{
  "abstract": "Protein-protein interactions underpin nearly all biological processes. Yet, designing proteins with desired interactions remains challenging due to the structural complexity governing molecular recognition. This study views protein design as a search optimization problem over a combinatorial sequence space under expensive structural evaluation. Toward this goal, we introduce a novel tree-based search framework, ProteoCraft, that employs approximate structural gradients from diffusion-based structure predictors as effective proposal policies to specify where the search should explore. Complete no-gradient inference of folding models separately assigns values to the resulting sequences, determining what is good. ProteoCraft allocates this verification budget through a coarse-to-fine paradigm: multi-site edits first explore distinct sequence basins, then verified promising states undergo strict single-site refinement. Across fourteen de novo binder-design settings spanning eight target proteins, five immune-relevant TCR-facing targets, and four localized CDR redesign tasks, ProteoCraft improves design quality and high-confidence yield. These improvements persist under independent AF2-IG and Rosetta-based interface evaluation. Prospective experimental validation further yielded an 82.9% binding hit rate for PD-L1 miniproteins, with a best measured KD of 0.879 nM, and confirmed binding of designed IFNAR2 VHH. Our code is available at https://github.com/smiles724/ProteoCraft_v1.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2611.03963",
  "author_total": 27,
  "authors": [
    {
      "name": "Fang Wu"
    },
    {
      "name": "Hongbin Lin"
    },
    {
      "name": "Bingchen Duan"
    },
    {
      "name": "Yuchen Wang"
    },
    {
      "name": "Li Erran Li"
    },
    {
      "name": "Yanjie Huang"
    },
    {
      "name": "Mingxuan Cao"
    },
    {
      "name": "Yijun Ma"
    },
    {
      "name": "Yunxiang Mo"
    },
    {
      "name": "Yanchao Li"
    },
    {
      "name": "Kuan Pang"
    },
    {
      "name": "Juangui Xu"
    },
    {
      "name": "Hanqun Cao"
    },
    {
      "name": "Dongwei Jiang"
    },
    {
      "name": "Xinyue Xu"
    },
    {
      "name": "Xiangru Tang"
    },
    {
      "name": "Zehong Wang"
    },
    {
      "name": "Jian Ma"
    },
    {
      "name": "Kejun Ying"
    },
    {
      "name": "Guanlue Li"
    },
    {
      "name": "Mingran Cao"
    },
    {
      "name": "Fanjin Wang"
    },
    {
      "name": "Tianfan Fu"
    },
    {
      "name": "Shuangjia Zheng"
    },
    {
      "name": "Yao Shu"
    },
    {
      "name": "Jure Leskovec"
    },
    {
      "name": "Yejin Choi"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/d1e8n10nhnz6w.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2611.03963",
  "fulltext_url": null,
  "id": "d1e8n10nhnz6w",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2611.03963",
  "language": null,
  "licence": "CC-BY-4.0",
  "licence_label": "CC BY 4.0",
  "licence_source": "article",
  "licence_url": "http://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "cs.AI"
    ],
    [
      "arxiv",
      "cs.CE"
    ],
    [
      "arxiv",
      "q-bio.BM"
    ]
  ],
  "openalex": null,
  "pdf_url": "https://arxiv.org/pdf/2611.03963",
  "pmcid": null,
  "pmid": null,
  "published": "2026-11-02",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/d1e8n10nhnz6w.ris",
  "sources": [
    {
      "first_seen": "2026-11-04T15:21:30Z",
      "native_id": "2611.03963",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2611.03963"
    }
  ],
  "subjects": [
    {
      "field": "biochemistry",
      "origin": "arxiv:q-bio.BM",
      "subfield": "biophysics"
    }
  ],
  "title": "ProteoCraft: Protein Design as Proposal-Verification Search",
  "title_text": "ProteoCraft: Protein Design as Proposal-Verification Search",
  "type": "preprint",
  "updated_at": "2026-11-06T18:21:04Z",
  "url": "https://research.draconitic.com/paper/d1e8n10nhnz6w",
  "venue": "arXiv",
  "versions": []
}