EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Prediction of adverse drug reactions due to genetic predisposition using deep neural networks

Bryan Dafniet, Olivier Taboureau

Molecular Informatics · 2024

DOI: 10.1002/minf.202400021 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Molecular Informatics, 2024. Verfasst von Bryan Dafniet und 1 weiteren Autor:innen. Beteiligte Einrichtung: INSERM U1133, CNRS UMR 8251, Université Paris Cité, 35 rue Hélène Brion, Paris, 75013, France. Hauptthemen laut MEDLINE: Drug-Related Side Effects and Adverse Reactions, Polymorphism, Single Nucleotide, Genetic Predisposition to Disease, Deep Learning. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 36 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: the European Union's Horizon 2020.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Drug development is a long and costly process, often limited by the toxicity and adverse drug reactions (ADRs) caused by drug candidates. Even on the market, some drugs can cause strong ADRs that can vary depending on an individual polymorphism. The development of Genome‐wide association studies (GWAS) allowed the discovery of genetic variants of interest that may cause these effects. In this study, the objective was to investigate a deep learning approach to predict genetic variations potentially related to ADRs. We used single nucleotide polymorphisms (SNPs) information from dbSNP to create a network based on ADR‐drug‐target‐mutations and extracted matrixes of interaction to build deep Neural Networks (DNN) models. Considering only information about mutations known to impact drug efficacy and drug safety from PharmGKB and drug adverse reactions based on the MedDRA System Organ Classes (SOCs), these DNN models reached a balanced accuracy of 0.61 in average. Including molecular fingerprints representing structural features of the drugs did not improve the performance of the models. To our knowledge, this is the first model that exploits DNN to predict ADR‐drug‐target‐mutations. Although some improvements are suggested, these models can be of interest to analyze multiple compounds over all of the genes and polymorphisms information accessible and thus pave the way in precision medicine.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Drug-Related Side Effects and Adverse ReactionsPolymorphism, Single NucleotideGenetic Predisposition to DiseaseDeep LearningNeural Networks, ComputerHumansGenome-Wide Association Study

Stichwörter der Autor:innen

adverse drug reactionsdeep neural networkdrugsgenetic variationssingle nucleotide polymorphisms

Autor:innen und Institutionen

  • INSERM U1133, CNRS UMR 8251, Université Paris Cité, 35 rue Hélène Brion, Paris, 75013, France.

Förderung

  • the European Union's Horizon 2020

Zitieren

APA

Dafniet, B., & Taboureau, O. (2024). Prediction of adverse drug reactions due to genetic predisposition using deep neural networks. Molecular Informatics. https://doi.org/10.1002/minf.202400021

Vancouver

Dafniet B, Taboureau O. Prediction of adverse drug reactions due to genetic predisposition using deep neural networks. Molecular Informatics. 2024. doi:10.1002/minf.202400021

BibTeX
@article{Dafniet2024,
  author = {Dafniet, Bryan and Taboureau, Olivier},
  title = {Prediction of adverse drug reactions due to genetic predisposition using deep neural networks},
  journal = {Molecular Informatics},
  year = {2024},
  doi = {10.1002/minf.202400021}
}
Kostenlos starten →