EUVIMEDEUVIMED entdecken
Crossref

HALO: Hybrid Attention Model for Subcellular Localization

Shafayat Ahmed, Nazifa Ahmed Moumi, Liqing Zhang

Biocomputing 2026 · 2025

DOI: 10.1142/9789819824755_0032 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Biocomputing 2026, 2025. Verfasst von Shafayat Ahmed und 2 weiteren Autor:innen. Beteiligte Einrichtung: Virginia Tech, Blacksburg, VA, USA, shafayatpiyal@vt.edu. Hauptthemen laut MEDLINE: Proteins. Gefördert von: National Science Foundation.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Subcellular localization prediction is critical for understanding protein functions and interactions, providing insights into cellular mechanisms and potential therapeutic targets. We propose HALO (Hybrid Attention model for subcellular LOcalization), a framework that integrates semantic embeddings from fine-tuned protein language models (e.g., ESM) with structural information derived from AlphaFold. HALO uses a graph attention network (GAT) to incorporate biochemical, structural, and sequence-derived features into a unified representation, while dynamically balancing their contributions. Crucially, the design allows HALO to operate in two modes: (i) a sequence-only mode, where predictions are made from the fine-tuned protein language model (PLM) when structural data are unavailable, and (ii) a hybrid mode, where structural adjacency and biochemical features complement PLM predictions, especially in low-confidence regions. We evaluate HALO on multiple datasets with minimal homology between training and test sets, where it achieves competitive performance across key metrics. By flexibly combining sequence-based and structure-informed predictions, HALO addresses the limitations of relying on a single modality and offers an adaptable framework for accurate and generalizable subcellular localization.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

ProteinsComputational BiologyGraph Neural NetworksDatabases, ProteinHumansAlgorithmsSemantics

Substanzen

Proteins

Autor:innen und Institutionen

  • Virginia Tech, Blacksburg, VA, USA, shafayatpiyal@vt.edu.
  • Virginia Tech, Blacksburg, VA, USA, moumi@vt.edu.
  • Virginia Tech, Blacksburg, VA, USA, lqzhang@vt.edu.

Förderung

  • National Science Foundation

Zitieren

APA

Ahmed, S., Moumi, N. A., & Zhang, L. (2025). HALO: Hybrid Attention Model for Subcellular Localization. Biocomputing 2026. https://doi.org/10.1142/9789819824755_0032

Vancouver

Ahmed S, Moumi NA, Zhang L. HALO: Hybrid Attention Model for Subcellular Localization. Biocomputing 2026. 2025. doi:10.1142/9789819824755_0032

BibTeX
@article{Ahmed2025,
  author = {Ahmed, Shafayat and Moumi, Nazifa Ahmed and Zhang, Liqing},
  title = {HALO: Hybrid Attention Model for Subcellular Localization},
  journal = {Biocomputing 2026},
  year = {2025},
  doi = {10.1142/9789819824755_0032}
}
Kostenlos starten →