Join us for our monthly live webinar series in which we feature contributing developers demonstrating their software, highlighting new features, and previewing future developments. You'll hear the latest news and have opportunity to ask questions directly relevant to your research. Be sure to subscribe to SBGridTV to receive alerts when we post new recordings and view our full collection of past tutorials.
Up next: TOPAZ
February 26th at 12pm EST
Cryo-electron microscopy (cryoEM) is an increasingly popular method for protein structure determination. However, identifying a sufficient number of particles for analysis (often >100,000) can take months of manual effort. Current computational approaches are limited by high false positive rates and require significant ad-hoc post-processing, especially for unusually shaped particles. To address this shortcoming, we develop Topaz, an efficient and accurate particle picking pipeline using neural networks trained with few labeled particles by newly leveraging the remaining unlabeled particles through the framework of positive-unlabeled (PU) learning. Remarkably, despite using minimal labeled particles, Topaz allows us to improve reconstruction resolution by up to 0.15 Å over published particles on three public cryoEM datasets without any post-processing. Furthermore, we show that our novel generalized-expectation criteria approach to PU learning outperforms existing general PU learning approaches when applied to particle detection, especially for challenging datasets of non-globular proteins.
Webinar connection instructions: We are now using BlueJeans to connect for webinars. Connection instructions:
- Call in number: +1.408.740.7256 (United States) or +1.408.317.9253
- You can find international access numbers at https://www.bluejeans.com/numbers
- Download BlueJeans at https://www.bluejeans.com/downloads
Full Webinar Lineup 2018-2019
- October 2: Phenix/DivCon with Lance Westerhoff - XModeScore: using crystallography to determine protonation states, fragment binding modes, and flip-states.
- November 6: Relion 3.0 with Sjors Scheres - RELION-3: new tools for automated high-resolution cryo-EM structure determination
- December 4: PanDDA with Nicholas Pearce - PanDDA: extracting ligand-bound protein states from conventionally uninterpretable crystallographic electron density
- January 22: DENSS with Thomas Grant
- February 26: TOPAZ with Tristan Bepler
- April 2: TomoAlign with Jose-Jesus Fernandez:
- May 7: crYOLO with Thorsten Wagner: