{
  "abstract": "We present FLOWR.ROOT, an S E (3)-equivariant flow-matching foundation model that unifies pocket-aware 3D ligand generation with multi-endpoint binding affinity prediction (pIC 50 , p K i , p K d , pEC 50 ) and pLDDT-based confidence estimation in a single backbone. One trained model supports de novo pocket-conditional generation, interaction- and pharmacophore-conditional sampling, scaffold hopping and elaboration, and fragment growing or replacement, enabled by a mixed isotropic–anisotropic prior placement strategy. Training proceeds in three stages: large-scale pre-training on billions of ligand conformations and millions of mixed-fidelity protein–ligand complexes, refinement on curated co-crystal data, and project-specific adaptation via parameter-efficient LoRA finetuning. Joint structure–affinity modelling enables inference-time importance-sampling guidance for single- and multi-objective design without external scoring functions. Case studies on kinase selectivity (CK2 α /CLK3) and scaffold elaboration on TYK2, ER α , and BACE1 illustrate utility from hit identification through lead optimization.",
  "abstract_shown": true,
  "affiliations": [
    "Machine Learning & Computational Sciences, Pfizer Worldwide R&D, Berlin, Germany. jn.cremer@icloud.com",
    "Machine Learning & Computational Sciences, Pfizer Worldwide R&D, Berlin, Germany",
    "Computational Chemistry, Medicine Design, Pfizer Worldwide R&D, Cambridge, MA, USA",
    "Computational Chemistry, Medicine Design, Pfizer Worldwide R&D, Cambridge, USA",
    "Department of Physicochemical Drug Analysis, Faculty of Pharmacy, Jagiellonian University Medical College, Cracow, Poland",
    "Doctoral School of Medical and Health Sciences, Jagiellonian University Medical College, Cracow, Poland",
    "Institute of Structural Biology, Molecular Targets and Therapeutics Center, Helmholtz Munich, Neuherberg, Germany. filipe.menezes@helmholtz-munich.de",
    "TUM School of Natural Sciences, Department of Bioscience, Bayerisches NMR Zentrum, Technical University of Munich, Garching, Germany. filipe.menezes@helmholtz-munich.de",
    "Institute of Structural Biology, Molecular Targets and Therapeutics Center, Helmholtz Munich, Neuherberg, Germany",
    "TUMSchool of Natural Sciences, Department of Bioscience, Bayerisches NMR Zentrum, Technical University of Munich, Garching, Germany"
  ],
  "article_type": null,
  "arxiv": null,
  "author_total": 6,
  "authors": [
    {
      "affs": [
        0,
        1
      ],
      "name": "Julian Cremer",
      "orcid": "0000-0001-6319-7283"
    },
    {
      "affs": [
        1
      ],
      "name": "Tuan Le",
      "orcid": "0000-0001-7634-502X"
    },
    {
      "affs": [
        2,
        3
      ],
      "name": "Mohammad Mehdi Ghahremanpour",
      "orcid": "0000-0002-1129-6041"
    },
    {
      "affs": [
        4,
        5
      ],
      "name": "Emilia Sługocka",
      "orcid": "0000-0001-5355-577X"
    },
    {
      "affs": [
        6,
        7,
        8,
        9
      ],
      "name": "Filipe Menezes",
      "orcid": "0000-0002-7630-5447"
    },
    {
      "affs": [
        1
      ],
      "name": "Djork-Arné Clevert",
      "orcid": "0000-0003-4191-2156"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/7dagp9z9r334t.bib",
  "cited_by": 9,
  "doi": "10.1038/s41467-026-74130-9",
  "fulltext_url": null,
  "id": "7dagp9z9r334t",
  "issns": [
    "2041-1723"
  ],
  "landing_url": "https://doi.org/10.1038/s41467-026-74130-9",
  "language": "en",
  "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",
      "3002|Computational Drug Discovery Methods"
    ]
  ],
  "openalex": "W4415981587",
  "pdf_url": "https://www.nature.com/articles/s41467-026-74130-9.pdf",
  "pmcid": "PMC13338463",
  "pmid": "42409794",
  "published": "2026-07-06",
  "publisher": "Nature Portfolio",
  "ris": "https://research.draconitic.com/paper/7dagp9z9r334t.ris",
  "sources": [
    {
      "first_seen": "2026-11-06T13:20:40Z",
      "native_id": "W4415981587",
      "source": "openalex",
      "url": "https://doi.org/10.1038/s41467-026-74130-9"
    }
  ],
  "subjects": [
    {
      "field": "chemistry",
      "origin": "openalex:3002|Computational Drug Discovery Methods",
      "subfield": "medicinal"
    }
  ],
  "title": "FLOWR.ROOT – A flow matching-based foundation model for joint multi-purpose structure-aware 3D ligand generation and affinity prediction",
  "title_text": "FLOWR.ROOT – A flow matching-based foundation model for joint multi-purpose structure-aware 3D ligand generation and affinity prediction",
  "type": "peer-reviewed",
  "updated_at": "2026-11-09T13:21:17Z",
  "url": "https://research.draconitic.com/paper/7dagp9z9r334t",
  "venue": "Nature Communications",
  "versions": []
}