CYTO 2026 Scientific Tutorial: Meta Logical: Structuring Your Cytometry Data for Cleaner Models and Clearer Insights

Meta Logical: Structuring Your Cytometry Data for Cleaner Models and Clearer Insights

Presenters:
Arielle Ginsberg, MSc,SCYM, CEO, terraFlow
Ryan Duggan, BS, Principal Research Scientist, Abbvie

Abstract:

With the increasing volume and complexity of data in cytometry and related research fields, metadata has become essential for ensuring data quality, reproducibility, and utility across studies and modalities. Additionally, well annotated metadata is crucial for single-cell based large language models (LLMs) as it provides an AI-ready structure to the data, enhances data organization, and improves the model’s ability to interpret. In parallel, well annotated data allows it to provide maximal impact by being FAIR (Findable, Accessible, Interoperable, and Reusable)—principles that maximize data’s scientific value by ensuring it can be efficiently shared, understood, and repurposed across studies.

However, current practices for metadata management often fall short due to lack of standardization, inadequate tools, and limited awareness of best practices. This tutorial will provide participants with practical guidance for improving metadata organization, standardization, and documentation to support FAIR and AI-ready data practices. Drawing from established frameworks such as MIFlowCyt, SOULCAP, and data-sharing resources like ImmPort, the session will illustrate how cytometry researchers can align with broader community standards while enhancing reproducibility and downstream analytical potential.

Through a primarily didactic format with opportunities for open discussion and Q&A, participants will gain actionable strategies to improve metadata quality and foster a culture of data interoperability and long-term reusability within their research environments as well as opportunities to share successful strategies for overcoming challenges to implementation of FAIR data practices.

Learning Objectives
By the end of this tutorial, participants will be able to:

1) Define the principles of AI-ready and FAIR metadata in the context of cytometry data management.

2) Identify common challenges and barriers to implementing standardized metadata practices.

3) Apply FAIR and MIFlowCyt-aligned strategies to enhance data discoverability, reproducibility, and interoperability.

4) Evaluate current metadata workflows for compliance with FAIR principles and opportunities for improvement.

5) Formulate an actionable plan to integrate AI-ready and FAIR-compliant metadata practices within their research or core facility.

Expected Outcomes

Participants will leave with a clear understanding of how to structure metadata to support FAIR data principles and AI-ready analyses, along with practical strategies to promote data standardization and interoperability within their research environment

Keywords: Fundamental Cytometry Concepts, Experimental Design and Controls, Meta Data, MIFlowCyt, Data Annotation, Data Management

CMLE Credit: 1.5