EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A comprehensive benchmarking of machine learning algorithms and dimensionality reduction methods for drug sensitivity prediction

Lea Eckhart iD, Kerstin Lenhof iD, Lisa-Marie Rolli iD, Hans-Peter Lenhof iD

Briefings in Bioinformatics · 2024

DOI: 10.1093/bib/bbae242 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Briefings in Bioinformatics, 2024. Verfasst von Lea Eckhart und 3 weiteren Autor:innen. Beteiligte Einrichtung: Center for Bioinformatics, Saarland Informatics Campus, Saarland University, 66123, Saarland, Germany. Hauptthemen laut MEDLINE: Machine Learning, Benchmarking, Antineoplastic Agents, Algorithms. Die Arbeit wurde bisher 26-mal zitiert (Crossref) und nennt 76 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Saarland University.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

A major challenge of precision oncology is the identification and prioritization of suitable treatment options based on molecular biomarkers of the considered tumor. In pursuit of this goal, large cancer cell line panels have successfully been studied to elucidate the relationship between cellular features and treatment response. Due to the high dimensionality of these datasets, machine learning (ML) is commonly used for their analysis. However, choosing a suitable algorithm and set of input features can be challenging. We performed a comprehensive benchmarking of ML methods and dimension reduction (DR) techniques for predicting drug response metrics. Using the Genomics of Drug Sensitivity in Cancer cell line panel, we trained random forests, neural networks, boosting trees and elastic nets for 179 anti-cancer compounds with feature sets derived from nine DR approaches. We compare the results regarding statistical performance, runtime and interpretability. Additionally, we provide strategies for assessing model performance compared with a simple baseline model and measuring the trade-off between models of different complexity. Lastly, we show that complex ML models benefit from using an optimized DR strategy, and that standard models—even when using considerably fewer features—can still be superior in performance.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Machine LearningBenchmarkingAntineoplastic AgentsAlgorithmsHumansNeoplasmsNeural Networks, ComputerCell Line, Tumor

Stichwörter der Autor:innen

cancer cell linesdimension reductiondrug sensitivity predictionfeature extractionfeature selectionmachine learning

Substanzen

Antineoplastic Agents

Autor:innen und Institutionen

  • Center for Bioinformatics, Saarland Informatics Campus, Saarland University, 66123, Saarland, Germany.

ORCID-Profile: Lea Eckhart, Kerstin Lenhof, Lisa-Marie Rolli, Hans-Peter Lenhof

Förderung

  • Saarland University

Zitieren

APA

Eckhart, L., Lenhof, K., Rolli, L. M., & Lenhof, H. P. (2024). A comprehensive benchmarking of machine learning algorithms and dimensionality reduction methods for drug sensitivity prediction. Briefings in Bioinformatics. https://doi.org/10.1093/bib/bbae242

Vancouver

Eckhart L, Lenhof K, Rolli LM, Lenhof HP. A comprehensive benchmarking of machine learning algorithms and dimensionality reduction methods for drug sensitivity prediction. Briefings in Bioinformatics. 2024. doi:10.1093/bib/bbae242

BibTeX
@article{Eckhart2024,
  author = {Eckhart, Lea and Lenhof, Kerstin and Rolli, Lisa-Marie and Lenhof, Hans-Peter},
  title = {A comprehensive benchmarking of machine learning algorithms and dimensionality reduction methods for drug sensitivity prediction},
  journal = {Briefings in Bioinformatics},
  year = {2024},
  doi = {10.1093/bib/bbae242}
}
Kostenlos starten →