Skip to main content

ORIGINAL RESEARCH article

Front. Drug Discov.
Sec. In silico Methods and Artificial Intelligence for Drug Discovery
Volume 4 - 2024 | doi: 10.3389/fddsv.2024.1460672
This article is part of the Research Topic Pharmacokinetics Modeling in the Artificial Intelligence Era View all 3 articles

Drug-Drug Interaction Extraction based on Multimodal Feature Fusion by Transformer and BiGRU

Provisionally accepted
Changqing Yu Changqing Yu *Shanwen Zhang Shanwen Zhang Xuqi Wang Xuqi Wang Tailong Shi Tailong Shi Chen Jiang Chen Jiang Sizhe Liang Sizhe Liang Guanghao Ma Guanghao Ma
  • Xijing University, Xi'an, Shaanxi Province, China

The final, formatted version of the article will be published soon.

    Understanding drug-drug interactions (DDIs) play a vital role in the fields of drug disease treatment, drug development, preventing medical error, and controlling health care-cost. Extracting potential from biomedical corpora is a major complement to the existing DDIs. Most of the existing DDI extraction (DDIE) methods do not consider the graph and structure of drug molecular, which can improve the performance of DDIE. Considering the different advantages of Bi-directional Gated Recurrent Unit (BiGRU), Transformer and attention mechanism in DDIE task, a multimodal feature fusion model by combining BiGRU and Transformer (BiGGT) is constructed for DDIE. In BiGGT, the vector embeddings of medical corpora, drug molecule topology graph and structure are conducted by Word2vec, Mol2vec and GCN, respectively, BiGRU and multi-head self-attention (MHSA) are integrated into Transformer to extract the local-global contextual DDIE features, which is important for DDIE. The extensive experiment results on the DDIExtraction 2013 shared task dataset show that the BiGGT based DDIE method outperforms the state-of-the-art DDIE approaches with precision of 78.22%. BiGGT expands the application of multimodal deep learning in the field of multimodal DDIE.

    Keywords: Drug-drug interaction (DDI)1, DDI extraction (DDIE)2, Graph Convolutional Networks (GCN)3, transformer4, Multimodal feature fusion (MMFF)5

    Received: 06 Jul 2024; Accepted: 08 Oct 2024.

    Copyright: © 2024 Yu, Zhang, Wang, Shi, Jiang, Liang and Ma. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.

    * Correspondence: Changqing Yu, Xijing University, Xi'an, Shaanxi Province, China

    Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.