BBL-GAT: A Novel Method for Drug-Drug Interaction Extraction From Biomedical Literature

被引:1
|
作者
Jia, Yaxun [1 ]
Yuan, Zhu [2 ]
Wang, Haoyang [3 ]
Gong, Yunchao [3 ,4 ]
Yang, Haixiang [5 ]
Xiang, Zuo-Lin [1 ,6 ]
机构
[1] Tongji Univ, Shanghai East Hosp, Sch Med, Dept Radiat Oncol, Shanghai 200120, Peoples R China
[2] Natl Police Univ Criminal Justice, Dept Informat Management, Baoding 071000, Peoples R China
[3] Beijing Informat Sci & Technol Univ, Beijing Key Lab Internet Culture & Digital Dissemi, Beijing 100101, Peoples R China
[4] Qinghai Normal Univ, Comp Coll, Xining 810008, Peoples R China
[5] Minist Publ Secur, Big Data Ctr, Beijing 100070, Peoples R China
[6] Shanghai East Hosp Jian Hosp, Dept Radiat Oncol, Jian, Peoples R China
来源
IEEE ACCESS | 2024年 / 12卷
基金
中国国家自然科学基金;
关键词
Long short term memory; Drugs; Biological system modeling; Feature extraction; Recurrent neural networks; Semantics; Attention mechanisms; Deep learning; BiLSTM; Drug-drug interactions; deep learning; BioBERT; GAT;
D O I
10.1109/ACCESS.2024.3462101
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
The identification of Drug-Drug Interactions (DDIs) is crucial for optimizing patient treatment and avoiding adverse reactions. With the rapid growth of biomedical literature, manual screening for DDIs has become impractical. Hence, the demand for automated DDI extraction methods is continuously increasing. Currently, although many methods have been proposed, feature supplementation and the latest GCN-based methods still face the problem of being unable to effectively extract key information. In this paper, we propose BBL-GAT, a novel method combining BioBERT-BiLSTM and Graph Attention Network (GAT), to extract DDIs from biomedical literature. BioBERT is employed for its ability to capture the semantic relationships between complex medical terms and drug names. BiLSTM is utilized to handle bidirectional contextual information, which is essential for understanding the context of drug-disease relationships. GAT dynamically learns the significance of drug nodes in different interactions through attention mechanisms, enhancing the precision of relationship extraction. We evaluated BBL-GAT on the DDI Extraction 2013 dataset and compared it with other popular DDI extraction methods. The experimental results demonstrate that BBL-GAT achieves an precision of 81.76%, a recall of 84.38%, and an F1-score of 82.47%, illustrating its effectiveness and superiority in DDI relationship extraction tasks.
引用
收藏
页码:134167 / 134184
页数:18
相关论文
共 50 条
  • [21] Extraction of drug-drug interaction using neural embedding
    Hou, Wen Juan
    Ceesay, Bamfa
    JOURNAL OF BIOINFORMATICS AND COMPUTATIONAL BIOLOGY, 2018, 16 (06)
  • [22] Drug-drug Interaction Extraction Combining Semantics and Dependency
    Luo, Xi
    Zeng, Zhiying
    Wang, Jianxin
    An, Ying
    Hunan Daxue Xuebao/Journal of Hunan University Natural Sciences, 2022, 49 (06): : 90 - 100
  • [23] NAFCILLIN AND METHADONE: A NOVEL DRUG-DRUG INTERACTION
    Poorman, Elisabeth
    Parent, Bryce
    Baker, Sarah
    Bhatraju, Elenor
    JOURNAL OF GENERAL INTERNAL MEDICINE, 2021, 36 (SUPPL 1) : S248 - S248
  • [24] Phenelzine and Morphine Drug-Drug Interaction? A Literature Review
    Beechinor, Ryan J.
    Tyson, Rachel
    Roth, Mary E.
    JOURNAL OF PHARMACY PRACTICE, 2021, 34 (05) : 818 - 823
  • [25] A novel algorithm for analyzing drug-drug interactions from MEDLINE literature
    Yin Lu
    Dan Shen
    Maxwell Pietsch
    Chetan Nagar
    Zayd Fadli
    Hong Huang
    Yi-Cheng Tu
    Feng Cheng
    Scientific Reports, 5
  • [26] A novel algorithm for analyzing drug-drug interactions from MEDLINE literature
    Lu, Yin
    Shen, Dan
    Pietsch, Maxwell
    Nagar, Chetan
    Fadli, Zayd
    Huang, Hong
    Tu, Yi-Cheng
    Cheng, Feng
    SCIENTIFIC REPORTS, 2015, 5
  • [27] Enhancing Drug-Drug Interaction Extraction from Texts by Molecular Structure Information
    Asada, Masaki
    Miwa, Makoto
    Sasaki, Yutaka
    PROCEEDINGS OF THE 56TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, VOL 2, 2018, : 680 - 685
  • [28] Extracting drug-drug interactions from biomedical texts
    Isabel Segura-Bedmar
    Paloma Martínez
    César de Pablo-Sánchez
    BMC Bioinformatics, 11
  • [29] Extracting drug-drug interactions from biomedical texts
    Segura-Bedmar, Isabel
    Martinez, Paloma
    de Pablo-Sanchez, Cesar
    BMC BIOINFORMATICS, 2010, 11
  • [30] Novel method for the prediction of drug-drug Interaction based on gene expression profiles
    Taguchi, Yh.
    Turki, Turki
    EUROPEAN JOURNAL OF PHARMACEUTICAL SCIENCES, 2021, 160