{
  "abstract": "Natural products represent a major source of therapeutic molecules, yet their structural diversity and limited biological annotations pose substantial challenges for computational exploration and discovery. Here, we develop a multimodal molecular representation framework that integrates chemical language, molecular fingerprints, physicochemical descriptors, and molecular graphs into a unified latent space for natural product discovery. Using structurally out-of-distribution molecular spaces, we show that molecular representation and sampling strategy jointly determine which regions of chemical space are explored. Multimodal pretraining captured chemically informative representations that enabled exploration of structurally unseen natural products, while comparisons with singlemodality representations showed that representation advantages depended on the discovery objective rather than being universally superior. The pretrained representation was transferable across anti-inflammatory and antioxidant activity predictions, and its integration with active learning enabled data-efficient exploration of biologically active molecules. Prospective evaluation of structurally unseen natural products further connected model-guided exploration with experimental antioxidant activity. These findings establish molecular representation and sampling as coupled determinants of chemical-space exploration and show",
  "abstract_shown": true,
  "affiliations": [
    "Division of Pharmaceutical Chemistry",
    "Faculty of Pharmaceutical Sciences, Khon Kaen University",
    "Graduate School in the Program of Research and Development in Pharmaceuticals",
    "Faculty of Health Sciences",
    "College of Natural Sciences, Can Tho University"
  ],
  "article_type": null,
  "arxiv": null,
  "author_total": 3,
  "authors": [
    {
      "affs": [
        0,
        1
      ],
      "name": "Tarapong Srisongkram",
      "orcid": "0000-0001-8512-5379"
    },
    {
      "affs": [
        0,
        1
      ],
      "name": "Supreeya Paiboon"
    },
    {
      "affs": [
        2,
        1,
        3,
        4
      ],
      "name": "Huynh Anh Duy",
      "orcid": "0009-0008-0436-6014"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/3rczy7ntx9qeb.bib",
  "cited_by": 0,
  "doi": "10.26434/chemrxiv.15009161/v1",
  "fulltext_url": null,
  "id": "3rczy7ntx9qeb",
  "issns": [],
  "landing_url": "https://chemrxiv.org/doi/full/10.26434/chemrxiv.15009161/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",
      "1703|Computational Drug Discovery Methods"
    ]
  ],
  "openalex": "W7213883386",
  "pdf_url": null,
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-21",
  "publisher": "American Chemical Society (ACS)",
  "ris": "https://research.draconitic.com/paper/3rczy7ntx9qeb.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:17:19Z",
      "native_id": "10.26434/chemrxiv.15009161",
      "source": "chemrxiv",
      "url": "https://chemrxiv.org/doi/full/10.26434/chemrxiv.15009161/v1"
    }
  ],
  "subjects": [
    {
      "field": "chemistry",
      "origin": "source:chemrxiv",
      "subfield": "general"
    }
  ],
  "title": "Multimodal Representation Learning for Exploring Natural Product Chemical Space",
  "title_text": "Multimodal Representation Learning for Exploring Natural Product Chemical Space",
  "type": "preprint",
  "updated_at": "2026-10-30T12:17:19Z",
  "url": "https://research.draconitic.com/paper/3rczy7ntx9qeb",
  "venue": "ChemRxiv",
  "versions": []
}