David Ryan Koes

This study identifies a CAD defense system in C. elegans involving CYP-35B and PGP-13, showing their roles in CAD metabolism and efflux, and links bacteria to CAD defense activation.

This study shows that a small molecule Pfn1 inhibitor reduces tumor angiogenesis in renal cell carcinoma by targeting endothelial cell Pfn1.

The paper investigates how IL-1 receptor signaling dynamics are quantized and independent of ligand affinity using experimental and modeling approaches.

InfluenceNet directly encodes motif influence in cis-regulatory elements, enabling interpretable prediction of regulatory syntax with performance comparable to state-of-the-art models.

SWING is a novel interaction language model that predicts peptide:MHC interactions and protein-protein interaction disruptions using sequence data.

The paper introduces MASPR, a machine learning method using protein language models to predict adenylation domain substrate specificities, enabling the prediction of hybrid NRP-PK natural products.

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.

This paper introduces a method to improve protein structure predictions by incorporating molecular dynamics forces into deep learning training, resulting in lower potential energy and better structural quality.

This paper shows that incorporating protein structure information into protein language models improves their performance on structure-related tasks without requiring structure access during inference.