Connectivity in the yeast cell cycle transcription network: inferences from neural networks.
Connectivity in the yeast cell cycle transcription network: inferences from neural networks.
复制标题
DOI：
10.1371/journal.pcbi.0020169
复制
发表时间：
2006-12-22
影响因子：
4.3
通讯作者：
Wold, Barbara J.
中科院分区：
文献类型：
--
作者：
Hart, Christopher E.;Mjolsness, Eric;Wold, Barbara J.
当前的挑战是开发基于多种类型的大规模功能基因组数据的计算方法来推断基因网络调控关系。我们发现单层前馈人工神经网络（ANN）模型通过整合体内蛋白质：DNA相互作用数据（ChIP/Array）和全基因组微阵列RNA数据，可以有效地发现基因网络结构。我们在酵母细胞周期转录网络上进行了测试，该网络由数百个具有阶段特异性RNA输出的基因组成。这些人工神经网络对数据中的噪声和各种扰动具有鲁棒性。他们在204个已知的12个主要细胞周期因子中，根据平方和权重指标，可靠地确定并排名了10个。多个酵母菌种之间基序出现的比较分析独立地证实了从ANN权重分析推断的关系。人工神经网络模型可以利用生物基因网络的特性，这是其他类型的模型所不能做到的。人工神经网络自然地利用了与特定表达输出相关的因子结合的缺失模式和存在模式；它们很容易受到计算机“突变”的影响，以揭示生物冗余；他们可以使用所有的因子绑定值。细胞周期人工神经网络的一个突出特征表明，生物网络中可能存在类似的特性。这一假设认为，当一个网络模块（G2）相对于其他模块和有丝分裂网络外的基因类别明显不支持调控连接（这里是MBF和靶基因之间的连接）时，就会发生“网络局部歧视”。如果正确的话，这预示着MBF基序将从受歧视的阶级中大量消失，并且歧视将在进化过程中持续存在。对远亲Schizosaccharomyces pombe的分析证实了这一点，表明网络局部歧视是真实存在的，并且补充了G1类基因中众所周知的MBF位点富集。当前的挑战是开发计算方法，通过整合多种类型的大规模功能基因组数据来推断基因网络调控关系。本文表明，采用一种新方法的简单人工神经网络（ANNs）在这方面做得很好。人工神经网络模型非常适合利用基因网络的自然属性，这是许多以前的方法所不能做到的。由此推断的转录因子和RNA输出模式之间的基因网络连接对大规模输入数据集中的噪声和RNA聚类输入的差异具有鲁棒性。这是通过使用酵母细胞周期基因网络作为测试案例来证明的。这个周期有多种类型的振荡rna， Hart、Mjolsness和Wold表明，人工神经网络识别出每个细胞周期阶段组的基因与已知和候选调节因子之间的关键联系。跨多个基因组的网络连通性比较分析显示，尽管在最大的进化距离上，特定的靶基因主要改变了身份，但基本的因子-输出关系具有很强的保守性。
A current challenge is to develop computational approaches to infer gene network regulatory relationships based on multiple types of large-scale functional genomic data. We find that single-layer feed-forward artificial neural network (ANN) models can effectively discover gene network structure by integrating global in vivo protein:DNA interaction data (ChIP/Array) with genome-wide microarray RNA data. We test this on the yeast cell cycle transcription network, which is composed of several hundred genes with phase-specific RNA outputs. These ANNs were robust to noise in data and to a variety of perturbations. They reliably identified and ranked 10 of 12 known major cell cycle factors at the top of a set of 204, based on a sum-of-squared weights metric. Comparative analysis of motif occurrences among multiple yeast species independently confirmed relationships inferred from ANN weights analysis. ANN models can capitalize on properties of biological gene networks that other kinds of models do not. ANNs naturally take advantage of patterns of absence, as well as presence, of factor binding associated with specific expression output; they are easily subjected to in silico “mutation” to uncover biological redundancies; and they can use the full range of factor binding values. A prominent feature of cell cycle ANNs suggested an analogous property might exist in the biological network. This postulated that “network-local discrimination” occurs when regulatory connections (here between MBF and target genes) are explicitly disfavored in one network module (G2), relative to others and to the class of genes outside the mitotic network. If correct, this predicts that MBF motifs will be significantly depleted from the discriminated class and that the discrimination will persist through evolution. Analysis of distantly related Schizosaccharomyces pombe confirmed this, suggesting that network-local discrimination is real and complements well-known enrichment of MBF sites in G1 class genes. A current challenge is to develop computational approaches to infer gene network regulatory relationships by integrating multiple types of large-scale functional genomic data. This paper shows that simple artificial neural networks (ANNs) employed in a new way do this very well. The ANN models are well-suited to capitalize on natural properties of gene networks in ways that many previous methods do not. Resulting gene network connections inferred between transcription factors and RNA output patterns are robust to noise in large-scale input datasets and to differences in RNA clustering class inputs. This was shown by using the yeast cell cycle gene network as a test case. The cycle has multiple classes of oscillatory RNAs, and Hart, Mjolsness, and Wold show that the ANNs identify key connections that associate genes from each cell cycle phase group with known and candidate regulators. Comparative analysis of network connectivity across multiple genomes showed strong conservation of basic factor-to-output relationships, although at the greatest evolutionary distances the specific target genes have mainly changed identity.
登录
查看更多内容
影响因子：
64.8
作者：
ANDREWS, BJ;HERSKOWITZ, I
通讯作者：
HERSKOWITZ, I
影响因子：
16
作者：
Cho, RJ;Campbell, MJ;Davis, RW
通讯作者：
Davis, RW
影响因子：
30.8
作者：
Cho, RJ;Huang, MX;Lockhart, DJ
通讯作者：
Lockhart, DJ
影响因子：
5.1
作者：
Menges, M;Hennig, L;Murray, JAH
通讯作者：
Murray, JAH
影响因子：
56.9
作者：
Lee, TI;Rinaldi, NJ;Young, RA
通讯作者：
Young, RA