Add BPNet model ENCSR098SSC (ENCSR000EXZ)

.gitattributes

@@ -33,3 +33,8 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+fold_0/saved_model/variables/variables.data-00000-of-00001 filter=lfs diff=lfs merge=lfs -text
+fold_1/saved_model/variables/variables.data-00000-of-00001 filter=lfs diff=lfs merge=lfs -text
+fold_2/saved_model/variables/variables.data-00000-of-00001 filter=lfs diff=lfs merge=lfs -text
+fold_3/saved_model/variables/variables.data-00000-of-00001 filter=lfs diff=lfs merge=lfs -text
+fold_4/saved_model/variables/variables.data-00000-of-00001 filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,54 @@
+---
+license: cc-by-4.0
+library_name: bpnet
+tags:
+  - bpnet
+  - dna
+  - genomics
+  - transcription-factor-binding
+  - encode
+  - ChIP-seq
+  - hg38
+  - qc-unvalidated
+  - GATA3
+---
+
+# ENCODE BPNet -- GATA3 ChIP-seq in SH-SY5Y (ENCSR000EXZ)
+
+Trained BPNet model (ChIP-seq) from the ENCODE project.
+
+- Experiment: [ENCSR000EXZ](https://www.encodeproject.org/experiments/ENCSR000EXZ/)
+- Model annotation: [ENCSR098SSC](https://www.encodeproject.org/annotations/ENCSR098SSC/)
+- Assembly: hg38 · Target: GATA3 · Biosample: SH-SY5Y
+
+## QC
+- Status: **unvalidated**
+- Notes: Found direct motif (counts, profile); Low model performance (<0.5);
+
+## 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-GATA3-ChIP-seq-SH-SY5Y-ENCSR000EXZ-ENCSR098SSC")
+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).

config.json

@@ -0,0 +1,45 @@
+{
+    "input_len": 2114,
+    "output_profile_len": 1000,
+    "motif_module_params": {
+        "filters": [64],
+        "kernel_sizes": [21],
+        "padding": "valid"
+    },
+    "syntax_module_params": {
+        "num_dilation_layers": 8,
+        "filters": 64,
+        "kernel_size": 3,
+        "padding": "valid",
+        "pre_activation_residual_unit": true
+    },
+    "profile_head_params": {
+        "filters": 1,
+        "kernel_size":  75,
+        "padding": "valid"
+    },
+    "counts_head_params": {
+        "filters": 1,
+        "kernel_size":  75,
+        "padding": "valid",
+        "units": [1],
+        "activations":["linear"],
+		"dropouts":[0]
+		
+    },
+    "profile_bias_module_params": {
+        "kernel_sizes": [1]
+    },
+    "counts_bias_module_params": {
+    },
+    "use_attribution_prior": false,
+    "attribution_prior_params": {
+        "frequency_limit": 150,
+        "limit_softness": 0.2,
+        "grad_smooth_sigma": 3,
+        "profile_grad_loss_weight": 200,
+        "counts_grad_loss_weight": 100        
+    },
+    "loss_weights": [1, 75.7348652453741],
+    "counts_loss": "MSE"
+}

fold_0/model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6f43b762173a85191784639f33951d7cb3c1ab15a8c71ca298436a047e60c71
+size 561784

fold_0/saved_model/saved_model.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc55ceb9780b9bdcd6d0951dc096a76da47b21ab63530048d6e67e5e7d3a454c
+size 750200

fold_0/saved_model/variables/variables.data-00000-of-00001

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6041d45a4271d07a7a919c7987c7a99b8bac15a4b8b41792a1ba1909c0987ea
+size 1393322

fold_1/model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea7bbc0a7a3161922626d48bf4b1df568fd7654afd72226ab4683cfd839fef5a
+size 561784

fold_1/saved_model/saved_model.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b623b3240f3c0b80793f78decc7862faa3e6edf3da9280b22453e731b82dc74
+size 750200

fold_1/saved_model/variables/variables.data-00000-of-00001

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb46984dd5c8f327172a517f75a7468a291400f89305d1174ec9e42051b12d36
+size 1393322

fold_2/model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d768af665dab7d7a884018b28c6d887ec166d7d37dd0ab4a08344b84d98e7255
+size 561784

fold_2/saved_model/saved_model.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:624712d3b6e8fb50da0c7ec4ea1acd0598ac9c6c6cf130b0c2d3653d21bed3bb
+size 750200

fold_2/saved_model/variables/variables.data-00000-of-00001

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25b084943a3caee18202f6602e7581c0ac8fa9f498e3c733197b9631fe8784e0
+size 1393322

fold_3/model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6dabf4168b966fbce05f06a2fa4bbd27902278518ca008eebe61e7011d1a907a
+size 561784

fold_3/saved_model/saved_model.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b125f86a2b8aef5dcfd48fecd944a96f237637a4e331d338fc157a9a2883bf3d
+size 750200

fold_3/saved_model/variables/variables.data-00000-of-00001

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:215a1dfc904290bebf634cc9ca8937bb88f4ad668a301305ae2f39c69fa599bc
+size 1393322

fold_4/model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b966ebc3f15db5379d04b62536aabefc0106e9e478c1018bd28b3ef27ff17b2
+size 561784

fold_4/saved_model/saved_model.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dec789059e1564eab63b3e5b0038bd2f50dd935d31dd1ea0519999c98a20749f
+size 750200

fold_4/saved_model/variables/variables.data-00000-of-00001

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ec099cf0c4490f1ae5f9b2384faaffb1f756bfe4499542003d19c121c4a8114
+size 1393322