Research interests
My work sits at the intersection of statistical mechanics, machine learning, and structural biology. Three threads run through it:
- Protein conformational ensemble prediction using ML/AI
- Allosteric pathway prediction in protein complexes
- De novo protein design strategies using ML/AI
I'm comfortable operating across the full stack of computational biophysics — from the statistical mechanics of Hamiltonian dynamics and Markov state models, to the engineering of scalable HPC pipelines and PyTorch Geometric architectures. The throughline is connecting atomistic simulation insight to generative design workflows, toward structure-dynamics-informed therapeutic discovery.
Currently, I'm developing a deep learning model for predicting allosteric pathways, communications, and protein–protein interface hotspot residues, validated against experimentally known allosteric sites.