LOCATOR: feature extraction and spatial analysis of the cancer tissue microenvironment using mass cytometry imaging technologies

Abstract

Motivation: Recent advances in highly multiplexed imaging have provided unprecedented insights into the complex cellular organization of tissues, with many applications in translational medicine. However, downstream analyses of multiplexed imaging data introduce several technical barriers, and although some computational methods and bioinformatics tools are available, deciphering the complex spatial organisation of cellular ecosystems remains a challenging problem. Results: We developed a novel computational method, LOCATOR (anaLysis Of CAncer Tissue micrOenviRonment), for spatial analysis of cancer microenvironments using data acquired from mass cytometry imaging (MCI) technologies. LOCATOR introduces a graph-based representation of tissue images to describe features of the cellular organisation and deploys downstream analysis and visualisation utilities that can be used for data-driven patient risk stratification. Our case studies using MCI data from two well-annotated breast cancer cohorts re-confirmed that the spatial organisation of the tumour-immune microenvironment is strongly associated with the clinical outcome in breast cancer. In addition, we report interesting potential associations between the cellular organization of macrophages and patients survival. Our work introduces an automated and versatile analysis framework for MCI data with many applications in future cancer research projects. Availability: Datasets and codes of LOCATOR are publicly available at https://github.com/RezvanEhsani/LOCATOR.