Cracking the black box of deep sequence-based protein–protein interaction prediction
Briefings in Bioinformatics · 22.01.2024 · 25 (2)
DOI: 10.1093/bib/bbae076 ↗Kurz gefasst
Fachartikel in der Zeitschrift Briefings in Bioinformatics, online erschienen am 05.03.2024. Verfasst von Judith Bernett und 2 weiteren Autor:innen. Beteiligte Einrichtung: Data Science in Systems Biology, TUM School of Life Sciences, Technical University of Munich, Maximus-von-Imhof Forum 3, 85354, Freising, Germany. Hauptthemen laut MEDLINE: Machine Learning. Die Arbeit wurde bisher 123-mal zitiert (Crossref) und nennt 58 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Identifying protein–protein interactions (PPIs) is crucial for deciphering biological pathways. Numerous prediction methods have been developed as cheap alternatives to biological experiments, reporting surprisingly high accuracy estimates. We systematically investigated how much reproducible deep learning models depend on data leakage, sequence similarities and node degree information, and compared them with basic machine learning models. We found that overlaps between training and test sets resulting from random splitting lead to strongly overestimated performances. In this setting, models learn solely from sequence similarities and node degrees. When data leakage is avoided by minimizing sequence similarities between training and test set, performances become random. Moreover, baseline models directly leveraging sequence similarity and network topology show good performances at a fraction of the computational cost. Thus, we advocate that any improvements should be reported relative to baseline methods in the future. Our findings suggest that predicting PPIs remains an unsolved task for proteins showing little sequence similarity to previously studied proteins, highlighting that further experimental research into the ‘dark’ protein interactome and better computational methods are needed.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Data Science in Systems Biology, TUM School of Life Sciences, Technical University of Munich, Maximus-von-Imhof Forum 3, 85354, Freising, Germany.
- Biomedical Network Science Lab, Department Artificial Intelligence in Biomedical Engineering, Friedrich-Alexander-Universität Erlangen-Nürnberg, Werner-von-Siemens-Str. 61, 91052, Erlangen, Germany.
ORCID-Profile: Judith Bernett, David B Blumenthal, Markus List
Zitieren
APA
Bernett, J., Blumenthal, D. B., & List, M. (2024). Cracking the black box of deep sequence-based protein–protein interaction prediction. Briefings in Bioinformatics, 25(2). https://doi.org/10.1093/bib/bbae076
Vancouver
Bernett J, Blumenthal DB, List M. Cracking the black box of deep sequence-based protein–protein interaction prediction. Briefings in Bioinformatics. 2024;25(2). doi:10.1093/bib/bbae076
BibTeX
@article{Bernett2024,
author = {Bernett, Judith and Blumenthal, David B and List, Markus},
title = {Cracking the black box of deep sequence-based protein–protein interaction prediction},
journal = {Briefings in Bioinformatics},
year = {2024},
volume = {25},
number = {2},
doi = {10.1093/bib/bbae076}
}
EUVIMED