dr. Sofie Van Gassen (PhD)

CRIG member
Sofie Van Gassen


Postdoctoral researcher - Data Mining and Modelling for Biomedicine Group, Inflammation Research Center, UGent-VIB
Principal investigator: prof. Yvan Saeys (PhD)

 

Research focus

Flow cytometry is a unique technology which allows to measure characteristics of individual cells in a high-throughput setting (e.g. processing 10 000 cells / second, while measuring 10 to 30 properties per cell). This technology can give a detailed insight in the heterogeneity of tumor samples or allow follow-up of treatment. Especially in blood cancer research, flow cytometry is very valuable. 

My research focuses on the development of computational techniques to aid in the analysis of flow cytometry data. Where traditional analysis becomes slow and biased towards expected cell populations for high-dimensional datasets, the use of algorithmic tools allows to apply a more comprehensive analysis. I have developed the FlowSOM algorithm, which can automatically identify cell populations, and the FloReMi algorithm, which can be used to find correlations between identified populations and the patient survival time. We are now starting to apply these techniques onto clinical datasets.
 

Biography

Sofie Van Gassen (°1990, Lokeren, Belgium) received her M.S. degree in Computer Science from Ghent University in 2013 and her PhD in Computer Science Engineering from Ghent University in 2017.
During her PhD she developed machine learning techniques for flow and mass cytometry data.
This included the FlowSOM algorithm, a well-known clustering tool for flow cytometry data, which has recently been incorporated in the FlowJo software.
She also participated in the FlowCAP IV challenge, where the FloReMi pipeline got the best results in predicting progression time to AIDS for HIV patients.
Since 2018, she is an ISAC Marylou Ingram Scholar and as a postdoc she is further extending and improving machine learning techniques for single cell data as a postdoc in the DaMBi group (Center for Inflammation Research).
 

Key publications

  • ‘Myeloid cell heterogeneity in cancer: not a single cell alike’. Cellular immunology, 2018. (PMID: 29482836)
     

Contact & links