Location proteomics: determining the optimal grouping of proteins according to their subcellular location patterns as determined from fluorescence microscope images

Modeling of protein functions as envisaged by systems biology requires detailed knowledge about the subcellular distributions of all proteins. Unfortunately, such knowledge is limited or nonexistent for most proteins. Further, the available information is often of low resolution, distinguishing major organelles but not adequately capturing the incredible complexity of possible protein patterns. Our group has previously developed automated systems for determining subcellular location from fluorescence microscope images; these systems can discriminate between similar patterns better than humans. We have also developed approaches to grouping proteins by the patterns they display in 3D confocal microscope images.