This project is designed to process and analyze molecular data using Ligand based models run with CPSign. It includes components for data storage, processing, and web-based interaction.
- Navigate to the specified serving url.
- Upload a csv smiles file.
Se the example in test/smiles_example.csv for valid input file format.
There are two options. Docker-compose is fast to get started. The alternative and production-like alternative is skaffold. See skaffold.dev for more information on how to run.
To use this project, follow these steps:
-
Clone the repository:
git clone https://github.com/pharmbio/ptp.git cd ptp -
Run the application:
docker-compose up --build
-
Modify values.yaml according to your specification.
-
Deploy using Helm:
helm install --upgrade charts/ptp --values values.yaml
Note: The deployment will create a Job to fetch all depdendency models before starting services. This may take some time since there are 10Gb+ downloadables. This is only needed on load (new version) or reload of model library.
- Build and run the Docker containers:
docker-compose up --build
Model repository on Hugging Face: pharmbio/ptp
This project is licensed under the MIT License. See the LICENSE file for details.
- Jonathan Alvarsson - Research, scipipe version and models - jonathanalvarsson
- Morgan Ekmefjord - Web service, deployment and service packaging - morganekmefjord