Cis-to-trans ratio is computed as the ratio of long-range cis reads (>20kb) to trans reads plus long-range cis reads. Typically, cis-to-trans ratio higher than 40% is required. Percentage of long-range cis reads is the ratio of long-range cis reads to total number of reads. Minimum 15% is required and 40% or higher suggests a good library[1]. Convergence is determined as standard deviation of proportions of four read orientations to be <0.002 (Very good) or <0.05 (Good) (See below section Proportion of read orientation versus genomic separation). The slope of log10 contact probability vs distance between 10kb ~ 300kb representing TAD is also provided as well. (See below section Contact probability versus genomic separation.)

Contact frequency (number of reads, left) and proportion of reads (right) are shown, stratified by read orientation. Good four-cutter and six-cutter samples would converge at ~3kb (10^3.5) and ~30kb (10^4.5), respectively[1]. Convergence is determined by the standard deviation of the proportions being less than 0.005.

Figure 1.  Get High-res Image Proportion of read orientation versus genomic separation : 4DNFIFN1RUOT

Contact probability (number of reads, normalized by number of bins and bin size) is shown with respect to genomic separation between mates[2][3]. The slope between distance 10kb ~ 300kb (10^4 ~ 10^5.5) representing a TAD is calculated. A good mitotic sample would have a slope close to ~ -0.76[3].

Figure 2.  Get High-res Image Contact probability versus genomic separation : 4DNFIFN1RUOT