Generative AI designs functional thiolation domains for reprogramming non-ribosomal peptide synthetases

Abstract Large language models and generative protein design promise to accelerate biotechnology, but it remains unclear whether they can engineer dynamic megasynth(et)ases whose activity depends on transient, context-specific domain interfaces. Non-ribosomal peptide synthetases (NRPSs) are an especially demanding target, yet a high-value one because they produce many clinically important natural products and offer a route to analogs that are often difficult or impractical to access by chemical synthesis. Here we integrate pretrained generative models (ESM3, ProteinMPNN and EvoDiff) with design–build–test–learn cycles and data-guided prioritization to generate 76 de novo thiolation (T) domains. We built and tested 578 recombinant NRPS variants in vivo spanning minimal, full-length and hybrid assembly lines. AI-designed T-domains supported product formation across architectures, enabled catalytically active hybrids at recombined junctions and increased yields by up to ∼3-fold relative to NRPSs carrying the native T-domain. A representative design showed improved soluble expression, refolding, and a 12 °C higher melting temperature, while molecular dynamics simulations indicated preserved global stability but reshaped, state-dependent interdomain contact networks. Together, these results establish generative design as an effective route to context-conditioned optimization and reprogramming of biosynthetic assembly lines. Competing Interest Statement K.A.J.B. is a co-founder and CSO of Myria Biosciences AG. S.S. is a co-founder and CEO of Myria Biosciences AG. H.A.M. is employed by ETH and Myria Biosciences AG. E.F.B. has a consulting agreement with Myria Biosciences AG. R.H. is employed by ETH and works on an Innosuisse collaboration project between ETH and Myria Biosciences AG. The remaining authors declare no competing interests. Footnotes ↵† Co-first authors