| --- |
| license: mit |
| tags: |
| - bpnet |
| - bpnet-lite |
| - genomics |
| - chip-seq |
| - transcription-factor |
| - tbx19 |
| - mouse |
| - mm10 |
| library_name: bpnet-lite |
| --- |
| |
| # BPNet_ChIP-seq_TBX19 |
|
|
| A [BPNet](https://www.nature.com/articles/s41588-021-00782-6) model trained with |
| [`bpnet-lite`](https://github.com/jmschrei/bpnet-lite) on TBX19 (TPIT) ChIP-seq data |
| from mouse pituitary cells, used to model base-resolution binding signal and to |
| discover sequence motifs via TF-MoDISco. |
|
|
| > TBX19 (also known as TPIT) is the transcription factor; "TPIT" is the experiment/antibody |
| > label used in the underlying ChIP-seq files from which this model was trained. |
|
|
| ## Performance |
| Reported metrics found in `exp16_TPIT.performance.tsv`. |
|
|
| See `exp16_TPIT.evaluate.json` for the full evaluation output. |
|
|
| ## Files |
|
|
| | File | Description | |
| |---|---| |
| | `exp16_TPIT.torch` | Model weights (best validation checkpoint) | |
| | `exp16_TPIT.bpnet.fit.json` | Full training configuration (architecture, data paths, chrom split, hyperparameters) | |
| | `exp16_TPIT.bpnet.attribute.json` | Configuration used for computing attributions downstream | |
| | `exp16_TPIT.performance.tsv` | Reported performance metrics | |
| | `exp16_TPIT.evaluate.json` | Full evaluation output | |
| | `exp16_TPIT.log` | Training log | |
