Colloquium Computer Science: Prof. Barbara Hammer, Bielefeld University

Abstract:

In bioinformatics applications such as metagenomics, analysis of single-cell sequencing data, or analysis of data from flow cytometry, often, a first step concerns the sorting of data into homogeneous clusters, e.g. homogeneous cell populations or species. While this problem can be understood as a formal clustering problem, quite diverse (machine learning) technologies have been proposed in this realm. Within the talk, we shed some light onto two recent pipelines, namely "ACDC" for automatic contamination detecion in single cell sequencing, and "FlowLearn" for automated gating of flow cytometric data. We explain the underlying modelling and the involved machine learning technologies in comparison to alternatives, and we highlight their benefits and pitfalls.

Colloquium coordinators are Prof.dr. M. Aiello (e-mail : M.Aiello rug.nl ) and Prof.dr. M. Biehl (e-mail: M.Biehl rug.nl )

http://www.rug.nl/research/jbi/news/colloquia/computerscience