Rapid and reliable identification of Staphylococcus aureus capsular serotypes by means of artificial neural network-assisted Fourier-transform infrared spectroscopy.

GRUNERT T; WENNING M; BARBAGELATA MS; FRICKER M; SORDELLI, DO; BUZZOLA, FR; EHLING-SCHULZ M

JOURNAL OF CLINICAL MICROBIOLOGY

AMER SOC MICROBIOLOGY

Lugar: Washington; Año: 2013 vol. 51 p. 2261 - 2266

0095-1137

Staphylococcus aureuscapsular polysaccharides (CP) are important virulence  23 factors and represent putative targets for vaccine development. Therefore the  24 purpose of this study was to develop a high-throughput method to identify and  25 discriminate the clinically important S. aureuscapsular serotypes 5, 8 and NT (non- 26 typeable). A comprehensive set of clinical isolates derived from different origins and  27 control strains, representative for each serotype, were used to establish a CP typing  28 system based on Fourier-transform infrared(FTIR) spectroscopy and chemometric  29 techniques. By combining FTIR spectroscopy with artificial neuronal network (ANN)  30 analysis a system was successfully established, allowing a rapid identification and  31 discrimination of all three serotypes. The overall accuracy of the ANN-assisted FTIR  32 spectroscopy CP typing system was 96.7% for the internal validation and 98.2% for  33 the external validation, respectively. One isolate in the internal and one isolate in the  34 external validation failed in the classification procedure but none of the isolates was  35 incorrectly classified. The present study demonstrates that ANN-assisted FTIR  36 spectroscopy allows a rapid and reliable discrimination of S. aureuscapsular  37 serotypes. It is suitable for diagnostic as well as large scale epidemiologic  38 surveillance of S. aureuscapsule expression and provides useful information with  39 respect to chronicity of infection.    40