An important challenge in the post-genomic era is to identify subcellular location on a proteome-wide basis. A major source of information for this task will be imaging of tagged proteins in living cells using fluorescence microscopy. We have previously developed automated systems to interpret the images resulting from such experiments and demonstrated that they can perform as well or better than visual inspection. Recent work demonstrates that these methods can be applied to large collections of images from yeast (the UCSF yeast GFP localization database), human tissues (the Human Protein Atlas), and randomly GFP-tagged mouse 3T3 cell lines. A distinct but related task is learning from images what location patterns exist (rather than classifying them into pre-specified patterns). In this regard, we have obtained reasonable results on clustering mouse proteins into subcellular location families that share a statistically indistinguishable pattern. In order to be able to capture and communicate the pattern in each family, we have developed approaches to learning generative models of subcellular patterns from images. These can be used to synthesize images that in a statistical sense are drawn from the same underlying population as the images used for training. The models can be communicated in compact XML files that are compatible with cell model descriptions captured in SBML. We anticipate combining these models to construct cell models containing all expressed proteins in their proper locations. We are currently working to integrate our tools with existing cell modelling systems to permit accurate, well-structured information on subcellular location to be incorporated into systems biology efforts.
Copyright. All Rights Reserved.