Skip to main content

Table 1 Gmean and AUC scores across all {ML algorithm, Dataset} models

From: Machine learning-based predictions of dietary restriction associations across ageing-related genes

Feature type Num. of features Num. of instances Gmean AUC Mean
BRF EEC XGB CAT BRF EEC XGB CAT Gmean AUC
PathDIP 1640 986 genes 0.76 0.75 0.75 0.77 0.81 0.8 0.8 0.83 0.76 0.81
KEGG-Pertinence 312 799 genes 0.73 0.7 0.75 0.72 0.8 0.71 0.76 0.73 0.73 0.75
KEGG-Influence 1770 799 genes 0.7 0.7 0.67 0.67 0.78 0.71 0.69 0.68 0.69 0.72
PPI-measures 18 850 genes 0.64 0.59 0.65 0.65 0.69 0.6 0.65 0.67 0.63 0.65
PPI-adjacency 5718 850 genes 0.62 0.61 0.59 0.65 0.72 0.63 0.64 0.66 0.62 0.66
GO terms 8640 1124 genes 0.76 0.75 0.74 0.74 0.84 0.83 0.83 0.81 0.75 0.83
GTEx 55 1111 genes 0.5 0.52 0.5 0.51 0.5 0.53 0.52 0.52 0.51 0.52
Co-expression 44,946 1048 genes 0.5 0.57 0.42 0.56 0.52 0.57 0.54 0.54 0.51 0.54
Proteins-descriptors 156 6180 Proteins (from 1109 genes) 0.45 0.61 0.62 0.6 0.65 0.67 0.67 0.63 0.57 0.66
Whole-dataset imputation 63,099 1137 genes 0.67 0.65 0.6 0.66 0.72 0.66 0.65 0.67 0.65 0.68
Whole-dataset intersection 63,099 628 genes 0.61 0.66 0.56 0.64 0.64 0.67 0.63 0.66 0.62 0.65
Mean 0.63 0.65 0.62 0.65 0.70 0.67 0.67 0.67 0.64 0.68
  1. Gmean and AUC scores for the BRF, EEC, XGB, and CAT algorithms across all the 11 datasets (feature types). The average Gmean and AUC of each algorithm across all the datasets is shown in the last row; and the average Gmean and AUC of each feature type across all four algorithms is shown in the last two columns