Fine-tuning protein embeddings for functional similarity evaluation
Bioinformatics · 2024
DOI: 10.1093/bioinformatics/btae445 ↗Kurz gefasst
Fachartikel in der Zeitschrift Bioinformatics, 2024. Verfasst von Andrew Dickson und 1 weiteren Autor:innen. Beteiligte Einrichtung: Departments of Bioengineering and Mechanical Engineering, Molecular Cell Biomechanics Laboratory, University of California, Berkeley, CA 94720, Unite…. Hauptthemen laut MEDLINE: Proteins. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 45 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Motivation Proteins with unknown function are frequently compared to better characterized relatives, either using sequence similarity, or recently through similarity in a learned embedding space. Through comparison, protein sequence embeddings allow for interpretable and accurate annotation of proteins, as well as for downstream tasks such as clustering for unsupervised discovery of protein families. However, it is unclear whether embeddings can be deliberately designed to improve their use in these downstream tasks. Results We find that for functional annotation of proteins, as represented by Gene Ontology (GO) terms, direct fine-tuning of language models on a simple classification loss has an immediate positive impact on protein embedding quality. Fine-tuned embeddings show stronger performance as representations for K-nearest neighbor classifiers, reaching stronger performance for GO annotation than even directly comparable fine-tuned classifiers, while maintaining interpretability through protein similarity comparisons. They also maintain their quality in related tasks, such as rediscovering protein families with clustering. Availability and implementation github.com/mofradlab/go_metric
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Substanzen
Autor:innen und Institutionen
- Departments of Bioengineering and Mechanical Engineering, Molecular Cell Biomechanics Laboratory, University of California, Berkeley, CA 94720, United States.
ORCID-Profile: Andrew Dickson, Mohammad R K Mofrad
Zitieren
APA
Dickson, A., & Mofrad, M. R. K. (2024). Fine-tuning protein embeddings for functional similarity evaluation. Bioinformatics. https://doi.org/10.1093/bioinformatics/btae445
Vancouver
Dickson A, Mofrad MRK. Fine-tuning protein embeddings for functional similarity evaluation. Bioinformatics. 2024. doi:10.1093/bioinformatics/btae445
BibTeX
@article{Dickson2024,
author = {Dickson, Andrew and Mofrad, Mohammad R K},
title = {Fine-tuning protein embeddings for functional similarity evaluation},
journal = {Bioinformatics},
year = {2024},
doi = {10.1093/bioinformatics/btae445}
}
EUVIMED