EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Length-Adaptive LLM-Enhanced Method for Drug–Target Interaction Prediction

Hengli Zhao, Yongyi Zhang, Xinyu Tian, Yilin Chen, Wei Song

International Journal of Molecular Sciences · 12.07.2026 · 27 (14) · 6212

DOI: 10.3390/ijms27146212 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Molecular Sciences, online erschienen am 12.07.2026. Verfasst von Hengli Zhao und 4 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer Science and Artificial Intelligence, Zhengzhou University, No. 100, Science Avenue, Zhengzhou 450001, China. Hauptthemen laut MEDLINE: Proteins, Drug Discovery, Drug Repositioning. Die Arbeit nennt 49 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Key R&D Program of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Drug–target interaction (DTI) prediction is central to drug repurposing. Although existing methods integrate multi-dimensional features and have achieved certain progress, they rely heavily on molecular structure or graph structure information. This makes it difficult to capture complex biomedical semantic associations, leading to insufficient semantic information. To address this issue, this paper proposes BioLA-DTI, a large language model (LLM)-enhanced method for drug–target interaction prediction. The method leverages LLMs to provide semantic information for drugs and proteins. Furthermore, existing methods apply uniform weighting strategies to proteins with significantly different lengths. This introduces noise for short proteins and under-represents long ones. To tackle the feature imbalance problem caused by protein-length variation, this work designs a length-adaptive fusion module. This module dynamically weights the LLM-derived semantic features against structural features based on the actual protein-sequence length. Experiments on two benchmark datasets show that BioLA-DTI outperforms existing baseline methods across multiple evaluation metrics, particularly in cold-start scenarios. Case studies demonstrate that this model can provide valuable references for drug discovery. Ablation studies further confirm the critical roles of LLM enhancement and length adaptation modules.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

ProteinsDrug DiscoveryDrug RepositioningLarge Language ModelsHumansAlgorithms

Stichwörter der Autor:innen

deep learningdrug–target interactionlarge language modellength-adaptive fusionmulti-head attention

Substanzen

Proteins

Autor:innen und Institutionen

  • School of Computer Science and Artificial Intelligence, Zhengzhou University, No. 100, Science Avenue, Zhengzhou 450001, China.
  • National Supercomputing Center in Zhengzhou, Zhengzhou 450001, China.

Förderung

  • National Key R&D Program of China

Zitieren

APA

Zhao, H., Zhang, Y., Tian, X., Chen, Y., & Song, W. (2026). A Length-Adaptive LLM-Enhanced Method for Drug–Target Interaction Prediction. International Journal of Molecular Sciences, 27(14), 6212. https://doi.org/10.3390/ijms27146212

Vancouver

Zhao H, Zhang Y, Tian X, Chen Y, Song W. A Length-Adaptive LLM-Enhanced Method for Drug–Target Interaction Prediction. International Journal of Molecular Sciences. 2026;27(14):6212. doi:10.3390/ijms27146212

BibTeX
@article{Zhao2026,
  author = {Zhao, Hengli and Zhang, Yongyi and Tian, Xinyu and Chen, Yilin and Song, Wei},
  title = {A Length-Adaptive LLM-Enhanced Method for Drug–Target Interaction Prediction},
  journal = {International Journal of Molecular Sciences},
  year = {2026},
  volume = {27},
  number = {14},
  pages = {6212},
  doi = {10.3390/ijms27146212}
}
Kostenlos starten →