Throughout my research career, I’ve worked at the intersection of computational chemistry, biophysics, and machine learning to advance our understanding of biomolecular systems. Beginning with structural studies of a H⁺-ATPase, I’ve progressively developed more sophisticated computational approaches, including neural network-enhanced QM/MM simulations for protein disulfide exchange reactions and coarse-grained modeling of self-assembling peptides. My work consistently bridges theoretical and experimental methodologies, applying machine learning to optimize molecular simulations, predict protein behaviors, and develop databases that facilitate structure-function relationship studies. I’m particularly passionate about method and software development, which has become my favorite aspect of research. Looking forward, I aim to continue working with proteins, developing innovative computational tools that can accelerate discovery and provide deeper insights into protein structure-function relationships.