{
  "abstract": "Fixed-backbone sequence discovery, or inverse folding, is a critical recurring task in the development of new polypeptide therapeutics. Once promising backbones are established for a target pocket, computational inverse folding methods greatly help accelerate generation of candidate sequences. Such methods are mature for the traditional case of limiting to the fixed twenty-letter canonical vocabulary; however, they cannot access the broader space of non-canonical amino acids (NCAAs). This design constraint is exacerbated for peptide binders, a fast-growing modality that readily incorporates NCAAs, though in practice non-canonical design frequently depends on laborious medicinal-chemistry campaigns. An extension of inverse folding to NCAAs is thus critical to accelerating design of novel therapeutic peptides. AtomWeaver uses a joint all-site, atom-level generative scheme that does not restrict side-chain categorical assignment by either predetermined or co-resolving residue identity. Conditioned only on a fixed peptide backbone and its target protein, its multi-component flow guides side-chain atoms as unlabeled points in R3 from a nested shell prior to a variable-count final atom cloud. Identity is then read by matching each predicted cloud against a reference library of canonical and non-canonical templates. Since identity is decided only at decode time, the addressable vocabulary is a property of the library rather than of the trained weights: a new NCAA costs one reference structure and no retraining, and the model can select residues it was never prompted for and never saw in training. On a deep mutational scan of two peptide-target systems, AtomWeaver's canonical readout shows high observed mean agreement with experimental values among the compared inverse-folding methods. In the mixed canonical-noncanonical setting that canonical-only baselines cannot support at all, it likewise retains ranking signal across both systems. AtomWeaver also displayed self-consistent designs on de novo binder backbones, with the highest interface confidence among compared methods. Notably, it reached these metrics while achieving broad empirical coverage of our 300-residue vocabulary, including four non-canonical types never visible in training. AtomWeaver thus serves canonical and non-canonical peptide design alike, while transforming residue vocabulary to an expandable inference-time choice.",
  "abstract_shown": true,
  "affiliations": [
    "ProteinQure Inc"
  ],
  "article_type": "New results",
  "arxiv": null,
  "author_total": 9,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "A. Kitaygorodsky"
    },
    {
      "name": "D. E. Hostallero"
    },
    {
      "name": "A. Broom"
    },
    {
      "name": "E. Layne"
    },
    {
      "name": "S. Hwang"
    },
    {
      "name": "A. K. Kanawaty"
    },
    {
      "name": "T. Babej"
    },
    {
      "name": "G. L. Butterfoss"
    },
    {
      "name": "M. Fingerhuth"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/1e64rk01mn9ft.bib",
  "cited_by": 0,
  "doi": "10.64898/2026.09.23.753608",
  "fulltext_url": "https://www.biorxiv.org/content/10.64898/2026.09.23.753608v1.full",
  "id": "1e64rk01mn9ft",
  "issns": [],
  "landing_url": "https://www.biorxiv.org/content/10.64898/2026.09.23.753608v1",
  "language": null,
  "licence": "CC-BY",
  "licence_label": "CC BY",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "biorxiv",
      "bioengineering"
    ],
    [
      "openalex",
      "1312|Protein Structure and Dynamics"
    ]
  ],
  "openalex": "W7214776751",
  "pdf_url": "https://www.biorxiv.org/content/10.64898/2026.09.23.753608v1.full.pdf",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-23",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/1e64rk01mn9ft.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:25:02Z",
      "native_id": "10.64898/2026.09.23.753608",
      "source": "biorxiv",
      "url": "https://www.biorxiv.org/content/10.64898/2026.09.23.753608v1"
    }
  ],
  "subjects": [
    {
      "field": "biology",
      "origin": "biorxiv:bioengineering",
      "subfield": "systems-synthetic"
    }
  ],
  "title": "AtomWeaver: Multi-Component Flow Matching with a Structured Geometric Prior Facilitates Non-Canonical Peptide Design",
  "title_text": "AtomWeaver: Multi-Component Flow Matching with a Structured Geometric Prior Facilitates Non-Canonical Peptide Design",
  "type": "preprint",
  "updated_at": "2026-10-30T12:25:02Z",
  "url": "https://research.draconitic.com/paper/1e64rk01mn9ft",
  "venue": "bioRxiv",
  "versions": []
}