AI in chemistry and beyond: Molecular Generative Models: Diffusion for 3D Geometry Generation

Thumbnail

Event details

Date 02.05.2023
Hour 17:3018:30
Speaker Minkai Xu is a Ph.D. student in the Computer Science Department at Stanford University. Previously, he received his M.Sc degree from Mila and B.E. from Shanghai Jiaotong University. His research lies in probabilistic models, geometric representation learning, and ML for scientific discovery. He has published several influential papers on the above topics in top machine learning conferences (e.g., ICML, NeurIPS, ICLR, AAAI, and AAMAS) including the first diffusion models for molecular structure generation, which has been widely adopted in various drug and protein design problems. His research is generously supported by Sequoia Capital Stanford Graduate Fellowship.
Location Online
Category Conferences - Seminars
Event Language English

With the recent progress in geometric deep learning, generative modeling, and the availability of large-scale biological datasets, molecular geometry generative modeling has emerged as a highly promising direction for scientific discovery such as drug design. These generative methods enable efficient chemical space exploration and potential drug candidate generation. However, by representing molecules as 3D geometries, there exist many both fundamental and challenging problems for modeling the distribution of these irregular and complex relational data. In this talk, we will introduce the latest key developments in this field, covering important principles for designing  3D molecular geometry generation including our most recent diffusion generative models. We will outline the underlying problem characteristics, summarize key challenges, present unified views of the representative approaches, and highlight future research direction and potential impacts.