Springer Nature
Browse
12967_2017_1235_MOESM11_ESM.png (344.05 kB)

MOESM11 of Development of an objective gene expression panel as an alternative to self-reported symptom scores in human influenza challenge trials

Download (344.05 kB)
figure
posted on 2017-06-08, 05:00 authored by Julius Muller, Eneida Parizotto, Richard Antrobus, James Francis, Campbell Bunce, Amanda Stranks, Marshall Nichols, Micah McClain, Adrian Hill, Adaikalavan Ramasamy, Sarah Gilbert
Additional file 11: Figure S8. Prediction of Any Symptom (DSS > 0) or No Symptom (DSS = 0) classes using a random forest model on Fluidigm. A, Prediction probabilities are shown on the y-axis and samples with probabilities <0.5 are classified as No Symptom. B, Importance of individual markers for the categorized prediction within the panel of 19 primers. x-axis shows the decrease in Gini coefficient if the respective gene is left out of the model. C, ROC analysis of the categorized prediction.

Funding

Wellcome Trust Strategic Award

History