Integration of open-source AI models in Galaxy platform

[anuprulez]

Title

Integration of open-source AI models in Galaxy (web-based scientific data analysis platform)

Description

Galaxy (Europe) is a web-based, open-source data analysis platform. It offers several thousand tools to analyse scientific data analyses such as mapping DNA sequences, RNA expression analysis, variant calling, machine learning and deep learning. There are a lot of trained AI models available online in several model zoos but they lack a unified system promoting their usage for inference tasks.

• Aim is to provide seamless integration of openly available AI models into the Galaxy ecosystem
• Availability of tools to download and use AI models would promote the usage of such models for predictive analyses
• Examples of such high-quality models - BioModels and BioImage
• Provide powerful systems needed (for example: large compute infrastructure) for inference and easy-to-access platforms
• How to make such models easier to use for everyone (experts and non-experts in programming)
• A few proof-of-concepts have been created using Docker containers
• Development progress:
  • Add tool for analysing images using Bioimage AI models bgruening/galaxytools#1391
  • Integration of a few BioModels (ML models)  bgruening/galaxytools#1365

Organizational

Bioinformatics group, Freiburg Galaxy team, University of Freiburg, Germany

Host(s)

Anup Kumar
kumara@informatik.uni-freiburg.de

Format

Introduction talk followed by open discussion

Timeframe

30 min

Number of participants

There is NOT any limitation in the number of people who attend this session

Material

Beamer, markers, paper

[SusanneWenzel]

Dear @anuprulez ,

many thanks for your contribution! We hope your session was successful and constructive!

To make this not only a nice experience during the conference but a sustainable format, we would like to release a short result on the Helmholtz AI Website. Please provide us with a little report about the discussion in your session:

• One or two intro sentences about the topic and the respective format of your session
• What was most controversial, or about what did all participants agree on?
• What were the key ideas?
• Do you see any follow up on this discussion?

Depending on the intensity of the session it can be shorter (1/3 page) or longer (one pager).

Please post your report here by end of next week. Ina already confirmed to release that at a HAICON24 subpage at Helmholtz.ai.

Best regards,
@helenehoffmann and Susanne

[SusanneWenzel]

@anuprulez Its a while ago now. Can you still provide a short report please !? ☝️