Classification dataset for ENCODE-Roadmap DNase-seq peaks and Transcription Factor ChIP-seq peaks

Classification dataset for machine learning on epigenomic landscapes from ENCODE and Roadmap Epigenomics. The dataset includes the original peak files (BED format) for the DNase-seq and transcription factor (TF) ChIP-seq experiments that were used to label genomic regions as positives or negatives. The DNase-seq peak files along with processing details are in the file "encode-roadmap.DNase-seq.peaks.tar.gz". The TF ChIP-seq peak files along with processing details are in the file "encode.ChIP-seq.peaks.tar.gz". The processed dataset stored in hdf5 format files along with processing details are in the file "nn.encode-roadmap.hdf5_files.tar.gz".