Daniel Woldring

The paper develops methods to improve yeast surface display of FLS2 for detecting bacterial ligands, identifies glycosylation as a limiting factor, and shows how modifying glycosylation sites enhances binding specificity.

This study compares the evolvability of an ancestrally reconstructed and modern adenylate kinase, finding that the ancestral enzyme tolerates more mutations and generates more viable variants.

The paper develops a method to select tissue-specific proteins that direct extracellular vesicles in vivo, using EV-display libraries and a Markov chain model to predict selection dynamics.

This paper introduces HOLIgraph, a graph neural network model that predicts OATP1B1 inhibitors by integrating ligand features and protein-ligand interactions, achieving over 90% balanced accuracy.

This paper introduces RecombiCraft, a method for DNA library construction in E. coli using SLiCE and liquid culture, which minimizes sequence bias and reduces costs.

This paper evaluates an ancestral sequence reconstruction-informed data augmentation strategy for improving protein sequence generation and representation learning, showing improved thermostability in generated variants.

AP-LASR automates ancestral sequence reconstruction and generates diverse protein libraries by leveraging ASR uncertainty, improving eLnP scores over existing methods.

The paper evaluates how language models, ensemble learning, and sampling methods affect protein fitness prediction using binding affinity and thermal stability datasets.