@article{Kumar_Cuccuru_Gruning-acces_infra_for-2022,
author = {Kumar, Anup and Cuccuru, Gianmauro and Grüning, Björn and 
          Backofen, Rolf},
title = {An accessible infrastructure for artificial intelligence 
         using a {Docker}-based {JupyterLab} in {Galaxy}},
journal = {Gigascience},
year = {2022},
doi = {10.1093/gigascience/giad028},
volume = {12},
user = {backofen},
pmid = {37099385},
pages = {},
number = {},
issn = {2047-217X},
abstract = {BACKGROUND: Artificial intelligence (AI) programs that 
            train on large datasets require powerful compute 
            infrastructure consisting of several CPU cores and GPUs. 
            JupyterLab provides an excellent framework for developing AI 
            programs, but it needs to be hosted on such an 
            infrastructure to enable faster training of AI programs 
            using parallel computing. FINDINGS: An open-source, 
            docker-based, and GPU-enabled JupyterLab infrastructure is 
            developed that runs on the public compute infrastructure of 
            Galaxy Europe consisting of thousands of CPU cores, many 
            GPUs, and several petabytes of storage to rapidly prototype 
            and develop end-to-end AI projects. Using a JupyterLab 
            notebook, long-running AI model training programs can also 
            be executed remotely to create trained models, represented 
            in open neural network exchange (ONNX) format, and other 
            output datasets in Galaxy. Other features include Git 
            integration for version control, the option of creating and 
            executing pipelines of notebooks, and multiple dashboards 
            and packages for monitoring compute resources and 
            visualization, respectively. CONCLUSIONS: These features 
            make JupyterLab in Galaxy Europe highly suitable for 
            creating and managing AI projects. A recent scientific 
            publication that predicts infected regions in COVID-19 
            computed tomography scan images is reproduced using various 
            features of JupyterLab on Galaxy Europe. In addition, 
            ColabFold, a faster implementation of AlphaFold2, is 
            accessed in JupyterLab to predict the 3-dimensional 
            structure of protein sequences. JupyterLab is accessible in 
            2 ways-one as an interactive Galaxy tool and the other by 
            running the underlying Docker container. In both ways, 
            long-running training can be executed on Galaxy's compute 
            infrastructure. Scripts to create the Docker container are 
            available under MIT license at 
            https://github.com/usegalaxy-eu/gpu-jupyterlab-docker.}
}