PatternUnmixer (formerly called PUnmix) learns a model of fundamental subcellular patterns using user-specified images of "pure" subcellular patterns (e.g., lysosomes, endosomes) and then uses that model to calculate the fraction of probe in each subcellular compartment for images containing mixed patterns. It implements the approach described in
- T. Zhao, M. Velliste, M.V. Boland, and R.F. Murphy (2005). Object Type Recognition for Automated Analysis of Protein Subcellular Location. IEEE Trans. Image Proc. 14:1351-1359.
as extended in
- T. Peng, G.M.C. Bonamy, E. Glory, D. Rines, S. K. Chanda, and R. F. Murphy (2010) Automated Unmixing Of Subcellular Patterns: Determining the Distribution of Probes Between Different Subcellular Locations. Proc. Natl. Acad. Sci. U.S.A. 107:2944-2949.
To report bugs and suggest additions please open a ticket on GitHub.