3D de novo generation of organic molecules
Event details
| Date | 25.06.2024 |
| Hour | 15:15 › 16:15 |
| Speaker | Ian is a PhD Candidate in the joint Carnegie Mellon University - University of Pittsburgh Computational Biology PhD Program where he is advised by David Koes. His research is focused on developing deep generative models for applications in structure-based design. |
| Location | Online |
| Category | Conferences - Seminars |
| Event Language | English |
Deep generative models that can directly sample molecular structures with desired properties have the potential to accelerate chemical discovery by reducing or eliminating the need to engage in resource-intensive screening-based based discovery paradigms. Designing deep generative models to accurately sample the complex distribution of 3D molecular structures is a challenging, open problem. In this seminar we’ll present our recent work on adapting flow matching, a modern generative modeling framework with connections to normalizing flows and diffusion, for the task of 3D de novo generation of organic molecules. This includes in exploration on how to extend flow matching to model distributions of categorical variables. Additionally, we will discuss our work in the broader context of an emerging class of flow matching methods for sampling molecular structures.
Practical information
- General public
- Free
Organizer
- Philippe Schwaller, Andres M. Bran, Yannick Calvino, Rebecca M. Neeser
Contact
- Philippe Schwaller, Andres M. Bran, Yannick Calvino, Rebecca M. Neeser