Deriving Clinical Insights from Spatial Proteomics and Spatial Transcriptomics Data
Spatial proteomics and spatial transcriptomic profiles of the tumour microenvironment provide a rich trove of biological information of the dynamic processes underlying cancer progression, however deciphering clinically relevant information from these high dimensional data is a difficult challenge for spatial biologists. This talk will outline some of the machine learning and mathematical methods that the team at the Queensland Spatial Biology Centre utilises to drive translational impact from these data while exploring aspects of the underlying biology of cancer treatment response.
Bio
Aaron Kilgallon is a data scientist at the Queensland Spatial Biology Centre and a member of the clinicalOMx lab at the Frazer Institute at UQ. He works on interpretative and predictive modelling of clinical response from spatial proteomic and spatial transcriptomic datasets, focusing on machine learning and statistical techniques of looking at these high dimensional data. With a physics and mathematics background from his graduate studies in particle physics, he uses interdisciplinary approaches in order to drive translational impact from spatial studies.
