PhD in Biochemical Engineering at the University of Maryland, Baltimore County (2025), preceded by an M.S. in Biochemical Engineering (2020) and dual B.S. degrees in Chemical Engineering and Molecular Biology (2018). Currently an Informatics Scientist doing product research for my company's new multiplex immunoassay platform, where I integrated machine learning into NGS workflows.
Unsupervised clustering and random forest applied to genotype-to-phenotype inverse design, plus local LLM/RAG tooling for translating published literature into actionable features and algorithms.
Currently applying this at Meso Scale Discovery: clustering antibody-screening data to create new process features, with an R Shiny app for epitope mapping and cross-sample consensus.
Built a suite of GUI apps for time-dynamic NGS and proteomic data — anchored by DPoP, a derivative-profiling method built on flux theory that flags differentially changing signals standard differential analysis misses.
Wrote the accompanying bioinformatic pipeline end to end and validated it against existing methods and RT-qPCR-confirmed ground truth in A. nidulans.
Genetic programming and kinetic modeling (MATLAB, GPTIPS) for network inference — from an unstructured kinetic model of an arabinose switch that decouples cell growth from metabolite production, to how cell wall integrity signaling governs mycelial mechanics in Aspergillus nidulans.
Collaborated across fungal drug resistance, systems biology, and biomaterials work, connecting proteomic and transcriptomic dynamics back to whole-organism phenotype.
Engineering microbial hosts at the genetic level — multiplex CRISPR/Cas12 genome editing and a colorimetric genetic marker built by engineering sulfur metabolism, both in Yarrowia lipolytica.
Also applied metamaterials-inspired inverse design to tune the mechanical properties of mycelial biomaterials in Aspergillus nidulans.