UBC Math Bio Seminar: Robert Nabi

Super-resolution microscopy enables the use of fluorescent-based molecular localization tools to study molecular structure at the nanoscale level in the intact cell, bridging the mesoscale gap to classical structural biology methodologies. Analysis of super-resolution data by artificial intelligence (AI), or machine learning, offers tremendous potential for discovery of new biology, that by definition is not known and lacks ground truth. Application of weakly supervised learning paradigms to super-resolution microscopy enables the accelerated exploration of the molecular architecture of subcellular macromolecules and organelles. Biological applications to be discussed include:

1. Development of network graph analysis (SuperResNET) to determine molecular structure by single molecule localization microscopy (SMLM – dSTORM and some MinFlux)

2. Development of a Laplacian/scanning window-based algorithm (MCS-DETECT) for the sub-pixel resolution detection of mitochondria-ER contact sites (MERCs) from 3D STED microscopy.