourier transform , fourier transform spectroscopy , biological system , bacteria , physics , artificial intelligence , computer science , optics , genetics , botany , quantum mechanics
Differentiation of the species within the genusListeria is important for the food industry but only a few reliable methods are available so far. While a number of studies have used Fourier transform infrared (FTIR) spectroscopy to identify bacteria, the extraction of complex pattern information from the infrared spectra remains difficult. Here, we apply artificial neural network technology (ANN), which is an advanced multivariate data-processing method of pattern analysis, to identifyListeria infrared spectra at the species level. A hierarchical classification system based on ANN analysis forListeria FTIR spectra was created, based on a comprehensive reference spectral database including 243 well-defined reference strains ofListeria monocytogenes ,L. innocua ,L. ivanovii ,L. seeligeri , andL. welshimeri . In parallel, a univariate FTIR identification model was developed. To evaluate the potentials of these models, a set of 277 isolates of diverse geographical origins, but not included in the reference database, were assembled and used as an independent external validation for species discrimination. Univariate FTIR analysis allowed the correct identification of 85.2% of all strains and of 93% of theL. monocytogenes strains. ANN-based analysis enhanced differentiation success to 96% for allListeria species, including a success rate of 99.2% for correctL. monocytogenes identification. The identity of the 277-strain test set was also determined with the standard phenotypical APIListeria system. This kit was able to identify 88% of the test isolates and 93% ofL. monocytogenes strains. These results demonstrate the high reliability and strong potential of ANN-based FTIR spectrum analysis for identification of the fiveListeria species under investigation. Starting from a pure culture, this technique allows the cost-efficient and rapid identification ofListeria species within 25 h and is suitable for use in a routine food microbiological laboratory.