Spaces:
Running
Running
Merge branch 'main' of https://huggingface.co/spaces/ml-jku/tox21_gin_classifier
Browse files
README.md
CHANGED
|
@@ -9,11 +9,14 @@ license: cc-by-nc-4.0
|
|
| 9 |
short_description: Graph Isomorphism Network Baseline Classifier for Tox21
|
| 10 |
---
|
| 11 |
|
| 12 |
-
# Tox21 Graph Isomorphism Network Classifier
|
| 13 |
|
| 14 |
This repository hosts a Hugging Face Space that provides an examplary API for submitting models to the [Tox21 Leaderboard](https://huggingface.co/spaces/ml-jku/tox21_leaderboard).
|
| 15 |
|
| 16 |
-
|
|
|
|
|
|
|
|
|
|
| 17 |
|
| 18 |
**Important:** For leaderboard submission, your Space needs to include training code. The file `train.py` should train the model using the config specified inside the `config/` folder and save the final model parameters into a file inside the `checkpoints/` folder. The model should be trained using the [Tox21_dataset](https://huggingface.co/datasets/ml-jku/tox21) provided on Hugging Face. The datasets can be loaded like this:
|
| 19 |
```python
|
|
|
|
| 9 |
short_description: Graph Isomorphism Network Baseline Classifier for Tox21
|
| 10 |
---
|
| 11 |
|
| 12 |
+
# Tox21 Graph Isomorphism Network (GIN) Classifier
|
| 13 |
|
| 14 |
This repository hosts a Hugging Face Space that provides an examplary API for submitting models to the [Tox21 Leaderboard](https://huggingface.co/spaces/ml-jku/tox21_leaderboard).
|
| 15 |
|
| 16 |
+
Here a [Graph Isomorphism Network(GIN)](https://arxiv.org/abs/1810.00826) is trained on the Tox21 dataset, and the trained models are provided for
|
| 17 |
+
inference. Model input is a SMILES string of the small molecule, and the output are 12 numeric values for
|
| 18 |
+
each of the toxic effects of the Tox21 dataset.
|
| 19 |
+
|
| 20 |
|
| 21 |
**Important:** For leaderboard submission, your Space needs to include training code. The file `train.py` should train the model using the config specified inside the `config/` folder and save the final model parameters into a file inside the `checkpoints/` folder. The model should be trained using the [Tox21_dataset](https://huggingface.co/datasets/ml-jku/tox21) provided on Hugging Face. The datasets can be loaded like this:
|
| 22 |
```python
|
app.py
CHANGED
|
@@ -37,7 +37,7 @@ def root():
|
|
| 37 |
"/healthz": "GET - Health check",
|
| 38 |
"/predict": "POST - Predict toxicity for SMILES",
|
| 39 |
},
|
| 40 |
-
"usage": "Send POST to /predict with {'smiles': ['your_smiles_here']}
|
| 41 |
}
|
| 42 |
|
| 43 |
|
|
@@ -46,7 +46,6 @@ def metadata():
|
|
| 46 |
return {
|
| 47 |
"name": "Tox21 GIN Classifier",
|
| 48 |
"version": "0.1.0",
|
| 49 |
-
"max_batch_size": 256,
|
| 50 |
"tox_endpoints": [
|
| 51 |
"NR-AR",
|
| 52 |
"NR-AR-LBD",
|
|
@@ -74,5 +73,5 @@ def predict(request: Request):
|
|
| 74 |
predictions = predict_func(request.smiles)
|
| 75 |
return {
|
| 76 |
"predictions": predictions,
|
| 77 |
-
"model_info": {"name": "Tox21 GIN
|
| 78 |
}
|
|
|
|
| 37 |
"/healthz": "GET - Health check",
|
| 38 |
"/predict": "POST - Predict toxicity for SMILES",
|
| 39 |
},
|
| 40 |
+
"usage": "Send POST to /predict with {'smiles': ['your_smiles_here']}",
|
| 41 |
}
|
| 42 |
|
| 43 |
|
|
|
|
| 46 |
return {
|
| 47 |
"name": "Tox21 GIN Classifier",
|
| 48 |
"version": "0.1.0",
|
|
|
|
| 49 |
"tox_endpoints": [
|
| 50 |
"NR-AR",
|
| 51 |
"NR-AR-LBD",
|
|
|
|
| 73 |
predictions = predict_func(request.smiles)
|
| 74 |
return {
|
| 75 |
"predictions": predictions,
|
| 76 |
+
"model_info": {"name": "Tox21 GIN classifier", "version": "0.1.0"},
|
| 77 |
}
|