{
  "abstract": "High-dimensional data arrays in molecular representations pose some significant challenges for Machine Learning applications, including overfitting and computational inefficiency during training. This is particularly relevant for Morgan Fingerprint (MFP), widely used for tasks such as classification and property prediction, when dealing with large and complex molecular datasets. This article introduces embedded Morgan Fingerprint (eMFP), a method for dimensionality reduction of MFP, while preserving the key structural information of the encoded molecule. The implementation of eMFP offers an improved data representation that mitigates the risk of overfitting while enhancing model performance. Our results demonstrate that eMFP outperforms standard MFP in regression models, including Random Forest (RF), Multi-layer Perceptron (MLP), K-Neighbors Regressor (KNR), Gradient Booster Regressor (GBR) and a Deep Neural Network (DNN), across three different databases (RedDB, NFA, and QM9), with optimal compression sizes of q = 16, q = 32 and q = 64. These findings highlight the potential of eMFP as a faster and often superior alternative to MFP, offering more efficient hyperparameter optimization in regression models for molecular property predictions, and improved performance with large datasets where high-dimensional categorical data is encoded.",
  "abstract_shown": true,
  "affiliations": [
    "Department of Chemistry Swansea University Swansea UK",
    "Swansea University",
    "Grupo de Modelización y Diseño Molecular Departamento de Química Orgánica Facultad de Ciencias Universidad de Granada Granada Spain",
    "Universidad de Granada",
    "Department of Materials Science and Engineering Massachusetts Institute of Technology Cambridge Massachusetts USA",
    "Massachusetts Institute of Technology",
    "Centre for Integrative Semiconductor Materials (CISM) Swansea University Swansea UK",
    "Department of Chemistry Faculty of Natural, Mathematical and Engineering Sciences King’s College London London UK",
    "King's College London"
  ],
  "article_type": null,
  "arxiv": null,
  "author_total": 5,
  "authors": [
    {
      "affs": [
        0,
        1
      ],
      "name": "Emilio Nuñez-Andrade",
      "orcid": "0000-0003-1299-0147"
    },
    {
      "affs": [
        0,
        2,
        1,
        3
      ],
      "name": "Isaac Vidal",
      "orcid": "0000-0002-6082-316X"
    },
    {
      "affs": [
        4,
        5
      ],
      "name": "Rafael Gómez‐Bombarelli",
      "orcid": "0000-0002-9495-8599"
    },
    {
      "affs": [
        6,
        0,
        1
      ],
      "name": "James William Ryan",
      "orcid": "0000-0003-2268-512X"
    },
    {
      "affs": [
        7,
        0,
        8,
        1
      ],
      "name": "Francisco J. Martín‐Martínez",
      "orcid": "0000-0001-7149-5512"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/0a6xpx0zfbgyy.bib",
  "cited_by": 5,
  "doi": "10.1002/aidi.202500134",
  "fulltext_url": null,
  "id": "0a6xpx0zfbgyy",
  "issns": [
    "2943-9981"
  ],
  "landing_url": "https://doi.org/10.1002/aidi.202500134",
  "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": "W4411832464",
  "pdf_url": "https://onlinelibrary.wiley.com/doi/pdfdirect/10.1002/aidi.202500134",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-15",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/0a6xpx0zfbgyy.ris",
  "sources": [
    {
      "first_seen": "2026-11-07T13:21:00Z",
      "native_id": "W4411832464",
      "source": "openalex",
      "url": "https://doi.org/10.1002/aidi.202500134"
    }
  ],
  "subjects": [
    {
      "field": "chemistry",
      "origin": "openalex:3002|Computational Drug Discovery Methods",
      "subfield": "medicinal"
    }
  ],
  "title": "Embedded Morgan Fingerprints for More Efficient Molecular Property Predictions With Machine Learning",
  "title_text": "Embedded Morgan Fingerprints for More Efficient Molecular Property Predictions With Machine Learning",
  "type": "peer-reviewed",
  "updated_at": "2026-11-09T13:21:17Z",
  "url": "https://research.draconitic.com/paper/0a6xpx0zfbgyy",
  "venue": "Advanced Intelligent Discovery",
  "versions": [
    {
      "doi": "10.26434/chemrxiv-2025-6hfp8/v2",
      "pid": "bkkgjac9pg3sk",
      "relation": "preprint",
      "title": "Embedded Morgan Fingerprints for more efficient molecular property predictions with machine learning",
      "venue": "ChemRxiv"
    }
  ]
}