Li Haitao, Chu Yuanyuan, Jiang Liyuan, Li Lei, Lv GuoDong, Liu Yuansheng, Zheng Chunhou, Su Yansen
Key Laboratory of Intelligent Computing and Signal Processing, School of Artificial Intelligence, Anhui University, Hefei, China.
Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, Hefei, Anhui, China.
Front Genet. 2025 Jan 6;15:1465368. doi: 10.3389/fgene.2024.1465368. eCollection 2024.
Echinococcosis is a zoonotic parasitic disease caused by the larvae of echinococcus tapeworms infesting the human body. Drug combination therapy is highly valued for the treatment of echinococcosis because of its potential to overcome resistance and enhance the response to existing drugs. Traditional methods of identifying drug combinations via biological experimentation is costly and time-consuming. Besides, the scarcity of existing drug combinations for echinococcosis hinders the development of computational methods. In this study, we propose a transfer learning-based model, namely TransferBAN-Syn, to identify synergistic drug combinations against echinococcosis based on abundant information of drug combinations against parasitic diseases. To the best of our knowledge, this is the first work that leverages transfer learning to improve prediction accuracy with limited drug combination data in echinococcosis treatment. Specifically, TransferBAN-Syn contains a drug interaction feature representation module, a disease feature representation module, and a prediction module, where the bilinear attention network is employed in the drug interaction feature representation module to deeply extract the fusion feature of drug combinations. Besides, we construct a special dataset with multi-source information and drug combinations for parasitic diseases, including 21 parasitic diseases and echinococcosis. TransferBAN-Syn is designed and initially trained on the abundant data from the 21 parasitic diseases, which serves as the source domain. The parameters in the feature representation modules of drug interactions and diseases are preserved from this source domain, and those in the prediction module are then fine-tuned to specifically identify the synergistic drug combinations for echinococcosis in the target domain. Comparison experiments have shown that TransferBAN-Syn not only improves the accuracy of predicting echinococcosis drug combinations but also enhances generalizability. Furthermore, TransferBAN-Syn identifies potential drug combinations that hold promise in the treatment of echinococcosis. TransferBAN-Syn not only offers new synergistic drug combinations for echinococcosis but also provides a novel approach for predicting potential drug pairs for diseases with limited combination data.
棘球蚴病是一种人畜共患的寄生虫病，由棘球绦虫的幼虫侵染人体引起。药物联合疗法因具有克服耐药性和增强对现有药物反应的潜力，在棘球蚴病治疗中备受重视。通过生物实验识别药物组合的传统方法成本高且耗时。此外，现有的棘球蚴病药物组合稀缺，阻碍了计算方法的发展。在本研究中，我们提出了一种基于迁移学习的模型，即TransferBAN-Syn，以基于针对寄生虫病的丰富药物组合信息，识别针对棘球蚴病的协同药物组合。据我们所知，这是第一项利用迁移学习在棘球蚴病治疗中有限的药物组合数据提高预测准确性的工作。具体而言，TransferBAN-Syn包含一个药物相互作用特征表示模块、一个疾病特征表示模块和一个预测模块，其中在药物相互作用特征表示模块中采用双线性注意力网络来深度提取药物组合的融合特征。此外，我们构建了一个包含多源信息和寄生虫病药物组合的特殊数据集，包括21种寄生虫病和棘球蚴病。TransferBAN-Syn在来自21种寄生虫病的丰富数据上进行设计和初步训练，该数据作为源域。药物相互作用和疾病的特征表示模块中的参数从该源域保留，然后对预测模块中的参数进行微调，以具体识别目标域中针对棘球蚴病的协同药物组合。比较实验表明，TransferBAN-Syn不仅提高了预测棘球蚴病药物组合的准确性，还增强了泛化能力。此外，TransferBAN-Syn识别出在棘球蚴病治疗中具有潜力的潜在药物组合。TransferBAN-Syn不仅为棘球蚴病提供了新的协同药物组合，还为预测组合数据有限的疾病的潜在药物对提供了一种新方法。
