DeepBurst: Pretrained model checkpoints (H1, HepG2, GM12878)
Abstract
This record releases the pretrained DeepBurst model weights (checkpoints) for reproducing our experimental results and for downstream applications. DeepBurst is a Transformer-based framework that leverages promoter-proximal histone-modification features to predict transcriptional bursting–related phenotypes (e.g., classification/decision tasks for burst frequency and burst size, as defined in the manuscript).
Fields of Study & Subjects
Genomics and Chromatin Dynamics
Gene Regulatory Network Analysis
Single-cell and spatial transcriptomics
Publication details
- Journal / source
- Zenodo (CERN European Organization for Nuclear Research)
- Publication date
- 12 January 2026
- Document type
- Dataset