The dataset consists of 12,347 protein sequences endowed with 101,146 SRVs, including 39,812 P/LP SRVs and 61,334 B/LB SRVs.
The dataset consists of 1314 protein sequences endowed with 10,266 SRVs, including 4083 P/LP SRVs and 6183 B/LB SRVs.
This dataset consists of predictions performed with E-SNPs&GO on 2588 proteins endowed with 9165 Variants of Uncertain Significance (VUS).