Date: Friday 13th March 2020
Venue: Sackler Lecture Theatre, Cambridge Institute for Medical Research (level 7), Cambridge Biomedical Campus
Multicellular organisation requires the coordination of multiple signalling pathways that regulate cell shape as well as cell-cell and cell-micro environment interactions. Such coordination is often lost in cancer resulting in changes in tissue architecture, uncontrolled growth, and metastasis. Imaging technologies provide a powerful approach to simultaneously study the signalling and organisational state of cells. I will discuss the development of machine learning and computer vision methodologies for automated identification of genetic programmes underlying tissue organisation. Importantly, these studies reveal that cell context and shape can modulate cell signalling even in isogenic cell cultures. Using orthogonal datasets and integrative approaches, we validate the clinical relevance of cell shape and context in patient prognosis.
Dr Sailem's research is focused on understanding the interplay between genetic and phenotypic components underlying changes in tissue architecture in cancer. To achieve that she develops statistical and deep learning methodologies for analysing large biomedical datasets with a focus on cellular imaging and single cell data. In 2017, She was awarded a four-year Sir Henry Wellcome Research Fellowship to develop a knowledge-driven machine learning framework for characterising gene functions in different cancer cell types. She is also a Junior Research Fellow at Corpus Christi College (Oxford). She did her PhD at the Institute of Cancer Research in London. While at the ICR she developed methods for integrating phenotypic data with gene expression, modelling of the relationship between cell signalling and its context, and modelling the dynamics of cell morphogenesis. In these studies, she discovered new links between cell shape and breast cancer progression. Dr Sailem is also interested in data visualisation as an important tool for science communication. She devised PhenoPlot, one of the first tools that are specifically designed for visualising phenotypic data. This method facilitates the interpretation of high dimensional data by generating pictorial representations of cells based on hundreds to thousands of measurements.