{
  "abstract": "Protein mutation effect generation asks a model to describe the functional consequence of a point mutation in natural language. Existing protein-to-text systems typically encode mutation information into undifferentiated representations, overlooking the organization of mutation-induced evidence across structural and biochemical factors. We propose RipplePLM, a mutation-aware generation framework centered on Direct-Distal Cross-Attention (DDCA). By constructing a residue-level Mutation Perturbation Field from pre-trained protein language models, DDCA leverages predicted contact maps to organize mutation representations into two pathways: the mutation site's immediate contact neighborhood and its multi-hop distal context. To complement this structural decomposition, we further introduce the Property Latent Chain (PLChain), which injects expert-guided supervision of biochemical property changes (e.g., thermostability and optimal pH) into the LLM hidden-state pathway through latent property tokens. On MutaDescribe, RipplePLM improves over mutation-specific baselines on temporal and structural splits; under a matched-backbone comparison, average structural-split ROUGE-L increases from 22.23 to 35.65. Expert evaluation further shows a higher proportion of biologically accurate or relevant descriptions than the mutation-specific baseline. Additional ablations, representation diagnostics, and low-$N$ fitness regression experiments further support the effectiveness of the learned mutation-aware representations. Code: https://github.com/Lyu6PosHao/RipplePLM.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2610.01891",
  "author_total": 5,
  "authors": [
    {
      "name": "Liuzhenghao Lv"
    },
    {
      "name": "Yuyang Liu"
    },
    {
      "name": "Yuyang Gao"
    },
    {
      "name": "Li Yuan"
    },
    {
      "name": "Yonghong Tian"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/d20ne08kwq6f1.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2610.01891",
  "fulltext_url": null,
  "id": "d20ne08kwq6f1",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2610.01891",
  "language": null,
  "licence": "CC-BY-4.0",
  "licence_label": "CC BY 4.0",
  "licence_source": "article",
  "licence_url": "http://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "cs.CE"
    ],
    [
      "arxiv",
      "q-bio.BM"
    ],
    [
      "openalex",
      "1312|Machine Learning in Bioinformatics"
    ]
  ],
  "openalex": "W7216304346",
  "pdf_url": "https://arxiv.org/pdf/2610.01891",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-03",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/d20ne08kwq6f1.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:27:11Z",
      "native_id": "2610.01891",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2610.01891"
    }
  ],
  "subjects": [
    {
      "field": "biochemistry",
      "origin": "arxiv:q-bio.BM",
      "subfield": "biophysics"
    }
  ],
  "title": "RipplePLM: Structural and Property Decoupling for Protein Mutation Effect Generation",
  "title_text": "RipplePLM: Structural and Property Decoupling for Protein Mutation Effect Generation",
  "type": "preprint",
  "updated_at": "2026-10-30T12:27:11Z",
  "url": "https://research.draconitic.com/paper/d20ne08kwq6f1",
  "venue": "arXiv",
  "versions": []
}