Molecular simulations provide an unprecedented level of detail for studying molecular processes. Molecular dynamics simulations find utility in various fields like drug discovery, materials science, and modeling chemical reactions. They are also applicable for simulating biological systems such as proteins and nucleic acids. However, these simulations are computationally intensive, severely limiting their practical application. In this project, the chosen candidate will utilize generative AI to expedite simulations, enabling a deeper understanding of complex molecular systems, particularly proteins.
Machine learning introduces exciting possibilities in the natural sciences, encompassing disciplines like physics, chemistry, and biology. Its potential applications range from designing new drugs to combat multi-resistant pathogens and deciphering the impact of genetic mutations on protein function to accelerating computer simulations for unraveling fundamental scientific phenomena and crafting efficient algorithms for upcoming quantum computers. The journey toward these applications harnesses the capabilities of deep learning to efficiently represent and process high-dimensional data while encapsulating the laws of nature and inherent symmetries.
To join our team, we are seeking a collaborative and self-motivated candidate with expertise in statistical mechanics, machine learning, or dynamical systems, preferably a combination thereof, acquired through academic coursework or completed projects (e.g., publications or software libraries).
PhD Project Description
- 80% Research and coursework
- 20% Service, which includes educational contributions