{
  "abstract": "Autonomous drug discovery via generative molecular design is critically bottlenecked by the production of chemically intractable structures. Multi-trillion-scale make-on-demand libraries guarantee synthetic feasibility, but conventional virtual screening cannot efficiently navigate these vast spaces or address multi-parameter optimization. We introduce Hyper Screening X, a generative AI framework integrating structure-based design with automated synthesis hardware. By encoding deterministic reaction logic in a generative flow network, the framework evaluates only 10 million candidates to navigate an 11-trillion-compound space, jointly optimizing physicochemical properties while ensuring compatibility with automated synthesis. Prospective validation against an SLC1A5 variant with a cryptic interface yielded a 96% synthesis success rate and a 50% functional hit rate, identifying two first-in-class lead compounds. This synthesis-aware strategy advances autonomous, closed-loop drug discovery.",
  "abstract_shown": true,
  "affiliations": [
    "Department of Chemistry, KAIST, Daejeon, Republic of Korea; HITS Inc., Seoul, Republic of Korea"
  ],
  "article_type": "New results",
  "arxiv": null,
  "author_total": 15,
  "authors": [
    {
      "name": "S. Seo"
    },
    {
      "name": "Y. Sung"
    },
    {
      "name": "S.-Y. Hwang"
    },
    {
      "name": "M. Kang"
    },
    {
      "name": "J. Lee"
    },
    {
      "name": "S. Bordi"
    },
    {
      "name": "L. Raguz"
    },
    {
      "name": "J. Choi"
    },
    {
      "name": "D. Melnichenko"
    },
    {
      "name": "W. Namkung"
    },
    {
      "name": "S. Lee"
    },
    {
      "name": "J. Lim"
    },
    {
      "name": "B. M. Wanner"
    },
    {
      "name": "J. M. Han"
    },
    {
      "affs": [
        0
      ],
      "name": "W. Y. Kim"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/d3gx7dyyk1s2k.bib",
  "cited_by": 0,
  "doi": "10.64898/2026.10.01.755933",
  "fulltext_url": "https://www.biorxiv.org/content/10.64898/2026.10.01.755933v1.full",
  "id": "d3gx7dyyk1s2k",
  "issns": [],
  "landing_url": "https://www.biorxiv.org/content/10.64898/2026.10.01.755933v1",
  "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",
      "bioinformatics"
    ],
    [
      "openalex",
      "1703|Computational Drug Discovery Methods"
    ]
  ],
  "openalex": "W7220937369",
  "pdf_url": "https://www.biorxiv.org/content/10.64898/2026.10.01.755933v1.full.pdf",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-01",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/d3gx7dyyk1s2k.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:26:38Z",
      "native_id": "10.64898/2026.10.01.755933",
      "source": "biorxiv",
      "url": "https://www.biorxiv.org/content/10.64898/2026.10.01.755933v2"
    }
  ],
  "subjects": [
    {
      "field": "biology",
      "origin": "biorxiv:bioinformatics",
      "subfield": "bioinformatics"
    }
  ],
  "title": "Synthesis-aware generative design in trillion-scale chemical spaces for automated drug discovery",
  "title_text": "Synthesis-aware generative design in trillion-scale chemical spaces for automated drug discovery",
  "type": "preprint",
  "updated_at": "2026-10-30T12:26:46Z",
  "url": "https://research.draconitic.com/paper/d3gx7dyyk1s2k",
  "venue": "bioRxiv",
  "versions": []
}