oa Towards cell level protein interaction in multivariate bioimages

Recently, new bioimaging techniques have been proposed to visualize the interaction of several proteins within individual cells. Such techniques could provide the key to understanding complex biological systems such as the protein interactions involved in cancer. Currently, there is a strong urge for sophisticated analytical methods to extract molecular signatures of diseases (such as cancer) in order to not only understand the biological processes behind cancer development but also to aid us in early diagnosis and appropriate treatment. We propose a paradigm for mining of molecular signatures in multivariate bioimages. In contrast to the traditional pixel-level analysis approaches, which ignore cellular structures as units that can be crucial when analyzing cancerous cells, our method incorporates cell-level analysis. We use this framework to perform cell level protein-protein interaction analysis to visualize cellular heterogeneity at a molecular level.