Ctrl-DNA × NTV3-100M-POST per-cell enhancer generators (T1)
Lagrangian primal-dual reinforcement-learning fine-tunes of
InstaDeepAI's NTv3 backbones for cell-type-specific enhancer
generation in a 7-cell brain panel (Excitatory, Inhibitory, OPC,
Astrocyte, Oligodendrocyte, Microglia, Endothelial). One model is
trained per target cell; the on-target oracle drives the reward,
and the six off-target oracles drive the constraint terms. Following
the Ctrl-DNA recipe (Chen et al., 2025; bowang-lab/Ctrl-DNA), 2000
RL steps × per-cell on a stratified 35,000-row T1 subset
(train.enhancer_generation.strat7c.n35k).
Folder layout
Each cell type has its own subfolder; load the policy via
regureasoner.baselines.ctrl_dna.policy.CtrlDNAPolicy.load(...)
with the matching NTv3 backbone snapshot.
Ex/ best.pt # full policy state dict (NTv3 + lambda + step)
metrics.json # 28-column eval against gold n7k held-out test
samples_generated.jsonl # ~64 generated enhancers from final policy
training_log.jsonl # per-step train metrics (loss / reward / lambda)
In/ ...
OPC/ ...
Ast/ ...
Oli/ ...
Mic/ ...
End/ ...
Headline eval (held-out gold n7k, oracle-based)
Higher argmax_acc and specificity are better; lower fid is
better. Random argmax baseline = 0.143 (1/7 cells).
| cell | parse_rate | argmax_acc | on_target | off_target | specificity | FID |
|---|---|---|---|---|---|---|
| Ex | 1.000 | 0.625 | 0.045 | -20.283 | 20.329 | 22.946 |
| In | 1.000 | 0.625 | -1.379 | -15.172 | 13.793 | 48.750 |
| OPC | 1.000 | 0.000 | -2.984 | -3.627 | 0.644 | 342.561 |
| Ast | 1.000 | 0.109 | -18.677 | -15.324 | -3.354 | 90.369 |
| Oli | 1.000 | 0.703 | 2.115 | -2.494 | 4.609 | 433.018 |
| Mic | 1.000 | 0.000 | -6.625 | -10.303 | 3.677 | 210.108 |
| End | 1.000 | 0.562 | 2.611 | -1.775 | 4.386 | 432.451 |
Training recipe (verbatim)
# Per-cell run (one of seven, NTv3-650M shown — 100M variant
# uses NTV3_SNAPSHOT_PATH=/extra/.../ntv3_local/100m_post)
TARGET_CELL=Ex N_RL_STEPS=2000 BATCH_SIZE=8 \
NTV3_SNAPSHOT_PATH=/extra/zhanglab0/INDV/pengchx3/ntv3_local/generative \
sbatch slurm/run_ctrl_dna_t1.sh
See the upstream Ctrl-DNA repository for the algorithmic background and the lab port at explcre/biomodel_reasoning_calling_study2 for our extension (NTv3 backbone, oracle reward, 7-cell panel).
Citation
@misc{dnathinker_ctrl_dna_per_cell_2026,
title = {Per-cell Ctrl-DNA enhancer generators on the NTv3 backbone},
author = {Xu, Pengcheng and the DNAThinker team},
year = {2026},
howpublished = {\url{https://huggingface.co/explcre/ctrl_dna_*_per_cell_t1}}
}