{
  "abstract": "Pre-training graph neural networks on large unlabeled datasets has substantially improved molecular property prediction, yet pre-training approaches for reaction property prediction remain underexplored. We introduce CheMeleon-Rxn, a pre-trained reaction graph neural network that adapts the CheMeleon framework to condensed graphs of reaction (CGR) and demonstrates that descriptor-regression is an effective pre-training strategy for low-data reaction property prediction. An O(10M)-parameter D-MPNN encoder was pre-trained on ∼2 million reactions by regressing onto dense reaction descriptors pooled from classical molecular descriptors, then fine-tuned on small reaction property prediction datasets. Across regression tasks spanning gasphase activation energies, reaction enthalpies, experimental yields, and rate coefficients, CheMeleon-Rxn is best or statistically tied-for-best on seven of eight tasks. It outperforms the same encoder trained from scratch, as well as classical-descriptor, fingerprint, and pre-trained-fingerprint baselines. We further tested the pre-training strategy across various graph neural network architectures and found that its benefit holds for other edge-aware backbones such as GINE, and that it is robust to the choice of descriptor set, pooling operation, and other pre-training hyperparameters. We visualized and analyzed the CheMeleon-Rxn embeddings, which reveal chemically coherent structure in the learned reaction representation space. The CheMeleon-Rxn code has been released publicly (https://github.com/MSDLLCpapers/chemeleon-rxn) to encourage adoption and extension by the community. The model weights will be released upon publication.",
  "abstract_shown": true,
  "affiliations": [
    "Department of Chemical Engineering",
    "Massachusetts Institute of Technology",
    "Modeling and Informatics",
    "Merck & Co., Inc."
  ],
  "article_type": null,
  "arxiv": null,
  "author_total": 7,
  "authors": [
    {
      "affs": [
        0,
        1,
        2,
        3
      ],
      "name": "Akshat Shirish Zalte"
    },
    {
      "affs": [
        2,
        3
      ],
      "name": "Cheng Fang"
    },
    {
      "affs": [
        2,
        3
      ],
      "name": "Yiting Zheng"
    },
    {
      "affs": [
        2,
        3
      ],
      "name": "Essam Metwally"
    },
    {
      "affs": [
        2,
        3
      ],
      "name": "Alan Cheng"
    },
    {
      "affs": [
        2,
        3
      ],
      "name": "Alec Glisman"
    },
    {
      "affs": [
        2,
        3
      ],
      "name": "Hao-Wei Pang",
      "orcid": "0000-0001-9381-7500"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/43mqky4qth8ha.bib",
  "cited_by": 0,
  "doi": "10.26434/chemrxiv.15008692/v1",
  "fulltext_url": null,
  "id": "43mqky4qth8ha",
  "issns": [],
  "landing_url": "https://chemrxiv.org/doi/full/10.26434/chemrxiv.15008692/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": "W7212293459",
  "pdf_url": null,
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-11",
  "publisher": "American Chemical Society (ACS)",
  "ris": "https://research.draconitic.com/paper/43mqky4qth8ha.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:17:19Z",
      "native_id": "10.26434/chemrxiv.15008692",
      "source": "chemrxiv",
      "url": "https://chemrxiv.org/doi/full/10.26434/chemrxiv.15008692/v1"
    }
  ],
  "subjects": [
    {
      "field": "chemistry",
      "origin": "source:chemrxiv",
      "subfield": "general"
    }
  ],
  "title": "Descriptor-Based Pre-Training Improves Reaction Property Prediction",
  "title_text": "Descriptor-Based Pre-Training Improves Reaction Property Prediction",
  "type": "preprint",
  "updated_at": "2026-10-30T12:17:19Z",
  "url": "https://research.draconitic.com/paper/43mqky4qth8ha",
  "venue": "ChemRxiv",
  "versions": []
}