Limits...
Ensemble Methods for MiRNA Target Prediction from Expression Data.

Le TD, Zhang J, Liu L, Li J - PLoS ONE (2015)

Bottom Line: Identifying miRNA functions is very important in understanding disease mechanisms and determining the efficacy of drugs.Further analysis of the results of this ensemble method shows that the ensemble method can obtain more targets which could not be found by any of the single methods, and the discovered targets are more statistically significant and functionally enriched.The source codes, datasets, miRNA target predictions by all methods, and the ground truth for validation are available in the Supplementary materials.

View Article: PubMed Central - PubMed

Affiliation: School of Information Technology and Mathematical Sciences, University of South Australia, Adelaide, South Australia, Australia.

ABSTRACT

Background: microRNAs (miRNAs) are short regulatory RNAs that are involved in several diseases, including cancers. Identifying miRNA functions is very important in understanding disease mechanisms and determining the efficacy of drugs. An increasing number of computational methods have been developed to explore miRNA functions by inferring the miRNA-mRNA regulatory relationships from data. Each of the methods is developed based on some assumptions and constraints, for instance, assuming linear relationships between variables. For such reasons, computational methods are often subject to the problem of inconsistent performance across different datasets. On the other hand, ensemble methods integrate the results from individual methods and have been proved to outperform each of their individual component methods in theory.

Results: In this paper, we investigate the performance of some ensemble methods over the commonly used miRNA target prediction methods. We apply eight different popular miRNA target prediction methods to three cancer datasets, and compare their performance with the ensemble methods which integrate the results from each combination of the individual methods. The validation results using experimentally confirmed databases show that the results of the ensemble methods complement those obtained by the individual methods and the ensemble methods perform better than the individual methods across different datasets. The ensemble method, Pearson+IDA+Lasso, which combines methods in different approaches, including a correlation method, a causal inference method, and a regression method, is the best performed ensemble method in this study. Further analysis of the results of this ensemble method shows that the ensemble method can obtain more targets which could not be found by any of the single methods, and the discovered targets are more statistically significant and functionally enriched. The source codes, datasets, miRNA target predictions by all methods, and the ground truth for validation are available in the Supplementary materials.

No MeSH data available.


Related in: MedlinePlus

Pearson+IDA+Lasso with different integration approaches.Borda-Topk and Borda (Original Borda from [32]) are better than cross-entropy Monte Carlo in all three datasets.
© Copyright Policy
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC4482624&req=5

pone.0131627.g002: Pearson+IDA+Lasso with different integration approaches.Borda-Topk and Borda (Original Borda from [32]) are better than cross-entropy Monte Carlo in all three datasets.

Mentions: The Borda count applied for top predicted targets (Borda-Topk) presented in this paper has the same principle as the Original Borda count method [32]. However, Borda-Topk provides a way for flexibility in the cut-off targets, i.e. users may only be interested in the top 200 targets of a particular miRNA. If k is set to the number of mRNAs in the dataset, the two methods are identical. Fig 2 shows the comparison results of the best ensemble method (Pearson+IDA+Lasso) using three different ranking integration approaches, including Borda-Topk, Original Borda, and the popular rank aggregation approach using cross-entropy Monte Carlo algorithm [37] in the R package called RankAggreg [58]. In Fig 2, we compare the ranking scores of the three approaches in each dataset and in all datasets. The ranking scores are calculated based on the number of confirmed interactions in the top 100, 200, 300 and 400 predicted targets of all miRNAs in each dataset. We can see from Fig 2 that, the Borda-Topk is the best approach in the EMT and BR51 datasets, but overall Borda-Topk and Original Borda are similar. Meanwhile, Cross-Entropy Monte Carlo is the worst approach in all three datasets. In the following sections, we discuss the results of the Borda-Topk approach.


Ensemble Methods for MiRNA Target Prediction from Expression Data.

Le TD, Zhang J, Liu L, Li J - PLoS ONE (2015)

Pearson+IDA+Lasso with different integration approaches.Borda-Topk and Borda (Original Borda from [32]) are better than cross-entropy Monte Carlo in all three datasets.
© Copyright Policy
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC4482624&req=5

pone.0131627.g002: Pearson+IDA+Lasso with different integration approaches.Borda-Topk and Borda (Original Borda from [32]) are better than cross-entropy Monte Carlo in all three datasets.
Mentions: The Borda count applied for top predicted targets (Borda-Topk) presented in this paper has the same principle as the Original Borda count method [32]. However, Borda-Topk provides a way for flexibility in the cut-off targets, i.e. users may only be interested in the top 200 targets of a particular miRNA. If k is set to the number of mRNAs in the dataset, the two methods are identical. Fig 2 shows the comparison results of the best ensemble method (Pearson+IDA+Lasso) using three different ranking integration approaches, including Borda-Topk, Original Borda, and the popular rank aggregation approach using cross-entropy Monte Carlo algorithm [37] in the R package called RankAggreg [58]. In Fig 2, we compare the ranking scores of the three approaches in each dataset and in all datasets. The ranking scores are calculated based on the number of confirmed interactions in the top 100, 200, 300 and 400 predicted targets of all miRNAs in each dataset. We can see from Fig 2 that, the Borda-Topk is the best approach in the EMT and BR51 datasets, but overall Borda-Topk and Original Borda are similar. Meanwhile, Cross-Entropy Monte Carlo is the worst approach in all three datasets. In the following sections, we discuss the results of the Borda-Topk approach.

Bottom Line: Identifying miRNA functions is very important in understanding disease mechanisms and determining the efficacy of drugs.Further analysis of the results of this ensemble method shows that the ensemble method can obtain more targets which could not be found by any of the single methods, and the discovered targets are more statistically significant and functionally enriched.The source codes, datasets, miRNA target predictions by all methods, and the ground truth for validation are available in the Supplementary materials.

View Article: PubMed Central - PubMed

Affiliation: School of Information Technology and Mathematical Sciences, University of South Australia, Adelaide, South Australia, Australia.

ABSTRACT

Background: microRNAs (miRNAs) are short regulatory RNAs that are involved in several diseases, including cancers. Identifying miRNA functions is very important in understanding disease mechanisms and determining the efficacy of drugs. An increasing number of computational methods have been developed to explore miRNA functions by inferring the miRNA-mRNA regulatory relationships from data. Each of the methods is developed based on some assumptions and constraints, for instance, assuming linear relationships between variables. For such reasons, computational methods are often subject to the problem of inconsistent performance across different datasets. On the other hand, ensemble methods integrate the results from individual methods and have been proved to outperform each of their individual component methods in theory.

Results: In this paper, we investigate the performance of some ensemble methods over the commonly used miRNA target prediction methods. We apply eight different popular miRNA target prediction methods to three cancer datasets, and compare their performance with the ensemble methods which integrate the results from each combination of the individual methods. The validation results using experimentally confirmed databases show that the results of the ensemble methods complement those obtained by the individual methods and the ensemble methods perform better than the individual methods across different datasets. The ensemble method, Pearson+IDA+Lasso, which combines methods in different approaches, including a correlation method, a causal inference method, and a regression method, is the best performed ensemble method in this study. Further analysis of the results of this ensemble method shows that the ensemble method can obtain more targets which could not be found by any of the single methods, and the discovered targets are more statistically significant and functionally enriched. The source codes, datasets, miRNA target predictions by all methods, and the ground truth for validation are available in the Supplementary materials.

No MeSH data available.


Related in: MedlinePlus