Metadata-Version: 2.1
Name: eosce
Version: 0.1.0
Summary: Ersilia Compound Embeddings
Author: Ersilia
Author-email: hello@ersilia.io
Requires-Python: >=3.7,<4.0
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.7
Classifier: Programming Language :: Python :: 3.8
Classifier: Programming Language :: Python :: 3.9
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Provides-Extra: gpu
Requires-Dist: click (==8.1.3)
Requires-Dist: joblib (==1.2.0)
Requires-Dist: onnxruntime (>=1.14.0,<2.0.0)
Requires-Dist: onnxruntime-gpu (==1.14.0) ; extra == "gpu"
Requires-Dist: rdkit-pypi (==2022.9.4)
Description-Content-Type: text/markdown

# Ersilia Embeddings

A lite wrapper for Ersilia compound embeddings model.

## Quick start guide

### 1. Clone the repository

```bash
git clone https://github.com/ersilia-os/compound-embedding-lite.git
cd compound-embedding-lite
```

### 2. Install the package with pip

```bash
pip install .
```

or if you have a GPU

```bash
pip install .[gpu]
```

### 3. Programatically generate embeddings

```python
from eosce.models import ErsiliaCompoundEmbeddings
model = ErsiliaCompoundEmbeddings()
embeddings = model.transform(["CCOC(=O)C1=CC2=CC(OC)=CC=C2O1"])
```

### 4. Generate embeddings using the cli

```bash
eosce embed "CCOC(=O)C1=CC2=CC(OC)=CC=C2O1"
```

