{
  "abstract": "Biocatalysis offers a greener alternative to chemical processes, yet industrial adoption is bottlenecked by the prohibitive cost of enzyme engineering. Here, we report a multi-modal computational framework that integrates synergistic descriptors of substrate binding, protein stability, and aggregation traits. Using galactose oxidase as a model system, this approach achieves 77% precision in identifying active variants across 13 structurally diverse secondary alcohols despite being trained exclusively on a single substrate. By implementing sequence conservation-based filtering, we demonstrate that training data can be reduced by 41% without compromising predictive fidelity. Furthermore, the multi-modal model generalizes to combinatorial variants (2–5 mutations) with 100% precision on a limited library. Experimental validation yields a curated panel of starting points for the synthesis of high-value functional ingredients, including optical brighteners and fragrance stabilizers. Our multi-modal approach facilitates more cost-effective enzyme engineering, supporting the development of biocatalytic routes for sustainable chemical manufacturing.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": "Article",
  "arxiv": null,
  "author_total": 13,
  "authors": [
    {
      "name": "Jhoann M.T. Miyajima"
    },
    {
      "name": "Dillon W.P. Tay"
    },
    {
      "name": "Wan Lin Yeo"
    },
    {
      "name": "Ying Sin Koo"
    },
    {
      "name": "Shreyas Supekar"
    },
    {
      "name": "Adrielle Xianwen Chen"
    },
    {
      "name": "Charmaine Chia"
    },
    {
      "name": "Nazreen Abdul Muthaliff"
    },
    {
      "name": "Tong Mei Teh"
    },
    {
      "name": "Hao Fan"
    },
    {
      "name": "Yee Hwee Lim"
    },
    {
      "name": "Sebastian Maurer-Stroh"
    },
    {
      "name": "Ee Lui Ang",
      "orcid": "0000-0002-3070-8056"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/8jz5qevn276p1.bib",
  "cited_by": 0,
  "doi": "10.1016/j.isci.2026.118003",
  "fulltext_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC13734987/",
  "id": "8jz5qevn276p1",
  "issns": [
    "2589-0042"
  ],
  "landing_url": "https://www.cell.com/iscience/fulltext/S2589-0042(26)03386-9",
  "language": "en",
  "licence": "CC-BY-NC-ND-4.0",
  "licence_label": "CC BY-NC-ND 4.0",
  "licence_source": "article",
  "licence_url": "http://creativecommons.org/licenses/by-nc-nd/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "heading",
      "Article"
    ],
    [
      "heading",
      "Biocatalysis"
    ],
    [
      "heading",
      "Bioengineering"
    ],
    [
      "heading",
      "Computational chemistry"
    ],
    [
      "heading",
      "Machine learning"
    ],
    [
      "heading",
      "Protein"
    ],
    [
      "heading",
      "Structural biology"
    ],
    [
      "openalex",
      "1312|Enzyme Catalysis and Immobilization"
    ]
  ],
  "openalex": "W7223680285",
  "pdf_url": null,
  "pmcid": "PMC13734987",
  "pmid": "42991048",
  "published": "2026-10-26",
  "publisher": "Elsevier BV",
  "ris": "https://research.draconitic.com/paper/8jz5qevn276p1.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:17:16Z",
      "native_id": "10.1016/j.isci.2026.118003",
      "source": "feed-cell",
      "url": "https://www.cell.com/iscience/fulltext/S2589-0042(26)03386-9"
    },
    {
      "first_seen": "2026-10-30T12:17:49Z",
      "native_id": "10.1016/j.isci.2026.118003",
      "source": "crossref",
      "url": "https://linkinghub.elsevier.com/retrieve/pii/S2589004226033869"
    },
    {
      "first_seen": "2026-11-09T12:20:46Z",
      "native_id": "PMC13734987",
      "source": "pmc",
      "url": "https://doi.org/10.1016/j.isci.2026.118003"
    }
  ],
  "subjects": [
    {
      "field": "biochemistry",
      "origin": "heading:Structural biology",
      "subfield": "structural-biology"
    },
    {
      "field": "biology",
      "origin": "heading:Bioengineering",
      "subfield": "systems-synthetic"
    },
    {
      "field": "chemistry",
      "origin": "heading:Computational chemistry",
      "subfield": "theoretical"
    }
  ],
  "title": "Expanding the galactose oxidase substrate repertoire via a multi-modal computational strategy",
  "title_text": "Expanding the galactose oxidase substrate repertoire via a multi-modal computational strategy",
  "type": "peer-reviewed",
  "updated_at": "2026-11-09T12:20:46Z",
  "url": "https://research.draconitic.com/paper/8jz5qevn276p1",
  "venue": "iScience",
  "versions": []
}