Chemical Physics
Machine Learning Interatomic Potentials (MLIPs)
In our group, we develop foundational machine learning interatomic potentials (MLIPs) that go beyond single-point energy predictions to enable more accurate and transferable molecular simulations. A key focus is designing advanced training strategies that enhance MLIP accuracy across diverse chemical environments while maintaining computational efficiency. We explore innovative approaches to extend MLIPs for molecular dynamics (MD) simulations, capturing long-timescale structural and dynamic properties with quantum-level accuracy. Additionally, we integrate MLIPs into transition state pathway predictions, enabling more efficient exploration of reaction mechanisms and energy landscapes. By improving both training methodologies and application strategies, our work expands the capabilities of MLIPs, making them more reliable for complex simulations in chemistry and materials science.
Interfacial Water Structure, Reactivity and Spectroscopy
We study the structure and reactivity of water at oil–water and plastic–water interfaces. Physics-based models connect Raman signatures at the water–oil interface with structural disorder and strong interfacial electric fields, while ReaxFF–CGeM simulations at water–plastic interfaces link hydroxide coordination and dangling OH with fluorescence and polymer-dependent interfacial reactivity.
Completely Multipolar Model
We develop advanced functional forms for energy decomposition models that enable fast and accurate molecular dynamics simulations. This work focuses on constructing detailed models of molecular interactions while retaining the efficiency needed for simulation, including applications to the density of water shown in our current work.
Bond Rearrangement Descriptors
We develop descriptors for understanding how chemical bonds rearrange. Polarizability provides an electronic observable and a basis for understanding bond rearrangements, while bond indices provide local, pair-specific information that can distinguish breaking and forming bonds.
M-Chem: An MD Engine
M-Chem is being developed to perform classical molecular dynamics simulations and to extend to ab initio molecular dynamics and hybrid quantum mechanics/molecular mechanics functionalities. The goal is to support simulations of biomolecular systems ranging from thousands to several hundred thousand atoms.
Protein Sciences and Drug Discovery
Large Language Models for Drug Discovery
We fine-tune large language models using drug discovery datasets to develop expert models for downstream tasks. These applications include de novo design, hit expansion, synthesis planning, fragment growing, and scaffold hopping.
Protein–Ligand Cofolding Models
We investigate protein–ligand cofolding models for allosteric drug discovery. Our current work includes CAFE, a cofolding protocol that uses competitive orthosteric blockers to divert fragments toward non-canonical binding sites.
Intrinsically Disordered Proteins (IDPs)
More than 60% of human proteins contain intrinsically disordered regions for which structural prediction models cannot provide a single defined structure. We develop diffusion models that generate IDP and IDR ensembles that agree with experimental data.