Chromatin accessibility and regulatory vocabulary across indicine cattle tissues

Abstract

Background: Spatiotemporal changes in the chromatin accessibility landscape are essential to cell differentiation, development, health, and disease. The quest of identifying regulatory elements in open chromatin regions across different tissues and developmental stages is led by large international collaborative efforts mostly focusing on model organisms, such as ENCODE. Recently, the Functional Annotation of Animal Genomes (FAANG) has been established to unravel the regulatory elements in non-model organisms, including cattle. Now, we can transition from prediction to validation by experimentally identifying the regulatory elements in tropical indicine cattle. The identification of regulatory elements, their annotation and comparison with the taurine counterpart, holds high promise to link regulatory regions to adaptability traits and improve animal productivity and welfare.

Results: We generate open chromatin profiles for liver, muscle, and hypothalamus of indicine cattle through ATAC-seq. Using robust methods for motif discovery, motif enrichment and transcription factor binding sites, we identify potential master regulators of the epigenomic profile in these three tissues, namely HNF4, MEF2, and SOX factors, respectively. Integration with transcriptomic data allows us to confirm some of their target genes. Finally, by comparing our results with Bos taurus data we identify potential indicine-specific open chromatin regions and overlaps with indicine selective sweeps.

Conclusions: Our findings provide insights into the identification and analysis of regulatory elements in non-model organisms, the evolution of regulatory elements within two cattle subspecies as well as having an immediate impact on the animal genetics community in particular for a relevant productive species such as tropical cattle.

Keywords: ATAC-seq; Bos indicus; Motif discovery; Open chromatin region.

Fig. 1

Comparison of ATAC-seq peaks across different tissues (considering chromosomes 1-29 and X). A Profile of peaks relative to transcription start sites (TSS), considering a ± 3 kb region, for individual tissues (top heatmap) and comparing tissue average profiles (bottom distribution). B Percentage of overlap between peaks and genomic features. C Percentage of peaks upstream and downstream from the TSS of their nearest genes

Fig. 2

Comparison between tissue-specific (TS) peaks and constitutive regions for muscle (MUS), liver (LIV), and hypothalamus (HYP). A Profile of peaks relative to transcription start sites (TSS) considering a ± 3 kb region—confidence intervals were estimated by bootstrap method (500 iterations) and is shown as the shading that follows each curve. B Percentage of overlap between peaks and genomic features. C Functional enrichment of top 10 gene ontology (GO) terms for genes associated to peaks

Fig. 3

Top 5 iRegulon motif discovery results on liver-specific (A), muscle-specific (B), and hypothalamus-specific (C) open chromatin regions

Fig. 4

Liver-specific master regulator HNF4 and its predicted targets. Dotted edges represent predicted targets, continuous edges and red borders represent targets with significant co-expression using RNA-seq data

Fig. 5

Potential indicine-specific peaks in muscle (MUS), liver (LIV) and hypothalamus (HYP). A Profile of peaks relative to transcription start sites (TSS) considering a ± 3 kb region—confidence intervals were estimated by bootstrap method (500 iterations) and is shown as the shading that follows each curve. B Percentage of overlap between peaks and genomic features. C Representation of bovine chromosome 5 and the location of indicine selective sweeps (green dots), peaks from all three tissues overlapping selective sweeps (red dots), and genes in close proximity (blue dots)