Skip to main content
Figure 3 | BMC Genomics

Figure 3

From: Using biomarker signature patterns for an mRNA molecular diagnostic of mouse embryonic stem cell differentiation state

Figure 3

Prediction accuracy. Box plots of the accuracy (sensitivity or specificity) of the prediction of the differentiation state of embryonic stem cells using "n" (2 to 20) mRNA transcript levels as diagnostic signature patterns. The box has lines at the lower quartile (25th), median (50th), and upper (75th) quartile values. The whiskers are lines extending 1.5 × (inter-quartile ranges) from each end of the box with outliers ('+') marked. The box plot shows the average prediction accuracy (based on 500 random divisions of the sample set into training and test sub-sets) for the 30,000 diagnostic models created for each "n". The diagnostic models were built using Gstemness (size = 114), Gsecreted proteins (size = 21), Gmembrane proteins (size = 25) and Gextracellular proteins (size = 46) separately. Extracellular proteins include secreted and membrane proteins.

Back to article page