EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A systematic benchmark of machine learning methods for protein–RNA interaction prediction

Marc Horlacher, Giulia Cantini, Julian Hesse, Patrick Schinke, Nicolas Goedert, Shubhankar Londhe, Lambert Moyon, Annalisa Marsico

Briefings in Bioinformatics · 20.09.2023 · 24 (5)

DOI: 10.1093/bib/bbad307 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Briefings in Bioinformatics, online erschienen am 26.08.2023. Verfasst von Marc Horlacher und 7 weiteren Autor:innen. Beteiligte Einrichtung: Computational Health Center, Helmholtz Center Munich, Germany. Hauptthemen laut MEDLINE: Chromatin Immunoprecipitation Sequencing. Die Arbeit wurde bisher 30-mal zitiert (Crossref) und nennt 85 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Helmholtz Association, Munich School for Data Science, Deutsche Forschungsgemeinschaft.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

RNA-binding proteins (RBPs) are central actors of RNA post-transcriptional regulation. Experiments to profile-binding sites of RBPs in vivo are limited to transcripts expressed in the experimental cell type, creating the need for computational methods to infer missing binding information. While numerous machine-learning based methods have been developed for this task, their use of heterogeneous training and evaluation datasets across different sets of RBPs and CLIP-seq protocols makes a direct comparison of their performance difficult. Here, we compile a set of 37 machine learning (primarily deep learning) methods for in vivo RBP–RNA interaction prediction and systematically benchmark a subset of 11 representative methods across hundreds of CLIP-seq datasets and RBPs. Using homogenized sample pre-processing and two negative-class sample generation strategies, we evaluate methods in terms of predictive performance and assess the impact of neural network architectures and input modalities on model performance. We believe that this study will not only enable researchers to choose the optimal prediction method for their tasks at hand, but also aid method developers in developing novel, high-performing methods by introducing a standardized framework for their evaluation.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Chromatin Immunoprecipitation SequencingBinding SitesMachine LearningRNA

Stichwörter der Autor:innen

RNA biologyRNA-binding proteinsbenchmarkdeep learning

Substanzen

RNA

Autor:innen und Institutionen

  • Computational Health Center, Helmholtz Center Munich, Germany.
  • School of Computation, Information and Technology, Technical University Munich (TUM), Germany.

Förderung

  • Helmholtz Association
  • Munich School for Data Science
  • Deutsche Forschungsgemeinschaft

Zitieren

APA

Horlacher, M., Cantini, G., Hesse, J., Schinke, P., Goedert, N., Londhe, S., Moyon, L., & Marsico, A. (2023). A systematic benchmark of machine learning methods for protein–RNA interaction prediction. Briefings in Bioinformatics, 24(5). https://doi.org/10.1093/bib/bbad307

Vancouver

Horlacher M, Cantini G, Hesse J, Schinke P, Goedert N, Londhe S, et al. A systematic benchmark of machine learning methods for protein–RNA interaction prediction. Briefings in Bioinformatics. 2023;24(5). doi:10.1093/bib/bbad307

BibTeX
@article{Horlacher2023,
  author = {Horlacher, Marc and Cantini, Giulia and Hesse, Julian and Schinke, Patrick and Goedert, Nicolas and Londhe, Shubhankar and Moyon, Lambert and Marsico, Annalisa},
  title = {A systematic benchmark of machine learning methods for protein–RNA interaction prediction},
  journal = {Briefings in Bioinformatics},
  year = {2023},
  volume = {24},
  number = {5},
  doi = {10.1093/bib/bbad307}
}
Kostenlos starten →