Gene-Specific Variant Classifier (DPYD-Varifier) to Identify Deleterious Alleles of Dihydropyrimidine Dehydrogenase

Shikshya Shrestha, Cheng Zhang, Calvin R. Jerde, Qian Nie, Hu Li, Steven M. Offer, Robert B Diasio

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

Deleterious variants in dihydropyrimidine dehydrogenase (DPD, DPYD gene) can be highly predictive of clinical toxicity to the widely prescribed chemotherapeutic 5-fluorouracil (5-FU). However, there are very limited data pertaining to the functional consequences of the >450 reported no-synonymous DPYD variants. We developed a DPYD-specific variant classifier (DPYD-Varifier) using machine learning and in vitro functional data for 156 missense DPYD variants. The developed model showed 85% accuracy and outperformed other in silico prediction tools. An examination of feature importance within the model provided additional insight into functional aspects of the DPD protein relevant to 5-FU toxicity. In the absence of clinical data for unstudied variants, prediction tools like DPYD-Varifier have great potential to individualize medicine and improve the clinical decision-making process.

Original languageEnglish (US)
JournalClinical Pharmacology and Therapeutics
DOIs
StateAccepted/In press - Jan 1 2018

Fingerprint

Dihydrouracil Dehydrogenase (NADP)
Fluorouracil
Alleles
Precision Medicine
Computer Simulation
Genes
Proteins

ASJC Scopus subject areas

  • Pharmacology
  • Pharmacology (medical)

Cite this

Gene-Specific Variant Classifier (DPYD-Varifier) to Identify Deleterious Alleles of Dihydropyrimidine Dehydrogenase. / Shrestha, Shikshya; Zhang, Cheng; Jerde, Calvin R.; Nie, Qian; Li, Hu; Offer, Steven M.; Diasio, Robert B.

In: Clinical Pharmacology and Therapeutics, 01.01.2018.

Research output: Contribution to journalArticle

@article{98fefc21389f454e884f098378895eb1,
title = "Gene-Specific Variant Classifier (DPYD-Varifier) to Identify Deleterious Alleles of Dihydropyrimidine Dehydrogenase",
abstract = "Deleterious variants in dihydropyrimidine dehydrogenase (DPD, DPYD gene) can be highly predictive of clinical toxicity to the widely prescribed chemotherapeutic 5-fluorouracil (5-FU). However, there are very limited data pertaining to the functional consequences of the >450 reported no-synonymous DPYD variants. We developed a DPYD-specific variant classifier (DPYD-Varifier) using machine learning and in vitro functional data for 156 missense DPYD variants. The developed model showed 85{\%} accuracy and outperformed other in silico prediction tools. An examination of feature importance within the model provided additional insight into functional aspects of the DPD protein relevant to 5-FU toxicity. In the absence of clinical data for unstudied variants, prediction tools like DPYD-Varifier have great potential to individualize medicine and improve the clinical decision-making process.",
author = "Shikshya Shrestha and Cheng Zhang and Jerde, {Calvin R.} and Qian Nie and Hu Li and Offer, {Steven M.} and Diasio, {Robert B}",
year = "2018",
month = "1",
day = "1",
doi = "10.1002/cpt.1020",
language = "English (US)",
journal = "Clinical Pharmacology and Therapeutics",
issn = "0009-9236",
publisher = "Nature Publishing Group",

}

TY - JOUR

T1 - Gene-Specific Variant Classifier (DPYD-Varifier) to Identify Deleterious Alleles of Dihydropyrimidine Dehydrogenase

AU - Shrestha, Shikshya

AU - Zhang, Cheng

AU - Jerde, Calvin R.

AU - Nie, Qian

AU - Li, Hu

AU - Offer, Steven M.

AU - Diasio, Robert B

PY - 2018/1/1

Y1 - 2018/1/1

N2 - Deleterious variants in dihydropyrimidine dehydrogenase (DPD, DPYD gene) can be highly predictive of clinical toxicity to the widely prescribed chemotherapeutic 5-fluorouracil (5-FU). However, there are very limited data pertaining to the functional consequences of the >450 reported no-synonymous DPYD variants. We developed a DPYD-specific variant classifier (DPYD-Varifier) using machine learning and in vitro functional data for 156 missense DPYD variants. The developed model showed 85% accuracy and outperformed other in silico prediction tools. An examination of feature importance within the model provided additional insight into functional aspects of the DPD protein relevant to 5-FU toxicity. In the absence of clinical data for unstudied variants, prediction tools like DPYD-Varifier have great potential to individualize medicine and improve the clinical decision-making process.

AB - Deleterious variants in dihydropyrimidine dehydrogenase (DPD, DPYD gene) can be highly predictive of clinical toxicity to the widely prescribed chemotherapeutic 5-fluorouracil (5-FU). However, there are very limited data pertaining to the functional consequences of the >450 reported no-synonymous DPYD variants. We developed a DPYD-specific variant classifier (DPYD-Varifier) using machine learning and in vitro functional data for 156 missense DPYD variants. The developed model showed 85% accuracy and outperformed other in silico prediction tools. An examination of feature importance within the model provided additional insight into functional aspects of the DPD protein relevant to 5-FU toxicity. In the absence of clinical data for unstudied variants, prediction tools like DPYD-Varifier have great potential to individualize medicine and improve the clinical decision-making process.

UR - http://www.scopus.com/inward/record.url?scp=85041184588&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85041184588&partnerID=8YFLogxK

U2 - 10.1002/cpt.1020

DO - 10.1002/cpt.1020

M3 - Article

JO - Clinical Pharmacology and Therapeutics

JF - Clinical Pharmacology and Therapeutics

SN - 0009-9236

ER -