BEGIN:VCALENDAR VERSION:2.0 METHOD:PUBLISH PRODID:-//Missouri State University/Calendar of Events//EN CALSCALE:GREGORIAN X-WR-TIMEZONE:America/Chicago BEGIN:VTIMEZONE TZID:America/Chicago BEGIN:DAYLIGHT TZOFFSETFROM:-0600 TZOFFSETTO:-0500 DTSTART:20070311T020000 RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU TZNAME:CDT END:DAYLIGHT BEGIN:STANDARD TZOFFSETFROM:-0500 TZOFFSETTO:-0600 DTSTART:20071104T020000 RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU TZNAME:CST END:STANDARD END:VTIMEZONE BEGIN:VEVENT UID:373f0c31-3135-4c06-87bb-e173e9af33cf.231898@calendar.missouristate.edu CREATED:20231024T191833Z LAST-MODIFIED:20231024T191833Z LOCATION: SUMMARY:Computer Science Seminar - Dr. Jianlin Cheng DESCRIPTION:Title - 3D-Equivariant Graph Neural Networks and Transformers for Refining and Evaluating Protein Structures\n\n\nDeep learning is revo lutionizing the prediction of protein structure and is close to solving t his grand challenge hanging over the scientific world for many years. In this talk\, Dr. Cheng will describe how this artificial intelligence (AI) technology emerged in the field\, how it overcame various technical hurd les to reach a high accuracy of predicting protein structures as demonstr ated by AlphaFold2\, and where it is going now. Dr. Cheng will present hi s latest work of applying 3D-equivariant graph neural networks and transf ormers to refine and evaluate protein structural models. The experiments demonstrate that 3D-equivariant graph network networks and transformers t hat are robust against the rotation and translation of 3D objects can eva luate and improve the quality of protein structures more effectively than the existing methods.\n\n\nDr. Jianlin Cheng is the Thompson Distinguish ed Professor in the Department of Electrical Engineering and Computer Sci ence Department at the University of Missouri - Columbia\, USA. He earned his Ph.D. in Computer Science from the University of California\, Irvine in 2006. His research is focused on bioinformatics and machine learning. \n\n\nJoin Zoom Meeting https://missouristate.zoom.us/j/96444127305?from= addon Meeting ID: 964 4412 7305 X-ALT-DESC;FMTTYPE=text/html:<html><head><title></title></head><body><p><s trong>Title - 3D-Equivariant Graph Neural Networks and Transformers for R efining and Evaluating Protein Structures</strong></p>\n<p>Deep learning is revolutionizing the prediction of protein structure and is close to so lving this grand challenge hanging over the scientific world for many yea rs. In this talk\, Dr. Cheng will describe how this artificial intelligen ce (AI) technology emerged in the field\, how it overcame various technic al hurdles to reach a high accuracy of predicting protein structures as d emonstrated by AlphaFold2\, and where it is going now. Dr. Cheng will pre sent his latest work of applying 3D-equivariant graph neural networks and transformers to refine and evaluate protein structural models. The exper iments demonstrate that 3D-equivariant graph network networks and transfo rmers that are robust against the rotation and translation of 3D objects can evaluate and improve the quality of protein structures more effective ly than the existing methods.</p>\n<p>Dr. Jianlin Cheng is the Thompson D istinguished Professor in the Department of Electrical Engineering and Co mputer Science Department at the University of Missouri - Columbia\, USA. He earned his Ph.D. in Computer Science from the University of Californi a\, Irvine in 2006. His research is focused on bioinformatics and machine learning.</p>\n<p><span>Join Zoom Meeting<br> <a href="https://missouris tate.zoom.us/j/96444127305?from=addon">https://missouristate.zoom.us/j/96 444127305?from=addon</a><br> <br> Meeting ID: 964 4412 7305</span></p></b ody></html> DTSTART;TZID=America/Chicago:20231130T123000 DTEND;TZID=America/Chicago:20231130T133000 SEQUENCE:0 URL: CATEGORIES:Current Students,Faculty,Staff END:VEVENT END:VCALENDAR