Murphy Lab

OMERO.searcher

This system provides the ability to search databases for images based on image content rather than the context (annotations). The first version has been released and described in a manuscript published by Nature Methods (Cho et al, 2012 [5]). Future improvements will include the ability to search multiple databases simultaneously and search using 3D and 4D images.

PatternUnmixer

This is the first system for determining the fraction of a protein that is in each of various organelles, which can be done using either supervised methods (Peng et al., 2010 [2]) or unsupervised methods (Coelho et al., 2010 [3]).

CellOrganizer

This is the first system for automatically building computational models of sub-cellular organisation from images, capturing both the essence of (and variation in) cell shape, nuclear shape and organelle patterns (Zhao and Murphy, 2007 [1]; Peng and Murphy, 2011 [4]). These models are both descriptive and generative, in that they describe the images they are created from but also allow new images to be synthesised which, in a statistical sense, are drawn from the same population as the images they were trained with. These enable the possibility of a “global” mathematical definition of organelle shape, structure and distribution that would go far beyond current conceptual models (such as what the Golgi complex looks like).

Further information is available on the Murphy Lab website

Robert F. Murphy is the Ray and Stephanie Lane Professor of Computational Biology and Professor of Biological Sciences, Biomedical Engineering, and Machine Learning at Carnegie Mellon University, and Director (Department Head) of the Lane Center for Computational Biology in the School of Computer Science. He is also Honorary Professor of Biology at the Albert Ludwig University of Freiburg, Germany. Dr. Murphy has co-edited two books and three special journal issues on cell imaging, and has published over 180 research papers. He is Past-President of the International Society for Advancement of Cytometry, and is a member of the National Advisory General Medical Sciences Council and the NIH Council of Councils.

Dr. Murphy’s career has centred on combining fluorescence-based cell measurement methods with quantitative and computational methods. In the mid 1990’s, his group pioneered the application of Machine Learning methods to high-resolution fluorescence microscope images depicting sub-cellular location patterns. His current research interests include image-derived models of cell organisation and active Machine Learning approaches to experimental biology.

Ivan Cao-Berg

References

[1]

T. Zhao and R.F. Murphy (2007). Automated Learning of Generative Models for Subcellular Location: Building Blocks for Systems Biology. Cytometry 71A:978-990.

[2]

T. Peng, G.M.C. Bonamy, E. Glory-Afshar, D. R. Rines, S. K. Chanda, and R. F. Murphy (2010) Determining the distribution of probes between different subcellular locations through automated unmixing of subcellular patterns. Proc. Natl. Acad. Sci. U.S.A. 107:2944-2949.

[3]

L. P. Coelho, T. Peng, and R. F. Murphy (2010) Quantifying the distribution of probes between subcellular locations using unsupervised pattern unmixing. Bioinformatics 26:i7-i12.

[4]

T. Peng and R.F. Murphy (2011) Image-derived, Three-dimensional Generative Models of Cellular Organization. Cytometry Part A 79A:383-391.

[5]

B.H. Cho, I. Cao-Berg, J.A. Bakal, and R.F. Murphy (2012) OMERO.searcher: Content-based image search for microscope images. Nature Methods 9:633-634.