2023/08/16 by Daniel Flam-Shepherd, Kevin Zhu, Flam-Shepherd, Daniel +4 · 1 voice
Biochemistry, Genetics and Molecular Biology · Computer Science · Materials Science · #Biomolecules (q-bio.BM) #FOS: Biological sciences #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning in Bioinformatics #Machine Learning in Materials Science #Protein Structure and Dynamics #cs.LG #q-bio.BM
paper · pdf · doi:10.48550/arxiv.2308.09482
openalex publication_date 2023/08/16 · arxiv published 2023/08/16 · arxiv updated 2023/08/16 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Protein language models learn powerful representations directly from sequences of amino acids. However, they are constrained to generate proteins with only the set of amino acids represented in their vocabulary. In contrast, chemical language models learn atom-level representations of smaller molecules that include every atom, bond, and ring. In this work, we show that chemical language models can learn atom-level representations of proteins enabling protein generation unconstrained to the standard genetic code and far beyond it. In doing so, we show that language models can generate entire proteins atom by atom -- effectively learning the multiple hierarchical layers of molecular information that define proteins from their primary sequence to their secondary, and tertiary structure. We demonstrate language models are able to explore beyond protein space -- generating proteins with modified sidechains that form unnatural amino acids. Even further, we find that language models can explore chemical space and protein space simultaneously and generate novel examples of protein-drug conjugates. The results demonstrate the potential for biomolecular design at the atom level using language models.