A novel short-term high-lactose culture approach combined with a matrix-assisted laser desorption ionization-time of flight mass spectrometry assay for differentiating Escherichia coli and Shigella species using artificial neural networks

• DOI: 10.1371/journal.pone.0222636
• Publication Date: 2019-10-08T17:21:28Z
• Authors: Jin Ling; Hong Wang; Gaomin Li; Zhen Feng; Yufei Song; Peng Wang; Hong Shao; Hu Zhou; Gang Chen
• Keywords: 0301 basic medicine; Science; Q; R; Cell Culture Techniques; Lactose; 3. Good health; 03 medical and health sciences; Spectrometry, Mass, Matrix-Assisted Laser Desorption-Ionization; Escherichia coli; Medicine; Neural Networks, Computer; Shigella; Research Article

Background Escherichia coli is currently unable to be reliably differentiated from Shigella species by routine matrix-assisted laser desorption ionization-time of flight mass spectrometry (MALDI-TOF MS) analysis. In the present study, a reliable and rapid identification method was established for based on short-term high-lactose culture using MALDI-TOF MS artificial neural networks (ANN). Materials methods The colonies, treated with (Condition 1)/without 2) an in-house developed fluid medium, were prepared assays. spectra acquired in linear positive mode, range 2000 12000 Da then compared discover new biomarkers identification. Finally, data sets 1 2, extracted two conditions, used ANN training investigate benefit bacterial classification produced biomarkers. Results Twenty-seven characteristic peaks summarized. Seven unreported peaks, m/z 2330.745, 2341.299, 2371.581, 2401.038, 3794.851, 3824.839 3852.548, discovered only E. strains after identified as belonging acid shock protein. prediction accuracies models, set 97.71±0.16% 74.39±0.34% (n = 5), extremely remarkable difference (p < 0.001), areas under curve receiver operating 0.72 0.99, respectively. Conclusions summary, adding approach before analysis enabled easy differentiation ANN.