Limits...
Machine learning for regulatory analysis and transcription factor target prediction in yeast.

Holloway DT, Kon M, Delisi C - Syst Synth Biol (2007)

Bottom Line: For the purpose of illustration we discuss several results, including biochemical pathway predictions for Gcn4 and Rap1.Future work on this method will focus on increasing the accuracy and quality of predictions using feature reduction and clustering strategies.Since predictions have been made on only 104 TFs in yeast, new classifiers will be built for the remaining 100 factors which have available binding data.

View Article: PubMed Central - PubMed

Affiliation: Molecular Biology Cell Biology and Biochemistry, Boston University, Boston, MA, 02215, USA, dth128@bu.edu.

ABSTRACT
High throughput technologies, including array-based chromatin immunoprecipitation, have rapidly increased our knowledge of transcriptional maps-the identity and location of regulatory binding sites within genomes. Still, the full identification of sites, even in lower eukaryotes, remains largely incomplete. In this paper we develop a supervised learning approach to site identification using support vector machines (SVMs) to combine 26 different data types. A comparison with the standard approach to site identification using position specific scoring matrices (PSSMs) for a set of 104 Saccharomyces cerevisiae regulators indicates that our SVM-based target classification is more sensitive (73 vs. 20%) when specificity and positive predictive value are the same. We have applied our SVM classifier for each transcriptional regulator to all promoters in the yeast genome to obtain thousands of new targets, which are currently being analyzed and refined to limit the risk of classifier over-fitting. For the purpose of illustration we discuss several results, including biochemical pathway predictions for Gcn4 and Rap1. For both transcription factors SVM predictions match well with the known biology of control mechanisms, and possible new roles for these factors are suggested, such as a function for Rap1 in regulating fermentative growth. We also examine the promoter melting temperature curves for the targets of YJR060W, and show that targets of this TF have potentially unique physical properties which distinguish them from other genes. The SVM output automatically provides the means to rank dataset features to identify important biological elements. We use this property to rank classifying k-mers, thereby reconstructing known binding sites for several TFs, and to rank expression experiments, determining the conditions under which Fhl1, the factor responsible for expression of ribosomal protein genes, is active. We can see that targets of Fhl1 are differentially expressed in the chosen conditions as compared to the expression of average and negative set genes. SVM-based classifiers provide a robust framework for analysis of regulatory networks. Processing of classifier outputs can provide high quality predictions and biological insight into functions of particular transcription factors. Future work on this method will focus on increasing the accuracy and quality of predictions using feature reduction and clustering strategies. Since predictions have been made on only 104 TFs in yeast, new classifiers will be built for the remaining 100 factors which have available binding data.

No MeSH data available.


Related in: MedlinePlus

Expression plot of Fhl1 targets over top 25 discriminative conditions. Average expression is plotted over all 5571 yeast genes (solid blue), over the negative set for Fhl1 (dashed blue), the positive targets (dashed red), and the most significant targets (solid red), P(true / distance from classifier) ≥ 0.99. The best targets have expression significantly different than the average or negative genes. The chosen expression conditions, ranked by w-vector from the expression based classifier, are shown under the graph with numbers indicating the position of the conditions in the graph. These conditions make sense since Fhl1 is regulated by the TOR signalling pathway, which is blocked by rapamycin. There is also some support in the literature for TOR having a role in meiosis and stress response
© Copyright Policy
Related In: Results  -  Collection


getmorefigures.php?uid=PMC2533145&req=5

Fig7: Expression plot of Fhl1 targets over top 25 discriminative conditions. Average expression is plotted over all 5571 yeast genes (solid blue), over the negative set for Fhl1 (dashed blue), the positive targets (dashed red), and the most significant targets (solid red), P(true / distance from classifier) ≥ 0.99. The best targets have expression significantly different than the average or negative genes. The chosen expression conditions, ranked by w-vector from the expression based classifier, are shown under the graph with numbers indicating the position of the conditions in the graph. These conditions make sense since Fhl1 is regulated by the TOR signalling pathway, which is blocked by rapamycin. There is also some support in the literature for TOR having a role in meiosis and stress response

Mentions: By the hypergeometric test, expression data is a significant predictor (p = 6.12e − 14) of targets for Fhl1, a forkhead-like TF known to be involved in rRNA processing and ribosomal protein gene expression. The w for this TF’s classifier from expression data has been calculated and sorted to determine the conditions having the highest weight. Figure 7 shows a plot of expression values over the top 25 conditions for the average yeast gene (solid blue), the average for genes in Fhl1’s negative set (dashed blue), the average in the positive set (dashed red), and the average in the most significant (P(true) ≥ 0.99) 48 targets of this TF (solid red).Fig. 7


Machine learning for regulatory analysis and transcription factor target prediction in yeast.

Holloway DT, Kon M, Delisi C - Syst Synth Biol (2007)

Expression plot of Fhl1 targets over top 25 discriminative conditions. Average expression is plotted over all 5571 yeast genes (solid blue), over the negative set for Fhl1 (dashed blue), the positive targets (dashed red), and the most significant targets (solid red), P(true / distance from classifier) ≥ 0.99. The best targets have expression significantly different than the average or negative genes. The chosen expression conditions, ranked by w-vector from the expression based classifier, are shown under the graph with numbers indicating the position of the conditions in the graph. These conditions make sense since Fhl1 is regulated by the TOR signalling pathway, which is blocked by rapamycin. There is also some support in the literature for TOR having a role in meiosis and stress response
© Copyright Policy
Related In: Results  -  Collection

Show All Figures
getmorefigures.php?uid=PMC2533145&req=5

Fig7: Expression plot of Fhl1 targets over top 25 discriminative conditions. Average expression is plotted over all 5571 yeast genes (solid blue), over the negative set for Fhl1 (dashed blue), the positive targets (dashed red), and the most significant targets (solid red), P(true / distance from classifier) ≥ 0.99. The best targets have expression significantly different than the average or negative genes. The chosen expression conditions, ranked by w-vector from the expression based classifier, are shown under the graph with numbers indicating the position of the conditions in the graph. These conditions make sense since Fhl1 is regulated by the TOR signalling pathway, which is blocked by rapamycin. There is also some support in the literature for TOR having a role in meiosis and stress response
Mentions: By the hypergeometric test, expression data is a significant predictor (p = 6.12e − 14) of targets for Fhl1, a forkhead-like TF known to be involved in rRNA processing and ribosomal protein gene expression. The w for this TF’s classifier from expression data has been calculated and sorted to determine the conditions having the highest weight. Figure 7 shows a plot of expression values over the top 25 conditions for the average yeast gene (solid blue), the average for genes in Fhl1’s negative set (dashed blue), the average in the positive set (dashed red), and the average in the most significant (P(true) ≥ 0.99) 48 targets of this TF (solid red).Fig. 7

Bottom Line: For the purpose of illustration we discuss several results, including biochemical pathway predictions for Gcn4 and Rap1.Future work on this method will focus on increasing the accuracy and quality of predictions using feature reduction and clustering strategies.Since predictions have been made on only 104 TFs in yeast, new classifiers will be built for the remaining 100 factors which have available binding data.

View Article: PubMed Central - PubMed

Affiliation: Molecular Biology Cell Biology and Biochemistry, Boston University, Boston, MA, 02215, USA, dth128@bu.edu.

ABSTRACT
High throughput technologies, including array-based chromatin immunoprecipitation, have rapidly increased our knowledge of transcriptional maps-the identity and location of regulatory binding sites within genomes. Still, the full identification of sites, even in lower eukaryotes, remains largely incomplete. In this paper we develop a supervised learning approach to site identification using support vector machines (SVMs) to combine 26 different data types. A comparison with the standard approach to site identification using position specific scoring matrices (PSSMs) for a set of 104 Saccharomyces cerevisiae regulators indicates that our SVM-based target classification is more sensitive (73 vs. 20%) when specificity and positive predictive value are the same. We have applied our SVM classifier for each transcriptional regulator to all promoters in the yeast genome to obtain thousands of new targets, which are currently being analyzed and refined to limit the risk of classifier over-fitting. For the purpose of illustration we discuss several results, including biochemical pathway predictions for Gcn4 and Rap1. For both transcription factors SVM predictions match well with the known biology of control mechanisms, and possible new roles for these factors are suggested, such as a function for Rap1 in regulating fermentative growth. We also examine the promoter melting temperature curves for the targets of YJR060W, and show that targets of this TF have potentially unique physical properties which distinguish them from other genes. The SVM output automatically provides the means to rank dataset features to identify important biological elements. We use this property to rank classifying k-mers, thereby reconstructing known binding sites for several TFs, and to rank expression experiments, determining the conditions under which Fhl1, the factor responsible for expression of ribosomal protein genes, is active. We can see that targets of Fhl1 are differentially expressed in the chosen conditions as compared to the expression of average and negative set genes. SVM-based classifiers provide a robust framework for analysis of regulatory networks. Processing of classifier outputs can provide high quality predictions and biological insight into functions of particular transcription factors. Future work on this method will focus on increasing the accuracy and quality of predictions using feature reduction and clustering strategies. Since predictions have been made on only 104 TFs in yeast, new classifiers will be built for the remaining 100 factors which have available binding data.

No MeSH data available.


Related in: MedlinePlus