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

Pair Feature Importance Analysis. Distribution of highest scoring experts for the yeast pheromone response pathway validation. For definition of P, F, S, E experts, see details in Table 1 and the 'Feature' section. (a) shows the frequency at which each of the four experts had the maximal score for the 33 known interacting pairs. (b) shows the frequency at which each of the four experts had the maximal score for the 18 new predictions.
© Copyright Policy - open-access
Related In: Results  -  Collection

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

Figure 7: Pair Feature Importance Analysis. Distribution of highest scoring experts for the yeast pheromone response pathway validation. For definition of P, F, S, E experts, see details in Table 1 and the 'Feature' section. (a) shows the frequency at which each of the four experts had the maximal score for the 33 known interacting pairs. (b) shows the frequency at which each of the four experts had the maximal score for the 18 new predictions.

Mentions: Figure 7(a) shows the frequency at which each of the four experts showed maximal contributions among validated pairs. In line with biological intuition, the direct high-throughput evidence (expert P) and functional databases (expert F) are the predominant experts in the correct predictions. Figure 7(b) shows that the majority of the 18 new predictions are based on recommendations by expert F. Based on the reliability of expert F in making correct predictions, this result indicates that the majority of the new predictions may turn out to be correct, once experimentally tested.


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

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

Pair Feature Importance Analysis. Distribution of highest scoring experts for the yeast pheromone response pathway validation. For definition of P, F, S, E experts, see details in Table 1 and the 'Feature' section. (a) shows the frequency at which each of the four experts had the maximal score for the 33 known interacting pairs. (b) shows the frequency at which each of the four experts had the maximal score for the 18 new predictions.
© Copyright Policy - open-access
Related In: Results  -  Collection

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

Figure 7: Pair Feature Importance Analysis. Distribution of highest scoring experts for the yeast pheromone response pathway validation. For definition of P, F, S, E experts, see details in Table 1 and the 'Feature' section. (a) shows the frequency at which each of the four experts had the maximal score for the 33 known interacting pairs. (b) shows the frequency at which each of the four experts had the maximal score for the 18 new predictions.
Mentions: Figure 7(a) shows the frequency at which each of the four experts showed maximal contributions among validated pairs. In line with biological intuition, the direct high-throughput evidence (expert P) and functional databases (expert F) are the predominant experts in the correct predictions. Figure 7(b) shows that the majority of the 18 new predictions are based on recommendations by expert F. Based on the reliability of expert F in making correct predictions, this result indicates that the majority of the new predictions may turn out to be correct, once experimentally tested.

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