EUVIMEDEUVIMED entdecken
Open Access

Phenome-wide identification of therapeutic genetic targets, leveraging knowledge graphs, graph neural networks, and UK Biobank data

Lawrence Middleton iD, Ioannis Melas, Chirag Vasavda iD, Arwa Raies iD, Benedek Rozemberczki iD, Ryan S Dhindsa iD, Justin S Dhindsa, Blake Weido iD, Quanli Wang, Andrew R Harper iD, Gavin Edwards iD, Slavé Petrovski iD und 1 weitere

Science Advances · 2024

DOI: 10.1126/sciadv.adj1424 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Science Advances, 2024. Verfasst von Lawrence Middleton und 12 weiteren Autor:innen. Beteiligte Einrichtung: Centre for Genomics Research, Discovery Sciences, BioPharmaceuticals R&D, AstraZeneca, Cambridge, UK. Hauptthemen laut MEDLINE: Neural Networks, Computer. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 52 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The ongoing expansion of human genomic datasets propels therapeutic target identification; however, extracting gene-disease associations from gene annotations remains challenging. Here, we introduce Mantis-ML 2.0, a framework integrating AstraZeneca’s Biological Insights Knowledge Graph and numerous tabular datasets, to assess gene-disease probabilities throughout the phenome. We use graph neural networks, capturing the graph’s holistic structure, and train them on hundreds of balanced datasets via a robust semi-supervised learning framework to provide gene-disease probabilities across the human exome. Mantis-ML 2.0 incorporates natural language processing to automate disease-relevant feature selection for thousands of diseases. The enhanced models demonstrate a 6.9% average classification power boost, achieving a median receiver operating characteristic (ROC) area under curve (AUC) score of 0.90 across 5220 diseases from Human Phenotype Ontology, OpenTargets, and Genomics England. Notably, Mantis-ML 2.0 prioritizes associations from an independent UK Biobank phenome-wide association study (PheWAS), providing a stronger form of triaging and mitigating against underpowered PheWAS associations. Results are exposed through an interactive web resource.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Neural Networks, ComputerHumansAlgorithmsComputational BiologyDatabases, GeneticGenetic Predisposition to DiseaseGenome-Wide Association StudyGenomicsPhenomicsPhenotypeUK BiobankUnited Kingdom

Autor:innen und Institutionen

  • Centre for Genomics Research, Discovery Sciences, BioPharmaceuticals R&D, AstraZeneca, Cambridge, UK.
  • Centre for Genomics Research, Discovery Sciences, BioPharmaceuticals R&D, AstraZeneca, Waltham, MA 02451, USA.
  • Biological Insights Knowledge Graph (BIKG), Research D&A, R&D IT, AstraZeneca, Cambridge, UK.
  • Department of Molecular and Human Genetics, Baylor College of Medicine, Houston, TX 77030, USA.
  • Jan and Dan Duncan Neurological Research Institute at Texas Children's Hospital, Houston, TX 77030, USA.
  • Medical Scientist Training Program, Baylor College of Medicine, Houston, TX 77030, USA.

ORCID-Profile: Lawrence Middleton, Chirag Vasavda, Arwa Raies, Benedek Rozemberczki, Ryan S Dhindsa, Blake Weido, Andrew R Harper, Gavin Edwards, Slavé Petrovski, Dimitrios Vitsios

Zitieren

APA

Middleton, L., Melas, I., Vasavda, C., Raies, A., Rozemberczki, B., Dhindsa, R. S., Dhindsa, J. S., Weido, B., Wang, Q., Harper, A. R., Edwards, G., Petrovski, S., & Vitsios, D. (2024). Phenome-wide identification of therapeutic genetic targets, leveraging knowledge graphs, graph neural networks, and UK Biobank data. Science Advances. https://doi.org/10.1126/sciadv.adj1424

Vancouver

Middleton L, Melas I, Vasavda C, Raies A, Rozemberczki B, Dhindsa RS, et al. Phenome-wide identification of therapeutic genetic targets, leveraging knowledge graphs, graph neural networks, and UK Biobank data. Science Advances. 2024. doi:10.1126/sciadv.adj1424

BibTeX
@article{Middleton2024,
  author = {Middleton, Lawrence and Melas, Ioannis and Vasavda, Chirag and Raies, Arwa and Rozemberczki, Benedek and Dhindsa, Ryan S and Dhindsa, Justin S and Weido, Blake and Wang, Quanli and Harper, Andrew R and Edwards, Gavin and Petrovski, Slavé and Vitsios, Dimitrios},
  title = {Phenome-wide identification of therapeutic genetic targets, leveraging knowledge graphs, graph neural networks, and UK Biobank data},
  journal = {Science Advances},
  year = {2024},
  doi = {10.1126/sciadv.adj1424}
}
Kostenlos starten →