Genome-wide chromatin remodeling identified at GC-rich long nucleosome-free regions

Abstract

To gain deeper insights into principles of cell biology, it is essential to understand how cells reorganize their genomes by chromatin remodeling. We analyzed chromatin remodeling on next generation sequencing data from resting and activated T cells to determine a whole-genome chromatin remodeling landscape. We consider chromatin remodeling in terms of nucleosome repositioning which can be observed most robustly in long nucleosome-free regions (LNFRs) that are occupied by nucleosomes in another cell state. We found that LNFR sequences are either AT-rich or GC-rich, where nucleosome repositioning was observed much more prominently in GC-rich LNFRs - a considerable proportion of them outside promoter regions. Using support vector machines with string kernels, we identified a GC-rich DNA sequence pattern indicating loci of nucleosome repositioning in resting T cells. This pattern appears to be also typical for CpG islands. We found out that nucleosome repositioning in GC-rich LNFRs is indeed associated with CpG islands and with binding sites of the CpG-island-binding ZF-CXXC proteins KDM2A and CFP1. That this association occurs prominently inside and also prominently outside of promoter regions hints at a mechanism governing nucleosome repositioning that acts on a whole-genome scale.

Figure 1. GC content distributions of LNFRs versus random fragments from the human genome.

GC content distributions of LNFRs in resting T cells (A) and activated T cells (B) compared to the GC content distribution of fragments drawn randomly from the human genome (C). For both resting and activated T cells, the LNFRs are divided into two groups, an AT-rich and a GC-rich one. For resting T cells, the two groups are very clearly separated by a GC content threshold of about 60%, while this threshold is at 50% for activated T cells.

Figure 2. Maximum nucleosome occupancy scores over masked LNFRs.

Panel A shows a histogram of maximum nucleosome occupancy scores in activated T cells over masked (i.e. without the first and the last 25 bp) LNFRs in resting state. Panel B shows a histogram of maximum nucleosome occupancy scores in resting T cells over masked LNFRs in activated state. AT-rich LNFRs generally exhibit lower nucleosome coverage than GC-rich LNFRs, which indicates that GC-rich LNFRs show a stronger remodeling tendency than AT-rich LNFRs.

Figure 3. Classification performance versus sub-sequence length.

Two-fold cross validation accuracies for the classification of GC-rich LNFRs showing remodeling versus randomly selected non-LNFR sequences for different choices of , the sub-sequence length parameter of the spectrum kernel. For resting T cells, the accuracy peaks at , while 's between 4 and 6 are best for classifying GC-rich remodeling LNFRs in activated T cells.

Figure 4. Sequence logo of remodeling pattern for both DNA strands.

The pattern was identified by applying MEME to the regions of interest obtained from the prediction profiles computed by the SVM with the spectrum kernel with .

Figure 5. Average prediction profiles around occurrences of the pattern GGGGCGGGG/CCCCGCCCC.

Each curve corresponds to the average prediction profiles around the occurrences of the pattern in GC-rich remodeled LNFRs of resting T cells. The different curves correspond to different choices of .

Figure 6. Proportion of LNFRs overlapping with CpG islands plotted versus the LNFRs' GC content.

Each curve plots the proportion of LNFRs overlapping with CpG islands in relation to the GC content of the considered LNFRs. The plot in panel A shows data for LNFRs of resting T cells, while the plot in panel B shows data for LNFRs of activated T cells. For resting T cells, a clear difference between remodeled and non-remodeled LNFRs is visible, both if we consider all LNFRs and if we restrict to non-promoter LNFRs. The proportions of overlaps of LNFRs of activated T cells with CpG islands are generally lower and no clear difference is visible between remodeled and non-remodeled LNFRs.