Analysis methods for studying the 3D architecture of the genome

Abstract

The rapidly increasing quantity of genome-wide chromosome conformation capture data presents great opportunities and challenges in the computational modeling and interpretation of the three-dimensional genome. In particular, with recent trends towards higher-resolution high-throughput chromosome conformation capture (Hi-C) data, the diversity and complexity of biological hypotheses that can be tested necessitates rigorous computational and statistical methods as well as scalable pipelines to interpret these datasets. Here we review computational tools to interpret Hi-C data, including pipelines for mapping, filtering, and normalization, and methods for confidence estimation, domain calling, visualization, and three-dimensional modeling.

Fig. 1

Overview of Hi-C analysis pipelines. These pipelines start from raw reads and produce raw and normalized contact maps for further interpretation. The colored boxes represent alternative ways to accomplish a given step in the pipeline. RE, restriction enzyme. At each step, commonly used file formats (‘.fq’, ‘.bam’, and ‘.txt’) are indicated. a, The blue, pink and green boxes correspond to pre-truncation, iterative mapping and allowing split alignments, respectively. b, Several filters are applied to individual reads. c, The blue and pink boxes correspond to strand filters and distance filters, respectively. d, Three alternative methods for normalization

Fig. 2

Impact of normalization on Hi-C contact maps. a, b Hi-C contact maps of chromosome 8 from the schizont stage of the parasite Plasmodium falciparum [16] at 10 kb resolution before and after normalization. Blue dashed lines represent the centromere location. c, d Density scatter plots of counts before (x-axis) and after (y-axis) normalization of Hi-C data from the human cell line IMR90 [15] at two different resolutions. Correlation values are computed using all intra-chromosomal contacts within human chromosome 8. Only a subset of points are shown for visualization purposes

Fig. 3

Visualization of Hi-C data. An Epigenome Browser snapshot of a 4 Mb region of human chromosome 10. Top track shows Refseq genes. All other tracks display data from the human lymphoblastoid cell line GM12878. From top to bottom these tracks are: smoothed CTCF signal from ENCODE [130]; significant contact calls by Fit-Hi-C using 1 kb resolution Hi-C data (only the contacts >50 kb distance and − log(p-value) ≤25 are shown) [20]; arrowhead domain calls at 5 kb resolution [18]; Armatus multiscale domain calls for three different values of the domain-length scaling factor γ [87]; DI HMM TAD calls at 50 kb resolution [15]; and the heatmap of 10 kb resolution normalized contact counts for GM12878 Hi-C data [18]. The color scale of the heatmap is truncated to the range 20 to 400, with higher contact counts corresponding to a darker color