EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

INTREPPPID—an orthologue-informed quintuplet network for cross-species prediction of protein–protein interaction

Joseph Szymborski iD, Amin Emad iD

Briefings in Bioinformatics · 2024

DOI: 10.1093/bib/bbae405 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Briefings in Bioinformatics, 2024. Verfasst von Joseph Szymborski und 1 weiteren Autor:innen. Beteiligte Einrichtung: Department of Electrical and Computer Engineering, McGill University, 845 Sherbrooke Street West, Montréal, QC H3A 0G4, Canada. Hauptthemen laut MEDLINE: Protein Interaction Mapping, Neural Networks, Computer, Computational Biology. Die Arbeit wurde bisher 12-mal zitiert (Crossref) und nennt 55 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: Natural Sciences and Engineering Research Council of Canada (NSERC).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

An overwhelming majority of protein–protein interaction (PPI) studies are conducted in a select few model organisms largely due to constraints in time and cost of the associated ‘wet lab’ experiments. In silico PPI inference methods are ideal tools to overcome these limitations, but often struggle with cross-species predictions. We present INTREPPPID, a method that incorporates orthology data using a new ‘quintuplet’ neural network, which is constructed with five parallel encoders with shared parameters. INTREPPPID incorporates both a PPI classification task and an orthologous locality task. The latter learns embeddings of orthologues that have small Euclidean distances between them and large distances between embeddings of all other proteins. INTREPPPID outperforms all other leading PPI inference methods tested on both the intraspecies and cross-species tasks using strict evaluation datasets. We show that INTREPPPID’s orthologous locality loss increases performance because of the biological relevance of the orthologue data and not due to some other specious aspect of the architecture. Finally, we introduce PPI.bio and PPI Origami, a web server interface for INTREPPPID and a software tool for creating strict evaluation datasets, respectively. Together, these two initiatives aim to make both the use and development of PPI inference tools more accessible to the community.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Protein Interaction MappingNeural Networks, ComputerComputational BiologySoftwareHumansAlgorithmsDatabases, ProteinAnimalsProtein Interaction MapsSpecies Specificity

Stichwörter der Autor:innen

cross-speciesdeep learningorthologyprotein-protein interactions

Autor:innen und Institutionen

  • Department of Electrical and Computer Engineering, McGill University, 845 Sherbrooke Street West, Montréal, QC H3A 0G4, Canada.
  • Mila, Quebec AI Institute, 6666 St-Urbain Street #200, Montréal, QC H2S 3H1, Canada.
  • The Rosalind and Morris Goodman Cancer Institute, 1160 Pine Avenue, Montréal, QC H3A 1A3, Canada.

ORCID-Profile: Joseph Szymborski, Amin Emad

Förderung

  • Natural Sciences and Engineering Research Council of Canada (NSERC)

Zitieren

APA

Szymborski, J., & Emad, A. (2024). INTREPPPID—an orthologue-informed quintuplet network for cross-species prediction of protein–protein interaction. Briefings in Bioinformatics. https://doi.org/10.1093/bib/bbae405

Vancouver

Szymborski J, Emad A. INTREPPPID—an orthologue-informed quintuplet network for cross-species prediction of protein–protein interaction. Briefings in Bioinformatics. 2024. doi:10.1093/bib/bbae405

BibTeX
@article{Szymborski2024,
  author = {Szymborski, Joseph and Emad, Amin},
  title = {INTREPPPID—an orthologue-informed quintuplet network for cross-species prediction of protein–protein interaction},
  journal = {Briefings in Bioinformatics},
  year = {2024},
  doi = {10.1093/bib/bbae405}
}
Kostenlos starten →