Application of machine learning approaches to big datasets to understand the host response to lung and tissue damage.

During the life course our lungs are continuously challenged by environmental contaminants and infectious agents resulting in airway remodeling and lifelong breathing complications. Understanding how these changes occur through mapping signaling pathways and changes in the host the response will prove critical in the design of effective therapeutic countermeasures, treatment and clinical care pathways.
The project will use and develop machine learning approaches to interrogate large transcriptomic and proteomic datasets that have been generated from experimental systems exposed to biological and chemical agents. This will be particularly focused on lung and blood tissues but may include data from other organs. The analysis and comparison of many thousands of data points can only be achieved through joining high resolution approaches with computational approaches. This project will focus on utilizing machine learning to provide a detailed map of the biological response to challenges and aid in the evaluation and selection of potential therapeutic countermeasures. The project will particularly develop the analysis of patterns from noisy data.