PLoS Computational Biology Conference Postcards from ISMB 2010

Hatice Ulku Osmanbeyoglu,Mickey Kosloff,Guilhem Chalancon,Saras Saraswathi

doi:10.1371/journal.pcbi.1002000

Abstract

The annual international conference on Intelligent Systems for Molecular Biology (ISMB) is the largest meeting of the International Society for Computational Biology (ISCB). In 2010 it was held in Boston, United States, July 11–13. What follows are four conference postcards that reflect different activities considered exciting and important by younger attendees. Postcards, as the name suggests, are brief reports on the talks and other events that interested attendees. You can read more about the idea of conference postcards at http://www.ploscompbiol.org/doi/pcbi.1000746, and if you are a graduate student or postdoctoral fellow, please consider contributing postcards at any future meetings of interest to the PLoS Computational Biology readership. We want to hear your view of the science being presented.

Highlights

Murphy, who is a professor at Carnegie Mellon University, presented a tool called PatternUnmixer [1] that uses high-throughput automated microscopy data to quantify the distribution of fluorescently labeled proteins across different cellular compartments [2]
The features of the objects—such as their size, shape, and distance from the nucleus, for instance—are collected. These features are used to classify every individual object into categories called ‘‘object types’’ that are defined for a cell type in a given set of conditions and for one probe
Once the object types are defined for all the probes, the tested set of images— which contains mixed patterns—is investigated

Summary

Introduction

Murphy, who is a professor at Carnegie Mellon University, presented a tool called PatternUnmixer [1] that uses high-throughput automated microscopy data to quantify the distribution of fluorescently labeled proteins across different cellular compartments [2]. There is a strong need for automated and accurate acquisition of protein localization data, which requires advanced computational methods. By training their method to identify objects marked by two different trackers (lysosomal or mitochondrial), they were able to unmix the two signals in cells with mixed labeling.

Results

Conclusion