Model-based analysis of ChIP-Seq (MACS)

Abstract

We present Model-based Analysis of ChIP-Seq data, MACS, which analyzes data generated by short read sequencers such as Solexa's Genome Analyzer. MACS empirically models the shift size of ChIP-Seq tags, and uses it to improve the spatial resolution of predicted binding sites. MACS also uses a dynamic Poisson distribution to effectively capture local biases in the genome, allowing for more robust predictions. MACS compares favorably to existing ChIP-Seq peak-finding algorithms, and is freely available.

Figure 1

MACS model for FoxA1 ChIP-Seq. (a,b) The 5' ends of strand-separated tags from a random sample of 1,000 model peaks, aligned by the center of their Watson and Crick peaks (a) and by the FKHR motif (b). (c) The tag count in ChIP versus control in 10 kb windows across the genome. Each dot represents a 10 kb window; red dots are windows containing ChIP peaks and black dots are windows containing control peaks used for FDR calculation. (d) Tag density profile in control samples around FoxA1 ChIP-Seq peaks. (e,f) MACS improves the motif occurrence in the identified peak centers (e) and the spatial resolution (f) for FoxA1 ChIP-Seq through tag shifting and λ_local. Peaks are ranked by p-value. The motif occurrence is calculated as the percentage of peaks with the FKHR motif within 50 bp of the peak summit. The spatial resolution is calculated as the average distance from the summit to the nearest FKHR motif. Peaks with no FKHR motif within 150 bp of the peak summit are removed from the spatial resolution calculation.

Figure 2

Comparison of MACS with ChIPSeq Peak Finder, FindPeaks and QuEST. (a-f) Shown is the FDR for FoxA1 (a) and NRSF (b) ChIP-Seq, motif occurrence within 50 bp of the peak centers for FoxA1 (c) and NRSF (d), and the average distance from the peak center to the nearest motif (peaks with no motif within 150 bp from peak center are removed) for FoxA1 (e) and NRSF (f).

Figure 3

Comparison of FoxA1 ChIP-Seq and ChIP-chip. (a) Overlap between the FoxA1 binding sites detected by ChIP-chip (MAT; FDR <1% and fold-enrichment >2) and ChIP-Seq (MACS; FDR <1%). Shown are the numbers of regions detected by both platforms (that is, having at least 1 bp in common) or unique to each platform. (b) The distributions of ChIP-Seq tag number and ChIP-chip MATscore [13] for FoxA1 binding sites identified by both platforms. (c) MATscore distributions of FoxA1 ChIP-chip at ChIP-Seq/chip overlapping peaks, ChIP-Seq unique peaks, and genome background. For each peak, the mean MATscore for all probes within the 300 bp region centered at the ChIP-Seq peak summit is used. Genome background is based on MATscores of all array probes in the FoxA1 ChIP-chip data. (d) Width distributions of FoxA1 ChIP-Seq/chip overlapping peaks and ChIP-Seq unique peaks at different fold-enrichments (less than 25, 25 to 50, and larger than 50). (e) Spatial resolution for FoxA1 ChIP-chip and ChIP-Seq peaks. The Wilcoxon test was used to calculate the p-values for (d) and (e). (f) Motif occurrence within the central 200 bp regions for FoxA1 ChIP-Seq/chip overlapping peaks and platform unique peaks. Error bars showing standard deviation were calculated from random sampling of 500 peaks ten times for each category. Background motif occurrences are based on 100,000 randomly selected 200 bp regions in the human genome, excluding regions in genome assembly gaps (containing 'N').