Zachary A. Martinez

This paper shows that protein language models prioritize sequence novelty over structural diversity, leading to a tradeoff in generating realistic protein structures.

This study optimizes the One-Pot PURE system by addressing expression instability and proteolysis in E. coli strains, improving protein production efficiency.

This study benchmarks protein language models for predicting protein crystallization propensity and identifies novel potentially crystallizable proteins.

This paper introduces foldtuning, a method to generate novel protein sequences with target structures, bypassing evolutionary barriers and enabling synthetic biology applications.

TRILL enables scalable, modular deep-learning workflows for protein analysis and engineering by integrating models like ESM-2 and DiffDock.