EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Squidly harnesses enzyme functional hierarchy and contrastive learning to efficiently predict catalytic residues from sequence

William J F Rieger iD, Mikael Bodén, Frances Arnold iD, Ariane Mora iD

eLife · 2026

DOI: 10.7554/elife.108186 ↗

Kurz gefasst

Fachartikel in der Zeitschrift eLife, 2026. Verfasst von William J F Rieger und 3 weiteren Autor:innen. Beteiligte Einrichtung: School of Chemistry and Molecular Biology, University of Queensland, Queensland, Australia. Hauptthemen laut MEDLINE: Enzymes, Machine Learning, Computational Biology. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 49 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Australian Government, Schmidt Science Fellows.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Enzymes present a sustainable alternative to traditional chemical industries, drug synthesis, and bioremediation applications. Because catalytic residues are the key amino acids that drive enzyme function, their accurate prediction facilitates enzyme function prediction. Sequence similarity-based approaches such as BLAST are fast but require previously annotated homologues. Machine-learning (ML) approaches aim to overcome this limitation; however, current gold-standard ML-based methods require high-quality 3D structures limiting their application to large datasets. To address these challenges, we developed Squidly, a sequence-only tool that leverages contrastive representation learning with a biology-informed, rationally designed pairing scheme to distinguish catalytic from non-catalytic residues using per-token Protein Language Model embeddings. Squidly surpasses state-of-the-art ML annotation methods in catalytic residue prediction while remaining sufficiently fast to enable wide-scale screening of databases. We ensemble Squidly with BLAST to provide an efficient tool that annotates catalytic residues with high precision and recall for both in- and out-of-distribution sequences.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

EnzymesMachine LearningComputational BiologyPrediction AlgorithmsCatalytic DomainPredictive Learning Models

Stichwörter der Autor:innen

biochemistrycatalytic residueschemical biologycomputational biologyenzymesmachine learningsystems biology

Substanzen

Enzymes

Autor:innen und Institutionen

  • School of Chemistry and Molecular Biology, University of Queensland, Queensland, Australia.
  • Division of Chemistry and Chemical Engineering, California Institute of Technology, Pasadena, United States.

ORCID-Profile: William J F Rieger, Frances Arnold, Ariane Mora

Förderung

  • Australian Government
  • Schmidt Science Fellows

Zitieren

APA

Rieger, W. J. F., Bodén, M., Arnold, F., & Mora, A. (2026). Squidly harnesses enzyme functional hierarchy and contrastive learning to efficiently predict catalytic residues from sequence. eLife. https://doi.org/10.7554/elife.108186

Vancouver

Rieger WJF, Bodén M, Arnold F, Mora A. Squidly harnesses enzyme functional hierarchy and contrastive learning to efficiently predict catalytic residues from sequence. eLife. 2026. doi:10.7554/elife.108186

BibTeX
@article{Rieger2026,
  author = {Rieger, William J F and Bodén, Mikael and Arnold, Frances and Mora, Ariane},
  title = {Squidly harnesses enzyme functional hierarchy and contrastive learning to efficiently predict catalytic residues from sequence},
  journal = {eLife},
  year = {2026},
  doi = {10.7554/elife.108186}
}
Kostenlos starten →