EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

DeepKOALA: a scalable deep learning framework for KEGG Orthology assignment

Zhaoxi Yu iD, Lingjie Meng iD, Canh Hao Nguyen, Hiroshi Mamitsuka, Minoru Kanehisa iD, Hiroyuki Ogata iD

Briefings in Bioinformatics · 03.07.2026 · 27 (4)

DOI: 10.1093/bib/bbag445 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Briefings in Bioinformatics, online erschienen am 19.08.2026. Verfasst von Zhaoxi Yu und 5 weiteren Autor:innen. Beteiligte Einrichtung: Bioinformatics Center, Institute for Chemical Research, Kyoto University, Gokasho, Uji, 611-0011, Japan. Hauptthemen laut MEDLINE: Deep Learning, Molecular Sequence Annotation, Computational Biology, Software. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 32 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: JSPS, SuperComputer System, Institute for Chemical Research.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The KEGG Orthology (KO) system links DNA and protein sequences to biological functions and pathways, providing a curated, fundamental, and consistent annotation framework across all domains of life. While accurate, traditional sequence alignment-based annotation methods are computationally expensive, which severely limits their application in large-scale datasets. To address this challenge, we introduce Deep KEGG Orthology and Links Annotation (DeepKOALA), a deep learning approach based on Gated Recurrent Units (GRU), which frames KO annotation as an open-set recognition task. This design reduces false positives arising from out-of-scope sequences and, together with a lightweight GRU backbone, enables high-throughput annotation. The GRU-based model was benchmarked against four other deep learning architectures and showed the best balance between speed and accuracy. We then trained a GRU-based model, DeepKOALA, and performed a cross-species evaluation against existing KO annotation tools. In this comparison, DeepKOALA achieved a F1 of 83.37%, which is comparable to existing alignment-based tools. Meanwhile, the speed of DeepKOALA was 36.5-fold faster than Blast KEGG Orthology and Links Annotation (BlastKOALA). We also provide a specialized fragment model for handling incomplete sequences and an optional multi-domain mode. Together, these features make DeepKOALA a scalable and efficient option for high-throughput function annotation.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningMolecular Sequence AnnotationComputational BiologySoftwareSequence AlignmentAlgorithms

Stichwörter der Autor:innen

KEGG Orthologydeep learningmetagenomicsprotein function annotation

Autor:innen und Institutionen

  • Bioinformatics Center, Institute for Chemical Research, Kyoto University, Gokasho, Uji, 611-0011, Japan.

ORCID-Profile: Zhaoxi Yu, Lingjie Meng, Minoru Kanehisa, Hiroyuki Ogata

Förderung

  • JSPS
  • SuperComputer System
  • Institute for Chemical Research
  • Kyoto University

Zitieren

APA

Yu, Z., Meng, L., Nguyen, C. H., Mamitsuka, H., Kanehisa, M., & Ogata, H. (2026). DeepKOALA: a scalable deep learning framework for KEGG Orthology assignment. Briefings in Bioinformatics, 27(4). https://doi.org/10.1093/bib/bbag445

Vancouver

Yu Z, Meng L, Nguyen CH, Mamitsuka H, Kanehisa M, Ogata H. DeepKOALA: a scalable deep learning framework for KEGG Orthology assignment. Briefings in Bioinformatics. 2026;27(4). doi:10.1093/bib/bbag445

BibTeX
@article{Yu2026,
  author = {Yu, Zhaoxi and Meng, Lingjie and Nguyen, Canh Hao and Mamitsuka, Hiroshi and Kanehisa, Minoru and Ogata, Hiroyuki},
  title = {DeepKOALA: a scalable deep learning framework for KEGG Orthology assignment},
  journal = {Briefings in Bioinformatics},
  year = {2026},
  volume = {27},
  number = {4},
  doi = {10.1093/bib/bbag445}
}
Kostenlos starten →