Barcoding bacterial cells: a SERS-based methodology for pathogen identification

A principal component analysis (PCA) based on the sign of the second derivative of the surf ace-enhanced Raman scattering (SERS) spectrum obtained on in situ grown Au-cluster-covered SiO2 substrates results in improved reproducibility and enhanced specificity for bacterial diagnostics. The barcode-generated clustering results are systematically compared with those obtained from the corresponding spectral intensities, first derivatives and second derivatives for the SERS spectra of closely related cereus group Bacillus strains. PCA plots and the corresponding hierarchical cluster analysis (HCA) dendrograms illustrate the improved bacterial identification resulting from the barcode spectral data reduction. Supervised discriminant function analysis (DFA) plots result in slightly improved group separation but show more susceptibility to false positive classifications than the corresponding PCA contours. In addition, this PCA treatment is used to highlight the enhanced bacterial species specificity observed for SERS as compared to normal bulk (non-SERS) Raman spectra. The identification algorithm described here is critical for the development of SERS microscopy as a rapid, reagentless and portable diagnostic of bacterial pathogens. Copyright (C) 2008 John Wiley & Sons, Ltd.