EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

Decoding phenotypic screening: A comparative analysis of image representations

Adriana Borowa, Dawid Rymarczyk, Marek Żyła, Maciej Kańdula, Ana Sánchez-Fernández, Krzysztof Rataj, Łukasz Struski, Jacek Tabor, Bartosz Zieliński

Computational and Structural Biotechnology Journal · 2024-12 · 23 · 1181-1188

DOI: 10.1016/j.csbj.2024.02.022 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Computational and Structural Biotechnology Journal, online erschienen am 12.03.2024. Verfasst von Adriana Borowa und 8 weiteren Autor:innen. Beteiligte Einrichtung: Jagiellonian University, Faculty of Mathematics and Computer Science, Kraków, Poland. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 47 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: Narodowe Centrum Nauki.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Biomedical imaging techniques such as high content screening (HCS) are valuable for drug discovery, but high costs limit their use to pharmaceutical companies. To address this issue, The JUMP-CP consortium released a massive open image dataset of chemical and genetic perturbations, providing a valuable resource for deep learning research. In this work, we aim to utilize the JUMP-CP dataset to develop a universal representation model for HCS data, mainly data generated using U2OS cells and CellPainting protocol, using supervised and self-supervised learning approaches. We propose an evaluation protocol that assesses their performance on mode of action and property prediction tasks using a popular phenotypic screening dataset. Results show that the self-supervised approach that uses data from multiple consortium partners provides representation that is more robust to batch effects whilst simultaneously achieving performance on par with standard approaches. Together with other conclusions, it provides recommendations on the training strategy of a representation model for HCS images.

Schlagwörter

Stichwörter der Autor:innen

Activity predictionDeep LearningHigh Content ScreeningImage representationSelf-supervised learning

Autor:innen und Institutionen

  • Jagiellonian University, Faculty of Mathematics and Computer Science, Kraków, Poland.
  • Jagiellonian University, Doctoral School of Exact and Natural Sciences, Kraków, Poland.
  • Ardigen SA, Kraków, Poland.
  • Janssen Pharmaceutica NV, Beerse, Belgium.

Förderung

  • Narodowe Centrum Nauki

Zitieren

APA

Borowa, A., Rymarczyk, D., Żyła, M., Kańdula, M., Sánchez-Fernández, A., Rataj, K., Struski, Ł., Tabor, J., & Zieliński, B. (2024). Decoding phenotypic screening: A comparative analysis of image representations. Computational and Structural Biotechnology Journal, 23, 1181-1188. https://doi.org/10.1016/j.csbj.2024.02.022

Vancouver

Borowa A, Rymarczyk D, Żyła M, Kańdula M, Sánchez-Fernández A, Rataj K, et al. Decoding phenotypic screening: A comparative analysis of image representations. Computational and Structural Biotechnology Journal. 2024;23:1181-1188. doi:10.1016/j.csbj.2024.02.022

BibTeX
@article{Borowa2024,
  author = {Borowa, Adriana and Rymarczyk, Dawid and Żyła, Marek and Kańdula, Maciej and Sánchez-Fernández, Ana and Rataj, Krzysztof and Struski, Łukasz and Tabor, Jacek and Zieliński, Bartosz},
  title = {Decoding phenotypic screening: A comparative analysis of image representations},
  journal = {Computational and Structural Biotechnology Journal},
  year = {2024},
  volume = {23},
  pages = {1181--1188},
  doi = {10.1016/j.csbj.2024.02.022}
}
Kostenlos starten →