Cell profiling of drug treated high content screening image data

• Main Author: Ng, Alvin Yu-Jin
• Other Authors: Rajapakse Jagath Chandana
• Format: Theses and Dissertations
• Language: English
• Published: 2014
• Subjects: DRNTU::Engineering::Computer science and engineering
• Online Access: http://hdl.handle.net/10356/60706
• Institution: Nanyang Technological University

High Content Screening (HCS) is an automated platform based on light microscopy that analyzes large number of individual cells with sub-cellular resolution. There are needs to develop analytical and visualization tools to extract, manage and simplify large scale HCS data sets such that it can be understood and developed into new knowledge. We developed a simple, biological interpretable and scalable framework for analyzing HCS Image Data. We proposed a method of selecting static image based features, creating cytological profiles by clustering cell morphologies and techniques to ascertain differential effects based on drugs. Next, we introduced a Support Vector Machine (SVM) classifier to make predictions on actin organization based on cellular, nuclear and cytoplasm information. Finally, we conducted live imaging experiments to better understand the biology of the cytoskeleton on cell motility and validated the previously determined and observed drug trends and profiles.