{
  "abstract": "Plants recruit antagonistic microbes to defend against phytopathogens, offering a route to rational biocontrol beyond empirical screening. Here, using six generations of leaf-microbiome data from natural Arabidopsis populations infected by the oomycete Albugo laibachii , we show that microbial diversity is driven by infection, site, and host genotype, and that infected plants form modular networks with increased inter-kingdom antagonism. We train four machine-learning models to discriminate infected from uninfected plants by microbiota composition and identify microbes enriched in diseased (disease-associated) or healthy (health-associated) plants. Testing the most predictive bacteria, fungi, and cercozoa in planta , we find all confer varying protection against Albugo , with health-associated microbes outperforming disease-associated taxa. The best candidate, a Cystofilobasidium fungus, is validated in a synthetic community, where genomic and community assays indicate biocontrol acts mainly through microbe-microbe interactions rather than plant immune activation. This work shows that pairing microbiome data with machine learning identifies effective biocontrol agents.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": null,
  "author_total": 10,
  "authors": [
    {
      "name": "Maryam Mahmoudi"
    },
    {
      "name": "Yiheng Hu"
    },
    {
      "name": "Juliana Almario"
    },
    {
      "name": "Paolo Stincone"
    },
    {
      "name": "Lynn-Marie Tenzer"
    },
    {
      "name": "Vasvi Chaudhry"
    },
    {
      "name": "Lukas Braun"
    },
    {
      "name": "Samuel Quinzer"
    },
    {
      "name": "Kay Nieselt"
    },
    {
      "name": "Eric Kemen"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/8295cn8kqy495.bib",
  "cited_by": 4,
  "doi": "10.1038/s41467-026-75789-w",
  "fulltext_url": null,
  "id": "8295cn8kqy495",
  "issns": [
    "2041-1723",
    "2041-1723"
  ],
  "landing_url": "https://hal.science/hal-05828875v1",
  "language": "en",
  "licence": "CC-BY-4.0",
  "licence_label": "CC BY 4.0",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "hal",
      "0.info"
    ],
    [
      "hal",
      "0.sde"
    ],
    [
      "hal",
      "0.sdv"
    ],
    [
      "hal",
      "1.info.info-lg"
    ],
    [
      "hal",
      "1.info.info-mo"
    ],
    [
      "hal",
      "1.sde.be"
    ],
    [
      "hal",
      "1.sdv.bv"
    ],
    [
      "hal",
      "1.sdv.ee"
    ],
    [
      "hal",
      "1.sdv.mp"
    ],
    [
      "hal",
      "2.sdv.bv.pep"
    ],
    [
      "hal",
      "2.sdv.ee.ieo"
    ],
    [
      "openalex",
      "1110|Plant-Microbe Interactions and Immunity"
    ]
  ],
  "openalex": "W7171513178",
  "pdf_url": "https://hal.science/hal-05828875/document",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-21",
  "publisher": "Nature Publishing Group",
  "ris": "https://research.draconitic.com/paper/8295cn8kqy495.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:18:00Z",
      "native_id": "hal-05828875",
      "source": "hal",
      "url": "https://hal.science/hal-05828875v1"
    }
  ],
  "subjects": [
    {
      "field": "biology",
      "origin": "hal:1.sde.be",
      "subfield": "ecology"
    },
    {
      "field": "biology",
      "origin": "hal:1.sdv.mp",
      "subfield": "microbiology"
    },
    {
      "field": "biology",
      "origin": "hal:1.sdv.bv",
      "subfield": "plant-biology"
    },
    {
      "field": "earth",
      "origin": "hal:0.sde",
      "subfield": "environmental-science"
    }
  ],
  "title": "Machine learning reveals biocontrol agents shaping disease outcome in natural Arabidopsis populations",
  "title_text": "Machine learning reveals biocontrol agents shaping disease outcome in natural Arabidopsis populations",
  "type": "peer-reviewed",
  "updated_at": "2026-10-30T12:18:00Z",
  "url": "https://research.draconitic.com/paper/8295cn8kqy495",
  "venue": "Nature Communications",
  "versions": []
}