@article{Bacolla01102008,
author = {Bacolla, Albino and Larson, Jacquelynn E. and Collins, Jack R. and Li, Jian and Milosavljevic, Aleksandar and Stenson, Peter D. and Cooper, David N. and Wells, Robert D.}, 
title = {Abundance and length of simple repeats in vertebrate genomes are determined by their structural properties},
volume = {18}, 
number = {10}, 
pages = {1545-1553}, 
year = {2008}, 
doi = {10.1101/gr.078303.108}, 
abstract ={Microsatellites are abundant in vertebrate genomes, but their sequence representation and length distributions vary greatly within each family of repeats (e.g., tetranucleotides). Biophysical studies of 82 synthetic single-stranded oligonucleotides comprising all tetra- and trinucleotide repeats revealed an inverse correlation between the stability of folded-back hairpin and quadruplex structures and the sequence representation for repeats ≥30 bp in length in nine vertebrate genomes. Alternatively, the predicted energies of base-stacking interactions correlated directly with the longest length distributions in vertebrate genomes. Genome-wide analyses indicated that unstable sequences, such as CAG:CTG and CCG:CGG, were over-represented in coding regions and that micro/minisatellites were recruited in genes involved in transcription and signaling pathways, particularly in the nervous system. Microsatellite instability (MSI) is a hallmark of cancer, and length polymorphism within genes can confer susceptibility to inherited disease. Sequences that manifest the highest MSI values also displayed the strongest base-stacking interactions; analyses of 62 tri- and tetranucleotide repeat-containing genes associated with human genetic disease revealed enrichments similar to those noted for micro/minisatellite-containing genes. We conclude that DNA structure and base-stacking determined the number and length distributions of microsatellite repeats in vertebrate genomes over evolutionary time and that micro/minisatellites have been recruited to participate in both gene and protein function.}, 
URL = {http://genome.cshlp.org/content/18/10/1545.abstract}, 
eprint = {http://genome.cshlp.org/content/18/10/1545.full.pdf+html}, 
journal = {Genome Research} 
}