Artificial Intelligence-Aided Design of Peptides with Custom Secondary Structure Motifs and Reduced Amino Acid Alphabets

Abstract

Proteins are highly diverse functional polymers where the specific sequence of amino acids, selected from a standard genetically encoded alphabet of 20 (C20), determines the structure and ultimately the function of the resulting folded protein. This standard alphabet has been identified to be nonrandomly distributed in physicochemical properties crucial to both structure formation and function, often referred to as coverage theory. While machine learning models have drastically improved protein structure prediction, success of protein design models lags structure prediction, particularly for custom secondary structure motifs and amino acid alphabets. Here, we therefore bridge contemporary biological theory with recent advancements in artificial intelligence (AI) to develop and evaluate a generative AI protein design model, trained on hundreds of thousands of proteins within the RCSB PDB, for custom secondary structure motifs using reduced amino acid alphabets (RAAs). Results indicate an overall success in designing novel proteins with desired secondary structure motifs for a broad range of amino acid alphabets and complexity of designs. Interestingly, for a substantial fraction of designs, ESMFold predicts a fold close to that of the target structure despite training only on physicochemical sequence space and secondary structure information. The development of this model advances research across multiple disciplines, from general scientific AI architecture development to protein design for biotechnology, astrobiology, and early-Earth evolutionary biology.