B. Kuhlman

Invariant point message passing for protein side chain packing

This paper introduces PIPPack, a deep learning method for protein side chain packing that is competitive with state-of-the-art methods but significantly faster.

In silico evolution of protein binders with deep learning models for structure prediction and sequence design

This study uses deep learning models to design high-affinity protein binders for PD-L1 without extensive screening, achieving KD values below 150 nM.

AlphaFold accurately predicts distinct conformations based on oligomeric state of a de novo designed protein

The paper tests AlphaFold's ability to predict different protein conformations based on oligomeric state, finding it accurately predicts both monomeric and dimeric structures of a designed protein.

Control of microtubule dynamics using an optogenetic microtubule plus end-F-actin cross-linker

This paper introduces an optogenetic tool, SxIP-iLID, to control microtubule dynamics by cross-linking MT plus ends with F-actin, revealing effects on MT growth and lamellar exclusion zones.

The Rosetta all-atom energy function for macromolecular modeling and design

The paper explains the Rosetta all-atom energy function, its mathematical models, and its application to biomolecular modeling and design, including new capabilities for membrane proteins and other macromolecules.