spatzie: an R package for identifying significant transcription factor motif co-enrichment from enhancer-promoter interactions

Abstract

Genomic interactions provide important context to our understanding of the state of the genome. One question is whether specific transcription factor interactions give rise to genome organization. We introduce spatzie, an R package and a website that implements statistical tests for significant transcription factor motif cooperativity between enhancer-promoter interactions. We conducted controlled experiments under realistic simulated data from ChIP-seq to confirm spatzie is capable of discovering co-enriched motif interactions even in noisy conditions. We then use spatzie to investigate cell type specific transcription factor cooperativity within recent human ChIA-PET enhancer-promoter interaction data. The method is available online at https://spatzie.mit.edu.

Figure 1.

spatzie identifies motif pairs underlying enhancer–promoter interactions using co-occurrence and correlation statistics. (A) spatzie is designed to identify transcription factors which are facilitating interactions between enhancers and promoters based on detecting co-enrichment relationships between the presence of DNA-binding motifs in enhancer–promoter pairs. (B) Given input of a database of transcription factor DNA-binding motifs and a set of enhancer–promoter interactions, scan interactions for motifs, then limit analysis by filtering to motifs that are frequently present within the interactions of interest. Next we compute pairwise significance of motif co-occurrence in the enhancer and promoter data. Finally, we filter motif pairs that significantly co-occur under multiple hypothesis correction.

Figure 2.

spatzie validates co-enrichment of ELF1 and USF1 on simulated enhancer–promoter interaction data. (A) spatzie cooperativity estimation computed using correlation of motif scores shows significant enhancer–promoter interactions for USF1 and ELF1 motifs. (B) spatzie cooperativity estimation computed using correlation of counts shows strongest enrichment between USF1 and ELF1 motifs. (C) spatzie cooperativity estimation computed using motif instance co-occurrence shows significant co-enrichment of USF2 and ELF1 motifs. Adjusted P-values were corrected with the Benjamini-Hochberg procedure. Randomization experiments where top of enhancer events are randomly permuted shows shrinking significance of co-enrichment under noisy data for (D) score correlation, (E) count correlation and (F) hypergeometric co-enrichment. Dashed line represents the significance threshold at p < 0.05 under Bonferroni correction.

Figure 3.

spatzie identifies transcription factor cooperation underlying interactions that are germ line and tissue-specific. (A) Pearson correlation of pairwise interactions shows similarity between related tissues. PCA on spatzie discovered transcription factor interactions shows (B) germ layer and (C) tissue type clustering. (D) Pairwise correlation of spatzie transcription factor motif interactions shows increasing relatedness of germ layer and tissue type. Significance computed by Wilcoxon rank-sum test. (E) Extraction of germ layer-specific transcription factor motif interactions include relevant lineage-determining transcription factor families, such as Fox in endoderm and ectoderm. Spatzie correlation scores are z-scores normalized by row. Each column represents an independent cell type, the colors above denote the germ layer. (F) Extraction of tissue-specific transcription factor motif interactions include potential transcription factor trade-offs at the promoter and enhancer that may mediate tissue-specific enhancer–promoter interactions. Spatzie correlation scores are z-scores normalized by row.