Predicting potential drug-drug interactions (DDIs) from biomedical data plays a critical role in drug therapy, drug development, drug regulation, and public health. However, it remains challenging due to the large number of possible drug combinations, and multimodal biomedical data, which is disorder, imbalanced, more prone to linguistic errors, and difficult to label. A Semantic Cross-Attention Transformer (SCAT) model is constructed to address the above challenge. In the model, BioBERT, Doc2Vec and graph convolutional network are utilized to embed the multimodal biomedical data into vector representation, BiGRU is adopted to capture contextual dependencies in both forward and backward directions, Cross-Attention is employed to integrate the extracted features and explicitly model dependencies between them, and a feature-joint classifier is adopted to implement DDI predication (DDIP). The experiment results on the DDIExtraction-2013 dataset demonstrate that SCAT outperforms the state-of-the-art DDIP approaches. SCAT expands the application of multimodal deep learning in the field of multimodal DDIP, and can be applied to drug regulation systems to predict novel DDIs and DDI-related events.

Keywords: DDI predication (DDIP); Drug-drug interaction (DDI); Multimodal feature fusion (MMFF); Semantic cross attention transformer (SCAT).

© 2025. The Author(s).

从生物医学数据中预测潜在的药物相互作用（DDI）在药物治疗、药物开发、药物监管和公共卫生方面起着关键作用。然而，由于可能的药物组合数量庞大以及多模态生物医学数据存在无序性、不平衡性、更易出现语言错误且难以标注等特点，这一任务仍然具有挑战性。为此构建了一个语义交叉注意力变换器（SCAT）模型来解决上述难题。在该模型中，BioBERT、Doc2Vec 和图卷积网络被用来将多模态生物医学数据嵌入到向量表示中；BiGRU 被采用以捕获前后双向上下文依赖性；交叉注意力用于整合提取的特征，并显式建模它们之间的依赖关系；一个特征联合分类器被采用来实现药物相互作用预测（DDIP）。在 DDIExtraction-2013 数据集上的实验结果表明，SCAT 超过了最先进的 DDIP 方法。SCAT 扩展了多模态深度学习在多模态 DDIP 领域的应用，并可以应用于药物监管系统以预测新的 DDI 和与 DDI 相关的事件。

关键词： 药物相互作用预测（DDIP）；药物相互作用（DDI）；多模态特征融合（MMFF）；语义交叉注意力变换器（SCAT）。

© 2025. 作者保留所有权利。