Towards a microRNA‐based Johne's disease diagnostic predictive system: Preliminary results

Background: Johne's disease, caused by Mycobacterium avium subspecies paratuberculosis (MAP), is a chronic enteritis that adversely affects welfare and productivity in cattle. Screening and subsequent removal of affected animals is a common approach for disease management, but efforts are hindered by low diagnostic sensitivity. Expression levels of small non‐coding RNA molecules involved in gene regulation (microRNAs), which may be altered during mycobacterial infection, may present an alternative diagnostic method. Methods: The expression levels of 24 microRNAs affected by mycobacterial infection were measured in sera from MAP‐positive (n = 66) and MAP‐negative cattle (n = 65). They were then used within a machine learning approach to build an optimal classifier for MAP diagnosis. Results: The method provided 72% accuracy, 73% sensitivity and 71% specificity on average, with an area under the curve of 78%. Limitations: Although control samples were collected from farms nominally MAP‐free, the low sensitivity of current diagnostics means some animals may have been misclassified. Conclusion: MicroRNA profiling combined with advanced predictive modelling enables rapid and accurate diagnosis of Johne's disease in cattle.