From: GAVIN: Gene-Aware Variant INterpretation for medical sequencing
Dataset | Benign variants (n) | Pathogenic variants (n) | Origin |
---|---|---|---|
VariBench tolerance DS7, training set | 11,347 | 6143 | PhenCode database, IDbases, and 18 individual LSDBs |
VariBench tolerance DS7, test set | 1377 | 510 | PhenCode database, IDbases, and 18 individual LSDBs |
MutationTaster2 benchmark set | 1194 | 161 | HGMD Professional and 1000 Genomes |
ClinVar (additions of Nov 2015 to Feb 2016) | 1668 | 1688 | Submissions by clinical molecular geneticists, expert panels, diagnostic laboratories, and companies |
UMCG, variants exported from clinical diagnostic interpretation software | 1176 | 174 | Clinical diagnostic classifications of variants in cardiology, dermatology, epilepsy, dystonia, and preconception screening |
UMCG, germline variants for familial cancer cases | 301 | 26 | Hereditary cancer variant classifications by an MD following ACMG guidelines |
Total | 17,063 | 8702 | 25,765 |