About me

🌟 Currently

Currently at Recursion Pharmaceuticals, I build and deploy state-of-the-art machine learning pipelines to industrialize and accelerate drug discovery. This involves architecting scalable systems that handle massive datasets, developing predictive models for key biological properties, and ensuring the seamless integration of these tools into our R&D workflow. My role is to transform the entire drug discovery process into a data-driven, automated enterprise.

🎓 Academic Research Background

My research is dedicated to engineering the next generation of medicines by operating at the intersection of machine learning, computational biology, and high-throughput experimentation. My goal is to translate complex biological data into tangible therapeutic innovations.

🔬 Postdoctoral Fellowship at University of Toronto.

As a senior Postdoctoral Fellow in the Kim Lab, my work focused on designing novel protein therapeutics, commonly known as biologics. These molecules offer significant advantages over traditional drugs, including higher specificity, a broader range of targets, and enhanced safety. This research led to the successful filing of two patents, demonstrating the direct clinical and commercial potential of my work. One patent covers the design of novel proteins, while the other is for a peptide that represents a new therapeutic strategy for treating Parkinson’s disease.

My core strategy involved fusing computational structural biology with systems-level data. To achieve this, I applied and developed innovative high-throughput screening methods—such as the multireporter bacterial-two-hybrid (M2H) system, Phage-display, and pooled lentiviral screens—to map vast networks of protein-protein interactions. I then leveraged this wealth of data to build sophisticated predictive models with machine learning to design therapeutic candidates. These designed candidates were further polished and improved by applying free energy calculations to accurately predict mutation effects on peptide stability and affinity.

🔬 PhD Research

This predictive work is built upon a deep foundational understanding of biophysics from my PhD. During my doctoral studies, I applied molecular dynamics simulations and free-energy calculations to investigate the intricate details of protein structure and conformational equilibrium. A key project involved elucidating the complex dynamics of the Abl kinase, revealing how its function is modulated by allosteric interactions and providing me with hands-on experience in experimental validation techniques like calorimetry and spectroscopy.

Bridging the gap between fundamental research and industrial application, my experience also includes working as a Scientific Data Manager at Almirall laboratories. There, I collaborated across departments to design and implement robust protocols for the preprocessing and digital storage of experimental data, which gave me a crucial perspective on the entire drug discovery pipeline.

Overall, my career tells a story of increasing scale and impact—from modeling the physics of a single protein to engineering entire biological systems. This unique combination of experience in biophysics, large-scale data analysis, and machine learning allows me to build the end-to-end strategies necessary to transform basic scientific discoveries into life-saving medicines.