Proteins with ESM

Predict the whole sequence and 3D structure of masked protein sequences with ESM by Evolutionary Scale.

How to use it

Locally - Build from scratch

The predictions are computationally-intense, you should have at least 16GB RAM and 4 core CPU

1. Clone this repository:

git clone https://github.com/AstraBert/proteins-w-esm.git
cd proteins-w-esm

2. Rename .env.example to .env and modify it with your Hugging Face access token (read or write permissions, fine-grained is nut supported)
3. Launch the application and wait for it to load on http://localhost:7860

python3 app.py

Locally - Use Docker image

1. Pull Docker image

docker pull astrabert/proteinswithesm:latest

2. Run the image and wait for it to load on http://localhost:7860:

docker run -p 7860:7860 astrabert/proteinswithesm:latest

Online - Hugging Face demo

Use directly the Hugging Face Space demo that you can find here.

Online - Use GitHub CodeSpaces

Click the <> Code green button and then click on CodeSpaces -> Create CodeSpace on 'main'.

You should be redirected to a VSCode-based space connected to the port on which the app runs, directly accessible under the "Ports" section of the VSCode interface.