SIFT predicts whether an amino acid substitution affects protein function. SIFT prediction is based on the degree of conservation of amino acid residues in sequence alignments derived from closely related sequences. The score can range from 0 to 1, when scores below 0.05 are considered deleterious.

FATHMM predicts the functional effects of protein missense mutations by combining sequence conservation within hidden Markov models (HMMs), representing the alignment of homologous sequences and conserved protein domains, with 'pathogenicity weights', representing the overall tolerance of the protein/domain to mutations. The score can range from -16.13 to 10.64 with smaller scores are more likely of being deleterious. Scores below -1.5 are considered as deleterious.

DANN is a functional prediction score based on a deep neural network. The score can range from 0 to 1, when higher values are more likely to be deleterious.

MetaLR logistic regression (LR) based ensemble prediction score, which incorporated 10 scores (SIFT, PolyPhen-2 HDIV, PolyPhen-2 HVAR, GERP++, MutationTaster, Mutation Assessor, FATHMM, LRT, SiPhy, PhyloP) and the maximum frequency observed in the 1000 genomes populations. The score can range from 0 to 1, when higher values are more likely to be deleterious.

REVEL is an ensemble method for predicting the pathogenicity of missense variants based on a combination of scores from 13 individual tools: MutPred, FATHMM v2.3, VEST 3.0, PolyPhen-2, SIFT, PROVEAN, MutationAssessor, MutationTaster, LRT, GERP++, SiPhy, phyloP, and phastCons. REVEL was trained using recently discovered pathogenic and rare neutral missense variants, excluding those previously used to train its constituent tools. The REVEL score for an individual missense variant can range from 0 to 1, with higher scores reflecting the greater likelihood that the variant is disease-causing.

MutationAssessor predicts the functional impact of amino-acid substitutions in proteins, such as mutations discovered in cancer or missense polymorphisms. The functional impact is assessed based on the evolutionary conservation of the affected amino acid in protein homologs. Score range is -5.135 to 6.49, score<0.8 Benign, (0.8,1.95) Low deleterious probability, (1.935, 3.5)Medium deleterious probability, >3.5 High deleterious probability

PolyPhen-2 predicts the possible impact of an amino acid substitution on the structure and function of a human protein using straightforward physical and comparative considerations. The score can range from 0 to 1, when scores can be interpreted as the probability of the variant being deleterious, with higher scores reflecting the greater likelihood that the variant is disease-causing.

MutationTaster employs a Bayes classifier to eventually predict the disease potential of an alteration. The Bayes classifier predicts the functional consequences of not only amino acid substitutions but also intronic and synonymous alterations, short insertion and/or deletion (indel) mutations and variants spanning intron-exon borders. The score can range from 0 to 1, when higher values are more likely to be deleterious

PrimateAI predicts the pathogenicity of missense variants using deep learning algorithms trained on humans and non-human primate species. The score can range from 0 to 1, where authors suggest for score >0.803 as pathogenic.

BayesDel (no AF) is a deleteriousness meta-score. The range of the score is from -1.29334 to 0.75731. The higher the score, the more likely the variant is pathogenic. Author suggested cutoff between deleterious (D) and tolerated (T) is -0.0570105.

SpliceAI uses deep neural networks to predict whether splicing events occur. The score can range from 0 to 1, when scores can be interpreted as the probability of the variant being splice-altering.

dbscSNV Ada predicts for SNVs within splicing consensus regions (−3 to +8 at the 5’ splice site and −12 to +2 at the 3’ splice site), their potential of altering splicing by using ensemble score computed using AdaBoost algorithm on the outputs of several other prediction tools. The score can range from 0 to 1, when scores can be interpreted as the probability of the variant being splice-altering.

GERP identifies constrained elements in multiple alignments by quantifying substitution deficits. These deficits represent substitutions that would have occurred if the element were neutral DNA, but did not occur because the element has been under functional constraint. Score range is -12.3 to 6.17. Scores. score<3.0 Low Constraint, (3.0,4.4) Medium Constraint, >4.4 High Constraint.

GenoCanyon is a whole-genome annotation method that performs unsupervised statistical learning using 22 computational and experimental annotations thereby inferring the functional potential of each position in the human genome. The score can range from 0 to 1, when scores can be interpreted as the probability of the variant being deleterious, with higher scores reflecting greater likelihood that the variant is disease-causing.

fitCons integrates functional assays (such as ChIP-Seq) with selective pressure and produces a score that indicates the fraction of genomic positions evincing a particular pattern (or 'fingerprint') of functional assay results, that are under selective pressure. The score can range from 0 to 1, when scores can be interpreted as the probability of the variant being deleterious, with higher scores reflecting greater likelihood that the variant is disease-causing.

MitoTip predicts pathogenicity of mitochondrial tRNA variants. Scores range from -5.9 to 21.8 where >16.25 are considered likely pathogenic, and < 8.44 likely benign"

APOGEE uses machine learning methods to predict the pathogenicity of mitochondrial non-synonymous genome variation. The score can range from 0 to 1, when higher values are more likely of being deleterious.",