Physical Chemistry Seminar: Professor Fang Liu, Emory University
About the Seminar
"Synergizing Quantum Chemistry and Machine Learning for Molecular Discoveries in the Condensed Phase"
Machine learning (ML) and big data play increasingly critical roles in chemical discovery. However, datasets and ML models for condensed-phase molecular systems, such as solvated molecules and molecule assemblies, remain scarce. My research group leverages GPU-accelerated quantum chemistry and machine learning to address these gaps.
Many crucial solvent-solute interactions cannot be captured by the implicit solvent models routinely used in quantum chemistry calculation and require explicit solvent treatment. To streamline the simulation workflow for explicit-solvent calculations, we developed AutoSolvate, an open-source toolkit, which was later developed into a chatbot-assisted, cloud-based platform that automates simulation setup and execution using cloud computing resources. These tools have enabled the efficient generation of computational datasets for solvated molecules, which were used to train Δ-ML models to enhance the accuracy of low-cost computational methods against experimental measurements. For molecular assemblies, we developed a size-transferable machine-learned exciton model to rapidly model their excited-state properties. Additionally, we aim to bridge the gap between simulated and experimental datasets by leveraging large volumes of computational data to train ML models for real-time analysis in autonomous experiments. As a proof of concept, we successfully trained an ML model to detect material phase transitions in situ using angle-resolved photoemission spectroscopy (ARPES).
About the Speaker
Fang Liu is an Assistant Professor in the Department of Chemistry at Emory University. She received her B.S. from the Department of Chemical Physics at University of Science and Technology of China in 2011 and her Ph.D. in Chemistry from Stanford University under the supervision of Professor Todd J. Martínez in 2017. She completed postdoc at the Massachusetts Institute of Technology with Professor Heather J. Kulik, prior to joining Emory as a faculty member in 2020. Her research focuses on developing GPU algorithms for quantum chemistry methods, streamline molecular simulation workflows, and develop machine learning models to accelerate molecular discovery in the condensed phase. She was awarded the JCP-DCP Future of Chemical Physics Lectureship in 2023, a Cottrell Scholar Award in 2024, an Early Career Research Award of the Department of Energy in 2024, and an ACS COMP OpenEye Cadence Molecular Sciences Outstanding Junior Faculty Award in 2025.