Fig. 4

Probability scores generated by the classification model: A multi-class SVM classifier concurrently generates two scores for every subject as the probability of having a DNA methylation profile similar to patients with Claes-Jensen syndrome (a) and healthy carriers of KDM5C mutations (b). y-axis represents scores 0–1, with higher scores indicating a higher chance of carrying a methylation profile related to any of the two statuses. The x-axis represents the classification scores for 10 patients with Claes-Jensen syndrome, 8 healthy carriers of KDM5C mutations, a total of 650 normal controls, and 587 patients with other conditions that present with intellectual disability as described in the “Methods” and “Results” sections. By default, the SVM classifier defines a cutoff of 0.5 for predicting the class; however, the vast majority of the tested individuals received a score close to 0 or 1. Therefore, for the purpose of better visualization, the points are jittered. Every point represents the probability score received for a single sample. This figure represents scores obtained by both the subjects in the training and testing cohorts