Skip to main content
. 2024 Nov 4;6(1):100380. doi: 10.1016/j.xhgg.2024.100380

Figure 3.

Figure 3

Assessment of the NEDAUS episignature

(A) The Euclidean hierarchical clustering heatmap shows each column as an NEDAUS discovery case (highlighted in red), along with negative samples (in purple), VUS (in orange), and a VUS+ sample (in yellow). Each row represents a specific probe chosen for this episignature. A clear distinction is evident between the cases (in red) and controls (in blue).

(B) The multidimensional scaling (MDS) plot displays the separation between NEDAUS cases and controls, including the negative sample identified in (A).

(C) In the SVM classifier model, the selected NEDAUS episignature probes were used for training. Seventy-five percent of controls and 75% of samples from other neurodevelopmental disorders (NDDs; shown in blue) were used for training, while the remaining 25% of controls and 25% of the other disorder samples (gray) were used for testing. The plot indicates that all NEDAUS samples have MVP scores near 1. Additionally, NEDAUS testing samples, including negatives and VUS, generally showed low MVP scores, except for a VUS sample that scored 0.16.