Big Data Innovation and Entrepreneurship Education Center of Hunan Province, Changsha University, Changsha, 410022, China.
Sci Rep. 2024 Sep 6;14(1):20847. doi: 10.1038/s41598-024-71837-x.
Microbes have been demonstrated to be closely linked to diseases that pose a major threat to human health. Computing technologies can help researchers find potential microbe-drug associations more quickly and precisely. In this study, we introduced a novel computational prediction model called GLNNMDA based on global and local features of microbes and drugs to infer possible microbe-drug correlations. In GLNNMDA, we first constructed a heterogeneous network based on known microbe-drug relationships by integrating multiple similarity metrics of drugs and microbes. Subsequently, low-dimensional features will be extracted for nodes in the heterogeneous network by adopting the graph attention encoder. Next, based on combining these low-dimensional features with multiple properties of microbes and drugs to form a new comprehensive feature matrix, we would utilize the GLF module to extract the global and local features for microbes and drugs respectively, and then, we would further fuse these global and local features to come up with predictions of possible microbe-drug associations. Moreover, in order to evaluate the prediction performance of GLNNMDA, under the framework of fivefold cross-validation, intensive comparative experiments and case studies were done on different well-known public databases. The results showed that GLNNMDA obtained the highest AUC values as well as AUPR values of 0.9802 ± 0.0011, 0.9773 ± 0.0021 and 0.8586 ± 0.0004, 0.8008 ± 0.0031 in the two databases, MDAD and aBiofilm, respectively, compared to the state-of-the-art competing prediction methods. In addition, case studies of well-known microorganisms and drugs have demonstrated the effectiveness of GLNNMDA in inferring potential microbial drug associations, which implies that GLNNMDA may be a useful tool for microbe-drug association prediction in the future. The source code is available at: " https://github.com/KuangHaiYue/GLNNMDA.git ".
微生物与对人类健康构成重大威胁的疾病密切相关。计算技术可以帮助研究人员更快、更准确地发现潜在的微生物-药物关联。在这项研究中，我们引入了一种名为 GLNNMDA 的新型计算预测模型，该模型基于微生物和药物的全局和局部特征来推断可能的微生物-药物相关性。在 GLNNMDA 中，我们首先通过整合药物和微生物的多种相似性度量，基于已知的微生物-药物关系构建了一个异构网络。随后，通过采用图注意编码器，对异构网络中的节点提取低维特征。接下来，基于结合这些低维特征和微生物和药物的多种特性，形成新的综合特征矩阵，我们将利用 GLF 模块分别提取微生物和药物的全局和局部特征，然后，进一步融合这些全局和局部特征，得出可能的微生物-药物关联的预测。此外，为了评估 GLNNMDA 的预测性能，在五重交叉验证的框架下，我们在不同的知名公共数据库上进行了密集的对比实验和案例研究。结果表明，与最先进的竞争预测方法相比，GLNNMDA 在 MDAD 和 aBiofilm 两个数据库中分别获得了最高的 AUC 值和 AUPR 值，分别为 0.9802±0.0011、0.9773±0.0021 和 0.8586±0.0004、0.8008±0.0031。此外，对知名微生物和药物的案例研究表明，GLNNMDA 在推断潜在微生物药物关联方面是有效的，这意味着 GLNNMDA 可能成为未来微生物-药物关联预测的有用工具。源代码可在“https://github.com/KuangHaiYue/GLNNMDA.git”获取。
