---
license: cc-by-4.0
library_name: bpnet
tags:
  - bpnet
  - dna
  - genomics
  - transcription-factor-binding
  - encode
  - ChIP-seq
  - hg38
  - qc-passed
  - CTCF
---

# ENCODE BPNet -- CTCF ChIP-seq in breast epithelium (ENCSR697YIN)

Trained BPNet model (ChIP-seq) from the ENCODE project.

- Experiment: [ENCSR697YIN](https://www.encodeproject.org/experiments/ENCSR697YIN/)
- Model annotation: [ENCSR582FZD](https://www.encodeproject.org/annotations/ENCSR582FZD/)
- Assembly: hg38 · Target: CTCF · Biosample: breast epithelium

## QC
- Status: **passed**
- Notes: Found direct motif (counts, profile);

## Files
5-fold cross-validation. Each `fold_*/` holds the trained model in two forms:
- `model.h5` — Keras weights (needs the `bpnet` custom layer to load)
- `saved_model/` — TensorFlow SavedModel (portable; loads with no extra deps)

## Load
```python
from huggingface_hub import snapshot_download
import tensorflow as tf
d = snapshot_download("kundajelab/encode-bpnet-CTCF-ChIP-seq-breast-epithelium-ENCSR697YIN-ENCSR582FZD")
model = tf.saved_model.load(f"{d}/fold_0/saved_model")  # portable
# Keras .h5 (needs the bpnet package):
# from bpnet.model.custommodel import CustomModel
# m = tf.keras.models.load_model(f"{d}/fold_0/model.h5",
#         custom_objects={'CustomModel': CustomModel})
```

## Inference inputs
The `serving_default` signature takes **three** inputs (not sequence alone):
- `sequence` — one-hot DNA, shape `(N, 2114, 4)`
- `profile_bias_input_0` — control (bias) profile track, shape `(N, 1000, 2)`
- `counts_bias_input_0` — control log-count(s), shape `(N, 2)`

The bias inputs are the experiment's matched control signal (the model file's `derived_from` control bigWigs on the ENCODE portal). Outputs: `profile_predictions` `(N, 1000, 2)` and `logcounts_predictions` `(N, 1)`. Reverse-complement averaging is the production default.

## License & citation
Released under CC-BY-4.0, matching the [ENCODE data-use policy](https://www.encodeproject.org/about/data-use-policy/). Please cite the ENCODE Project Consortium and the model software: [BPNet](https://github.com/kundajelab/bpnet) (Avsec et al., Nat Genet 2021).