Lukas F. Milles

A structure-conditioned nucleotide-level Potts model designs protein and coding sequences jointly, enabling tRNA adaptation and RNA motif embedding beyond synonymous codons with designability comparable to Caliby.

This paper introduces scalable experimental and computational workflows to accelerate protein design by improving throughput, reducing costs, and enabling rapid validation of thousands of protein designs.

The paper designs de novo proteins that form autocatalytic isopeptide bonds, enabling rigid covalent protein assemblies through intramolecular and intermolecular crosslinking.

This study investigates how intra-protein interfaces influence folding dynamics and mechanical stability in a designed repeat protein using single-molecule techniques and simulations.

This study designs miniproteins that inhibit MERS-CoV by targeting the spike protein, showing broad neutralization and protective efficacy in mice.

The paper designs TrkA agonists that activate neuronal differentiation and neurite outgrowth without triggering pain-related gene expression.

The paper develops a method to assess solution properties of designed proteins using mass spectrometry and peptide barcoding, enabling analysis of large protein libraries.

The paper designs closed repeat proteins with central pockets using deep learning and validates them in E. coli, showing structural consistency and potential for small molecule binding.

Fine-tuning RoseTTAFold as a diffusion denoiser gives RFdiffusion, a general protein backbone generator; a designed influenza haemagglutinin binder matched its model by cryo-EM.

A sequence-only protein language model, sampled under a structure-compatibility energy, produced designs of which 152 of 228 tested behaved as soluble monomers, some with no detectable UniRef90 match.