SOMEA: self-organizing map based extraction algorithm for DNA motif identification with heterogeneous model

Abstract

BackgroundDiscrimination of transcription factor binding sites (TFBS) from background sequences plays a key role in computational motif discovery. Current clustering based algorithms employ homogeneous model for problem solving, which assumes that motifs and background signals can be equivalently characterized. This assumption has some limitations because both sequence signals have distinct properties.ResultsThis paper aims to develop a Self-Organizing Map (SOM) based clustering algorithm for extracting binding sites in DNA sequences. Our framework is based on a novel intra-node soft competitive procedure to achieve maximum discrimination of motifs from background signals in datasets. The intra-node competition is based on an adaptive weighting technique on two different signal models to better represent these two classes of signals. Using several real and artificial datasets, we compared our proposed method with several motif discovery tools. Compared to SOMBRERO, a state-of-the-art SOM based motif discovery tool, it is found that our algorithm can achieve significant improvements in the average precision rates (i.e., about 27%) on the real datasets without compromising its sensitivity. Our method also performed favourably comparing against other motif discovery tools.ConclusionsMotif discovery with model based clustering framework should consider the use of heterogeneous model to represent the two classes of signals in DNA sequences. Such heterogeneous model can achieve better signal discrimination compared to the homogeneous model.

Self-Organizing Map for Characterizing Heterogeneous Nucleotide and Amino Acid Sequence Motifs

“…In contrast, Markov models can overcome this problem ( [8] pp. 110-114) and have been used in conjunction with SOM [21].…”

“…One may use SOM to characterize these heterogeneous splice sites, quantify similarities among them, and potentially discover new type of introns. Several studies have demonstrated the values of using SOM to characterize sequence motifs [17][18][19][20][21][22], but their efforts do not seem sufficiently appreciated by biologists. Given the many advantages of SOM over conventional clustering [1], biologists should gain a new perspective on the relationship among sequence motifs through the SOM extension in this paper.…”

Motif Discovery and Data Mining in Bioinformatics

“…Motif discovery in DNA data sets is a challenging problem domain because of lack of understanding of the nature of the data, and the mechanisms to which proteins recognize and interact with its binding sites are still complicated to biologists [35]. If the motif is TFBS; recent studies have shown that the underlying regulatory mechanisms of TFBS are complex, dynamic (especially in higher organisms) and can be arranged in multiple hierarchical levels [43].…”

On the use of algorithms to discover motifs in DNA sequences

“…Hence, a SOM-based clustering algorithm was presented in [23], in which the authors extracted binding sites in DNA sequences. The main novelty of this work was to consider two different types signals in DNA sequences, showing that treating them separably better results can be achieved.…”

“…The tool proposed a intra-node soft competitive procedure in each node model to achieve maximum discrimination of motif from background signals, by weighting two different models: position specific scoring matrix and Markov chain. As it happened in [23] and [27], this method was inserted in another SOM-based approach, called SOMBRERO [28], that constructed models for motifs that were structurally similar.…”