Web application - Hierarchical generative and regressive machine learning for next generation materials screening
This repository contains the source code for web-application for the paper:
Ortega, Raul & Benediktsson, Bardi & Sechi, Renata & Jørgensen, Peter & Bhowmik, Arghya. (2023). "Materials Funnel 2.0 - Data-driven hierarchical search for exploration of vast chemical spaces". 10.26434/chemrxiv-2023-s8t6s-v2.
For the source code of the method implementation https://github.com/raulorteg/hts_funnel
This is a web-application built to serve as an easier way to interact to the method proposed in "Materials Funnel 2.0 - Data-driven hierarchical search for exploration of vast chemical spaces" as a web-application.
- For the source code of the method implementation: https://github.com/raulorteg/hts_funnel
- Clone the repository:
git clone https://github.com/raulorteg/hts_funnel-app
- Create the python virtual environment (I use python 3.9.14):
virtualenv --py=python3.9 hts_funnel_app
- Activate virtualenv
source hts_funnel_app/bin/activate
- Install requirements
python -m pip install -r requirements.txt
Note: Your system might need a different torch installation (https://pytorch.org/get-started/locally/)
see the requirements.txt
file
From /app
launch the web-application by running the command:
python -m uvicorn main:app --reload
Then open https://127.0.0.1:8000
on the browser to see the web-application.
Build the Docker image
sudo docker build . --tag="funnelapp:latest"
Run the docker image
sudo docker run --rm -it -p 80:80/tcp funnelapp:latest
Then open https://0.0.0.0:80
on the browser to see the web-application.
Use isort 5.10.1 and black 22.10.0:
python -m pip install isort==5.10.1 black==22.10.0
Sort the imports:
python -m isort <file_or_directory>
To format:
python -m black <file_or_directory>