24 Mart 2024 Veri seti Açık Erişim

Nurdan Kuru; Onur Dereli; Emrah Akkoyun; Aylin Bircan; Oznur Tastan; Ogün Adebali

JSON-LD (schema.org)

{
  "@context": "https://schema.org/", 
  "@id": "https://doi.org/10.48623/aperta.263791", 
  "@type": "Dataset", 
  "creator": [
    {
      "@type": "Person", 
      "affiliation": "Sabanc\u0131 \u00dcniversitesi", 
      "name": "Nurdan Kuru"
    }, 
    {
      "@type": "Person", 
      "affiliation": "Sabanc\u0131 \u00dcniversitesi", 
      "name": "Onur Dereli"
    }, 
    {
      "@type": "Person", 
      "affiliation": "Sabanc\u0131 \u00dcniversitesi", 
      "name": "Emrah Akkoyun"
    }, 
    {
      "@type": "Person", 
      "affiliation": "Sabanc\u0131 \u00dcniversitesi", 
      "name": "Aylin Bircan"
    }, 
    {
      "@type": "Person", 
      "affiliation": "Sabanc\u0131 \u00dcniversitesi", 
      "name": "Oznur Tastan"
    }, 
    {
      "@id": "https://orcid.org/0000-0001-9213-4070", 
      "@type": "Person", 
      "affiliation": "Sabanc\u0131 \u00dcniversitesi", 
      "name": "Og\u00fcn Adebali"
    }
  ], 
  "datePublished": "2024-03-24", 
  "description": "<p>Most algorithms that are used to predict the effects of variants rely on evolutionary conservation. However, a majority of such techniques compute evolutionary conservation by solely using the alignment of multiple sequences while overlooking the evolutionary context of substitution events. We had introduced PHACT, a scoring-based pathogenicity predictor for missense mutations that can leverage phylogenetic trees, in our previous study. By building on this foundation, we now propose PHACTboost, a gradient boosting tree-based classifier that combines PHACT scores with information from multiple sequence alignments, phylogenetic trees, and ancestral reconstruction. The results of comprehensive experiments on carefully constructed sets of variants demonstrated that PHACTboost can outperform 40 prevalent pathogenicity predictors reported in the dbNSFP, including conventional tools, meta-predictors, and deep learning-based approaches as well as state-of-the-art tools, AlphaMissense, EVE, and CPT-1. The superiority of PHACTboost over these methods was particularly evident in case of hard variants for which different pathogenicity predictors offered conflicting results. We provide predictions of 215 million amino acid alterations over 20,191 proteins. PHACTboost can improve our understanding of genetic diseases and facilitate more accurate diagnoses.</p>", 
  "distribution": [
    {
      "@type": "DataDownload", 
      "contentUrl": "https://aperta.ulakbim.gov.tr/api/files/c0b245af-1aa3-406e-9b99-9b1e18322da3/Results_PHACTboost.zip", 
      "fileFormat": "zip"
    }
  ], 
  "identifier": "https://doi.org/10.48623/aperta.263791", 
  "keywords": [
    "missense mutations", 
    "phylogenetics", 
    "PHACT", 
    "PHCTboost", 
    "mutation effect prediction", 
    "protein sequences"
  ], 
  "license": "https://creativecommons.org/licenses/by-nc-sa/4.0/", 
  "name": "PHACTboost predictions", 
  "url": "https://aperta.ulakbim.gov.tr/record/263791", 
  "version": "1.0"
}