| library_name: regrex | |
| license: other | |
| license_name: allen-institute-software-license | |
| license_link: LICENSE | |
| tags: | |
| - pytorch | |
| - lightning | |
| - genomics | |
| - regrex | |
| - neuroscience | |
| - regulatory-genomics | |
| - sequence-to-function | |
| - basal-ganglia | |
| - human | |
| - dilated_cnn | |
| # AllenInstitute/BG-human-dilatedCNN | |
| Dilated CNN trained on human (*Homo sapiens*) basal ganglia chromatin accessibility across 59 cell-type tracks. Part of the DNA sequence-modeling resources for the basal ganglia cell atlas. Published in [Johansen, Fu et al., 2025](https://doi.org/10.64898/2025.12.15.694496). | |
| ### Background | |
| Learns cis-regulatory sequence logic underlying basal ganglia cell-type specialization from snATAC-seq accessibility profiles. Use it to score candidate enhancers, run in silico mutagenesis, or guide cell-type-specific sequence design. | |
| ### Availability | |
| Currently private. RegRex (formerly `enhancer-designer`) is an internal Allen Institute tool with a public release planned. For early access contact Kasia Kedzierska (kasia.kedzierska@alleninstitute.org). | |
| ## Model Details | |
| - **Architecture:** dilated_cnn | |
| - **Species:** human | |
| - **Number of tracks:** 59 | |
| - **Framework:** PyTorch Lightning | |
| - **Checkpoint format:** Lightning .ckpt | |
| ## Target Tracks | |
| - AMY-SLEA-BNST_D1_GABA | |
| - AMY-SLEA-BNST_GABA | |
| - Astrocyte | |
| - BAM | |
| - BF_SKOR1_Glut | |
| - B_cells | |
| - COP | |
| - Endo | |
| - Ependymal | |
| - GPe-NDB-SI_LHX6-LHX8-GBX1_GABA | |
| - ... (49 more) | |
| ## Usage | |
| ```python | |
| from regrex.models import load_model | |
| model = load_model("AllenInstitute/BG-human-dilatedCNN") | |
| ``` | |