You need to agree to share your Hugging Face information to access this model
This repository is publicly accessible, but you have to accept the conditions to access its files and content.
PEAgent models are shared before publication for review and collaboration. Please do not redistribute the weights or use them in a publication without contacting the authors.
Log in or Sign Up to review the conditions and access this model content.
PEAgent atlas models (maize, rice, soybean)
Sequence-to-single-cell chromatin-accessibility models from Yao J. et al., "Sequence-based
modeling of plant epigenomes reveals cell-type-specific cis-regulatory grammar" (under review).
Each model reads 1,344 bp of DNA and predicts accessibility in every nucleus of a single-cell
ATAC atlas; predictions are averaged into tissue_celltype groups.
| Species | Assembly | Nuclei | Groups | ACRs |
|---|---|---|---|---|
| Maize (Zea mays) | B73 NAM-5.0 | 50,639 | 94 | 158,586 |
| Rice (Oryza sativa) | Nipponbare MSU7 | 104,029 | 128 | 128,764 |
| Soybean (Glycine max) | Wm82.a4.v1 | 200,732 | 98 | 303,113 |
Files
| Path | Content |
|---|---|
models/<species>/model.h5 |
Keras weights only (no architecture). Rebuild with peagent_tool before loading. |
metadata/<species>_group_metadata.csv |
tissue_celltype groups and the nucleus indices in each. |
acr/<species>_acr_peaks.bed |
Training ACR set, 0-based BED. Model window = 1,344 bp centred on (start+end)//2. |
backgrounds/<species>_synergy_backgrounds.fa |
The paper's 100 GC-matched non-accessible genomic windows used for motif-synergy tests. |
paper/Table_S1..S6_*.tsv, paper/lexicon_celltypes.tsv |
The paper's supplementary result tables, queryable by the agent. |
MD5SUMS |
Checksums. |
Use
These files are downloaded automatically by peagent-agent
(the PEAgent agent plugin and the peagent_tool Python library) once access is granted:
export HF_TOKEN=hf_xxx # a read token of an approved account
Interactive portal: https://peagent.org
- Downloads last month
- -