{
  "abstract": "Models trained on protein sequences can predict mutational effects, but their outputs represent a convolution of different phenotypes. Isolating stability-independent activity effects is essential for rational enzyme design, allosteric drug design and functional annotation, yet existing pLM-based deconvolution methods lack interpretability. Here, we introduce a hybrid framework that pairs stability predictors with probabilistic graphical models of coevolution. Benchmarked on all enzymes with available multidimensional deep mutational scanning data, our framework isolates stability-independent activity effects with a fidelity that matches analogous pLM-based approaches. Crucially, we reveal biophysically plausible communication pathways that align with previous knowledge and that we validate with experimental data across a diverse set of targets. This hybrid approach merges statistical and geometric deep learning into a zero-shot, explainable tool for targeted engineering and mechanistic discovery.",
  "abstract_shown": true,
  "affiliations": [
    "Harvard Medical School"
  ],
  "article_type": "New results",
  "arxiv": null,
  "author_total": 6,
  "authors": [
    {
      "name": "S. Garcia Busto"
    },
    {
      "name": "E. Eschbach"
    },
    {
      "name": "T. A. Hopf"
    },
    {
      "name": "C. Sander"
    },
    {
      "name": "S. Bacallado"
    },
    {
      "affs": [
        0
      ],
      "name": "D. S. Marks"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/398jn8j5094zy.bib",
  "cited_by": 0,
  "doi": "10.64898/2026.10.15.759402",
  "fulltext_url": "https://www.biorxiv.org/content/10.64898/2026.10.15.759402v1.full",
  "id": "398jn8j5094zy",
  "issns": [],
  "landing_url": "https://www.biorxiv.org/content/10.64898/2026.10.15.759402v1",
  "language": null,
  "licence": "CC-BY",
  "licence_label": "CC BY",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "biorxiv",
      "bioinformatics"
    ],
    [
      "openalex",
      "1312|Protein Structure and Dynamics"
    ]
  ],
  "openalex": "W7221910969",
  "pdf_url": "https://www.biorxiv.org/content/10.64898/2026.10.15.759402v1.full.pdf",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-15",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/398jn8j5094zy.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:28:00Z",
      "native_id": "10.64898/2026.10.15.759402",
      "source": "biorxiv",
      "url": "https://www.biorxiv.org/content/10.64898/2026.10.15.759402v1"
    }
  ],
  "subjects": [
    {
      "field": "biology",
      "origin": "biorxiv:bioinformatics",
      "subfield": "bioinformatics"
    }
  ],
  "title": "Dual-graph deconvolution of enzyme fitness: an interpretable framework to identify and explain catalytic modulators",
  "title_text": "Dual-graph deconvolution of enzyme fitness: an interpretable framework to identify and explain catalytic modulators",
  "type": "preprint",
  "updated_at": "2026-10-30T12:28:00Z",
  "url": "https://research.draconitic.com/paper/398jn8j5094zy",
  "venue": "bioRxiv",
  "versions": []
}