Limits...
Connectivity in the yeast cell cycle transcription network: inferences from neural networks.

Hart CE, Mjolsness E, Wold BJ - PLoS Comput. Biol. (2006)

Bottom Line: ANN models can capitalize on properties of biological gene networks that other kinds of models do not.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.

View Article: PubMed Central - PubMed

Affiliation: Division of Biology, California Institute of Technology, Pasadena, California, United States of America.

ABSTRACT
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.

Show MeSH

Related in: MedlinePlus

Transcription Factor Rankings by aobANN Weights for Alpha Factor Arrest Data(A) ANN weights are sorted by the SOS metric described in the text and in Figure 3B.(B) ANN weights from the aobANN network, as in Figure 4, for ANNs trained to predict RNA expression clusters derived from yeast cultures synchronized using alpha factor arrest to syncrhonize cells [1].
© Copyright Policy
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC1761652&req=5

pcbi-0020169-g009: Transcription Factor Rankings by aobANN Weights for Alpha Factor Arrest Data(A) ANN weights are sorted by the SOS metric described in the text and in Figure 3B.(B) ANN weights from the aobANN network, as in Figure 4, for ANNs trained to predict RNA expression clusters derived from yeast cultures synchronized using alpha factor arrest to syncrhonize cells [1].

Mentions: Cdc15ts-synchronized cells are arrested at the end of M phase [1]. Correspondingly, we find the expression cluster that peaks first—at 10 min in the Cdc15 data—associates strongly with the early G1 factors Swi5 and Ace2 (EM1 in Figure 7). Note that in the previous cdc28 ANN, the same association was made, even though—under that release condition—genes of this regulatory group are not upregulated until the second cycle after release [9] and above). Alpha factor arrest is similar in this way to cdc28, reflecting their similar blockade points. Thus, the ANNs easily related the cdc15 early G1 cluster to the alpha factor and cdc28 early G1 clusters, even though the cluster trajectory is strikingly different and the clusters themselves contain no individual genes in common with the cdc28 or alpha factor datasets (Figures 4, 8, and 9). Other high-ranking regulators appear in one or two, but not all three ANN cell cycle models. Yox1 and Yhp1, for example, differ among the models, because the gene classes derived from the RNA clusterings differ in content. Finally, Pho2 emerges as a potentially significant regulator associated with an M-phase kinetic pattern in the two Spellman datasets, consistent with the previously reported Pho2/Pho4 mediated, cell cycle expression for some phosphate-regulated genes [37]. This is thought to be due to intracellular polyphosphate pools, which vary through the cycle in some culture conditions, but can also be influenced by growth media and history.


Connectivity in the yeast cell cycle transcription network: inferences from neural networks.

Hart CE, Mjolsness E, Wold BJ - PLoS Comput. Biol. (2006)

Transcription Factor Rankings by aobANN Weights for Alpha Factor Arrest Data(A) ANN weights are sorted by the SOS metric described in the text and in Figure 3B.(B) ANN weights from the aobANN network, as in Figure 4, for ANNs trained to predict RNA expression clusters derived from yeast cultures synchronized using alpha factor arrest to syncrhonize cells [1].
© Copyright Policy
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC1761652&req=5

pcbi-0020169-g009: Transcription Factor Rankings by aobANN Weights for Alpha Factor Arrest Data(A) ANN weights are sorted by the SOS metric described in the text and in Figure 3B.(B) ANN weights from the aobANN network, as in Figure 4, for ANNs trained to predict RNA expression clusters derived from yeast cultures synchronized using alpha factor arrest to syncrhonize cells [1].
Mentions: Cdc15ts-synchronized cells are arrested at the end of M phase [1]. Correspondingly, we find the expression cluster that peaks first—at 10 min in the Cdc15 data—associates strongly with the early G1 factors Swi5 and Ace2 (EM1 in Figure 7). Note that in the previous cdc28 ANN, the same association was made, even though—under that release condition—genes of this regulatory group are not upregulated until the second cycle after release [9] and above). Alpha factor arrest is similar in this way to cdc28, reflecting their similar blockade points. Thus, the ANNs easily related the cdc15 early G1 cluster to the alpha factor and cdc28 early G1 clusters, even though the cluster trajectory is strikingly different and the clusters themselves contain no individual genes in common with the cdc28 or alpha factor datasets (Figures 4, 8, and 9). Other high-ranking regulators appear in one or two, but not all three ANN cell cycle models. Yox1 and Yhp1, for example, differ among the models, because the gene classes derived from the RNA clusterings differ in content. Finally, Pho2 emerges as a potentially significant regulator associated with an M-phase kinetic pattern in the two Spellman datasets, consistent with the previously reported Pho2/Pho4 mediated, cell cycle expression for some phosphate-regulated genes [37]. This is thought to be due to intracellular polyphosphate pools, which vary through the cycle in some culture conditions, but can also be influenced by growth media and history.

Bottom Line: ANN models can capitalize on properties of biological gene networks that other kinds of models do not.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.

View Article: PubMed Central - PubMed

Affiliation: Division of Biology, California Institute of Technology, Pasadena, California, United States of America.

ABSTRACT
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.

Show MeSH
Related in: MedlinePlus