Integrated profiling of cell surface protein and nuclear marker for discriminant analysis

Cell membrane proteins play an important role in tissue architecture and cell-cell communication. We hypothesize that segmentation and multivariate characterization of the distribution of cell membrane proteins, on a cell-cell basis, enable improved classification of treatment groups and identify important characteristics that can otherwise be hidden. We have developed a series of computational steps to (i) delineate cell membrane protein signals and associate them with specific nuclei, (ii) compute a coupled representation of the multiplexed DNA content with membrane proteins and other end points, (iii) evaluate computed features associated with such a multivariate representation, and (iv) discriminate between treatment groups in an optimal fashion. The novelty of our method is in the segmentation of the membrane signal and the multivariate representation of phenotypes on a cell-cell basis. To test the utility of the new method, the proposed computational steps were applied to images of cells that have been irradiated with different radiation qualities in the presence and absence of TGFbeta. These samples are labeled for their DNA content and E-cadherin membrane protein. We demonstrate that multivariate representation of cell-cell phenotypes improves predictive and visualization capabilities among different treatment groups, and increases quantitative sensitivity of cellular responses.