EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Pitfalls of machine learning models for protein–protein interaction networks

Loïc Lannelongue iD, Michael Inouye

Bioinformatics · 01.02.2024 · 40 (2)

DOI: 10.1093/bioinformatics/btae012 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Bioinformatics, online erschienen am 10.01.2024. Verfasst von Loïc Lannelongue und 1 weiteren Autor:innen. Beteiligte Einrichtung: Cambridge Baker Systems Genomics Initiative, Department of Public Health and Primary Care, University of Cambridge, CB2 0BB Cambridge, United Kingdom. Hauptthemen laut MEDLINE: Protein Interaction Maps, Saccharomyces cerevisiae. Die Arbeit wurde bisher 21-mal zitiert (Crossref) und nennt 26 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: British Heart Foundation, University of Cambridge, Munz Chair of Cardiovascular Prediction and Prevention.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Motivation Protein–protein interactions (PPIs) are essential to understanding biological pathways as well as their roles in development and disease. Computational tools, based on classic machine learning, have been successful at predicting PPIs in silico, but the lack of consistent and reliable frameworks for this task has led to network models that are difficult to compare and discrepancies between algorithms that remain unexplained. Results To better understand the underlying inference mechanisms that underpin these models, we designed an open-source framework for benchmarking that accounts for a range of biological and statistical pitfalls while facilitating reproducibility. We use it to shed light on the impact of network topology and how different algorithms deal with highly connected proteins. By studying functional genomics-based and sequence-based models on human PPIs, we show their complementarity as the former performs best on lone proteins while the latter specializes in interactions involving hubs. We also show that algorithm design has little impact on performance with functional genomic data. We replicate our results between both human and S. cerevisiae data and demonstrate that models using functional genomics are better suited to PPI prediction across species. With rapidly increasing amounts of sequence and functional genomics data, our study provides a principled foundation for future construction, comparison, and application of PPI networks. Availability and implementation The code and data are available on GitHub: https://github.com/Llannelongue/B4PPI.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Protein Interaction MapsSaccharomyces cerevisiaeHumansReproducibility of ResultsProteinsAlgorithmsMachine LearningProtein Interaction Mapping

Substanzen

Proteins

Autor:innen und Institutionen

  • Cambridge Baker Systems Genomics Initiative, Department of Public Health and Primary Care, University of Cambridge, CB2 0BB Cambridge, United Kingdom.
  • British Heart Foundation Cardiovascular Epidemiology Unit, Department of Public Health and Primary Care, University of Cambridge, CB2 0BB Cambridge, United Kingdom.
  • Victor Phillip Dahdaleh Heart and Lung Research Institute, University of Cambridge, CB2 0BB Cambridge, United Kingdom.
  • Health Data Research UK Cambridge, Wellcome Genome Campus and University of Cambridge, Cambridge, United Kingdom.
  • Cambridge Baker Systems Genomics Initiative, Baker Heart and Diabetes Institute, Melbourne, 3004 Victoria, Australia.
  • British Heart Foundation Centre of Research Excellence, University of Cambridge, CB2 0BB Cambridge, United Kingdom.

ORCID-Profile: Loïc Lannelongue

Förderung

  • British Heart Foundation
  • University of Cambridge
  • Munz Chair of Cardiovascular Prediction and Prevention
  • NIHR Cambridge Biomedical Research Centre
  • UK Economic and Social Research 878 Council
  • NIHR
  • Department of Health and Social Care
  • Health Data Research UK

Zitieren

APA

Lannelongue, L., & Inouye, M. (2024). Pitfalls of machine learning models for protein–protein interaction networks. Bioinformatics, 40(2). https://doi.org/10.1093/bioinformatics/btae012

Vancouver

Lannelongue L, Inouye M. Pitfalls of machine learning models for protein–protein interaction networks. Bioinformatics. 2024;40(2). doi:10.1093/bioinformatics/btae012

BibTeX
@article{Lannelongue2024,
  author = {Lannelongue, Loïc and Inouye, Michael},
  title = {Pitfalls of machine learning models for protein–protein interaction networks},
  journal = {Bioinformatics},
  year = {2024},
  volume = {40},
  number = {2},
  doi = {10.1093/bioinformatics/btae012}
}
Kostenlos starten →