Title: Intelligent 3D Cryo-EM Data Analysis for Next Generation Biomedicine
Presenter: Dong Si, University of Washington Bothell
Abstract: Life ultimately depends on the interactions of large biological molecules, such as proteins. The nature of these interactions depends on the three dimensional (3D) shape and structure of these molecules. Electron cryo-microscopy (cryo-EM) as a cutting edge technology has carved a niche for itself in the study of large-scale protein complex. The accuracy of secondary structure elements (SSEs) and backbone structure detection from the volumetric protein density images is critical for ab initio modeling in cryo-EM. So far it is challenging to detect the SSEs and backbone structures automatically and accurately from the density images at medium-high resolutions. We have combined image processing, machine learning, geometric modeling, computer graphics techniques and developed SSETracer, SSELearner, StrandTwister, StrandRoller, BarrelMiner along with recent developed deep learning framework to allow for the automatic and accurate prediction of SSEs and backbone structures from experimental derived 3D cryo-EM images of protein complexes.
Bio:Dong Si is currently an assistant professor at University of Washington Bothell. He received his M.S. and Ph.D. in Computer Science from Old Dominion University Virginia, and his B.S. in Electronic Information Science from Nanjing University China. Over the years, Dong’s research has included visual data analytics, feature detection and pattern recognition, machine learning and data mining, geometric modeling, and computational structural bioinformatics. He is currently the lead guest editor of Journal of Molecular Based Mathematical Biology and reviewer of multiple international journals including BMC Bioinformatics and Journal of Data Mining and Bioinformatic. His also serves in the organizing and program committee for many international conferences including ACM-BCB.
