{
  "abstract": "We tested whether graph, transformer and topological molecular representations improve antimalarial activity prediction beyond an ECFP4-random-forest baseline under chemicaldistribution shift.The scaffold split is treated as a distribution shift rather than a stricter evaluation, following recent literature on molecular out-of-distribution specification, residual similarity leakage in scaffold and Butina splits, and multi-splitter evidence that Bemis-Murcko partitions are among the milder OOD regimes relative to ECFP4-cluster or nearest-neighbour strata [1][2][3].The open question is whether the representation-task alignment of learned models compensates for their OOD extrapolation deficit relative to ECFP4, or whether the fingerprint advantage is concentrated in the out-of-distribution tail.On a frozen panel of 19 836 African antimalarial natural products, five-fold cross-validation was repeated over five seeds (25 fold-seed replicates per model and split).Under the scaffold protocol, ECFP4-RF reached mean ROC AUC 0.830 0, above GIN-TFP (0.813 8), GIN-TNE (0.809 0), GIN (0.804 7) and ChemBERTa (0.786 7); the four contrasts against ECFP4-RF remained significant after Benjamini-Hochberg correction.Two protocol elements distinguish the comparison: fold-independent restoration of pretrained transformer weights removing crossfold leakage, and controlled insertion of persistent-homology and tensor-network descriptors into a graph architecture under scaffold-held-out evaluation.Persistent-image dimensions carried the largest projection-weight magnitudes in the fusion head, but the salience did not improve ranking.A nearest-training-neighbour Tanimoto decile stratification (Section 3.5.1)answers the open question: the ECFP4 advantage is concentrated in the OOD tail (deciles D1-D4, ∆ ∈ 0.016 --0.027) and in D9 (∆ = 0.017), while mid-range D5-D8 exhibit nearparity (∆ ∈ 0.001 --0.007).Representation-task alignment therefore does not compensate for the learned models' OOD deficit on this panel; the fingerprint advantage is confined to the out-of-distribution tail.The findings characterise the OOD response of the evaluated panel, splits, architectures and training budgets and do not generalise to all learned molecular models.",
  "abstract_shown": true,
  "affiliations": [
    "Department of Physics",
    "University of Yaounde I",
    "Department of Medical Imaging and Radiation Sciences, Université de Sherbrooke, Sherbrooke, QC, Sherbrooke, QC, Canada",
    "Department of Biochemistry"
  ],
  "article_type": null,
  "arxiv": null,
  "author_total": 5,
  "authors": [
    {
      "affs": [
        0,
        1
      ],
      "name": "Jean-Pierre TCHAPET NJAFA",
      "orcid": "0000-0002-1936-8353"
    },
    {
      "affs": [
        2
      ],
      "name": "Penabei SAMAFOU",
      "orcid": "0000-0002-9683-7678"
    },
    {
      "affs": [
        3,
        1
      ],
      "name": "Fon Wilfred MBACHAM",
      "orcid": "0000-0002-3934-3233"
    },
    {
      "affs": [
        0,
        1
      ],
      "name": "Serge Guy NANA ENGO",
      "orcid": "0000-0002-7484-3508"
    },
    {
      "affs": [
        0,
        1
      ],
      "name": "Myke Vital SAO TEMGOUA",
      "orcid": "0009-0004-5170-2309"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/5vzg129xev6yg.bib",
  "cited_by": 0,
  "doi": "10.26434/chemrxiv.15008517/v1",
  "fulltext_url": null,
  "id": "5vzg129xev6yg",
  "issns": [],
  "landing_url": "https://chemrxiv.org/doi/full/10.26434/chemrxiv.15008517/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": "W7211962174",
  "pdf_url": "https://chemrxiv.org/doi/pdf/10.26434/chemrxiv.15008517/v1",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-08",
  "publisher": "American Chemical Society (ACS)",
  "ris": "https://research.draconitic.com/paper/5vzg129xev6yg.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:17:19Z",
      "native_id": "10.26434/chemrxiv.15008517",
      "source": "chemrxiv",
      "url": "https://chemrxiv.org/doi/full/10.26434/chemrxiv.15008517/v1"
    }
  ],
  "subjects": [
    {
      "field": "chemistry",
      "origin": "source:chemrxiv",
      "subfield": "general"
    }
  ],
  "title": "Scaffold-Controlled Evaluation of Molecular Representations for Antimalarial Activity Prediction",
  "title_text": "Scaffold-Controlled Evaluation of Molecular Representations for Antimalarial Activity Prediction",
  "type": "preprint",
  "updated_at": "2026-10-30T12:17:19Z",
  "url": "https://research.draconitic.com/paper/5vzg129xev6yg",
  "venue": "ChemRxiv",
  "versions": []
}