Assessing the Pathogenicity of Insertion and Deletion Variants with the Variant Effect Scoring Tool (VEST‐Indel)

Abstract

Insertion/deletion variants (indels) alter protein sequence and length, yet are highly prevalent in healthy populations, presenting a challenge to bioinformatics classifiers. Commonly used features-DNA and protein sequence conservation, indel length, and occurrence in repeat regions-are useful for inference of protein damage. However, these features can cause false positives when predicting the impact of indels on disease. Existing methods for indel classification suffer from low specificities, severely limiting clinical utility. Here, we further develop our variant effect scoring tool (VEST) to include the classification of in-frame and frameshift indels (VEST-indel) as pathogenic or benign. We apply 24 features, including a new "PubMed" feature, to estimate a gene's importance in human disease. When compared with four existing indel classifiers, our method achieves a drastically reduced false-positive rate, improving specificity by as much as 90%. This approach of estimating gene importance might be generally applicable to missense and other bioinformatics pathogenicity predictors, which often fail to achieve high specificity. Finally, we tested all possible meta-predictors that can be obtained from combining the four different indel classifiers using Boolean conjunctions and disjunctions, and derived a meta-predictor with improved performance over any individual method.

The genetic profile of Leber congenital amaurosis in an Australian cohort

“…), SIFT INDEL (Ng and Henikoff ), and VEST INDEL (Douville et al. ). Nonsense variants were assessed using Mutation Taster and, together with frameshift variants, were examined for predicted ability to invoke nonsense‐mediated decay (NMD).…”

Variation Interpretation Predictors: Principles, Types, Performance, and Choice

“…Table S1). CADD [Kircher et al., ], MutationTaster2 [Schwarz et al., ], PROVEAN [Choi et al., ], and VEST [Carter et al., ; Douville et al., ] can predict impacts of insertions, deletions, as well as amino acid substitutions.…”

“…Tools in this domain include KD4i [Bermejo- Das-Neves et al, 2014] and SIFT Indel [Hu and Ng, 2013] that predict the impact of nonframeshifting insertions and deletions. Some other tools predict the impact of frameshifting as well as nonframeshifting insertions and deletions [Zia and Moses, 2011;Hu and Ng, 2012;Zhao et al, 2013;Liu et al, 2014;Douville et al, 2016] (Supp . Table S1).…”

CRAVAT 4: Cancer-Related Analysis of Variants Toolkit

“…3, 4 CHASM uses a Random Forest classifier that is trained from a positive class of cancer driver mutations from COSMIC 5 and a putative set of passenger mutations; thus, CHASM classifies mutations as cancer drivers or passengers . VEST uses a Random Forest classifier that is trained from a positive class of disease-associated germline mutations from the Human Gene Mutation Database (HGMD) 6 and a negative class of common mutations from the exome sequencing project 7 ; thus, VEST classifies mutations as pathogenic or benign .…”