EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Optimal fusion of genotype and drug embeddings in predicting cancer drug response

Trang Nguyen, Anthony Campbell, Ankit Kumar, Edwin Amponsah, Madalina Fiterau iD, Leili Shahriyari iD

Briefings in Bioinformatics · 2024

DOI: 10.1093/bib/bbae227 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Briefings in Bioinformatics, 2024. Verfasst von Trang Nguyen und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Science, University of Massachusetts Amherst, Amherst 01002, MA, United States. Hauptthemen laut MEDLINE: Neoplasms, Antineoplastic Agents, Genotype, Neural Networks, Computer. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 42 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Predicting cancer drug response using both genomics and drug features has shown some success compared to using genomics features alone. However, there has been limited research done on how best to combine or fuse the two types of features. Using a visible neural network with two deep learning branches for genes and drug features as the base architecture, we experimented with different fusion functions and fusion points. Our experiments show that injecting multiplicative relationships between gene and drug latent features into the original concatenation-based architecture DrugCell significantly improved the overall predictive performance and outperformed other baseline models. We also show that different fusion methods respond differently to different fusion points, indicating that the relationship between drug features and different hierarchical biological level of gene features is optimally captured using different methods. Considering both predictive performance and runtime speed, tensor product partial is the best-performing fusion function to combine late-stage representations of drug and gene features to predict cancer drug response.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

NeoplasmsAntineoplastic AgentsGenotypeNeural Networks, ComputerHumansDeep LearningGenomicsComputational Biology

Stichwörter der Autor:innen

cancer drug response prediction modelsdeep learningdrug embeddingfusion functionfusion pointsvisible neural networks

Substanzen

Antineoplastic Agents

Autor:innen und Institutionen

  • Department of Computer Science, University of Massachusetts Amherst, Amherst 01002, MA, United States.
  • Department of Mathematics and Statistics, University of Massachusetts Amherst, Amherst 01002, MA, United States.

ORCID-Profile: Madalina Fiterau, Leili Shahriyari

Zitieren

APA

Nguyen, T., Campbell, A., Kumar, A., Amponsah, E., Fiterau, M., & Shahriyari, L. (2024). Optimal fusion of genotype and drug embeddings in predicting cancer drug response. Briefings in Bioinformatics. https://doi.org/10.1093/bib/bbae227

Vancouver

Nguyen T, Campbell A, Kumar A, Amponsah E, Fiterau M, Shahriyari L. Optimal fusion of genotype and drug embeddings in predicting cancer drug response. Briefings in Bioinformatics. 2024. doi:10.1093/bib/bbae227

BibTeX
@article{Nguyen2024,
  author = {Nguyen, Trang and Campbell, Anthony and Kumar, Ankit and Amponsah, Edwin and Fiterau, Madalina and Shahriyari, Leili},
  title = {Optimal fusion of genotype and drug embeddings in predicting cancer drug response},
  journal = {Briefings in Bioinformatics},
  year = {2024},
  doi = {10.1093/bib/bbae227}
}
Kostenlos starten →