Abstract
Sepsis is a clinical syndrome that can be caused by bacteria or fungi. Early knowledge on the nature of the causative agent is a prerequisite for targeted anti-microbial therapy. Besides currently used detection methods like blood culture and PCR-based assays, the analysis of the transcriptional response of the host to infecting organisms holds great promise. In this study, we aim to examine the transcriptional footprint of infections caused by the bacterial pathogens Staphylococcus aureus and Escherichia coli and the fungal pathogens Candida albicans and Aspergillus fumigatus in a human whole-blood model. Moreover, we use the expression information to build a random forest classifier to classify if a sample contains a bacterial, fungal, or mock-infection. After normalizing the transcription intensities using stably expressed reference genes, we filtered the gene set for biomarkers of bacterial or fungal blood infections. This selection is based on differential expression and an additional gene relevance measure. In this way, we identified 38 biomarker genes, including IL6, SOCS3, and IRG1 which were already associated to sepsis by other studies. Using these genes, we trained the classifier and assessed its performance. It yielded a 96% accuracy (sensitivities >93%, specificities >97%) for a 10-fold stratified cross-validation and a 92% accuracy (sensitivities and specificities >83%) for an additional test dataset comprising Cryptococcus neoformans infections. Furthermore, the classifier is robust to Gaussian noise, indicating correct class predictions on datasets of new species. In conclusion, this genome-wide approach demonstrates an effective feature selection process in combination with the construction of a well-performing classification model. Further analyses of genes with pathogen-dependent expression patterns can provide insights into the systemic host responses, which may lead to new anti-microbial therapeutic advances.
Highlights
Sepsis is a critical medical condition with high mortality rates
While ntree describes the number of trees that are built by the random forest algorithm, mtry represents the number of genes used at each split when building a tree
We present an transcriptome analysis of human wholeblood data comparing bacterial and fungal infections with mockinfected control samples
Summary
Sepsis is a critical medical condition with high mortality rates. It is characterized by a dysregulation of the inflammatory response of the host due to a microbial infection. While the overall incidence of sepsis is increasing about 5–10% every year, the cases of sepsis caused by fungi have increased by more than 200% in the US between 1979 and 2000 (Martin et al, 2003) Since both types of pathogens, bacteria and fungi, require fundamentally different anti-microbial therapies, the early classification is crucial. It has been shown that prompt treatment is a prerequisite for successful therapy, as each hour of delay reduces the chances of survival on average by 8% (Kumar et al, 2006) This direct relation emphasizes the necessity for quick and reliable classification methods
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have