Dennis Della Corte

This paper develops enhanced NanoLuc luciferase variants using a hybrid approach of deep learning and structure-guided design, improving thermostability and activity at elevated temperatures.

The paper introduces a benchmark and algorithm for designing proteins with conformational specificity, demonstrating success in redesigning MAP kinase ERK2 to maintain activity without phosphorylation.

The paper evaluates computational hit-finding methods for targeting the WDR domain of LRRK2, a Parkinson's disease protein, finding that diverse strategies yielded weakly potent compounds.

The paper defines protein stability and conformational specificity probabilistically and introduces BayesDesign, a sequence decoding algorithm that maximizes p(structure|seq) for protein design.