@misc{10481/33377,
year = {2011},
url = {http://hdl.handle.net/10481/33377},
abstract = {Background
Many k-mers (or DNA words) and genomic elements are known to be spatially clustered in the genome. Well established examples are the genes, TFBSs, CpG dinucleotides, microRNA genes and ultra-conserved non-coding regions. Currently, no algorithm exists to find these clusters in a statistically comprehensible way. The detection of clustering often relies on densities and sliding-window approaches or arbitrarily chosen distance thresholds.

Results
We introduce here an algorithm to detect clusters of DNA words (k-mers), or any other genomic element, based on the distance between consecutive copies and an assigned statistical significance. We implemented the method into a web server connected to a MySQL backend, which also determines the co-localization with gene annotations. We demonstrate the usefulness of this approach by detecting the clusters of CAG/CTG (cytosine contexts that can be methylated in undifferentiated cells), showing that the degree of methylation vary drastically between inside and outside of the clusters. As another example, we used WordCluster to search for statistically significant clusters of olfactory receptor (OR) genes in the human genome.

Conclusions
WordCluster seems to predict biological meaningful clusters of DNA words (k-mers) and genomic entities. The implementation of the method into a web server is available at http://bioinfo2.ugr.es/wordCluster/wordCluster.php webcite including additional features like the detection of co-localization with gene regions or the annotation enrichment tool for functional analysis of overlapped genes.},
organization = {The Spanish Government grants BIO2008-01353 to JLO, mobility PR2009-0285 to PC, Spanish Junta de Andalucía grants P07-FQM3163 to PC and P06-FQM1858 to PB are acknowledged. The Spanish 'Juan de la Cierva' grant to MH and Basque Country 'Programa de formación de investigadores del Departamento de Educación, Universidades e Investigación' grant to GB are also acknowledged.},
publisher = {Biomed Central},
keywords = {Genomic elements},
keywords = {DNA words},
keywords = {Bioinformatics},
keywords = {WordCluster},
title = {WordCluster: detecting clusters of DNA words and genomic elements},
doi = {10.1186/1748-7188-6-2},
author = {Hackenberg , Michael and Carpena, Pedro and Bernaola-Galván, Pedro and Barturen, Guillermo and Alganza, Ángel M. and Oliver, José Luis},
}