I am a final-year PhD candidate at MIT working with Patrick S. Doyle on nanoformulation for oral drug delivery. My research is motivated by the challenge of formulating hydrophobic small molecules and focuses on developing a versatile bottom-up approach that overcomes the limitations of industrial nanoformulation processes. My thesis work has included designing core-shell hydrogels, simulating molecular-level drug-excipient interactions, engineering size-controlled nanoparticles, and developing state-of-the-art molecular property prediction models using deep learning. I thrive at the interface of computational modeling and experimentation, using simulations to interpret experimental results and data-driven modeling to guide experimental design. More information can be found about my work on my personal website (lucasattia.github.io).
Research Interests
Broadly, I am interested in leveraging data science and molecular modeling to digitize industrial formulation design. Traditional formulation is often a trial-and-error process, but the complexity of emerging therapeutics like peptides, oligonucleotides, and PROTACs demands data-driven, mechanistic approaches. My goal is to bridge experimental formulation science with innovations in molecular ML and simulation to enable rational drug formulation. I am seeking a full-time position starting in summer 2026.