Fig. 3From: Boosting tissue-specific prediction of active cis-regulatory regions through deep learning and Bayesian optimization techniquesTop row: t-SNE projections of task AE + AP versus IE + IP: epigenomic data (a, b) and sequence data (c, d) for, respectively hg19 dataset (a, c) and hg38-dataset (b, d) on one hold-out of the GM12878 cell line. Bottom row: t-SNE projections of task AE + AP versus ELSE: epigenomic data (e) and sequence data (g) shown only for hg19 datasetBack to article page