{
  "abstract": "Accurate preparation of small-molecule databases for virtual screening is crucial for the success of computer-aided drug discovery. Although numerous free software options are available, they often underperform compared to commercial alternatives. Here, we introduce MolSanitizer, an open-source molecular preparation pipeline built on RDKit and designed for large-scale virtual screening. MolSanitizer extends existing open-source functionality through curated, chemical-environment-aware rules for protonation and tautomerization, systematic stereoisomer enumeration, and a dedicated conformer generator that combines knowledge-based structural preferences with stochastic torsional sampling. Our benchmarking results show that MolSanitizer achieves better performance than several free software alternatives while achieving performance levels comparable to commercial software. MolSanitizer features a modular and open-source design, allowing users to easily customize the tool to meet their specific needs. MolSanitizer also generates output files compatible with several widely used molecular docking programs, thereby facilitating a streamlined workflow for users. MolSanitizer is available for free at https://github.com/carlssonlab/MolSanitizer and via a web server at https://carlssonlabtools.icm.uu.se/molsani.",
  "abstract_shown": true,
  "affiliations": [
    "Department of Cell and Molecular Biology",
    "Uppsala University",
    "Institute of Pharmaceutical Chemistry",
    "Philipps-Universität Marburg",
    "Department of Biomedicine",
    "University of Bergen",
    "Department of Medical Biochemistry and Biophysics",
    "Karolinska Institutet",
    "Cancer Research Technology Program, Leidos Biomedical Research, Inc., P.O. Box B, Frederick, Maryland, 21702",
    "Department of Pharmaceutical Chemistry",
    "University of California",
    "Science for Life Laboratory (SciLifeLab"
  ],
  "article_type": null,
  "arxiv": null,
  "author_total": 11,
  "authors": [
    {
      "affs": [
        0,
        1
      ],
      "name": "Thua-Phong Lam",
      "orcid": "0000-0002-8149-9952"
    },
    {
      "affs": [
        0,
        1
      ],
      "name": "Szymon Pach",
      "orcid": "0000-0001-6109-7123"
    },
    {
      "affs": [
        0,
        1
      ],
      "name": "Philip Ullmann",
      "orcid": "0000-0003-2391-4609"
    },
    {
      "affs": [
        2,
        3
      ],
      "name": "Hocine El Khaoudi Enyoury"
    },
    {
      "affs": [
        4,
        5
      ],
      "name": "Ruth Brenk",
      "orcid": "0000-0002-6204-5488"
    },
    {
      "affs": [
        6,
        7
      ],
      "name": "Flavio Ballante",
      "orcid": "0000-0002-4831-3423"
    },
    {
      "affs": [
        8
      ],
      "name": "Trent E. Balius",
      "orcid": "0000-0002-6811-4667"
    },
    {
      "affs": [
        2,
        3
      ],
      "name": "Peter Kolb",
      "orcid": "0000-0003-4089-614X"
    },
    {
      "affs": [
        9,
        10
      ],
      "name": "John Irwin",
      "orcid": "0000-0002-1195-6417"
    },
    {
      "affs": [
        0,
        1,
        11
      ],
      "name": "Jens Carlsson",
      "orcid": "0000-0003-4623-2977"
    },
    {
      "affs": [
        0,
        1
      ],
      "name": "Israel Cabeza de Vaca",
      "orcid": "0000-0002-6208-1091"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/029myxhz9p0aq.bib",
  "cited_by": 0,
  "doi": "10.26434/chemrxiv.15010189/v1",
  "fulltext_url": null,
  "id": "029myxhz9p0aq",
  "issns": [],
  "landing_url": "https://chemrxiv.org/doi/full/10.26434/chemrxiv.15010189/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": "W7221087724",
  "pdf_url": "https://chemrxiv.org/doi/pdf/10.26434/chemrxiv.15010189/v1",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-09",
  "publisher": "American Chemical Society (ACS)",
  "ris": "https://research.draconitic.com/paper/029myxhz9p0aq.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:17:22Z",
      "native_id": "10.26434/chemrxiv.15010189",
      "source": "chemrxiv",
      "url": "https://chemrxiv.org/doi/full/10.26434/chemrxiv.15010189/v1"
    }
  ],
  "subjects": [
    {
      "field": "chemistry",
      "origin": "source:chemrxiv",
      "subfield": "general"
    }
  ],
  "title": "MolSanitizer: An open-source pipeline to prepare small-molecule databases for large-scale virtual screening",
  "title_text": "MolSanitizer: An open-source pipeline to prepare small-molecule databases for large-scale virtual screening",
  "type": "preprint",
  "updated_at": "2026-10-30T12:17:22Z",
  "url": "https://research.draconitic.com/paper/029myxhz9p0aq",
  "venue": "ChemRxiv",
  "versions": []
}