Fungal biomarker discovery by integration of classifiers.

BACKGROUND: The human immune system is responsible for protecting the host from infection. However, in immunocompromised individuals the risk of infection increases substantially with possible drastic consequences. In extreme, systemic infection can lead to sepsis which is responsible for innumerous deaths worldwide. Amongst its causes are infections by bacteria and fungi. To increase survival, it is mandatory to identify the type of infection rapidly. Discriminating between fungal and bacterial pathogens is key to determine if antifungals or antibiotics should be administered, respectively. For this, in situ experiments have been performed to determine regulation mechanisms of the human immune system to identify biomarkers. However, these studies led to heterogeneous results either due different laboratory settings, pathogen strains, cell types and tissues, as well as the time of sample extraction, to name a few. METHODS: To generate a gene signature capable of discriminating between fungal and bacterial infected samples, we employed Mixed Integer Linear Programming (MILP) based classifiers on several datasets comprised of the above mentioned pathogens. RESULTS: When combining the classifiers by a joint optimization we could increase the consistency of the biomarker gene list independently of the experimental setup. An increase in pairwise overlap (the number of genes that overlap in each cross-validation) of 43% was obtained by this approach when compared to that of single classifiers. The refined gene list was composed of 19 genes and ranked according to consistency in expression (up- or down-regulated) and most of them were linked either directly or indirectly to the ERK-MAPK signalling pathway, which has been shown to play a key role in the immune response to infection. Testing of the identified 12 genes on an unseen dataset yielded an average accuracy of 83%. CONCLUSIONS: In conclusion, our method allowed the combination of independent classifiers and increased consistency and reliability of the generated gene signatures.

Identification of vancomycin interaction with Enterococcus faecalis within 30 min of interaction time using Raman spectroscopy.

Vancomycin is an important glycopeptide antibiotic which is used to treat serious infections caused by Gram-positive bacteria. However, during the last years, a tremendous rise in vancomycin resistances, especially among Enterococci, was reported, making fast diagnostic methods inevitable. In this contribution, we apply Raman spectroscopy to systematically characterize vancomycin-enterococci interactions over a time span of 90 min using a sensitive Enterococcus faecalis strain and two different vancomycin concentrations above the minimal inhibitory concentration (MIC). Successful action of the drug on the pathogen could be observed already after 30 min of interaction time. Characteristic spectral changes are visualized with the help of multivariate statistical analysis (linear discriminant analysis and partial least squares regressions). Those changes were employed to train a statistical model to predict vancomycin treatment based on the Raman spectra. The robustness of the model was tested using data recorded by an independent operator. Classification accuracies of >90 % were obtained for vancomycin concentrations in the lower range of a typical trough serum concentration recommended for most patients during appropriate vancomycin therapy. Characterization of drug-pathogen interactions by means of label-free spectroscopic methods, such as Raman spectroscopy, can provide the knowledge base for innovative and fast susceptibility tests which could speed up microbiological analysis as well as finding applications in novel antibiotic screenings assays. Graphical Abstract E. faecalis is incubated with vancomycin and characterized by means of Raman spectroscopy after different time points. Characteristic spectral changes reveal efficient vancomycin-enterococci-interaction.