{
  "abstract": "Numerous Python tools are available for molecular machine learning, typically built around core modeling paradigms such as descriptor-based approaches (“RDKit + scikit-learn”), deep neural networks, graph neural networks, geometric deep learning, and foundation models. Multi-instance learning (MIL) was originally inspired by the drug discovery problem, where a molecule can adopt multiple conformers and the biologically active one is unknown. Despite its clear relevance, MIL has not yet been supported by a dedicated and comprehensive Python platform for molecular applications. Here, we present QSARmil, a Python package designed for molecular multi-instance machine learning, that provides an integrated workflow including instance generation (e.g., conformers), 2D and 3D descriptor calculation, implementation of diverse MIL algorithms, and key instance identification. By bringing these components together in a unified and user-friendly framework, QSARmil makes it straightforward to apply multi-instance learning to any molecular property prediction task.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": null,
  "author_total": 6,
  "authors": [
    {
      "name": "Dmitry Zankov",
      "orcid": "0000-0002-6201-3347"
    },
    {
      "name": "Tomasz Danel"
    },
    {
      "name": "Martin Šícho"
    },
    {
      "name": "Wim Dehaen"
    },
    {
      "name": "Pavel Polishchuk"
    },
    {
      "name": "Mario Barbatti"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/4mj1778cedd41.bib",
  "cited_by": 0,
  "doi": "10.26434/chemrxiv.15008449/v1",
  "fulltext_url": null,
  "id": "4mj1778cedd41",
  "issns": [],
  "landing_url": "https://chemrxiv.org/doi/full/10.26434/chemrxiv.15008449/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": "W7211970524",
  "pdf_url": "https://chemrxiv.org/doi/pdf/10.26434/chemrxiv.15008449/v1",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-07",
  "publisher": "American Chemical Society (ACS)",
  "ris": "https://research.draconitic.com/paper/4mj1778cedd41.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:17:17Z",
      "native_id": "10.26434/chemrxiv.15008449",
      "source": "chemrxiv",
      "url": "https://chemrxiv.org/doi/full/10.26434/chemrxiv.15008449/v1"
    }
  ],
  "subjects": [
    {
      "field": "chemistry",
      "origin": "source:chemrxiv",
      "subfield": "general"
    }
  ],
  "title": "QSARmil: A Package for Molecular Multi-Instance Machine Learning",
  "title_text": "QSARmil: A Package for Molecular Multi-Instance Machine Learning",
  "type": "preprint",
  "updated_at": "2026-10-30T12:17:17Z",
  "url": "https://research.draconitic.com/paper/4mj1778cedd41",
  "venue": "ChemRxiv",
  "versions": []
}