EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Drug-drug interaction classification via domain-adapted transformers leveraging textual features

BELKIS BÜYÜKPATPAT, BEGÜM MUTLU, EBRU AKÇAPINAR SEZER

Turkish Journal of Electrical Engineering and Computer Sciences · 13.11.2026 · 34 (6) · 1037-1053

DOI: 10.55730/1300-0632.4288 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Turkish Journal of Electrical Engineering and Computer Sciences, online erschienen am 13.11.2026. Verfasst von BELKIS BÜYÜKPATPAT und 2 weiteren Autor:innen. Die Arbeit nennt 27 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Drug-drug interaction (DDI) classification is a critical task for ensuring drug safety and supporting clinical decision-making, particularly in polypharmacy scenarios. Most existing DDI classification approaches were found to rely primarily on chemical and biological representations of drugs, whereas the potential of drug-related textual information remained comparatively underexplored. In this study, the effectiveness of using only textual features for DDI classification was investigated. To this end, drug textual features, including descriptions, indications, mechanisms, and pharmacodynamic information, were retrieved from DrugBank for two benchmark datasets, namely DDIMDL and MDF-SA-DDI. The textual features of each interacting drug pair were combined into a single sequence using special tokens, and the resulting sequence was used as input to transformer-based models, including BERT, BioBERT, UmlsBERT, and SAPBERT, enabling joint contextual modeling of information from both drugs. A systematic evaluation of general-purpose and domain-adapted transformer models for text-based DDI classification was conducted, with particular emphasis placed on UmlsBERT and SAPBERT, which incorporate biomedical knowledge from the Unified Medical Language System. Experimental results demonstrated that the domain-adapted SAPBERT model consistently achieved superior performance across both datasets, especially when description and mechanism features were leveraged, whereas the general-purpose BERT model yielded the lowest performance. On the DDIMDL dataset, SAPBERT was observed to outperform previously reported results based on alternative drug representations, while on the MDF-SA-DDI dataset, performance comparable to state-of-the-art methods was achieved, with an approximate 3% difference in F-score. Overall, the findings showed that competitive DDI classification performance could be achieved using textual features alone and that the use of domain-adapted language models positively contributed to capturing clinically relevant drug semantics.

Zitieren

APA

BÜYÜKPATPAT, B., MUTLU, B., & SEZER, E. A. (2026). Drug-drug interaction classification via domain-adapted transformers leveraging textual features. Turkish Journal of Electrical Engineering and Computer Sciences, 34(6), 1037-1053. https://doi.org/10.55730/1300-0632.4288

Vancouver

BÜYÜKPATPAT B, MUTLU B, SEZER EA. Drug-drug interaction classification via domain-adapted transformers leveraging textual features. Turkish Journal of Electrical Engineering and Computer Sciences. 2026;34(6):1037-1053. doi:10.55730/1300-0632.4288

BibTeX
@article{BYKPATPAT2026,
  author = {BÜYÜKPATPAT, BELKIS and MUTLU, BEGÜM and SEZER, EBRU AKÇAPINAR},
  title = {Drug-drug interaction classification via domain-adapted transformers leveraging textual features},
  journal = {Turkish Journal of Electrical Engineering and Computer Sciences},
  year = {2026},
  volume = {34},
  number = {6},
  pages = {1037--1053},
  doi = {10.55730/1300-0632.4288}
}
Kostenlos starten →