Comparison and integration of deleteriousness prediction methods for nonsynonymous SNVs in whole exome sequencing studies.

By Chengliang Dong, P. Wei, Xueqiu Jian, Richard A. Gibbs, Eric Boerwinkle, Kai Wang, Xiaomin Liu. 2015

1,063 citations recorded by the source corpus.

Subfields: Cancer Research, Genetics, Molecular Biology

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Cancer Research

In Genetics

In Molecular Biology

Citations in the corpus

A catalog of genetic loci associated with kidney function from analyses of a million individuals (2019, background): “The majority of the 22 11 variants had CADD score>15, indicating potential deleteriousness.(33) Several identified 23 genes are plausible biological candidates for driving the association signal (Table 1).”
PERCH: a unified framework for disease gene prioritization (2017, background): “Others have combined these assessments to produce an overall prediction, yielding a better performance than any predictor alone [González-Pérez and López-Bigas, 2011; Kircher et al., 2014; Dong et al., 2015].”
dbNSFP v3.0: A One-Stop Database of Functional Predictions and Annotations for Human Non-synonymous and Splice Site SNVs (2016, methodology): “We found that the two ensemble rank scores, MetaSVM and MetaLR, achieved excellent prediction accuracy (AUC > 0.9) in both testing datasets.”
dbNSFP v4: a comprehensive database of transcript-specific functional predictions and annotations for human nonsynonymous and splice-site SNVs (2020, background): “Interest-ingly, the ensemble scores or hybrid ensemble scores in dbNSFP form two separated clusters: cluster 1 includes CADD and CADD_hg19, ClinPred, BayesDel_addAF, BayesDel_noAF, and REVEL; cluster 2 includes MetaLR and MetaSVM [52], M-CAP, and DEOGEN2.”
Mutation severity spectrum of rare alleles in the human genome is predictive of disease type (2019, result): “DeepSAV’s performance is similar to (Eigen [51]) or worse than several meta-predictors (MetaSVM [52], MetaLR [52], and REVEL [53]) that use prediction results of a number of other stand-alone predictors (Fig 3A).”
Ensembl 2019 (2018, methodology): “We have also extended the range of impact predictions available in our transcript variant tables, adding results from CADD (30), MetaLR (31), MutationAssessor (32) and REVEL, alongside the pre-existing SIFT and PolyPhen-2 results (33) (see Figure 2).”
ClinPred: Prediction Tool to Identify Disease-Relevant Nonsynonymous Single-Nucleotide Variants. (2018, background): “23 We further investigated the effect of excluding/including AFs as a feature in the models and found that the inclusion of AFs signiﬁcantly increases AUC as well as increasing sensitivity and speciﬁcity (Figure S2).”
De novo mutations in Congenital Heart Disease with Neurodevelopmental and Other Birth Defects (2015, positive): “We extended the model by merging all possible transcripts to obtain transcript-independent probabilities and by adding rates for deleterious missense variants predicted by the Meta-SVM score (D-Mis) (11).”
Evaluation of in silico algorithms for use with ACMG/AMP clinical variant interpretation guidelines (2017, methodology): “For example, for benign variants the best performing combinations of three algorithms consisted of VEST3 [18], REVEL [19], and MetaSVM [20] with a true concordance rate of 81.3% and a false concordance rate of 2.8%, whereas for pathogenic variants the same combination resulted in a 70% true…”
Contribution of rare inherited and de novo variants in 2,871 congenital heart disease probands (2017, positive): “The MetaSVM algorithm, annotated using dbNSFP version 2.9 52 , was used to predict deleteriousness of missense variants (annotated as “D-Mis”) using software defaults 53 .”
M-CAP eliminates a majority of variants of uncertain significance in clinical exomes at high sensitivity (2016, methodology): “Most recently, the dbNSFP ensemble logistic regression 16 (MetaLR) score combined multiple scores to outperform any one individual method.”
DEOGEN2: prediction and interactive visualization of single amino acid variant deleteriousness in human proteins (2017, methodology): “Many computational tools for identifying these deleterious variants have been developed so far (8).”