Sean M Brown

The paper designs peptides with custom secondary structures using a generative AI model trained on protein data, achieving success in creating novel proteins with desired motifs and reduced amino acid alphabets.

The study shows that the 20 genetically-encoded amino acids are non-randomly distributed in functionally-relevant chemical properties like HOMO-LUMO gaps, expanding previous theories on amino acid alphabet design.

The paper shows that peptides made from non-standard amino acids can form protein-like secondary structures, expanding the known sequence-structure space beyond Earth's 20 amino acids.

This study shows random 25-mer peptides with a prebiotically plausible amino acid alphabet can self-assemble into thermostable beta-rich nanostructures.