I’m a computational scientist with a Ph.D. in Chemical and Biochemical Engineering, specializing in the intersection of molecular biology, machine learning, and rigorous statistical analysis.
My current work focuses on antibody developability assessment—identifying post-translational modification liabilities (particularly glycosylation risks) that AI-driven protein design tools often miss. I bridge the gap between computationally designed biologics and manufacturing reality.
Technical Focus
- Molecular Simulations: AMBER, molecular dynamics, protein structure analysis
- Machine Learning: PyTorch, scikit-learn, CNN-LSTM architectures for binding prediction
- Bayesian Statistics: Probabilistic modeling, uncertainty quantification
- Cloud Infrastructure: AWS, Docker, Kubernetes
Background
Over 10 years of experience applying computational methods to biological problems, including:
- Antibody glycoform heterogeneity modeling
- RNA-seq analysis and liver transcriptomics
- Clinical trial data analysis
- Large-scale trajectory data processing (100+ TB)
I value scientific rigor, reproducibility, and the ability to communicate complex findings clearly.