A genetic algorithm-Bayesian network approach for the analysis of metabolomics and spectroscopic data: application to the rapid identification of Bacillus spores and classification of Bacillus species

Article English OPEN
Correa, Elon ; Goodacre, Royston (2011)
  • Publisher: BioMed Central
  • Journal: BMC Bioinformatics, volume 12, pages 33-33 (issn: 1471-2105, eissn: 1471-2105)
  • Related identifiers: doi: 10.1186/1471-2105-12-33, pmc: PMC3228543
  • Subject: Molecular Biology | R858-859.7 | Methodology Article | Computer applications to medicine. Medical informatics | Biochemistry | Computer Science Applications | Biology (General) | QH301-705.5

<p>Abstract</p> <p>Background</p> <p>The rapid identification of <it>Bacillus </it>spores and bacterial identification are paramount because of their implications in food poisoning, pathogenesis and their use as potential biowarfare agents. Many automated analytical techniques such as Curie-point pyrolysis mass spectrometry (Py-MS) have been used to identify bacterial spores giving use to large amounts of analytical data. This high number of features makes interpretation of the data extremely difficult We analysed Py-MS data from 36 different strains of aerobic endospore-forming bacteria encompassing seven different species. These bacteria were grown axenically on nutrient agar and vegetative biomass and spores were analyzed by Curie-point Py-MS.</p> <p>Results</p> <p>We develop a novel genetic algorithm-Bayesian network algorithm that accurately identifies sand selects a small subset of key relevant mass spectra (biomarkers) to be further analysed. Once identified, this subset of relevant biomarkers was then used to identify <it>Bacillus </it>spores successfully and to identify <it>Bacillus </it>species via a Bayesian network model specifically built for this reduced set of features.</p> <p>Conclusions</p> <p>This final compact Bayesian network classification model is parsimonious, computationally fast to run and its graphical visualization allows easy interpretation of the probabilistic relationships among selected biomarkers. In addition, we compare the features selected by the genetic algorithm-Bayesian network approach with the features selected by partial least squares-discriminant analysis (PLS-DA). The classification accuracy results show that the set of features selected by the GA-BN is far superior to PLS-DA.</p>
  • References (42)
    42 references, page 1 of 5

    1. Atrih A, Foster SJ: The role of peptidoglycan structure and structural dynamics during endospore dormancy and germination. Antonie van Leeuwenhoek 1999, 75(4):299-307.

    2. Doyle MP, Beuchat LR, Montville TJ, (Eds): Food Microbiology: Fundamentals and Frontiers Washington DC: Amercian Society of Microbiology; 1997.

    3. Barnaby W: Plague Makers: The Secret World of Biolgoical Warfare Vision; 1999.

    4. Inglesby TV, Henderson DA, Bartlett JG, Ascher MS, Eitzen E, Friedlander AM, Hauer J, McDade J, Osterholm MT, O'Toole T, Parker G, Perl TM, Russell PK, Tonat K: Anthrax as a Biological Weapon - medical and Public Health Management. JAMA - Journal of the American Medical Association 1999, 281(18):1735-1745.

    5. Ghiamati E, Manoharan R, Nelson WH, Sperry JF: UV Resonance Raman Spectra of Bacillus Spores. Applied Spectroscopy 1992, 46(2):357-364.

    6. Tabor MW, MacGee J, Holland JW: Rapid determination of dipicolinic acid in the spores of Clostridium species by gas-liquid chromatography. Applied and Environmental Microbiology 1976, 31:25-28.

    7. Warth AD: Liquid Chromatographic Determination of Dipicolinic Acid from Bacterial Spores. Applied and Environmental Microbiology 1979, 38(6):1029-1033.

    8. Goodacre R, Shann B, Gilbert RJ, Timmins EM, McGovern AC, Alsberg BK, Kell DB, Logan NA: Detection of the Dipicolinic Acid Biomarker in Bacillus Spores Using Curie-Point Pyrolysis Mass Spectrometry and Fourier Transform Infrared Spectroscopy. Analytical Chemistry 2000, 72:119-127.

    9. DeLuca SJ, Sarver EW, Voorhees KJ: Direct analysis of bacterial glycerides by Curie-point pyrolysis-mass spectrometry. Journal of Analytical and Applied Pyrolysis 1992, 23:1-14.

    10. Snyder AP, Dworzanski JP, Tripathi A, Maswadeh WM, Wick CH: Correlation of mass spectrometry identified bacterial biomarkers from a fielded pyrolysis-gas chromatography-Ion mobility spectrometry biodetector with the microbiological gram stain classification scheme. Analytical Chemistry 2004, 76(21):6492-6499.

  • Metrics
    No metrics available
Share - Bookmark