{
  "abstract": "Structure-guided mutation design requires relating a proposed substitution to its molecular environment to anticipate its effects. Existing evaluations of large language models (LLMs) in protein engineering emphasize sequence-based prediction or tool-integrated workflows, leaving unclear whether LLMs themselves can infer mutation effects from structural evidence without dedicated predictors. We evaluate physical intuition-qualitative reasoning that connects structural observations with molecular interaction principles-using a benchmark that tests the same substitution in the same protein across different binding partners, with predictions based on local atomic coordinates and no dedicated mutation-effect predictors. In the tested comparisons, the best-performing LLM achieved group accuracy comparable to the evaluated energy predictors and Biomni, an LLM-driven tool workflow, while the methods differed in their prediction patterns. Most evaluated LLMs achieved higher group accuracy for larger affinity improvements. Structural interventions support selective dependence on mutation-site and partner information, while assessable structural claims largely agree with the supplied coordinates. These findings support direct LLM structural reasoning as a basis for developing rational mutation-design tools that connect molecular observations with partner-specific effects.",
  "abstract_shown": true,
  "affiliations": [
    "Department of Bioinformatics and Biostatistics, School of Life Sciences and Biotechnology, Shanghai Jiao Tong University"
  ],
  "article_type": "New results",
  "arxiv": null,
  "author_total": 5,
  "authors": [
    {
      "name": "L. Cheng"
    },
    {
      "name": "K. Zheng"
    },
    {
      "name": "W. Huang"
    },
    {
      "name": "H.-F. Chen"
    },
    {
      "affs": [
        0
      ],
      "name": "Z. Yu"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/3c2y182tvv2te.bib",
  "cited_by": 0,
  "doi": "10.64898/2026.10.09.757856",
  "fulltext_url": "https://www.biorxiv.org/content/10.64898/2026.10.09.757856v1.full",
  "id": "3c2y182tvv2te",
  "issns": [],
  "landing_url": "https://www.biorxiv.org/content/10.64898/2026.10.09.757856v1",
  "language": null,
  "licence": "CC-BY-NC-ND",
  "licence_label": "CC BY-NC-ND",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by-nc-nd/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "biorxiv",
      "bioinformatics"
    ],
    [
      "openalex",
      "1312|Protein Structure and Dynamics"
    ]
  ],
  "openalex": "W7221532654",
  "pdf_url": "https://www.biorxiv.org/content/10.64898/2026.10.09.757856v1.full.pdf",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-09",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/3c2y182tvv2te.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:27:18Z",
      "native_id": "10.64898/2026.10.09.757856",
      "source": "biorxiv",
      "url": "https://www.biorxiv.org/content/10.64898/2026.10.09.757856v1"
    }
  ],
  "subjects": [
    {
      "field": "biology",
      "origin": "biorxiv:bioinformatics",
      "subfield": "bioinformatics"
    }
  ],
  "title": "Probing Physical Intuition in Large Language Models through Partner-Dependent Mutation Prediction",
  "title_text": "Probing Physical Intuition in Large Language Models through Partner-Dependent Mutation Prediction",
  "type": "preprint",
  "updated_at": "2026-10-30T12:27:18Z",
  "url": "https://research.draconitic.com/paper/3c2y182tvv2te",
  "venue": "bioRxiv",
  "versions": []
}