kzkedzierska's picture
Upload README.md with huggingface_hub
80baadf verified
|
Raw
History Blame Contribute Delete
1.55 kB
metadata
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
  - macaque
  - dilated_cnn

AllenInstitute/BG-macaque-dilatedCNN

Dilated CNN trained on macaque (Macaca mulatta) basal ganglia chromatin accessibility across 58 cell-type tracks. Part of the DNA sequence-modeling resources for the basal ganglia cell atlas. Published in Johansen, Fu et al., 2025.

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: macaque
  • Number of tracks: 58
  • Framework: PyTorch Lightning
  • Checkpoint format: Lightning .ckpt

Target Tracks

  • AMY-SLEA-BNST_D1_GABA
  • AMY-SLEA-BNST_GABA
  • Astrocyte
  • BAM
  • BF_SKOR1_Glut
  • COP
  • Endo
  • Ependymal
  • GPe-NDB-SI_LHX6-LHX8-GBX1_GABA
  • GPe_MEIS2-SOX6_GABA
  • ... (48 more)

Usage

from regrex.models import load_model

model = load_model("AllenInstitute/BG-macaque-dilatedCNN")