{
  "abstract": "Pretrained chemical language models such as ChemBERTa and MoLFormer have become the default choice for molecular property prediction. However, they require large training sets to fine-tune effectively, and their computational footprint is substantial. We present Drugon, a compact alternative based on a Phase-Encoded Morgan fingerprint combined with a LightGBM regressor. Drugon requires approximately 15,000× fewer parameters and 40× less training time than fine-tuned transformers, while achieving higher predictive accuracy on three independent ChEMBL targets (n = 1378 to 2000). On the c-Abl dataset (CHEMBL4550), Drugon reaches a Pearson r = 0.749 under 5-fold cross-validation, compared with 0.605 for fine-tuned ChemBERTa and 0.551 for MoLFormer. Across all three targets, phase encoding provides a consistent, non-negative improvement over the classical binary Morgan fingerprint (∆r ∈ [0.000, 0.026]). Our results suggest that, in the low-data regime (n < 2000), fingerprint-based methods remain the most efficient and interpretable",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": null,
  "author_total": 1,
  "authors": [
    {
      "name": "Masoud Azizi"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/5m71kma4wm23k.bib",
  "cited_by": 0,
  "doi": "10.26434/chemrxiv.15009827/v1",
  "fulltext_url": null,
  "id": "5m71kma4wm23k",
  "issns": [],
  "landing_url": "https://chemrxiv.org/doi/full/10.26434/chemrxiv.15009827/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": "W7220374852",
  "pdf_url": "https://chemrxiv.org/doi/pdf/10.26434/chemrxiv.15009827/v1",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-04",
  "publisher": "American Chemical Society (ACS)",
  "ris": "https://research.draconitic.com/paper/5m71kma4wm23k.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:17:22Z",
      "native_id": "10.26434/chemrxiv.15009827",
      "source": "chemrxiv",
      "url": "https://chemrxiv.org/doi/full/10.26434/chemrxiv.15009827/v1"
    }
  ],
  "subjects": [
    {
      "field": "chemistry",
      "origin": "source:chemrxiv",
      "subfield": "general"
    }
  ],
  "title": "Drugon: Phase-Encoded Morgan Fingerprints Match Pretrained Chemical Transformers in Low-Data Affinity Prediction",
  "title_text": "Drugon: Phase-Encoded Morgan Fingerprints Match Pretrained Chemical Transformers in Low-Data Affinity Prediction",
  "type": "preprint",
  "updated_at": "2026-10-30T12:17:22Z",
  "url": "https://research.draconitic.com/paper/5m71kma4wm23k",
  "venue": "ChemRxiv",
  "versions": []
}