Learning a weighted sequence model of the nucleosome core and linker yields more accurate predictions in Saccharomyces cerevisiae and Homo sapiens

Sheila Moore Reynolds, Jeffrey A. Bilmes and William Stafford Noble

PLoS Computational Biology. 6(7):e10000834, 2010.


Background: DNA in eukaryotes is packaged into a chromatin complex, the most basic element of which is the nucleosome. Because the precise positioning of the nucleosome cores allows for selective access to the DNA, the mechanisms that control this positioning are important pieces of the gene expression puzzle.

Methodology/Principal Findings: We describe a large-scale nucleosome pattern that jointly characterizes the nucleosome core and the adjacent linkers and is predominantly characterized by long-range oscillations in the mono, di- and tri-nucleotide content of the DNA sequence, and we show that this pattern can be used to predict nucleosome positions in both Homo sapiens and Saccharomyces cerevisiae more accurately than previously published methods. Surprisingly, in both H. sapiens and S. cerevisiae, the most informative individual features are the mono-nucleotide patterns, although the inclusion of di- and tri-nucleotide features results in improved performance. Our approach combines a much longer pattern than has been previously used to predict nucleosome positioning from sequence — 301 base pairs, centered at the position to be scored — with a novel discriminative classification approach that selectively weights the contributions from each of the input features. The resulting scores are relatively insensitive to local AT-content and can be used to accurately discriminate putative dyad positions from adjacent linker regions without requiring an additional dynamic programming step and without the attendant edge effects and assumptions about linker length modeling and overall nucleosome density.

Conclusions/Significance: Our approach produces the best dyad-linker classification results published to date in H. sapiens, and outperforms two recently published models on a large set of S. cerevisiae nucleosome positions. Our results suggest that in both genomes, a comparable and relatively small fraction of nucleosomes are well-positioned and that these positions are predictable based on sequence alone. We believe that the bulk of the remaining nucleosomes follow a statistical positioning model.

Supplementary data

Following are links to four compressed text files with coordinates from the hg18 assembly of the human genome. The first file contains the 438652 positions published in the Zhang et al. paper (also available at http://liulab.dfci.harvard.edu/NPS/Result). The remaining three files contains the positions that we derived from the Schones dataset. The three lists are based on successively lower thresholds, so the 110 list contains about 200,000 positions, the 80 list contains roughly double that number, and the 50 list roughly doubles that count again. The threshold values are themselves rather arbitrary.