Downloaded from www.microbiologyresearch.org by IP: 54.70.40.11 On: Sat, 01 Dec 2018 20:36:12 Journal of Medical Microbiology (2005), 54, 1205–1211 DOI 10.1099/jmm.0.46223-0 46223 & 2005 SGM Printed in Great Britain 1205 Correspondence Oliver Schmid oliver.schmid@hpa.org.uk Received 1 July 2005 Accepted 16 August 2005 New approaches to identification of bacterial pathogens by surface enhanced laser desorption/ ionization time of flight mass spectrometry in concert with artificial neural networks, with special reference to Neisseria gonorrhoeae Oliver Schmid, 1 † Graham Ball, 2 † Lee Lancashire, 2 Renata Culak 1 and Haroun Shah 1 1 Molecular Identification Services Unit, Centre for Infections, Health Protection Agency, London, UK 2 The Nottingham Trent University, School of Biomedical and Natural Sciences, Nottingham, UK Surface enhanced laser desorption/ionization-time of flight mass spectrometry (SELDI-TOF MS) has been applied in large numbers of oncological studies but the microbiological field has not been extensively explored to date. This paper describes the application of SELDI-TOF MS in concert with a multi-layer perceptron artificial neural network (ANN) with a back propagation algorithm for the identification of Neisseria gonorrhoeae. N. gonorrhoeae, the aetiological agent of gonorrhoea, is the second most common sexually transmitted disease in the UK and USA. Analysis of over 350 strains of N. gonorrhoeae and closely related species by SELDI-TOF MS facilitated the design of an ANN model and revealed 20 ion peak descriptors of positive, negative and secondary nature that were paramount for the identification of the pathogen. The model performed with over 96 % efficiency when based on these 20 ion peak descriptors and exhibited a sensitivity of 95 . 7 % and a specificity of 97 . 1 %, with an area under the curve value of 0 . 996. The technology has the potential to link several ANN models for a comprehensive rapid identification platform for clinically important pathogens. INTRODUCTION Gonococcal infection is the second most common bacterial sexually transmitted infection in the UK, with more than 24 000 infections diagnosed in 2003. The number of con- firmed cases has risen steadily since 1995. Young people are most commonly infected, with males aged 20–24 years and females aged 16–19 years showing the highest rates of infection, especially in urban areas (http://www.hpa. org.uk/infections/topics_az/hiv_and_sti/sti-gonorrhoea/ gonorrhoea.htm; Gerbase et al., 1998). The causative organism, Neisseria gonorrhoeae, is currently confirmed in diagnostic laboratories using traditional bio- chemical tests and more recent 16S rDNA analysis. Conven- tional diagnostic methods for N. gonorrhoeae include direct microscopy, selective culturing, immunological tests, en- zyme reaction tests and nucleic acid amplification tests, among others (Johnson et al., 2002; Knapp, 1988). The population structure of N. gonorrhoeae is of an unstructured random mating or panmictic nature (Smith et al., 1993) causing frequent horizontal genetic exchange, which in addition to natural mutation causes the high levels of variability that enable bacterial adaptation and immune system evasion (Fredlund et al., 2004). In this pilot study, to explore more specific and rapid methods of diagnosis, we assessed the potential application of surface enhanced laser desorption/ionization-time of flight mass spectrometry (SELDI-TOF MS) in concert with artificial neural networks (ANNs) for bacterial identification. The former is a modified version of matrix-assisted laser desorption/ionization-TOF MS (MALDI-TOF MS), in that it utilizes ProteinChip arrays for selective capture of chemi- cally or biochemically distinct proteins from a mixed popu- lation (Fung & Enderwick, 2002). The protein arrays in SELDI-TOF MS are available with different types of receptors bound to their surface. In this study we used reverse phase H50 ProteinChip arrays. Their active surface contains 16 methylene groups that bind proteins through reverse phase †These authors contributed equally to this paper. Abbreviations: ANN, artificial neural network; MLP, multi-layer perceptron; PCA, principle component analysis; SELDI, surface enhanced laser desorption/ionization; TOF, time of flight.