Academy of Mathematics and Systems Science, CAS Colloquia & Seminars
Speaker:
Prof. Chandrajit Bajaj，Department of Computer Science, and Institute of Computational Engineering and Sciences, Center for Computational Visualization, The University of Texas at Austin? USA
Inviter:
陈冲 博士
Title:
Learning to Dock and Predict Assemblies
Time & Venue:
2018.11.13 15:00-16:00 N202
Abstract:
I shall present a multi-stage machine learning approach to automatically choosing weighting and threshold filter parameters, in a multi-term scoring functions and filters. Such scoring functions are often used in molecular docking software. In particular we have applied and compared the improvement of docking results achieved by using our Fast Fourier based docking and re-ranking software called F2Dock. I shall then describe TilerGen which generates which generates almost congruent polyhdedral tilings and layouts. The governing rules yields tile arrangements with maximal vertex, edge and face symmetries. The family of all such congruently tiled cages create a new generative class of polyhedra, beyond the well-studied regular, semi-regular and quasi-regular classes, and their duals (platonic, Catalan and Johnson). Our construction thus further enables the prediction of generative tiled assemblies. This is joint work with Dr. Muhibur Rasheed. 报告人简介： Chandrajit Bajaj is a Professor in the Department of Computer Science, and Institute of Computational Engineering and Sciences, and Center for Computational Visualization at The University of Texas at Austin, USA. He received his B.Tech. in Electrical Engineering (1980) from Indian Institute of Technology, New Delhi, India; and his M.S. and Ph.D. in Computer Sciences (1983, 1984) from the Cornell University, Ithaca, USA. He is the Fellow of AAAS, Fellow of ACM, Fellow of IEEE, and Fellow of SIAM.