Supervised, semi-supervised and unsupervised inference of gene regulatory networks.

Supervised, semi-supervised and unsupervised inference of gene regulatory networks.
复制标题

DOI:
10.1093/bib/bbt034
复制
发表时间:
2014-03
影响因子:
9.5
通讯作者:
Ragan MA
Ragan MA
中科院分区:
生物学2区
文献类型:
--
作者:
Maetschke SR;Madhamshettiwar PB;Davis MJ;Ragan MA

文献摘要

参考文献

被引文献

相似文献

从表达数据推断基因调控网络是一项具有挑战性的任务。为此目的已经开发了许多方法,但缺乏涵盖无监督、半监督和监督方法的综合评估,并为其实际应用提供指导。我们对模拟和实验表达数据的推理方法进行了广泛的评估。结果表明,除了针对敲除数据的 Z-SCORE 方法外,无监督技术的预测精度较低。在所有其他情况下,监督方法实现了最高的准确度,即使在只有少量正样本的半监督环境中,也优于无监督技术。
Inference of gene regulatory network from expression data is a challenging task. Many methods have been developed to this purpose but a comprehensive evaluation that covers unsupervised, semi-supervised and supervised methods, and provides guidelines for their practical application, is lacking. We performed an extensive evaluation of inference methods on simulated and experimental expression data. The results reveal low prediction accuracies for unsupervised techniques with the notable exception of the Z-SCORE method on knockout data. In all other cases, the supervised approach achieved the highest accuracies and even in a semi-supervised setting with small numbers of only positive samples, outperformed the unsupervised techniques.
WGCNA:用于加权相关网络分析的 R 包。
DOI: 10.1186/1471-2105-9-559
发表时间: 2008-12-29
期刊: BMC bioinformatics
影响因子: 3
作者:
Langfelder P;Horvath S
通讯作者: Horvath S
DOI: 10.1186/1471-2105-9-461
发表时间: 2008-10-29
期刊: BMC BIOINFORMATICS
影响因子: 3
作者:
Meyer, Patrick E.;Lafitte, Frederic;Bontempi, Gianluca
通讯作者: Bontempi, Gianluca
DOI: 10.1196/annals.1407.006
发表时间: 2007-01-01
期刊: REVERSE ENGINEERING BIOLOGICAL NETWORKS
影响因子: --
作者:
Camacho, Diogo;Licona, Paola Vera;Laubenbacher, Reinhard
通讯作者: Laubenbacher, Reinhard
DOI: 10.1093/bioinformatics/btg313
发表时间: 2003-11-22
期刊: BIOINFORMATICS
影响因子: 5.8
作者:
Husmeier, D
通讯作者: Husmeier, D
DOI: 10.1038/msb.2012.56
发表时间: 2012-11-01
影响因子: 9.9
作者:
He, Feng;Chen, Hairong;Balling, Rudi
通讯作者: Balling, Rudi