EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Machine Learning-Driven Data Valuation for Optimizing High-Throughput Screening Pipelines

Joshua Hesse iD, Davide Boldini, Stephan A Sieber iD

Journal of Chemical Information and Modeling · 11.11.2024 · 64 (21) · 8142-8152

DOI: 10.1021/acs.jcim.4c01547 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Chemical Information and Modeling, online erschienen am 23.10.2024. Verfasst von Joshua Hesse und 2 weiteren Autor:innen. Beteiligte Einrichtung: Technical University of Munich, TUM School of Natural Sciences, Department of Bioscience, Center for Functional Protein Assemblies (CPA), 85748 Garch…. Hauptthemen laut MEDLINE: High-Throughput Screening Assays, Machine Learning, Drug Discovery. Die Arbeit wurde bisher 12-mal zitiert (Crossref) und nennt 43 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: European Research Council, Merck KGaA.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In the rapidly evolving field of drug discovery, high-throughput screening (HTS) is essential for identifying bioactive compounds. This study introduces a novel application of data valuation, a concept for evaluating the importance of data points based on their impact, to enhance drug discovery pipelines. Our approach improves active learning for compound library screening, robustly identifies true and false positives in HTS data, and identifies important inactive samples in an imbalanced HTS training, all while accounting for computational efficiency. We demonstrate that importance-based methods enable more effective batch screening, reducing the need for extensive HTS. Machine learning models accurately differentiate true biological activity from assay artifacts, streamlining the drug discovery process. Additionally, importance undersampling aids in HTS data set balancing, improving machine learning performance without omitting crucial inactive samples. These advancements could significantly enhance the efficiency and accuracy of drug development.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

High-Throughput Screening AssaysMachine LearningDrug DiscoveryDrug Evaluation, Preclinical

Autor:innen und Institutionen

  • Technical University of Munich, TUM School of Natural Sciences, Department of Bioscience, Center for Functional Protein Assemblies (CPA), 85748 Garching bei München, Germany.

ORCID-Profile: Joshua Hesse, Stephan A Sieber

Förderung

  • European Research Council
  • Merck KGaA

Zitieren

APA

Hesse, J., Boldini, D., & Sieber, S. A. (2024). Machine Learning-Driven Data Valuation for Optimizing High-Throughput Screening Pipelines. Journal of Chemical Information and Modeling, 64(21), 8142-8152. https://doi.org/10.1021/acs.jcim.4c01547

Vancouver

Hesse J, Boldini D, Sieber SA. Machine Learning-Driven Data Valuation for Optimizing High-Throughput Screening Pipelines. Journal of Chemical Information and Modeling. 2024;64(21):8142-8152. doi:10.1021/acs.jcim.4c01547

BibTeX
@article{Hesse2024,
  author = {Hesse, Joshua and Boldini, Davide and Sieber, Stephan A},
  title = {Machine Learning-Driven Data Valuation for Optimizing High-Throughput Screening Pipelines},
  journal = {Journal of Chemical Information and Modeling},
  year = {2024},
  volume = {64},
  number = {21},
  pages = {8142--8152},
  doi = {10.1021/acs.jcim.4c01547}
}
Kostenlos starten →