Fig. 4: Development of an integrative score to predict the pathogenicity of missense variants. | Nature Communications

Fig. 4: Development of an integrative score to predict the pathogenicity of missense variants.

From: Genetic diversity of 1,845 rhesus macaques improves genetic variation interpretation and identifies disease models

Fig. 4

a The AUC distributions of 13 established in-silico scores for predicting the deleteriousness of 10,836 missense variants from ClinVar, including 5079 pathogenic variants and 5757 benign variants. TP: true positive. FP: false positive. b The AUC distributions of the integrative scores for assessing the 10,836 missense variants derived from seven machine learning models. c The AUC distributions of the integrative score based on the random forest model (the HM score) and 13 incorporated scores for assessing an independent test set from SwissVar. This test set comprised 889 benign variants and 1930 deleterious variants. d The distribution of the integrative HM score for 6195 missense variants in the rhesus macaque population. The red line indicates the HM score corresponding to the top 1% threshold (HM Score=0.98). Source data are provided in the Source Data file.

Back to article page