{
  "abstract": "N-heterocyclic carbenes (NHCs) are well established as catalysts and ligands in many chemical transformations. Recently, interest has grown in pyridine[1,5]imidazolium salt pre-catalysts, stable precursors to NHCs, because they are relatively easy to synthesize and highly adaptable. This work introduces a data-driven workflow to identify which pyridine[1,5]imidazolium salts are readily synthetically accessible, starting from exploratory synthesis attempts for 127 compounds. Our approach relies on a feedback loop with a supervised machine learning model to estimate and dynamically update the synthesizability for a combinatorial space of about 394 million pre-catalysts derived from commercially available precursors. Our final model estimates that 4.78% of the entire space are feasible, mapping the space of readily accessible candidates and providing a valuable set for future inverse design studies. We validated the prediction performance of our approach based on both literature data and a holdout set occupying extremes of the combinatorial space.",
  "abstract_shown": true,
  "affiliations": [
    "Stratingh Institute for Chemistry, University of Groningen, Nijenborgh 3, Groningen, Groningen, Netherlands, 9747 AG"
  ],
  "article_type": null,
  "arxiv": null,
  "author_total": 7,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "Hannes Hovorka"
    },
    {
      "affs": [
        0
      ],
      "name": "Noa Huismann"
    },
    {
      "affs": [
        0
      ],
      "name": "Yanchao Wang"
    },
    {
      "affs": [
        0
      ],
      "name": "Gian-Michele Cherchi"
    },
    {
      "affs": [
        0
      ],
      "name": "Michael Lesa"
    },
    {
      "affs": [
        0
      ],
      "name": "Shiquan Zhou"
    },
    {
      "affs": [
        0
      ],
      "name": "Robert Pollice",
      "orcid": "0000-0001-8836-6266"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/6g6ev2t2c83zn.bib",
  "cited_by": 0,
  "doi": "10.26434/chemrxiv.15010127/v1",
  "fulltext_url": null,
  "id": "6g6ev2t2c83zn",
  "issns": [],
  "landing_url": "https://chemrxiv.org/doi/full/10.26434/chemrxiv.15010127/v1",
  "language": null,
  "licence": "CC-BY-NC",
  "licence_label": "CC BY-NC",
  "licence_source": "journal",
  "licence_url": "https://creativecommons.org/licenses/by-nc/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "openalex",
      "2505|Machine Learning in Materials Science"
    ]
  ],
  "openalex": "W7221145890",
  "pdf_url": "https://chemrxiv.org/doi/pdf/10.26434/chemrxiv.15010127/v1",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-08",
  "publisher": "American Chemical Society (ACS)",
  "ris": "https://research.draconitic.com/paper/6g6ev2t2c83zn.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:17:22Z",
      "native_id": "10.26434/chemrxiv.15010127",
      "source": "chemrxiv",
      "url": "https://chemrxiv.org/doi/full/10.26434/chemrxiv.15010127/v1"
    }
  ],
  "subjects": [
    {
      "field": "chemistry",
      "origin": "openalex:2505|Machine Learning in Materials Science",
      "subfield": "materials-polymers"
    }
  ],
  "title": "Active synthesizability prediction for a virtual space of 395 million catalyst candidates with small data",
  "title_text": "Active synthesizability prediction for a virtual space of 395 million catalyst candidates with small data",
  "type": "preprint",
  "updated_at": "2026-10-30T12:17:22Z",
  "url": "https://research.draconitic.com/paper/6g6ev2t2c83zn",
  "venue": "ChemRxiv",
  "versions": []
}