EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

POSA-GO: Fusion of Hierarchical Gene Ontology and Protein Language Models for Protein Function Prediction

Yubao Liu, Benrui Wang, Bocheng Yan iD, Haiyue Jiang, Yinfei Dai iD

International Journal of Molecular Sciences · 2025

DOI: 10.3390/ijms26136362 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Molecular Sciences, 2025. Verfasst von Yubao Liu und 4 weiteren Autor:innen. Beteiligte Einrichtung: College of Computer Science and Technology, Changchun University, Changchun 130012, China. Hauptthemen laut MEDLINE: Gene Ontology, Proteins, Computational Biology. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 52 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Protein function prediction plays a crucial role in uncovering the molecular mechanisms underlying life processes in the post-genomic era. However, with the widespread adoption of high-throughput sequencing technologies, the pace of protein function annotation significantly lags behind that of sequence discovery, highlighting the urgent need for more efficient and reliable predictive methods. To address the problem of existing methods ignoring the hierarchical structure of gene ontology terms and making it challenging to dynamically associate protein features with functional contexts, we propose a novel protein function prediction framework, termed Partial Order-Based Self-Attention for Gene Ontology (POSA-GO). This cross-modal collaborative modelling approach fuses GO terms with protein sequences. The model leverages the pre-trained language model ESM-2 to extract deep semantic features from protein sequences. Meanwhile, it transforms the partial order relationships among Gene Ontology (GO) terms into topological embeddings to capture their biological hierarchical dependencies. Furthermore, a multi-head self-attention mechanism is employed to dynamically model the association weights between proteins and GO terms, thereby enabling context-aware functional annotation. Comparative experiments on the CAFA3 and SwissProt datasets demonstrate that POSA-GO outperforms existing state-of-the-art methods in terms of Fmax and AUPR metrics, offering a promising solution for protein functional studies.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Gene OntologyProteinsComputational BiologyMolecular Sequence AnnotationDatabases, ProteinHumansSemantics

Stichwörter der Autor:innen

gene ontologymultiple self-attention mechanismsprotein function predictionprotein language model

Substanzen

Proteins

Autor:innen und Institutionen

  • College of Computer Science and Technology, Changchun University, Changchun 130012, China.
  • College of Computer Science and Technology, Jilin University, Changchun 130025, China.

ORCID-Profile: Bocheng Yan, Yinfei Dai

Zitieren

APA

Liu, Y., Wang, B., Yan, B., Jiang, H., & Dai, Y. (2025). POSA-GO: Fusion of Hierarchical Gene Ontology and Protein Language Models for Protein Function Prediction. International Journal of Molecular Sciences. https://doi.org/10.3390/ijms26136362

Vancouver

Liu Y, Wang B, Yan B, Jiang H, Dai Y. POSA-GO: Fusion of Hierarchical Gene Ontology and Protein Language Models for Protein Function Prediction. International Journal of Molecular Sciences. 2025. doi:10.3390/ijms26136362

BibTeX
@article{Liu2025,
  author = {Liu, Yubao and Wang, Benrui and Yan, Bocheng and Jiang, Haiyue and Dai, Yinfei},
  title = {POSA-GO: Fusion of Hierarchical Gene Ontology and Protein Language Models for Protein Function Prediction},
  journal = {International Journal of Molecular Sciences},
  year = {2025},
  doi = {10.3390/ijms26136362}
}
Kostenlos starten →