EMD: an ensemble algorithm for discovering regulatory motifs in DNA sequences

Abstract

Background: Understanding gene regulatory networks has become one of the central research problems in bioinformatics. More than thirty algorithms have been proposed to identify DNA regulatory sites during the past thirty years. However, the prediction accuracy of these algorithms is still quite low. Ensemble algorithms have emerged as an effective strategy in bioinformatics for improving the prediction accuracy by exploiting the synergetic prediction capability of multiple algorithms.

Results: We proposed a novel clustering-based ensemble algorithm named EMD for de novo motif discovery by combining multiple predictions from multiple runs of one or more base component algorithms. The ensemble approach is applied to the motif discovery problem for the first time. The algorithm is tested on a benchmark dataset generated from E. coli RegulonDB. The EMD algorithm has achieved 22.4% improvement in terms of the nucleotide level prediction accuracy over the best stand-alone component algorithm. The advantage of the EMD algorithm is more significant for shorter input sequences, but most importantly, it always outperforms or at least stays at the same performance level of the stand-alone component algorithms even for longer sequences.

Conclusion: We proposed an ensemble approach for the motif discovery problem by taking advantage of the availability of a large number of motif discovery programs. We have shown that the ensemble approach is an effective strategy for improving both sensitivity and specificity, thus the accuracy of the prediction. The advantage of the EMD algorithm is its flexibility in the sense that a new powerful algorithm can be easily added to the system.

Figure 1

Overview of the EMD algorithm. After each component algorithm is run R times for an input sequence data set, K motifs are collected from each run. The right side of the figure illustrates the grouping phase of the algorithm for the sequence number 1 and the final prediction of sites for the site group number 1 of the input sequence No. 1. See the text for the details.

Figure 2

Scalability of the EMD algorithms. The nucleotide level prediction performance was compared with the best base algorithm MDscan (MD) and the best multi-restart algorithm (RS-BP). This evaluation is done on ECRDB61B-200 data set. The y-axis shows the nucleotide level accuracy (nPC). The error bars are not shown because the standard error is very small (less than 0.003).