Limits...
A markov classification model for metabolic pathways.

Hancock T, Mamitsuka H - Algorithms Mol Biol (2010)

Bottom Line: The results clearly show that HME3M outperformed the comparison methods in the presence of increasing network complexity and pathway noise.This paper clearly shows HME3M to be an accurate and robust method for classifying metabolic pathways.HME3M is shown to outperform all comparison methods and further is capable of identifying known biologically active pathways within microarray data.

View Article: PubMed Central - HTML - PubMed

Affiliation: Bioinformatics Center, Institute for Chemical Research, Kyoto University, Japan. timhancock@kuicr.kyoto-u.ac.jp

ABSTRACT

Background: This paper considers the problem of identifying pathways through metabolic networks that relate to a specific biological response. Our proposed model, HME3M, first identifies frequently traversed network paths using a Markov mixture model. Then by employing a hierarchical mixture of experts, separate classifiers are built using information specific to each path and combined into an ensemble prediction for the response.

Results: We compared the performance of HME3M with logistic regression and support vector machines (SVM) for both simulated pathways and on two metabolic networks, glycolysis and the pentose phosphate pathway for Arabidopsis thaliana. We use AltGenExpress microarray data and focus on the pathway differences in the developmental stages and stress responses of Arabidopsis. The results clearly show that HME3M outperformed the comparison methods in the presence of increasing network complexity and pathway noise. Furthermore an analysis of the paths identified by HME3M for each metabolic network confirmed known biological responses of Arabidopsis.

Conclusions: This paper clearly shows HME3M to be an accurate and robust method for classifying metabolic pathways. HME3M is shown to outperform all comparison methods and further is capable of identifying known biologically active pathways within microarray data.

No MeSH data available.


Related in: MedlinePlus

ROC curve of all paths for the optimal model (M = 2) for the pentose phosphate pathway for classifying oxidative stress pathways.
© Copyright Policy - open-access
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC2823754&req=5

Figure 9: ROC curve of all paths for the optimal model (M = 2) for the pentose phosphate pathway for classifying oxidative stress pathways.

Mentions: From Figure 9 we observe that the ROC curves for the optimal HME3M model (M = 2 tolerance = 0.05) clearly indicate one path for the oxidative label and another path for the control label. An interesting property of the ROC curves of each path is that the structure of m = 1 is almost exactly opposite to m = 2. The cause of this inverse similarity between the ROC curves is that a similar path is identified by each 3M component (θm = 1 and θm = 2 are correlated at r = 0.52) for both m = 1 and m = 2 but the signs of the PLR coefficients within each expert are flipped. In Table 4 we show the distribution of signs of the PLR coefficients for each of the two components. From Table 4 we see that for all cases when βm = 1 < 0 there is a 45% chance that the sign of the PLR coefficent is positive in path m = 2. The high correlation between the estimated pathway structure indicates that the same path is being found for both m = 1 and m = 2. However the flipping of the signs within the PLR coefficients changes the structure of m = 1 to predict the control label when the oxidative path in component m = 2 is not observed. The pathway duplication indicates that the main structure within the dataset is the activated oxidative pathway observed when Arabidopsis is under stress and the control group contains mainly noise pathways with little unique structure.


A markov classification model for metabolic pathways.

Hancock T, Mamitsuka H - Algorithms Mol Biol (2010)

ROC curve of all paths for the optimal model (M = 2) for the pentose phosphate pathway for classifying oxidative stress pathways.
© Copyright Policy - open-access
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC2823754&req=5

Figure 9: ROC curve of all paths for the optimal model (M = 2) for the pentose phosphate pathway for classifying oxidative stress pathways.
Mentions: From Figure 9 we observe that the ROC curves for the optimal HME3M model (M = 2 tolerance = 0.05) clearly indicate one path for the oxidative label and another path for the control label. An interesting property of the ROC curves of each path is that the structure of m = 1 is almost exactly opposite to m = 2. The cause of this inverse similarity between the ROC curves is that a similar path is identified by each 3M component (θm = 1 and θm = 2 are correlated at r = 0.52) for both m = 1 and m = 2 but the signs of the PLR coefficients within each expert are flipped. In Table 4 we show the distribution of signs of the PLR coefficients for each of the two components. From Table 4 we see that for all cases when βm = 1 < 0 there is a 45% chance that the sign of the PLR coefficent is positive in path m = 2. The high correlation between the estimated pathway structure indicates that the same path is being found for both m = 1 and m = 2. However the flipping of the signs within the PLR coefficients changes the structure of m = 1 to predict the control label when the oxidative path in component m = 2 is not observed. The pathway duplication indicates that the main structure within the dataset is the activated oxidative pathway observed when Arabidopsis is under stress and the control group contains mainly noise pathways with little unique structure.

Bottom Line: The results clearly show that HME3M outperformed the comparison methods in the presence of increasing network complexity and pathway noise.This paper clearly shows HME3M to be an accurate and robust method for classifying metabolic pathways.HME3M is shown to outperform all comparison methods and further is capable of identifying known biologically active pathways within microarray data.

View Article: PubMed Central - HTML - PubMed

Affiliation: Bioinformatics Center, Institute for Chemical Research, Kyoto University, Japan. timhancock@kuicr.kyoto-u.ac.jp

ABSTRACT

Background: This paper considers the problem of identifying pathways through metabolic networks that relate to a specific biological response. Our proposed model, HME3M, first identifies frequently traversed network paths using a Markov mixture model. Then by employing a hierarchical mixture of experts, separate classifiers are built using information specific to each path and combined into an ensemble prediction for the response.

Results: We compared the performance of HME3M with logistic regression and support vector machines (SVM) for both simulated pathways and on two metabolic networks, glycolysis and the pentose phosphate pathway for Arabidopsis thaliana. We use AltGenExpress microarray data and focus on the pathway differences in the developmental stages and stress responses of Arabidopsis. The results clearly show that HME3M outperformed the comparison methods in the presence of increasing network complexity and pathway noise. Furthermore an analysis of the paths identified by HME3M for each metabolic network confirmed known biological responses of Arabidopsis.

Conclusions: This paper clearly shows HME3M to be an accurate and robust method for classifying metabolic pathways. HME3M is shown to outperform all comparison methods and further is capable of identifying known biologically active pathways within microarray data.

No MeSH data available.


Related in: MedlinePlus