ICML 2011 workshop on unsupervised and transfer learning

Transfer Learning for Auto-gating of Flow Cytometry Data

Gyemin Lee, Lloyd Stoolman, and Clayton Scott
University of Michigan, Ann Arbor.

Flow cytometry is a technique for rapidly quantifying physical and chemical properties of large numbers of cells. In clinical applications, ow cytometry data must be manually "gated" to identify cell populations of interest. While several researchers have investigated statistical methods for automating this process, most of them falls under the framework of unsupervised learning and mixture model tting. We view the problem as one of transfer learning, which can leverage existing datasets previously gated by experts to automatically gate a new ow cytometry dataset while accounting for biological variation. We illustrate our proposed method by automatically gating lymphocytes from peripheral blood samples.