Table 2 Summary of VPPTs tested in the study
Tool | Cut-off | Year developed | Prediction model method |
|---|---|---|---|
SIFT53 | * | 2001 | MSA |
bStatistics54 | ā„500 | 2009 | MSA |
LRT55 | * | 2009 | MSA |
MutPred56 | ā„0.5 | 2009 | MSAā+āProtein parametersā+āSupervised ML (built on SIFT) |
SiPhy57 | ā„12.17 | 2009 | MSA |
phastCons470way-mammalian58 | ā„0.5 | 2010 | MSA |
phastCons17way-primate58 | ā„0.5 | 2010 | MSA |
phastCons100way-vertebrate58 | ā„0.5 | 2010 | MSA |
phyloP470way-mammalian58 | ā„1.6 | 2010 | MSA |
phyloP17way-primate58 | ā„1.6 | 2010 | MSA |
phyloP100way-vertebrate58 | ā„1.6 | 2010 | MSA |
PolyPhen2-DIV59 | * | 2010 | MSAā+āProtein parametersā+āSupervised ML |
PolyPhen2-VAR59 | * | 2010 | MSAā+āProtein parametersā+āSupervised ML |
MutationAssessor60 | * | 2011 | MSA |
PROVEAN61 | * | 2012 | MSA |
FATHMM62 | * | 2013 | MSA |
VEST463 | ā„0.5 | 2013 | Supervised ML |
CADD64 | >20 | 2014 | Meta-predictorā+āSupervised MLā+āUnsupervised ML |
MutationTaster65 | * | 2014 | MSA |
DANN66 | ā„0.99 | 2015 | Supervised MLā+āDL (with the same training data set and features as CADD) |
fathmm-MKL67 | * | 2015 | Supervised ML |
GenoCanyon68 | ā„0.5 | 2015 | Unsupervised ML |
GM12878_fitcons69 | ā„0.6 | 2015 | Unsupervised ML |
h1_fitcons69 | ā„0.6 | 2015 | Unsupervised ML |
HUVEC_fitcons69 | ā„0.6 | 2015 | Unsupervised ML |
integrated_fitcons69 | ā„0.6 | 2015 | Unsupervised ML |
MetaLR70 | * | 2015 | Meta-predictorā+āSupervised ML |
MetaSVM70 | * | 2015 | Meta-predictorā+āSupervised ML |
BayesDel_addAF71 | * | 2016 | Meta-predictorā+āSupervised ML |
BayesDel_noAF71 | * | 2016 | Meta-predictorā+āSupervised ML |
Eigen-PC46 | ā„0 | 2016 | Unsupervised ML |
Eigen-raw46 | ā„0 | 2016 | Unsupervised ML |
M-CAP72 | * | 2016 | Supervised ML |
REVEL73 | ā„0.5 | 2016 | Meta-predictorā+āSupervised ML |
SIFT-4G74 | * | 2016 | MSA |
DEOGEN275 | * | 2017 | Supervised ML |
LINSIGHT76 | ā„0.6 | 2017 | Unsupervised ML |
MPC77 | ā„2 | 2017 | MSA (also combined PolyPhen2) |
ClinPred78 | * | 2018 | Meta-predictorā+āSupervised MLā+āUnsupervised ML |
fathmm-XF79 | * | 2018 | Supervised ML |
PrimateAI80 | * | 2018 | Supervised MLā+āDL |
GERP-NR81 | ā„4 | 2020 | MSA |
GERP-RS81 | ā„4 | 2020 | MSA |
LIST-S282 | * | 2020 | MSA |
EVE83 | ā„0.5 | 2021 | Unsupervised ML |
MVP84 | ā„0.75 | 2021 | Supervised MLā+āDL |
VARITY-ER85 | ā„0.5 | 2021 | Supervised ML |
VARITY-ER-LOO85 | ā„0.5 | 2021 | Supervised ML |
VARITY-R85 | ā„0.5 | 2021 | Supervised ML |
VARITY-R-LOO85 | ā„0.5 | 2021 | Supervised ML |
gMVP86 | ā„0.75 | 2022 | Supervised ML |
MetaRNN87 | * | 2022 | Meta-predictorā+āSupervised MLā+āDL |
AlphaMissense88 | * | 2023 | Unsupervised ML |
ESM1b89 | * | 2023 | Unsupervised MLā+āDL |