Bayesian Modeling

I utilized Bayesian modeling techniques to improved predictive accuracy and uncertainty quantification. This includes:

  • Performing a Bayesian regression for global fitting of multiple types of biochemical and biophysical data and studying the dimerization and ligand binding of coronavirus main protease (Paper in 2025)

  • Applying Bayesian regression to quantify uncertainty in binding parameters from isothermal titration calorimetry (ITC) data, providing a more reliable analysis than traditional error propagation methods (Paper in 2023).

  • Comparing Bayesian frameworks such as NumPyro, Pyro, and PyMC3 for analyzing ITC data.

  • Using Bayesian regression and model selection to study binding affinities in enantiomeric mixtures through ITC (Paper in 2022).

Drug Design & Pharmacological Insights

My work in drug design focuses on improving data analysis methods for pharmacological screening. Key achievements include:

  • Applying enzyme kinetic model to predict cellular pEC50s of compounds targeting MERS-CoV (Preprint in 2026)

  • Enhancing concentration-response curve fitting by incorporating control data, leading to more accurate estimates of half-maximal concentrations (Paper in 2023).