Limits...
A mixture of feature experts approach for protein-protein interaction prediction.

Qi Y, Klein-Seetharaman J, Bar-Joseph Z - BMC Bioinformatics (2007)

Bottom Line: High-throughput methods can directly detect the set of interacting proteins in model species but the results are often incomplete and exhibit high false positive and false negative rates.However, due to missing data and high redundancy among the features used, different protein pairs may benefit from different features based on the set of attributes available.Our method improved upon the best previous methods for this task.

View Article: PubMed Central - HTML - PubMed

Affiliation: School of Computer Science, Carnegie Mellon University, Pittsburgh, PA 15213, USA. qyj@cs.cmu.edu

ABSTRACT

Background: High-throughput methods can directly detect the set of interacting proteins in model species but the results are often incomplete and exhibit high false positive and false negative rates. A number of researchers have recently presented methods for integrating direct and indirect data for predicting interactions. These methods utilize a common classifier for all pairs. However, due to missing data and high redundancy among the features used, different protein pairs may benefit from different features based on the set of attributes available. In addition, in many cases it is hard to directly determine which of the data sources contributed to a prediction. This information is important for biologists using these predications in the design of new experiments.

Results: To address these challenges we propose a Mixture-of-Feature-Experts method for protein-protein interaction prediction. We split the features into roughly homogeneous sets of feature experts. The individual experts use logistic regression and their scores are combined using another logistic regression. When combining the scores the weighting of each expert depends on the set of input attributes available for that pair. Thus, different experts will have different influence on the prediction depending on the available features.

Conclusion: We applied our method to predict the set of interacting proteins in yeast and human cells. Our method improved upon the best previous methods for this task. In addition, the weighting of the experts provides means to evaluate the prediction based on the high scoring features.

Show MeSH

Related in: MedlinePlus

Yeast Pheromone Response Pathway. The yeast pheromone response pathway. This figure is from the KEGG [25] database.
© Copyright Policy - open-access
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC2230507&req=5

Figure 6: Yeast Pheromone Response Pathway. The yeast pheromone response pathway. This figure is from the KEGG [25] database.

Mentions: To demonstrate the utility of this unique capability of the MFE method to reveal feature importance in specific predictions, we investigated a specific yeast pathway; the yeast pheromone response. For this pathway we compare the contribution of different experts in the known and predicted interacting pairs. Figure 6 presents the known interactions in this pathway as determined by the KEGG database [25]. In this pathway the yeast mating factors MAT alpha/a bind to their cognate membrane receptors Ste2/3, members of the G protein coupled receptor family. Subsequent binding and activation of the G protein induces a MAP kinase signaling pathway via G protein activation [35].


A mixture of feature experts approach for protein-protein interaction prediction.

Qi Y, Klein-Seetharaman J, Bar-Joseph Z - BMC Bioinformatics (2007)

Yeast Pheromone Response Pathway. The yeast pheromone response pathway. This figure is from the KEGG [25] database.
© Copyright Policy - open-access
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC2230507&req=5

Figure 6: Yeast Pheromone Response Pathway. The yeast pheromone response pathway. This figure is from the KEGG [25] database.
Mentions: To demonstrate the utility of this unique capability of the MFE method to reveal feature importance in specific predictions, we investigated a specific yeast pathway; the yeast pheromone response. For this pathway we compare the contribution of different experts in the known and predicted interacting pairs. Figure 6 presents the known interactions in this pathway as determined by the KEGG database [25]. In this pathway the yeast mating factors MAT alpha/a bind to their cognate membrane receptors Ste2/3, members of the G protein coupled receptor family. Subsequent binding and activation of the G protein induces a MAP kinase signaling pathway via G protein activation [35].

Bottom Line: High-throughput methods can directly detect the set of interacting proteins in model species but the results are often incomplete and exhibit high false positive and false negative rates.However, due to missing data and high redundancy among the features used, different protein pairs may benefit from different features based on the set of attributes available.Our method improved upon the best previous methods for this task.

View Article: PubMed Central - HTML - PubMed

Affiliation: School of Computer Science, Carnegie Mellon University, Pittsburgh, PA 15213, USA. qyj@cs.cmu.edu

ABSTRACT

Background: High-throughput methods can directly detect the set of interacting proteins in model species but the results are often incomplete and exhibit high false positive and false negative rates. A number of researchers have recently presented methods for integrating direct and indirect data for predicting interactions. These methods utilize a common classifier for all pairs. However, due to missing data and high redundancy among the features used, different protein pairs may benefit from different features based on the set of attributes available. In addition, in many cases it is hard to directly determine which of the data sources contributed to a prediction. This information is important for biologists using these predications in the design of new experiments.

Results: To address these challenges we propose a Mixture-of-Feature-Experts method for protein-protein interaction prediction. We split the features into roughly homogeneous sets of feature experts. The individual experts use logistic regression and their scores are combined using another logistic regression. When combining the scores the weighting of each expert depends on the set of input attributes available for that pair. Thus, different experts will have different influence on the prediction depending on the available features.

Conclusion: We applied our method to predict the set of interacting proteins in yeast and human cells. Our method improved upon the best previous methods for this task. In addition, the weighting of the experts provides means to evaluate the prediction based on the high scoring features.

Show MeSH
Related in: MedlinePlus