Predicting drug-target interactions using probabilistic matrix factorization.

Predicting drug-target interactions using probabilistic matrix factorization.
复制标题

DOI:
10.1021/ci400219z
复制
发表时间:
2013-12-23
影响因子:
5.6
通讯作者:
Bahar I
Bahar I
中科院分区:
化学2区
文献类型:
--
作者:
Cobanoglu MC;Liu C;Hu F;Oltvai ZN;Bahar I

文献摘要

参考文献

被引文献

相似文献

近年来,对已知药物-靶标相互作用的定量分析成为药物再利用和评估副作用的有用方法。在本研究中,我们提出了一种方法,使用概率矩阵分解(PMF)为此目的,这是特别有用的分析大型互动网络。基于PMF潜在变量聚类的DrugBank药物即使在缺乏3D形状相似性的情况下也显示出表型相似性。基准计算表明,该方法优于那些最近推出的已知的相互作用的输入数据集是足够大的酶和离子通道的情况下,但不是G-蛋白偶联受体(GPCR)和核受体。在隐藏了70%的已知交互后,在DrugBank上进行的测试显示,平均而言,前100个预测中有88个命中了隐藏的交互。从头预测使我们能够识别新的潜在相互作用。涉及神经生物学疾病的药物-靶点对在从头预测中占主导地位。
Quantitative analysis of known drug–target interactions emerged in recent years as a useful approach for drug repurposing and assessing side effects. In the present study, we present a method that uses probabilistic matrix factorization (PMF) for this purpose, which is particularly useful for analyzing large interaction networks. DrugBank drugs clustered based on PMF latent variables show phenotypic similarity even in the absence of 3D shape similarity. Benchmarking computations show that the method outperforms those recently introduced provided that the input data set of known interactions is sufficiently large—which is the case for enzymes and ion channels, but not for G-protein coupled receptors (GPCRs) and nuclear receptors. Runs performed on DrugBank after hiding 70% of known interactions show that, on average, 88 of the top 100 predictions hit the hidden interactions. De novo predictions permit us to identify new potential interactions. Drug–target pairs implicated in neurobiological disorders are overrepresented among de novo predictions.
DOI: 10.1126/science.1150021
发表时间: 2008-04-18
期刊: SCIENCE
影响因子: 56.9
作者:
Hillenmeyer, Maureen E.;Fung, Eula;Giaever, Guri
通讯作者: Giaever, Guri
DOI: 10.1016/j.sbi.2006.01.013
发表时间: 2006-02-01
影响因子: 6.8
作者:
Hopkins, AL;Mason, JS;Overington, JP
通讯作者: Overington, JP
DOI: 10.1371/journal.pcbi.1000423
发表时间: 2009-07
影响因子: 4.3
作者:
Kinnings SL;Liu N;Buchmeier N;Tonge PJ;Xie L;Bourne PE
通讯作者: Bourne PE
DOI: 10.1021/ci200192v
发表时间: 2011-09-26
影响因子: 5.6
作者:
Cheng T;Li Q;Wang Y;Bryant SH
通讯作者: Bryant SH
DOI: 10.1021/ct300117j
发表时间: 2012-07-10
影响因子: 5.5
作者:
Bakan, Ahmet;Nevins, Neysa;Lakdawala, Ami S.;Bahar, Ivet
通讯作者: Bahar, Ivet