EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

PlasGO: enhancing GO-based function prediction for plasmid-encoded proteins based on genetic structure

Yongxin Ji iD, Jiayu Shang iD, Jiaojiao Guan iD, Wei Zou iD, Herui Liao iD, Xubo Tang iD, Yanni Sun iD

GigaScience · 2024

DOI: 10.1093/gigascience/giae104 ↗

Kurz gefasst

Fachartikel in der Zeitschrift GigaScience, 2024. Verfasst von Yongxin Ji und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Electrical Engineering, City University of Hong Kong, Kowloon, Hong Kong SAR (HKG), China. Hauptthemen laut MEDLINE: Plasmids. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 64 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: University Grants Committee.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Plasmid, as a mobile genetic element, plays a pivotal role in facilitating the transfer of traits, such as antimicrobial resistance, among the bacterial community. Annotating plasmid-encoded proteins with the widely used Gene Ontology (GO) vocabulary is a fundamental step in various tasks, including plasmid mobility classification. However, GO prediction for plasmid-encoded proteins faces 2 major challenges: the high diversity of functions and the limited availability of high-quality GO annotations.

Results

In this study, we introduce PlasGO, a tool that leverages a hierarchical architecture to predict GO terms for plasmid proteins. PlasGO utilizes a powerful protein language model to learn the local context within protein sentences and a BERT model to capture the global context within plasmid sentences. Additionally, PlasGO allows users to control the precision by incorporating a self-attention confidence weighting mechanism. We rigorously evaluated PlasGO and benchmarked it against 7 state-of-the-art tools in a series of experiments. The experimental results collectively demonstrate that PlasGO has achieved commendable performance. PlasGO significantly expanded the annotations of the plasmid-encoded protein database by assigning high-confidence GO terms to over 95% of previously unannotated proteins, showcasing impressive precision of 0.8229, 0.7941, and 0.8870 for the 3 GO categories, respectively, as measured on the novel protein test set.

Conclusions

PlasGO, a hierarchical tool incorporating protein language models and BERT, significantly expanded plasmid protein annotations by predicting high-confidence GO terms. These annotations have been compiled into a database, which will serve as a valuable contribution to downstream plasmid analysis and research.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

PlasmidsGene OntologyComputational BiologyMolecular Sequence AnnotationSoftwareBacterial ProteinsDatabases, Protein

Stichwörter der Autor:innen

BERTGO term predictionplasmid protein functionprotein language model

Substanzen

Bacterial Proteins

Autor:innen und Institutionen

  • Department of Electrical Engineering, City University of Hong Kong, Kowloon, Hong Kong SAR (HKG), China.
  • Department of Information Engineering, The Chinese University of Hong Kong, Shatin, NT, Hong Kong SAR (HKG), China.

ORCID-Profile: Yongxin Ji, Jiayu Shang, Jiaojiao Guan, Wei Zou, Herui Liao, Xubo Tang, Yanni Sun

Förderung

  • University Grants Committee

Zitieren

APA

Ji, Y., Shang, J., Guan, J., Zou, W., Liao, H., Tang, X., & Sun, Y. (2024). PlasGO: enhancing GO-based function prediction for plasmid-encoded proteins based on genetic structure. GigaScience. https://doi.org/10.1093/gigascience/giae104

Vancouver

Ji Y, Shang J, Guan J, Zou W, Liao H, Tang X, et al. PlasGO: enhancing GO-based function prediction for plasmid-encoded proteins based on genetic structure. GigaScience. 2024. doi:10.1093/gigascience/giae104

BibTeX
@article{Ji2024,
  author = {Ji, Yongxin and Shang, Jiayu and Guan, Jiaojiao and Zou, Wei and Liao, Herui and Tang, Xubo and Sun, Yanni},
  title = {PlasGO: enhancing GO-based function prediction for plasmid-encoded proteins based on genetic structure},
  journal = {GigaScience},
  year = {2024},
  doi = {10.1093/gigascience/giae104}
}
Kostenlos starten →