Embedding-based alignment: combining protein language models with dynamic programming alignment to detect structural similarities in the twilight-zone
Bioinformatics · 02.01.2024 · 40 (1)
DOI: 10.1093/bioinformatics/btad786 ↗Kurz gefasst
Fachartikel in der Zeitschrift Bioinformatics, online erschienen am 04.01.2024. Verfasst von Lorenzo Pantolini und 5 weiteren Autor:innen. Beteiligte Einrichtung: Biozentrum, University of Basel, Basel 4056, Switzerland. Hauptthemen laut MEDLINE: Proteins, Amino Acids. Die Arbeit wurde bisher 63-mal zitiert (Crossref) und nennt 32 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: SIB Swiss Institute of Bioinformatics, Biozentrum, University of Basel.
Abstract (Originalsprache)
Motivation Language models are routinely used for text classification and generative tasks. Recently, the same architectures were applied to protein sequences, unlocking powerful new approaches in the bioinformatics field. Protein language models (pLMs) generate high-dimensional embeddings on a per-residue level and encode a “semantic meaning” of each individual amino acid in the context of the full protein sequence. These representations have been used as a starting point for downstream learning tasks and, more recently, for identifying distant homologous relationships between proteins. Results In this work, we introduce a new method that generates embedding-based protein sequence alignments (EBA) and show how these capture structural similarities even in the twilight zone, outperforming both classical methods as well as other approaches based on pLMs. The method shows excellent accuracy despite the absence of training and parameter optimization. We demonstrate that the combination of pLMs with alignment methods is a valuable approach for the detection of relationships between proteins in the twilight-zone. Availability and implementation The code to run EBA and reproduce the analysis described in this article is available at: https://git.scicore.unibas.ch/schwede/EBA and https://git.scicore.unibas.ch/schwede/eba_benchmark.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Substanzen
Autor:innen und Institutionen
- Biozentrum, University of Basel, Basel 4056, Switzerland.
- SIB Swiss Institute of Bioinformatics, Basel 4056, Switzerland.
ORCID-Profile: Lorenzo Pantolini, Gabriel Studer, Joana Pereira, Janani Durairaj, Gerardo Tauriello, Torsten Schwede
Förderung
- SIB Swiss Institute of Bioinformatics
- Biozentrum, University of Basel
Zitieren
APA
Pantolini, L., Studer, G., Pereira, J., Durairaj, J., Tauriello, G., & Schwede, T. (2024). Embedding-based alignment: combining protein language models with dynamic programming alignment to detect structural similarities in the twilight-zone. Bioinformatics, 40(1). https://doi.org/10.1093/bioinformatics/btad786
Vancouver
Pantolini L, Studer G, Pereira J, Durairaj J, Tauriello G, Schwede T. Embedding-based alignment: combining protein language models with dynamic programming alignment to detect structural similarities in the twilight-zone. Bioinformatics. 2024;40(1). doi:10.1093/bioinformatics/btad786
BibTeX
@article{Pantolini2024,
author = {Pantolini, Lorenzo and Studer, Gabriel and Pereira, Joana and Durairaj, Janani and Tauriello, Gerardo and Schwede, Torsten},
title = {Embedding-based alignment: combining protein language models with dynamic programming alignment to detect structural similarities in the twilight-zone},
journal = {Bioinformatics},
year = {2024},
volume = {40},
number = {1},
doi = {10.1093/bioinformatics/btad786}
}
EUVIMED