Skip to main content

Table 3 Prioritization with ProDiGe4 for 8 diseases with a large training set of known genes

From: ProDiGe: Prioritization Of Disease Genes with multitask machine learning from positive and unlabeled examples

Disease name MIM Id Training set Training ∩ IPA Precision (%) Recall (%) P-value
Prostate cancer 176807 12 12 41 7.5 5.3e-40
Colorectal cancer 114500 17 17 51 5.7 7.3e-44
Diabetes mellitus 125853 26 22 21 1.4 2.1e-06
Alzheimer 104300 11 10 23 2.3 3.8e-11
Gastric cancer 137215 12 12 16 7.1 9.3e-16
Leukemia acute myeloid 601626 17 16 13 10.0 2.8e-15
Breast cancer 114480 19 16 33 3.7 6.4e-22
Schizophrenia 181500 17 11 6 3.2 4.5e-05
  1. The results were validated by comparing our top 100 genes with a list of genes related to the disease, extracted from Ingenuity database.