{
  "abstract": "Focused DNA-encoded libraries (DELs) yield higher hit rates and cleaner selection data than billioncompound collections, and are affordable enough to build for a single target. Designing one means choosing a few hundred synthons from a much larger pool, and in the split-and-pool format that choice is collective and irreversible: the library is the full combinatorial product, so each synthon's value depends on every other one chosen alongside it. Brute force is out of reach – there are on the order of 10189 ways to draw 100 synthons from 3,000. We therefore recast the problem as sequence modeling. Treating a synthon as a token and an efficiency-ordered synthon set as a sentence, a generative pretrained transformer trained by next-token prediction learns context-dependent synthon value and composes new sets one synthon at a time. DEL-GPT was trained on one million ranked synthon sets drawn from NADEL, a validated 58,302-member library, with one model per target for five NAD+-dependent enzymes (PARP1, PARP2, PARP10, PARP12, PARP15). Across all five, DEL-GPT libraries outperformed those built from randomly drawn synthons – a demanding baseline, since every NADEL synthon is an expert-selected NAD+ mimetic – and contained two to three times more compounds that experimental affinity selection retained. Quality falls off once generated sets exceed the size range seen in training, but a model trained on longer sequences generated correspondingly larger high-quality sets – a validated recipe for scaling. The method is chemistryagnostic and applies to any combinatorial library over a shared building-block set.",
  "abstract_shown": true,
  "affiliations": [
    "Department of Chemistry, College of Arts and Sciences",
    "University of Missouri",
    "College of Pharmacy",
    "University of Utah"
  ],
  "article_type": null,
  "arxiv": null,
  "author_total": 4,
  "authors": [
    {
      "affs": [
        0,
        1
      ],
      "name": "Akhila Mettu"
    },
    {
      "affs": [
        0,
        1
      ],
      "name": "Naveed Naemi"
    },
    {
      "affs": [
        2,
        3
      ],
      "name": "Raphael Franzini"
    },
    {
      "affs": [
        0,
        1
      ],
      "name": "Dmitri Kireev",
      "orcid": "0000-0001-8479-8555"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/bj7zvn55fmm8f.bib",
  "cited_by": 0,
  "doi": "10.26434/chemrxiv.15008193/v1",
  "fulltext_url": null,
  "id": "bj7zvn55fmm8f",
  "issns": [],
  "landing_url": "https://chemrxiv.org/doi/full/10.26434/chemrxiv.15008193/v1",
  "language": null,
  "licence": "CC-BY",
  "licence_label": "CC BY",
  "licence_source": "journal",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "openalex",
      "1703|Computational Drug Discovery Methods"
    ]
  ],
  "openalex": "W7205004077",
  "pdf_url": "https://chemrxiv.org/doi/pdf/10.26434/chemrxiv.15008193/v1",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-02",
  "publisher": "American Chemical Society (ACS)",
  "ris": "https://research.draconitic.com/paper/bj7zvn55fmm8f.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:17:17Z",
      "native_id": "10.26434/chemrxiv.15008193",
      "source": "chemrxiv",
      "url": "https://chemrxiv.org/doi/full/10.26434/chemrxiv.15008193/v1"
    }
  ],
  "subjects": [
    {
      "field": "chemistry",
      "origin": "source:chemrxiv",
      "subfield": "general"
    }
  ],
  "title": "DEL-GPT: learning the language of DNA-encoded libraries to design focused screening collections",
  "title_text": "DEL-GPT: learning the language of DNA-encoded libraries to design focused screening collections",
  "type": "preprint",
  "updated_at": "2026-10-30T12:17:17Z",
  "url": "https://research.draconitic.com/paper/bj7zvn55fmm8f",
  "venue": "ChemRxiv",
  "versions": []
}