Fig. 2From: Boosting tissue-specific prediction of active cis-regulatory regions through deep learning and Bayesian optimization techniquesTop row: t-SNE projections of task AP versus IP: epigenomic data (a, b) and sequence data (c, d) for hg19 dataset (a, c) and hg38-dataset (b, d) on one hold-out of the GM12878 cell line, respectively. Bottom row: t-SNE projections of task AE versus IE: epigenomic data (e, f) and sequence data (g, h) for hg19 dataset (e, g) and hg38-dataset (f, h) on one hold-out of the GM12878 cell line, respectivelyBack to article page