“…eDiVA‐Score is built by training a random forest (RF) model using the R “randomForest” package with 1000 binary classification trees (Breiman, ; Hastie, Tibshirani, & Friedman, ) and five‐fold cross validation. Eleven features were selected to train the RF model: (a) the maximum minor allele frequency (MAF) of 1000Genomes and GnomAD databases; (b) four conservation measures (conservation in primates and mammals using the PhastCons (Hubisz et al, ) and PhyloP (Pollard, Hubisz, Rosenbloom, & Siepel, ); (c) four functional impact predictors: Condel (González‐Pérez & López‐Bigas, ), Phred‐scaled CADD score (Kircher et al, ), Eigen (Ionita‐Laza et al, ), and Mutation Assessor (Reva et al, ); (d) the likelihood to be in a segmental duplication, which correlates with false‐positive variant calls (Ho, Tsai, Chen, & Lin, ); and (e) an in‐house estimator of systematic sequencing errors called ABB‐score (Muyas et al, ). Note that Condel, Eigen and CADD are combination scores integrating several features also included in eDiVA‐score, namely evolutionary conservation (PhastCons and PhyloP in mammals and primates) and Mutation Assessor scores.…”