Skip to main content
Fig. 3 | Genome Medicine

Fig. 3

From: A machine learning classifier using 33 host immune response mRNAs accurately distinguishes viral and non-viral acute respiratory illnesses in nasal swab samples

Fig. 3

33-mRNA signature is robust to real world heterogeneity. Distributions of sample-specific 33-mRNA scores across multiple, real life, potential confounding: age (A), virus type (B), and viral load (C, D). In all panels, y-axis is 33-mRNA score. A Control groups (either healthy, HC or non-viral ARI, nvARI) are grey while viral ARI (vARI) is blue. p-value was calculated using Wilcox test. B Distribution of 33-mRNA score across different viruses in GSE163151. C, D Distribution of 33-mRNA score across different viral loads in GSE152075 and GSE188678, respectively. Viral load was defined by cycle threshold (Ct) of N1 target region of SARS-CoV-2 virus (C) or by RPM of SARS-CoV-2 virus (D). C and D share Y axis with B

Back to article page

Genome Medicine

ISSN: 1756-994X

Contact us