Using generative AI to transform peptide hits into small molecule leads

• Joshua Mills and
• Yu Heng Lau

Beilstein J. Org. Chem. 2026, 22, 672–679, doi:10.3762/bjoc.22.51

• , de novo peptide binder generation, diffusion models for generating novel small molecule scaffolds, and deep-learning predictors of binding affinity to rapidly triage candidates. Keywords: diffusion models; drug discovery; generative AI; peptides; small molecules; Introduction In drug discovery

• for small molecule design by leveraging data on peptide binders, and proposes potential opportunities where generative AI and machine learning (ML) tools may augment various stages throughout the pipeline from peptide hit discovery to small molecule lead. Perspective Current workflows for designing

• small molecules that mimic peptide pharmacophores Illustrative example of a non-AI workflow To understand where generative AI may play a role in transforming peptides into small molecules, we first briefly outline how traditional non-AI tools are typically used in the field. Starting from an