EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Detecting anomalous proteins using deep representations

Tomer Michael-Pitschaze, Niv Cohen, Dan Ofer iD, Yedid Hoshen, Michal Linial iD

NAR Genomics and Bioinformatics · 05.01.2024 · 6 (1)

DOI: 10.1093/nargab/lqae021 ↗

Kurz gefasst

Fachartikel in der Zeitschrift NAR Genomics and Bioinformatics, online erschienen am 27.02.2024. Verfasst von Tomer Michael-Pitschaze und 4 weiteren Autor:innen. Beteiligte Einrichtung: The Rachel and Selim Benin School of Computer Science and Engineering, The Hebrew University of Jerusalem, Jerusalem, Israel. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 60 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: Center for Interdisciplinary Data Science Research.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Many advances in biomedicine can be attributed to identifying unusual proteins and genes. Many of these proteins’ unique properties were discovered by manual inspection, which is becoming infeasible at the scale of modern protein datasets. Here, we propose to tackle this challenge using anomaly detection methods that automatically identify unexpected properties. We adopt a state-of-the-art anomaly detection paradigm from computer vision, to highlight unusual proteins. We generate meaningful representations without labeled inputs, using pretrained deep neural network models. We apply these protein language models (pLM) to detect anomalies in function, phylogenetic families, and segmentation tasks. We compute protein anomaly scores to highlight human prion-like proteins, distinguish viral proteins from their host proteome, and mark non-classical ion/metal binding proteins and enzymes. Other tasks concern segmentation of protein sequences into folded and unstructured regions. We provide candidates for rare functionality (e.g. prion proteins). Additionally, we show the anomaly score is useful in 3D folding-related segmentation. Our novel method shows improved performance over strong baselines and has objectively high performance across a variety of tasks. We conclude that the combination of pLM and anomaly detection techniques is a valid method for discovering a range of global and local protein characteristics.

Autor:innen und Institutionen

  • The Rachel and Selim Benin School of Computer Science and Engineering, The Hebrew University of Jerusalem, Jerusalem, Israel.
  • Department of Biological Chemistry, Institute of Life Sciences, The Hebrew University of Jerusalem, Jerusalem, Israel.

ORCID-Profile: Dan Ofer, Michal Linial

Förderung

  • Center for Interdisciplinary Data Science Research

Zitieren

APA

Michael-Pitschaze, T., Cohen, N., Ofer, D., Hoshen, Y., & Linial, M. (2024). Detecting anomalous proteins using deep representations. NAR Genomics and Bioinformatics, 6(1). https://doi.org/10.1093/nargab/lqae021

Vancouver

Michael-Pitschaze T, Cohen N, Ofer D, Hoshen Y, Linial M. Detecting anomalous proteins using deep representations. NAR Genomics and Bioinformatics. 2024;6(1). doi:10.1093/nargab/lqae021

BibTeX
@article{MichaelPitschaze2024,
  author = {Michael-Pitschaze, Tomer and Cohen, Niv and Ofer, Dan and Hoshen, Yedid and Linial, Michal},
  title = {Detecting anomalous proteins using deep representations},
  journal = {NAR Genomics and Bioinformatics},
  year = {2024},
  volume = {6},
  number = {1},
  doi = {10.1093/nargab/lqae021}
}
Kostenlos starten →