Fig. 3
From: Distributed gene expression modelling for exploring variability in epigenetic function
a Genome-wide accuracy of mRNA transcript abundance predictions (adj. R 2) for models trained and tested on each pairwise combination of cell lines. These results are strikingly non-symmetric, with significant dissimilarity between columns (predictions) but not rows (training observations). b Distribution of each fitted model parameter, \(\hat {\beta }_{m}\), across all cell-lines considered in this study