Learning How the Genome Folds in 3D
Since the human genome project, we've known the linear sequence of human DNA. However, the promised revolution in medicine is still yet to come; there is still much we do not know about how DNA regulates cell function. At Aiden lab, we explore how the two-meter long DNA molecule folds inside the cell. Our assay uses proximity ligation to determine which loci in the 1D genome are close together in 3D. We use deep learning to find "peaks" in the resulting contact maps. These peaks turn out to correspond to loops mediated by the protein CTCF, and link promoters and enhancers, correlating with gene activation.
Neva C. Durand is the chief computational scientist at Aiden lab at Baylor College of Medicine, where she creates analysis and visualization software for assays exploring how DNA folds in three dimensions. Her pipeline has been adopted as the NIH standard for this experiment. Previously, she developed object and feature recognition systems using machine learning in Poggio lab at MIT and in Ponce lab at INRIA. She received her PhD in computer science from the University of Washington in 2009.