2021
DOI: 10.1016/j.ajhg.2021.08.012
|View full text |Cite|
|
Sign up to set email alerts
|

Improved pathogenicity prediction for rare human missense variants

Abstract: The success of personalized genomic medicine depends on our ability to assess the pathogenicity of rare human variants, including the important class of missense variation. There are many challenges in training accurate computational systems, e.g., in finding the balance between quantity, quality, and bias in the variant sets used as training examples and avoiding predictive features that can accentuate the effects of bias. Here, we describe VARITY, which judiciously exploits a larger reservoir of training exa… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

1
79
0

Year Published

2022
2022
2024
2024

Publication Types

Select...
7
2
1

Relationship

0
10

Authors

Journals

citations
Cited by 91 publications
(80 citation statements)
references
References 69 publications
(245 reference statements)
1
79
0
Order By: Relevance
“…GRIA2 Ala643 is located at the lurcher site [17] in the highly conserved sequence (SYTANLA A F) that forms the upper AMPAR ion channel gate ( Fig 1f ). Bioinformatic predictions suggested that the variant was likely to be pathogenic – SIFT pathogenic, score 0 [18]; polyphen 2, probably damaging, score 0.999 [19]; VARITY R, score 0.953 [20]. Indeed, variants at this site have previously been suggested as disease-causing for GRIA1 [6], GRIA4 [4], and GRIA3 (present in ClinVar database) ( Fig 1f ).…”
Section: Resultsmentioning
confidence: 98%
“…GRIA2 Ala643 is located at the lurcher site [17] in the highly conserved sequence (SYTANLA A F) that forms the upper AMPAR ion channel gate ( Fig 1f ). Bioinformatic predictions suggested that the variant was likely to be pathogenic – SIFT pathogenic, score 0 [18]; polyphen 2, probably damaging, score 0.999 [19]; VARITY R, score 0.953 [20]. Indeed, variants at this site have previously been suggested as disease-causing for GRIA1 [6], GRIA4 [4], and GRIA3 (present in ClinVar database) ( Fig 1f ).…”
Section: Resultsmentioning
confidence: 98%
“…and/or other technical inaccuracies such as sequencing errors. More accurate variant effect prediction tools should further increase the power of these kinds of analyses 66,106,107 . We also found that using two techniques to derive informative somatic mutation phenotypes identified more replicated associations than using either approach alone.…”
Section: Discussionmentioning
confidence: 99%
“…M-CAP is based on a gradient boosting tree classifier model, and it applies 318 features as input into the model. MetaLR uses logistic regression to integrate nine independent variant deleteriousness scores [ 66 ]. PROVEAN is a prediction tool based on sequence clustering [ 67 ] to predict the modification of protein function due to amino acid substitution [ 68 , 69 ].…”
Section: Methodsmentioning
confidence: 99%