{
  "abstract": "Macrocyclic peptides are among the most promising therapeutic modalities, yet no general-purpose machine learned interatomic potential (MLIP) has been validated for their conformational analysis. We show that AIMNet2 matches the accuracy of MACE-OFF23(S) on the MPCONF196 macrocyclic benchmark, despite macrocycles being entirely absent from its training data, at three-to sixfold lower computational cost. To close the remaining accuracy gap, we introduce a continual training protocol that integrates fewer than 25,000 domain-specific conformers (<0.1% of the training corpus) while preserving accuracy on non-macrocyclic molecules, reducing macrocyclic conformational energy RMSE by 25–27%. Applied to cyclosporine A as an independent test case, the continually trained model reproduces DFT conformational energies with sub-kcal mol −1 accuracy (RMSE 0.78 kcal mol −1 ) and correct rank ordering of all metastable conformers, outperforming all other tested MLIPs and semi-empirical methods. This continual training strategy, together with expanded non-covalent interaction coverage, has been adopted in the AIMNet2 (2025) release, which unifies small-molecule, macrocyclic, and intermolecular interaction treatment in a single production potential.",
  "abstract_shown": true,
  "affiliations": [
    "Department of Chemistry",
    "Carnegie Mellon University",
    "Computational Biology Department, School of Computer Science",
    "Department of Materials Science and Engineering"
  ],
  "article_type": null,
  "arxiv": null,
  "author_total": 3,
  "authors": [
    {
      "affs": [
        0,
        1
      ],
      "name": "Runtian Gao",
      "orcid": "0009-0007-0702-0548"
    },
    {
      "affs": [
        0,
        1
      ],
      "name": "Roman Zubatyuk"
    },
    {
      "affs": [
        0,
        1,
        2,
        3
      ],
      "name": "Olexandr Isayev"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/cyrnk0sswqdrj.bib",
  "cited_by": 0,
  "doi": "10.26434/chemrxiv.15002334/v2",
  "fulltext_url": null,
  "id": "cyrnk0sswqdrj",
  "issns": [],
  "landing_url": "https://chemrxiv.org/doi/full/10.26434/chemrxiv.15002334/v2",
  "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",
      "2505|Machine Learning in Materials Science"
    ]
  ],
  "openalex": "W7212151602",
  "pdf_url": "https://chemrxiv.org/doi/pdf/10.26434/chemrxiv.15002334/v2",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-10",
  "publisher": "American Chemical Society (ACS)",
  "ris": "https://research.draconitic.com/paper/cyrnk0sswqdrj.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:17:19Z",
      "native_id": "10.26434/chemrxiv.15002334",
      "source": "chemrxiv",
      "url": "https://chemrxiv.org/doi/full/10.26434/chemrxiv.15002334/v2"
    }
  ],
  "subjects": [
    {
      "field": "chemistry",
      "origin": "openalex:2505|Machine Learning in Materials Science",
      "subfield": "materials-polymers"
    }
  ],
  "title": "Extending AIMNet2 to Macrocyclic Peptides Through Data-Efficient Continual Training",
  "title_text": "Extending AIMNet2 to Macrocyclic Peptides Through Data-Efficient Continual Training",
  "type": "preprint",
  "updated_at": "2026-10-30T12:17:19Z",
  "url": "https://research.draconitic.com/paper/cyrnk0sswqdrj",
  "venue": "ChemRxiv",
  "versions": []
}