ALAMBIC, or Active Learning Automation with Methods to Battle Insufficient Curation, is an open-source Dockerized web platform for the study and development of machine learning models with the help of active learning.
Available on https://trusted-ai-labs.github.io/ALAMBIC/
In the terminal, navigate to the folder of your choice and then type
git clone https://github.com/Trusted-AI-Labs/ALAMBIC.git
Go inside the GitHub repository newly created of ALAMBIC and type
docker-compose up
For the more expert, you can add options to that command (see here)
Note that you need to have all your data contained in the folder data_alambic situated in your user directory.
You can find ALAMBIC at the adress http://0.0.0.0:8000/ ! However, be careful, depending on how your OS and how it redirects the port. You could also find it at http://localhost:8000/ :)
You can stop the docker and flush the database of all the data and results by typing in the terminal
docker-compose down -v
This project was realised at the Interuniversity Institute of Bioinformatics in Brussels (IB2), a collaborative bioinformatics research initiative between Université Libre de Bruxelles (ULB) and Vrije Universiteit Brussel (VUB). Basic architecture and design was largely inspired by the work done by Alexandre Renaux for ORVAl (https://orval.ibsquare.be). This work was supported by Service Public de Wallonie Recherche under grant n° 2010235 -ARIAC by DIGITALWALLONIA4.AI.
This work is under a BSD-3-Clause license.
See above by clicking on "Cite this repository"