Quantifying biological heterogeneity from single-cell data
One of the main research goals of our team is understanding, modeling and quantifying different sources of heterogeneity from single-cell measurements, in health and disease.
Our team has developed CellCycleTRACER, a supervised machine-learning algorithm that classifies and sorts single-cell mass cytometry data according to their cell cycle, and allows to correct for cell-cycle-state and cell-volume heterogeneity. CellCycleTRACER is available as a simple and intuitive web application that runs on the IBM Cloud.
Breast cancer is a heterogeneous disease. Tumor cells and cells from their microenvironment form ecosystems that determine disease progression and response to therapy. We created a single-cell atlas of the tumor and immune ecosystem of breast cancer. This single-cell atlas deepens our understanding of breast tumor heterogeneity and suggests that ecosystem-based patient classification will enable precision medicine approaches targeting the tumor and its immune microenvironment.
Access the code reproducing our findings on GitHub.
Find out more about the CellCycleTRACER Web App.