Bayesian Probability Approach to Feature Significance for Infrared Spectra of Bacteria

The significance of a spectral feature is defined as the probability that the feature captures the structure of the data set at hand. In particular, the significance is equal to a value proportional to the variance of a feature within a particular data set. The larger the variance, the higher the probability that the feature will capture the underlying structure. This approach is particularly useful when significance is used to select features differentiating clusters of samples and for the construction of self-organizing maps (SOMs) of clusters. A significance spectrum is obtained by plotting significance as a function of wavenumber. After developing the approach for feature significance, the significance framework was applied to the construction of SOMs for clustering infrared spectra of bacteria. The significance framework consistently chooses features that make it possible to construct maps with reduced feature sets that are at least as good as the maps constructed on full feature sets. In addition, significance reliably picks features that are consistent with biological interpretations of the spectra.

[1]  Classification of Select Category A and B Bacteria by Fourier Transform Infrared Spectroscopy , 2009, Applied spectroscopy.

[2]  Harald Labischinski,et al.  Microbiological characterizations by FT-IR spectroscopy , 1991, Nature.

[3]  D. Naumann.  Infrared Spectroscopy in Microbiology , 2006 .

[4]  Harald Labischinski,et al.  The rapid differentiation and identification of pathogenic bacteria using Fourier transform infrared spectroscopic and multivariate statistical analysis , 1988 .

[5]  Luis E. Rodriguez-Saona,et al.  Differentiation of Selected Salmonella Enterica Serovars by Fourier Transform Mid-Infrared Spectroscopy , 2006, Applied spectroscopy.

[6]  Dieter Naumann,et al.  Identification of some bacterial cell components by FT-IR spectroscopy , 1995 .

[7]  R. Goodacre,et al.  The rapid identification of Acinetobacter species using Fourier transform infrared spectroscopy , 2004, Journal of applied microbiology.

[8]  Carla E. Brodley,et al.  Feature Selection for Unsupervised Learning , 2004, J. Mach. Learn. Res..

[9]  Lutz Hamel,et al.  Improved Interpretability of the Unified Distance Matrix with Connected Components To Appear Proceedings of DMIN ’ 11 , 2011 .

[10]  Douglas N Rutledge,et al.  Using ANOVA-PCA for discriminant analysis: application to the study of mid-infrared spectra of carrageenan gels as a function of concentration and temperature. , 2008, Analytica chimica acta.

[11]  Kevin J. Johnson,et al.  Pattern recognition of jet fuels: comprehensive GC×GC with ANOVA-based feature selection and principal component analysis , 2002 .

[12]  J. T. Magee,et al.  Modern Techniques for Rapid Microbiological Analysis , 1993 .

[13]  Hujun Yin,et al.  On the Distribution and Convergence of Feature Space in Self-Organizing Maps , 1995, Neural Computation.

[14]  D B Kell,et al.  Detection of the dipicolinic acid biomarker in Bacillus spores using Curie-point pyrolysis mass spectrometry and Fourier transform infrared spectroscopy. , 2000, Analytical chemistry.

[15]  H. Martens,et al.  Analysis of covariance patterns in gene expression data and FT-IR spectra. , 2006, Journal of microbiological methods.

[16]  Ryan J. Priore,et al.  Improved Dispersion of Bacterial Endospores for Quantitative Infrared Sampling on Gold Coated Porous Alumina Membranes , 2005, Applied spectroscopy.

[17]  Dieter Naumann,et al.  Rapid species and strain differentiation of non-tubercoulous mycobacteria by Fourier-Transform Infrared microspectroscopy. , 2007, Journal of microbiological methods.

[18]  M. Huleihel,et al.  FTIR microscopy as a method for identification of bacterial and fungal infections. , 2005, Journal of pharmaceutical and biomedical analysis.

[19]  Yin-Fong Su,et al.  The Infrared Spectra of Bacillus Bacteria Part I: Vegetative Bacillus versus Sporulated Cells and the Contributions of Phospholipids to Vegetative Infrared Spectra , 2009, Applied spectroscopy.

[20]  M. V. Velzen,et al.  Self-organizing maps , 2007 .

[21]  Peter de B. Harrington,et al.  Analysis of variance–principal component analysis: A soft tool for proteomic discovery , 2005 .

[22]  B. V. Bronk,et al.  Effects of Autoclaving on Bacterial Endospores Studied by Fourier Transform Infrared Microspectroscopy , 2004, Applied spectroscopy.

[23]  Magdi M. Mossoba,et al.  Fourier Transform Infrared Bacteria Identification with the Use of a Focal-Plane-Array Detector and Microarray Printing , 2004, Applied spectroscopy.

[24]  Henk J. Busscher,et al.  Grouping of streptococcus mitis strains grown on different growth media by FT-IR , 1996 .

[25]  Harald Labischinski,et al.  Elaboration of a procedure for identification of bacteria using Fourier-Transform IR spectral libraries: a stepwise correlation approach , 1991 .

[26]  Dieter Naumann,et al.  Characterization and Identification of Micro-Organisms by FT-IR Spectroscopy and FT-IR Microscopy , 1994 .

[27]  Merve Meinhardt-Wollweber,et al.  Hierarchical Cluster Analysis (HCA) of Microorganisms: An Assessment of Algorithms for Resonance Raman Spectra , 2011 .

[28]  D. Naumann,et al.  Classification and identification of bacteria by Fourier-transform infrared spectroscopy. , 1991, Journal of general microbiology.

[29]  D. Mouwen,et al.  Discrimination of Enterobacterial Repetitive Intergenic Consensus PCR Types of Campylobacter coli and Campylobacter jejuni by Fourier Transform Infrared Spectroscopy , 2005, Applied and Environmental Microbiology.

[30]  Sandra E Thompson,et al.  Identification of Bacterial Spores Using Statistical Analysis of Fourier Transform Infrared Photoacoustic Spectroscopy Data , 2003, Applied spectroscopy.

[31]  Eldon Puckrin,et al.  Passive standoff detection of Bacillus subtilis aerosol by Fourier-transform infrared radiometry. , 2003, Applied optics.

[32]  Barry K. Lavine,et al.  Spectral Pattern Recognition Using Self-Organizing MAPS , 2004, J. Chem. Inf. Model..

[33]  Miguel-Ángel Gómez,et al.  Identification of species of Brucella using Fourier transform infrared spectroscopy. , 2003 .

[34]  Int J Food Microbiol , 2011 .

[35]  R. Rosenfeld.  Nature , 2009, Otolaryngology--head and neck surgery : official journal of American Academy of Otolaryngology-Head and Neck Surgery.

[36]  Siegfried Scherer,et al.  Identification of coryneform bacteria and related taxa by Fourier-transform infrared (FT-IR) spectroscopy. , 2002, International journal of systematic and evolutionary microbiology.

[37]  E. de Bodt,et al.  A Statistical Tool to Assess the Reliability of Self-Organizing Maps , 2001, WSOM.

[38]  Marie Louie,et al.  Rapid identification of coagulase-negative staphylococci by Fourier transform infrared spectroscopy. , 2007, Journal of microbiological methods.

[39]  Xiao-Ying Wang,et al.  Novel Developments in Fuzzy Clustering for the Classification of Cancerous Cells Using FTIR Spectroscopy , 2007 .

[40]  L. Mariey,et al.  Sulfato/thiosulfato reducing bacteria characterization by FT-IR spectroscopy: a new approach to biocorrosion control. , 2006, Journal of microbiological methods.

[41]  Joseph Maria Kumar Irudayaraj,et al.  Differentiation and detection of microorganisms using fourier transform infrared photoacoustic spectroscopy , 2002 .

[42]  D. Naumann,et al.  FT-IR and FT-NIR Raman spectroscopy in biomedical research , 1998 .

[43]  M L Myrick,et al.  Fourier Transform Infrared Reflectance Microspectroscopy Study of Bacillus Subtilis Engineered without Dipicolinic Acid: The Contribution of Calcium Dipicolinate to the Mid-Infrared Absorbance of Bacillus Subtilis Endospores , 2005, Applied spectroscopy.

[44]  Barbara A Rasco,et al.  Fourier transform infrared spectroscopy, detection and identification of Escherichia coli O157:H7 and Alicyclobacillus strains in apple juice. , 2006, International journal of food microbiology.

[45]  Dieter Naumann,et al.  FT-IR spectroscopy and FT-Raman spectroscopy are powerful analytical tools for the non-invasive characterization of intact microbial cells , 1995 .

[46]  Sandra E Thompson,et al.  Identification of Sporulated and Vegetative Bacteria Using Statistical Analysis of Fourier Transform Mid-Infrared Transmission Data , 2004, Applied spectroscopy.

[47]  L. Rodriguez-Saona,et al.  Rapid detection and identification of bacterial strains by Fourier transform near-infrared spectroscopy. , 2001, Journal of agricultural and food chemistry.

[48]  J. Schmitt,et al.  Differentiation of Listeria monocytogenes Serovars by Using Artificial Neural Network Analysis of Fourier-Transformed Infrared Spectra , 2006, Applied and Environmental Microbiology.

[49]  A G Williams,et al.  Discrimination among Bacillus cereus, B. mycoides and B. thuringiensis and some other species of the genus Bacillus by Fourier transform infrared spectroscopy. , 1998, FEMS microbiology letters.

[50]  Robert A. Meyers,et al.  Encyclopedia of analytical chemistry : applications, theory and instrumentation , 2000 .

[51]  M. Curk,et al.  Fourier transform infrared (FTIR) spectroscopy for identifying Lactobacillus species , 1994 .

[52]  I. Kuzmanovski,et al.  Optimization of supervised self-organizing maps with genetic algorithms for classification of urinary calculi , 2005 .

[53]  Siegfried Scherer,et al.  Rapid and Reliable Identification of Food-Borne Yeasts by Fourier-Transform Infrared Spectroscopy , 1998, Applied and Environmental Microbiology.

[54]  Harald Labischinski,et al.  A New Method for the Rapid Identification and Differentiation of Pathogenic Microorganisms Using Fourier Transform Infrared Spectroscopy , 1985 .

[55]  L. Mariey,et al.  Discrimination, classification, identification of microorganisms using FTIR spectroscopy and chemometrics , 2001 .

[56]  G. Barnickel,et al.  Infrared spectroscopy, a tool for probing bacterial peptidoglycan. Potentialities of infrared spectroscopy for cell wall analytical studies and rejection of models based on crystalline chitin. , 1982, European journal of biochemistry.

[57]  Jürgen Popp,et al.  Towards a detailed understanding of bacterial metabolism--spectroscopic characterization of Staphylococcus epidermidis. , 2007, Chemphyschem : a European journal of chemical physics and physical chemistry.

[58]  Thomas Udelhoven,et al.  Development of a Hierarchical Classification System with Artificial Neural Networks and FT-IR Spectra for the Identification of Bacteria , 2000 .