Identification of drug-target interaction by a random walk with restart method on an interactome network.
Identification of drug-target interaction by a random walk with restart method on an interactome network.
复制标题
DOI：
10.1186/s12859-018-2199-x
复制
发表时间：
2018-06-13
影响因子：
3
通讯作者：
Nam H
中科院分区：
文献类型：
--
作者：
Lee I;Nam H
药物-靶标相互作用的鉴定在药物发现中起着关键作用。然而，通过体外、体内实验确定药物靶标相互作用是非常费力、耗时的。因此，使用计算方法预测药物-靶标相互作用是一个很好的选择。在最近的研究中，许多基于特征和基于相似性的机器学习方法在药物-靶标相互作用预测中显示出有希望的结果。先前的一项研究表明，考虑药物-药物和蛋白质-蛋白质相互作用的连通性信息，可以提高“联想内疚”概念的预测效果。然而，只考虑直连节点的方法往往会忽略从距离节点中获得的信息。因此，在本研究中，我们使用带重启的随机行走算法生成全局网络拓扑信息，并将全局拓扑信息应用于预测模型。因此，我们的预测模型与“关联负罪感”方法相比显示出更高的预测性能（训练和独立测试的AUC分别为0.89和0.67）。此外，我们还展示了通过随机漫步重新启动加权特征如何比原始特征产生更好的性能。此外，我们证实了在相互作用组网络上具有高度连通性的药物和蛋白质在我们的模型中产生更好的性能。考虑全局网络拓扑的加权特征预测模型与非加权模型和先前的“关联负罪感法”相比，在训练和测试中都提高了预测性能。综上所述，全局网络拓扑信息对蛋白质-蛋白质相互作用和药物-药物相互作用的预测性能有影响。本文的在线版本（10.1186/s12859-018-2199-x）包含补充材料，授权用户可以使用。
Identification of drug-target interactions acts as a key role in drug discovery. However, identifying drug-target interactions via in-vitro, in-vivo experiments are very laborious, time-consuming. Thus, predicting drug-target interactions by using computational approaches is a good alternative. In recent studies, many feature-based and similarity-based machine learning approaches have shown promising results in drug-target interaction predictions. A previous study showed that accounting connectivity information of drug-drug and protein-protein interactions increase performances of prediction by the concept of ‘guilt-by-association’. However, the approach that only considers directly connected nodes often misses the information that could be derived from distance nodes. Therefore, in this study, we yield global network topology information by using a random walk with restart algorithm and apply the global topology information to the prediction model. As a result, our prediction model demonstrates increased prediction performance compare to the ‘guilt-by-association’ approach (AUC 0.89 and 0.67 in the training and independent test, respectively). In addition, we show how weighted features by a random walk with restart yields better performances than original features. Also, we confirmed that drugs and proteins that have high-degree of connectivity on the interactome network yield better performance in our model. The prediction models with weighted features by considering global network topology increased the prediction performances both in the training and testing compared to non-weighted models and previous a ‘guilt-by-association method’. In conclusion, global network topology information on protein-protein interaction and drug-drug interaction effects to the prediction performance of drug-target interactions. The online version of this article (10.1186/s12859-018-2199-x) contains supplementary material, which is available to authorized users.
登录
查看更多内容
DOI：
10.1093/bioinformatics/btn162
发表时间：
2008-07-01
期刊：
Bioinformatics (Oxford, England)
影响因子：
--
作者：
Yamanishi Y;Araki M;Gutteridge A;Honda W;Kanehisa M
通讯作者：
Kanehisa M
DOI：
10.1023/a:1010967008838
发表时间：
2001-04-01
期刊：
JOURNAL OF PROTEIN CHEMISTRY
影响因子：
--
作者：
Lin, Z;Pan, XM
通讯作者：
Pan, XM
DOI：
10.1073/pnas.92.19.8700
发表时间：
1995-09-12
影响因子：
11.1
作者：
DUBCHAK, I;MUCHNIK, I;KIM, SH
通讯作者：
KIM, SH
影响因子：
4.3
作者：
Schaefer MH;Lopes TJ;Mah N;Shoemaker JE;Matsuoka Y;Fontaine JF;Louis-Jeune C;Eisfeld AJ;Neumann G;Perez-Iratxeta C;Kawaoka Y;Kitano H;Andrade-Navarro MA
通讯作者：
Andrade-Navarro MA
影响因子：
14.9
作者：
Wang Y;Bryant SH;Cheng T;Wang J;Gindulyte A;Shoemaker BA;Thiessen PA;He S;Zhang J
通讯作者：
Zhang J