pRoloc(cam.ac.uk)

The software tool 'pRoloc' is a unique transfer learning classification framework developed to improve the assignment and classification of sub-cellular proteins. The tool integrates heterogeneous data sources, including high-throughput mass spectrometry (MS), and third-party data sources like immunofluorescence microscopy and protein annotations and sequences.

Using a nearest-neighbor or support vector machine system, 'pRoloc' can classify proteins into tens of sub-cellular compartments with high generalization accuracy. The methodology behind this tool has been evaluated by analyzing five experimental datasets from four different species in conjunction with four auxiliary data sources.

The results demonstrate the utility of this tool, which has been further applied to an experiment on pluripotent mouse embryonic stem cells to classify a set of previously unknown proteins. The findings from this experiment have been validated against a recent high-resolution map of the mouse stem cell proteome. 'pRoloc' is distributed as part of the open-source Bioconductor pRoloc suite for spatial proteomics data analysis.