Skip to main content
Fig. 5 | BMC Bioinformatics

Fig. 5

From: DeepTSS: multi-branch convolutional neural network for transcription start site identification from CAGE data

Fig. 5

Evaluation of algorithms based on H3K4me3 and TF ChIP-Seq peaks as well as ChromHMM-derived chromatin states from the analysis of six histone modifications in K562 cells. Percentage of each algorithm’s positive (a) and negative (b) predictions overlapping chromatin states associated with genomic regions exhibiting active (left panel) and weak/repressed (right panel) transcription. Percentage of the algorithms’ positive predictions with at least one TFBS (c) and H3K4me3 peak (d) derived from ChIP-Seq

Back to article page

BMC Bioinformatics

ISSN: 1471-2105

Contact us