Skip to main content
. 2022 Nov 8;23(22):13664. doi: 10.3390/ijms232213664

Figure 5.

Figure 5

Assessment of TRIP12 variant of uncertain significance (VUS) using the Clark–Baraitser syndrome (TRIP12) episignature: (a) Euclidean hierarchical clustering (heatmap): each column represents a TRIP12 case or control; each row represents 1 of the 118 CpG probes selected for the episignature. This heatmap shows clear separation between 29 TRIP12 cases (red) used for training from controls (blue). The VUS case (purple) is shown to segregate with training cases. Two outlier cases (orange) are shown to segregate with controls; (b) Multidimensional scaling (MDS) plot shows the segregation of the TRIP12 VUS case with training and away from both controls and outlier cases; (c) Support Vector Machine (SVM) classifier model. Model was trained using the 118 selected TRIP12 episignature probes, 75% of controls and 75% of other neurodevelopmental disorder samples (blue). The remaining 25% controls and 25% of other disorder samples were used for testing (grey). Plot shows the TRIP12 VUS case with a methylation variant pathogenicity (MVP) score close to 1, similar to the TRIP12 training cases, showing the specificity of the classifier and episignature.