{
  "abstract": "Aqueous-solubility prediction depends on both molecular representation and the definition of the target. We compared fingerprint, descriptor, hybrid, and graph-based representations on the TDC Solubility_AqSolDB benchmark using five official scaffold splits and a fixed test set of 1,997 records. Hybrid-CatBoost achieved a five-run test MAE of 0.749631 ± 0.016216 TDC logS units, compared with 0.764558 ± 0.009666 for descriptor-only CatBoost. However, the corresponding validation improvement was small (ΔMAE = −0.004932) and occurred in only two of five matched splits. Errors increased toward both target extremes and showed opposite-signed residual biases. These results indicate that descriptor-based models capture most of the predictive signal in this benchmark, while the added Morgan fingerprint provides only a modest and split-dependent benefit. Interpretation is limited by incomplete assay metadata and the use of a single fixed test set, which does not provide external validation.",
  "abstract_shown": true,
  "affiliations": [
    "College of Life Science and Technology, Beijing University of Chemical Technology, North 3rd Ring, Beijing, China"
  ],
  "article_type": null,
  "arxiv": null,
  "author_total": 1,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "Ruming Li",
      "orcid": "0009-0004-0499-429X"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/ce7eya4q3g39q.bib",
  "cited_by": 0,
  "doi": "10.26434/chemrxiv.15009996/v1",
  "fulltext_url": null,
  "id": "ce7eya4q3g39q",
  "issns": [],
  "landing_url": "https://chemrxiv.org/doi/full/10.26434/chemrxiv.15009996/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": "W7220679730",
  "pdf_url": "https://chemrxiv.org/doi/pdf/10.26434/chemrxiv.15009996/v1",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-06",
  "publisher": "American Chemical Society (ACS)",
  "ris": "https://research.draconitic.com/paper/ce7eya4q3g39q.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:17:22Z",
      "native_id": "10.26434/chemrxiv.15009996",
      "source": "chemrxiv",
      "url": "https://chemrxiv.org/doi/full/10.26434/chemrxiv.15009996/v1"
    }
  ],
  "subjects": [
    {
      "field": "chemistry",
      "origin": "source:chemrxiv",
      "subfield": "general"
    }
  ],
  "title": "Hybrid-CatBoost: an empirical comparison of molecular representations for aqueous-solubility prediction on the TDC benchmark",
  "title_text": "Hybrid-CatBoost: an empirical comparison of molecular representations for aqueous-solubility prediction on the TDC benchmark",
  "type": "preprint",
  "updated_at": "2026-10-30T12:17:22Z",
  "url": "https://research.draconitic.com/paper/ce7eya4q3g39q",
  "venue": "ChemRxiv",
  "versions": []
}