Dataset Information

Blind prediction of deleterious amino acid variations with SNPs&GO.

ABSTRACT: SNPs&GO is a machine learning method for predicting the association of single amino acid variations (SAVs) to disease, considering protein functional annotation. The method is a binary classifier that implements a support vector machine algorithm to discriminate between disease-related and neutral SAVs. SNPs&GO combines information from protein sequence with functional annotation encoded by gene ontology (GO) terms. Tested in sequence mode on more than 38,000 SAVs from the SwissVar dataset, our method reached 81% overall accuracy and an area under the receiving operating characteristic curve of 0.88 with low false-positive rate. In almost all the editions of the Critical Assessment of Genome Interpretation (CAGI) experiments, SNPs&GO ranked among the most accurate algorithms for predicting the effect of SAVs. In this paper, we summarize the best results obtained by SNPs&GO on disease-related variations of four CAGI challenges relative to the following genes: CHEK2 (CAGI 2010), RAD50 (CAGI 2011), p16-INK (CAGI 2013), and NAGLU (CAGI 2016). Result evaluation provides insights about the accuracy of our algorithm and the relevance of GO terms in annotating the effect of the variants. It also helps to define good practices for the detection of deleterious SAVs.

SUBMITTER: Capriotti E

PROVIDER: S-EPMC5522651 | biostudies-literature | 2017 Sep

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Blind prediction of deleterious amino acid variations with SNPs&GO.

Capriotti Emidio E Martelli Pier Luigi PL Fariselli Piero P Casadio Rita R

Human mutation 20170502 9

SNPs&GO is a machine learning method for predicting the association of single amino acid variations (SAVs) to disease, considering protein functional annotation. The method is a binary classifier that implements a support vector machine algorithm to discriminate between disease-related and neutral SAVs. SNPs&GO combines information from protein sequence with functional annotation encoded by gene ontology (GO) terms. Tested in sequence mode on more than 38,000 SAVs from the SwissVar dataset, our ...[more]

PMID: 28102005

Similar Datasets

Project description:PurposeEphrin (Eph) receptor A2 (EPHA2) polymorphism has been associated with age-related cataract (ARC) in different populations worldwide, but the mechanisms by which this polymorphism results in the development of ARC are unclear. Here, we chose four EPHA2 single nucleotide polymorphisms (SNPs; rs35903225, rs145592908, rs137853199, and rs116506614) and studied their function in human lens epithelial cells (LECs).MethodsThe four EPHA2 mutants were overexpressed using lentiviral transduction in human LECs. Cells expressing wild-type (WT) and mutated EPHA2 were subjected to quantitative PCR (qPCR), western blot, immunoprecipitation (IP), and transwell migration assay. MG132 and chloroquine were used to inhibit the degradation of the WT and mutated EPHA2. The structural changes induced by rs137853199 were predicted and optimized using Schrödinger software. IP-mass spectrometry (IP-MS) was performed to examine the proteins that directly interact with WT and rs137853199 EPHA2. Sanger sequencing was performed to determine the frequency of rs137853199 in 184 patients with ARC (73 cortical cataracts, 56 nuclear cataracts, and 55 posterior subcapsular cataracts) and 49 normal controls.ResultsCompared with the WT and the other three mutations, the rs137853199 mutation specifically resulted in a significant decrease in the expression of EPHA2. We identified that EPHA2 rs137853199 is degraded via the ubiquitin-proteasomal pathway through a lysine-48 (K48) residue linkage. Furthermore, the knockdown of EPHA2 reduced cell migration; while the overexpression of WT EPHA2 rescued this defect, the overexpression of rs137853199 EPHA2 did not. In addition, in cells overexpressing rs137853199 EPHA2, the expression of β-catenin, a key protein that regulates cell migration, significantly decreased. We predicted that rs137853199 would induce a conformational change at a linker position in the carboxyl terminal of EPHA2. The IP-MS results showed that the main molecular functions of the proteins that specifically bind WT or rs137853199 EPHA2 are binding and catalysis, while the main protein class is the protein-modifying enzyme. Finally, we discovered that the minor allele frequency of rs137853199 was significantly higher in cortical cataract patients than it was in normal controls.ConclusionsIn summary, these findings suggest a mechanism by which a point mutation in EPHA2 disrupts protein stability, expedites protein degradation, and decreases cell mobility. Importantly, this mutant is associated with cortical cataracts.

Dataset Information

Blind prediction of deleterious amino acid variations with SNPs&GO.

Publications

Blind prediction of deleterious amino acid variations with SNPs&GO.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets