Improving chemometric results by optimizing the dimension reduction for Raman spectral data sets

In this contribution a new method for improving the accuracy of classification and identification experiments is presented. For this purpose the four most applied dimension reduction methods (principal component analysis, independent component analysis, partial least square dimension reduction and the linear discriminant analysis) are used as starting point for the optimization method. The optimization is done by a specially designed genetic algorithm, which is best suited for this kind of experiments. The presented multi-level chemometric approach has been tested for a Raman dataset containing over 2200 Raman spectra of eight classes of bacteria species (Bacillus anthracis, Bacillus cereus, Bacillus licheniformis, Bacillus mycoides, Bacillus subtilis, Bacillus thuringiensis, Bacillus weihenstephanensis and Paenibacillus polymyxa). The optimization of the dimension reduction improved the accuracy for classification by 6% compared with the accuracy, if the standard dimension reduction is applied. The identification rate is improved by 14% compared with the dimension reduction. The testing in a classification and identification experiment showed the robustness of the algorithm. Copyright © 2014 John Wiley & Sons, Ltd.

[1]  Erkki Oja,et al.  Independent component analysis: algorithms and applications , 2000, Neural Networks.

[2]  Jürgen Popp,et al.  The investigation of single bacteria by means of fluorescence staining and Raman spectroscopy , 2007 .

[3]  S. Lory,et al.  Complete genome sequence of Pseudomonas aeruginosa PAO1, an opportunistic pathogen , 2000, Nature.

[4]  J. Popp,et al.  Vibrational spectroscopy—A powerful tool for the rapid identification of microbial cells at the single‐cell level , 2009, Cytometry. Part A : the journal of the International Society for Analytical Cytology.

[5]  Jürgen Popp,et al.  How to pre-process Raman spectra for reliable and stable models? , 2011, Analytica chimica acta.

[6]  J. Popp,et al.  Online-calibration for reliable and robust lab-on-a-chip surface enhanced Raman spectroscopy measurement in a liquid/liquid segmented flow. , 2011, Analytical chemistry.

[7]  H. Bruining,et al.  Raman spectroscopic method for identification of clinically relevant microorganisms growing on solid culture medium. , 2000, Analytical chemistry.

[8]  A. Boulesteix.  PLS Dimension Reduction for Classification with Microarray Data , 2004, Statistical applications in genetics and molecular biology.

[9]  J. Popp,et al.  Identification and classification of organic and inorganic components of particulate matter via Raman spectroscopy and chemometric approaches , 2011 .

[10]  J. Popp,et al.  Identification of Bacillus anthracis via Raman spectroscopy and chemometric approaches. , 2012, Analytical chemistry.

[11]  Michael Schmitt,et al.  Chemotaxonomic Identification of Single Bacteria by Micro-Raman Spectroscopy: Application to Clean-Room-Relevant Biological Contaminations , 2005, Applied and Environmental Microbiology.

[12]  D. Livermore,et al.  Multiple mechanisms of antimicrobial resistance in Pseudomonas aeruginosa: our worst nightmare? , 2002, Clinical infectious diseases : an official publication of the Infectious Diseases Society of America.

[13]  R. Bimbot,et al.  Multiple angular scattering of heavy ions (16,17O, 40Ar, 86Kr and 100Mo) at intermediate energies (20–90 MeV/u) , 1988 .

[14]  Karl Pearson F.R.S..  LIII. On lines and planes of closest fit to systems of points in space , 1901 .

[15]  Jerome H. Friedman,et al.  On Bias, Variance, 0/1—Loss, and the Curse-of-Dimensionality , 2004, Data Mining and Knowledge Discovery.

[16]  Jürgen Popp,et al.  Direct analysis of clinical relevant single bacterial cells from cerebrospinal fluid during bacterial meningitis by means of micro‐Raman spectroscopy , 2009, Journal of biophotonics.

[17]  D. R. Cousens,et al.  SNIP, A STATISTICS-SENSITIVE BACKGROUND TREATMENT FOR THE QUANTITATIVE-ANALYSIS OF PIXE SPECTRA IN GEOSCIENCE APPLICATIONS , 1988 .

[18]  R. Fisher.  THE USE OF MULTIPLE MEASUREMENTS IN TAXONOMIC PROBLEMS , 1936 .

[19]  A. Chakrabarty,et al.  High osmolarity is a signal for enhanced algD transcription in mucoid and nonmucoid Pseudomonas aeruginosa strains , 1989, Journal of bacteriology.

[20]  J Popp,et al.  Raman Spectroscopic Detection of Anthrax Endospores in Powder Samples** , 2012, Angewandte Chemie.

[21]  Jürgen Popp,et al.  A comprehensive study of classification methods for medical diagnosis , 2009 .

[22]  K Baumann,et al.  Characterization of bacterial growth and the influence of antibiotics by means of UV resonance Raman spectroscopy. , 2006, Biopolymers.

[23]  K. Baumann,et al.  Gaussian mixture discriminant analysis for the single-cell differentiation of bacteria using micro-Raman spectroscopy , 2009 .

[24]  Ian P Thompson,et al.  Raman microscopic analysis of single microbial cells. , 2004, Analytical chemistry.