Developed various large-scale data analytics techniques alongside proprietary algorithmic solutions. Explored and designed solutions to deal with NP-complete / NP-hard solutions in the context of large-scale data, especially in biology and immunology. Developed web-based visualizations for large-scale data problems, such as classification algorithms.

Created a Python-based data pipeline that used correlative hierarchical clustering of nasal wash and blood plasma data to evaluate module-based relationships between various cytokines and other proteins, allowing for the examination of potential biologic pathways that correlate to specific phenotypic patient subsets. Subsequently created a Python-based GUI that allows scientists with little to no computer science knowledge the ability to upload and manipulate data and demographics files in real time, then analyze the data with hierarchical clustering.