MDDI-SCL: predicting multi-type drug-drug interactions via supervised contrastive learning.

MDDI-SCL: predicting multi-type drug-drug interactions via supervised contrastive learning.
复制标题

mdi - scl:通过监督对比学习预测多类型药物-药物相互作用。

DOI:
10.1186/s13321-022-00659-8
复制
发表时间:
2022-11-15
影响因子:
8.6
通讯作者:
--
中科院分区:
化学2区
文献类型:
--
作者:

文献摘要

参考文献

被引文献

相似文献

多种药物联合使用可能引起非预期的药物相互作用(DDI),给患者带来不良后果。准确识别DDI类型不仅可以为避免这些意外事件提供提示,还可以通过DDI如何发生来阐述其潜在机制。已经提出了几种计算方法用于多类型DDI预测,但预测性能仍有改进的空间。在这项研究中,我们提出了一个监督的对比学习的方法,MDDI-SCL,实现了三个级别的损失函数,预测多类型的DDI。MDDI-SCL主要由三个模块组成:药物特征编码与均方误差损失模块、药物潜在特征融合与监督对比损失模块、多类型DDI预测与分类损失模块。药物特征编码器和均方误差损失模块使用自注意机制和自动编码器来学习药物级潜在特征。药物潜在特征融合和监督对比损失模块使用多尺度特征融合来学习药物对级别的潜在特征。预测和分类损失模块预测每个药物对的DDI类型。我们评估MDDI-SCL在两个数据集的三个不同的任务。实验结果表明,MDDI-SCL实现更好的或相当的性能,作为国家的最先进的方法。通过消融实验验证了监督对比学习的有效性,并通过案例分析验证了MDDI-SCL的可行性。源代码可在https://github.com/ShenggengLin/MDDI-SCL上获得。在线版本包含补充材料,可通过10.1186/s13321-022-00659-8获取。
The joint use of multiple drugs may cause unintended drug-drug interactions (DDIs) and result in adverse consequence to the patients. Accurate identification of DDI types can not only provide hints to avoid these accidental events, but also elaborate the underlying mechanisms by how DDIs occur. Several computational methods have been proposed for multi-type DDI prediction, but room remains for improvement in prediction performance. In this study, we propose a supervised contrastive learning based method, MDDI-SCL, implemented by three-level loss functions, to predict multi-type DDIs. MDDI-SCL is mainly composed of three modules: drug feature encoder and mean squared error loss module, drug latent feature fusion and supervised contrastive loss module, multi-type DDI prediction and classification loss module. The drug feature encoder and mean squared error loss module uses self-attention mechanism and autoencoder to learn drug-level latent features. The drug latent feature fusion and supervised contrastive loss module uses multi-scale feature fusion to learn drug pair-level latent features. The prediction and classification loss module predicts DDI types of each drug pair. We evaluate MDDI-SCL on three different tasks of two datasets. Experimental results demonstrate that MDDI-SCL achieves better or comparable performance as the state-of-the-art methods. Furthermore, the effectiveness of supervised contrastive learning is validated by ablation experiment, and the feasibility of MDDI-SCL is supported by case studies. The source codes are available at https://github.com/ShenggengLin/MDDI-SCL. The online version contains supplementary material available at 10.1186/s13321-022-00659-8.
DOI: 10.1038/s42256-022-00459-7
发表时间: 2022-03-01
影响因子: 23.8
作者:
Chu, Yanyi;Zhang, Yan;Wei, Dong-Qing
通讯作者: Wei, Dong-Qing
DOI: 10.1136/amiajnl-2013-002512
发表时间: 2014-10-01
影响因子: 6.4
作者:
Cheng, Feixiong;Zhao, Zhongming
通讯作者: Zhao, Zhongming
DOI: 10.1109/tpami.2018.2858826
发表时间: 2020-02-01
影响因子: 23.6
作者:
Lin, Tsung-Yi;Goyal, Priya;Dollar, Piotr
通讯作者: Dollar, Piotr
DOI: 10.1093/bib/bbab421
发表时间: 2022-01-17
影响因子: 9.5
作者:
Lin, Shenggeng;Wang, Yanjing;Wei, Dong-Qing
通讯作者: Wei, Dong-Qing
DOI: 10.1093/bioinformatics/btaa775
发表时间: 2021-02-15
期刊: BIOINFORMATICS
影响因子: 5.8
作者:
Hu, Lun;Zhang, Jun;You, Zhu-Hong
通讯作者: You, Zhu-Hong