{
  "abstract": "In this work, we propose Molrep-SCF, a multimodal self-supervised pretraining framework for molecular representation learning using SMILES sequences, 2D molecular graphs, and 3D geometric structures. The three modalities are encoded using a Transformer, a graph neural network, and an invariant 3D graph neural network, respectively. To enrich geometric supervision beyond a single conformation, Molrep-SCF incorporates three selected and complementary 3D conformational views. We further introduce a 2D-guided conformational consistency refinement mechanism that uses molecular topology to guide the fusion and refinement of their geometric representations. Instead of relying on a single static conformation, our method enforces structural consistency across conformers under the guidance of 2D topological priors. Furthermore, we design a structure-aware cross-modal learning strategy with atomic-level alignment via position-specific masking, enabling fine-grained correspondence across modalities. In addition, masked reconstruction across modalities enhances deep semantic coupling and facilitates information exchange between heterogeneous representations. Extensive experiments demonstrate that Molrep-SCF consistently outperforms existing multi-modal frameworks on molecular property prediction and other tasks, showing stronger generalization and representation quality.",
  "abstract_shown": true,
  "affiliations": [
    "College of Information Engineering, Hunan Open University , ,"
  ],
  "article_type": "research article",
  "arxiv": null,
  "author_total": 5,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "Meng Ma"
    },
    {
      "affs": [
        0
      ],
      "name": "Qingqing Cao"
    },
    {
      "affs": [
        0
      ],
      "name": "Fang Liu"
    },
    {
      "affs": [
        0
      ],
      "name": "Caihua Chen"
    },
    {
      "affs": [
        0
      ],
      "name": "Yan Liu"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/422s39t45shvn.bib",
  "cited_by": 0,
  "doi": "10.3389/fphar.2026.1844064",
  "fulltext_url": "https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13661354/?tool=EBI",
  "id": "422s39t45shvn",
  "issns": [
    "1663-9812"
  ],
  "landing_url": "https://europepmc.org/article/PMC/PMC13661354",
  "language": "eng",
  "licence": "CC-BY",
  "licence_label": "CC BY",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "openalex",
      "1703|Computational Drug Discovery Methods"
    ]
  ],
  "openalex": "W7214885819",
  "pdf_url": "https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13661354/pdf/?tool=EBI",
  "pmcid": "PMC13661354",
  "pmid": null,
  "published": "2026-09-30",
  "publisher": "Frontiers Media SA",
  "ris": "https://research.draconitic.com/paper/422s39t45shvn.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:17:20Z",
      "native_id": "PMC:PMC13661354",
      "source": "europepmc",
      "url": "https://europepmc.org/article/PMC/PMC13661354"
    },
    {
      "first_seen": "2026-10-30T12:20:06Z",
      "native_id": "10.3389/fphar.2026.1844064",
      "source": "crossref",
      "url": "https://www.frontiersin.org/articles/10.3389/fphar.2026.1844064/full"
    }
  ],
  "subjects": [
    {
      "field": "medicine",
      "origin": "issn:1663-9812",
      "subfield": "pharmacology-toxicology"
    }
  ],
  "title": "Multimodal molecular representation and property prediction based on structured complementary feature fusion",
  "title_text": "Multimodal molecular representation and property prediction based on structured complementary feature fusion",
  "type": "peer-reviewed",
  "updated_at": "2026-10-30T12:20:06Z",
  "url": "https://research.draconitic.com/paper/422s39t45shvn",
  "venue": "Frontiers in pharmacology",
  "versions": []
}