Submitted: 2025-13-06
Administrative Section
Status (New/Update): New
Group Name: HUPO PSI AI-readiness Working Group (PSI-AI WG)
Chair (with affiliation and current email address): Tine Claeys (tineclae.claeys@ugent.be) – Ghent University – VIB, Ghent, Belgium
Co-Chairs (1 or 2) (with affiliation and current email address): Samuel Wein, –(samuel.wein@uni-tuebingen.de) University of Tübingen – OpenMS, Tübingen, Germany
Ralf Gabriels (ralf.gabriels@ugent.be), Ghent University – VIB, Ghent, Belgium
Secretary: Vacant
Other officers (optional) (with affiliation and current email address):
None
Description and Objectives
Focus and Purpose
The goal of the PSI-AI working group is to bridge the gap between artificial intelligence and public proteomics data. We focus on two complementary goals. The first is to make public proteomics data suitable for AI applications. The second is to support and standardize the use of AI in workflows that generate new data. We work toward these goals through the use of community standards and reproducible and accessible pipelines. Our aim is to integrate with, not duplicate, existing infrastructure.
Goals/Milestones
Goal 1: Publish a review on good reprocessing practices in large-scale proteomics
Goal 2: Curate a benchmark corpus of selected public datasets in homogeneous format
Goal 3: Collaborate with EuBIC-MS for the development of a retroactive metadata annotation pipeline
Goal 4: Development of a community-driven and open-access reprocessing workflow
Goal 5: Collaborate with existing benchmarking community efforts such as Proteobench to benchmark AI pipelines
Goal 6: Collaborate with existing educational community efforts such as ProteomicsML to educate users on AI applications within proteomics
Website: http://psidev.info/groups/ai-readiness