Pituitary BPNet - Models
Collection
3 items • Updated
A BPNet model trained with
bpnet-lite on PIT1 (POU1F1) CUT&RUN data,
used to model base-resolution binding signal and to discover sequence motifs via
TF-MoDISco.
Reported metrics found in exp20_PIT1.performance.tsv.
See exp20_PIT1.evaluate.json for the full evaluation output.
| File | Description |
|---|---|
exp20_PIT1.torch |
Model weights (best validation checkpoint) |
exp20_PIT1.bpnet.fit.json |
Full training configuration (architecture, data paths, chrom split, hyperparameters) |
exp20_PIT1.bpnet.attribute.json |
Configuration used for computing attributions downstream |
exp20_PIT1.performance.tsv |
Reported performance metrics |
exp20_PIT1.evaluate.json |
Full evaluation output |
exp20_PIT1.log |
Training log |