{
  "abstract": "Antibodies recognise their targets through hypervariable complementarity-determining regions (CDRs), which are interleaved with conserved frameworks in sequence space, making de novo CDR design an infilling problem. Autoregressive models generate residues left-to-right, which precludes full framework context during CDR generation and conflates framework and CDR likelihoods, leaving no natural prompt-response interface for feedback to steer generation. We present GenCDR, a family of LLaMa-based autoregressive language models that read all frameworks as a conditioning prompt and generate all CDRs jointly as a variable-length response, making CDR likelihoods a clean, separable target for reward attribution. The family comprises IgGenCDR, p-IgGenCDR, and NanoGenCDR, trained on unpaired, paired, and nanobody chains, respectively. GenCDR achieves the highest CDR recovery among autoregressive models and produces natural, diverse, human-like CDRs whose likelihoods correlate with fitness and developability assays. The prompt-response boundary also enables principled alignment: reward signals for binding affinity, expression, or developability can be composed to steer CDR generation. Over four rounds of alignment against antibody-antigen co-folding and developability objectives, we find that NanoGenCDR, which uses no explicit antigen encoding, can reach in silico structural interface metrics competitive with those of a structure-conditioned diffusion pipeline at roughly half the sampling budget, with more natural, developable designs. The same interface can be extended to integrate experimental feedback, opening a path to closed-loop antibody de novo design.",
  "abstract_shown": true,
  "affiliations": [
    "AstraZeneca"
  ],
  "article_type": "New results",
  "arxiv": null,
  "author_total": 9,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "F. Gonzalez Hernandez"
    },
    {
      "name": "O. M. Turnbull"
    },
    {
      "name": "M. Sultana"
    },
    {
      "name": "L. Roldan-Martin"
    },
    {
      "name": "R. J. Kumar"
    },
    {
      "name": "T. Diethe"
    },
    {
      "name": "R. Croasdale-Wood"
    },
    {
      "name": "C. Deane"
    },
    {
      "name": "D. Oglic"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/2sy3w2k36m3qg.bib",
  "cited_by": 0,
  "doi": "10.64898/2026.09.06.749721",
  "fulltext_url": "https://www.biorxiv.org/content/10.64898/2026.09.06.749721v1.full",
  "id": "2sy3w2k36m3qg",
  "issns": [],
  "landing_url": "https://www.biorxiv.org/content/10.64898/2026.09.06.749721v1",
  "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",
      "synthetic biology"
    ],
    [
      "openalex",
      "2741|Monoclonal and Polyclonal Antibodies Research"
    ]
  ],
  "openalex": "W7212258237",
  "pdf_url": "https://www.biorxiv.org/content/10.64898/2026.09.06.749721v1.full.pdf",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-06",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/2sy3w2k36m3qg.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:21:04Z",
      "native_id": "10.64898/2026.09.06.749721",
      "source": "biorxiv",
      "url": "https://www.biorxiv.org/content/10.64898/2026.09.06.749721v1"
    }
  ],
  "subjects": [
    {
      "field": "biology",
      "origin": "biorxiv:synthetic biology",
      "subfield": "systems-synthetic"
    }
  ],
  "title": "Generative Language Modeling for Antibody CDR Grafting and Alignment-driven De Novo Design",
  "title_text": "Generative Language Modeling for Antibody CDR Grafting and Alignment-driven De Novo Design",
  "type": "preprint",
  "updated_at": "2026-10-30T12:21:04Z",
  "url": "https://research.draconitic.com/paper/2sy3w2k36m3qg",
  "venue": "bioRxiv",
  "versions": []
}