2026-10-14T05:34:15Z https://api.figshare.com/v2/oai

oai:figshare.com:article/32983583 2026-09-23T07:02:57Z category_125 category_21 category_135 portal_81 item_type_3 month_year_09_2026

Generative AI designs functional thiolation domains for reprogramming non-ribosomal peptide synthetases Emre Fatih Bülbül (24392323) Seoung Gun Bang (24392325) Kevin George (24392328) Gabriele Bianchi (24392329) Prateek Raj (24392331) Seonyong Chung (24392337) Vincent Pauline (24392340) Ramon Hochstrasser (24392343) Hannah A. Minas (24392344) Walid A. M. Elgaher (9146458) Andreas M. Kany (24392352) Anna K.H. Hirsch (8359709) Steven Schmitt (24392355) Dirk W. Heinz (24392358) Olga V. Kalinina (10781) Dietrich Klakow (24392361) Kenan A. J. Bozhüyük (24392380) Bioinformatics Biotechnology Computational Biology NRPS engineering protein design Computational protein design This record contains the supplementary datasets underlying the study "Generative AI designs functional thiolation domains for reprogramming non-ribosomal peptide synthetases." Pretrained generative models (ESM3, ProteinMPNN and EvoDiff) were combined with iterative design–build–test–learn cycles to generate and experimentally evaluate de novo thiolation (T) domains for non-ribosomal peptide synthetases (NRPSs), testing 578 recombinant NRPS variants in vivo across minimal, full-length and hybrid assembly lines. The record includes two files: Supplementary_data_1_0303.xlsx — sequences and identifiers of all AI-designed T-domains; processed per-variant production data across design rounds; RapidFire LC–MS screening results (including minor products); residue-level molecular dynamics contact and hydrogen-bond interaction statistics for each catalytic state and replicate; and the T-domain sequences used for the phylogenetic analysis. Source_Data_0303.xlsx — the underlying numerical source data for all main-text and supplementary figures (Figs. 2–7 and the corresponding Supplementary Figures), including individual data points, biological replicate values, and the quantifications plotted in each panel. Data were generated in Escherichia coli using a bipartite type S GxpS platform, with peptide products quantified by LC-MS/MS. Full experimental and computational methods are described in the associated article and its Supplementary Information. 2026-09-23T07:02:57Z Dataset Dataset 10.6084/m9.figshare.32983583.v1 https://figshare.com/articles/dataset/Generative_AI_designs_functional_thiolation_domains_for_reprogramming_non-ribosomal_peptide_synthetases/32983583 CC BY 4.0