FlowSOM for handling cytometry data
FlowSOM for handling cytometry data
to be announced
General context
As cytometry experiments measure increasing numbers of markers, cells, and samples, traditional manual gating becomes time-consuming and subjective. Automated approaches provide a robust alternative, improving speed, reproducibility, and scalability.
This workshop introduces handling cytometry data in R using automated workflows, with a special focus on the FlowSOM clustering algorithm. You will learn practical strategies to streamline data quality control, visualization, and clustering for high-dimensional cytometry datasets
- Import and manage cytometry data in R.
- Perform quality control and data-cleaning steps.
- Apply visualization techniques to cytometry datasets.
- Use the FlowSOM clustering algorithm for automated analysis.
- Compare and interpret clustering results across samples.
The workshop combines demonstrations and hands-on exercises in R. You will practice using FlowSOM on an example dataset and are encouraged to bring your own FCS files to explore during the session.
Prior experience with traditional manual cytometry analysis and R is strongly recommended. If you have no experience with R, you can attend the R introduction training.
This course is part of the learning path Flow cytometry data.
AI methods used
This workshop applies unsupervised machine learning through the FlowSOM algorithm to automatically group cells based on their marker expression patterns. FlowSOM uses self-organizing maps and clustering to identify cell populations in high-dimensional cytometry data.
Trainers
Sofie Van Gassen
Sofie is Postdoc at Ghent University working on optimization of the analysis of flow cytometry data by developing suitable machine learning algorithms. She's the creator of the FlowSOM algorithm.