{
  "identifier": "tag:aim-pro.eu,2026:oer/618ee026c670/record",
  "profile": "aimpro-oer-profile/1",
  "normaliser": "oerlib.metadata/2",
  "status": "ready",
  "normalised_at": "2026-10-09T09:54:10+00:00",
  "resource": {
    "id": "618ee026c670",
    "identifier": "tag:aim-pro.eu,2026:oer/618ee026c670",
    "uri": "https://arxiv.org/abs/2602.03779",
    "title": "Generative AI for Enzyme Design and Biocatalysis",
    "description": "Sparked by innovations in generative artificial intelligence (AI), the field of protein design has undergone a paradigm shift with an explosion of new models for optimizing existing enzymes or creating them from scratch. After more than one decade of low success rates for computationally designed enzymes, generative AI models are now frequently used for designing proficient enzymes. Here, we provide a comprehensive overview and classification of generative AI models for enzyme design, highlighting models with experimental validation relevant to real-world settings and outlining their respective limitations. We argue that generative AI models now have the maturity to create and optimize enzymes for industrial applications. Wider adoption of generative AI models with experimental feedback loops can speed up the development of biocatalysts and serve as a community assessment to inform the next generation of models.",
    "creators": [
      "Lasse Middendorf",
      "Noelia Ferruz"
    ],
    "keywords": [
      "q-bio.BM"
    ],
    "kind": "html",
    "content_language": "en",
    "declared_language": "en",
    "word_count": 6972,
    "content_hash": "859fcc8167f0fc19",
    "metadata_only": false
  },
  "licence": {
    "raw": "CC-BY-NC-SA-4.0",
    "spdx": "CC-BY-NC-SA-4.0",
    "uri": "http://creativecommons.org/licenses/by-nc-sa/4.0/",
    "verdict": "OPEN_NC",
    "note": "open but Non-Commercial — SME/commercial reuse needs care",
    "ingestable": true,
    "commercial_ok": false,
    "derivable": true,
    "share_alike": true,
    "evidence": {
      "scope": "this submitted version of the paper",
      "method": "arXiv OAI-PMH GetRecord (metadataPrefix=arXiv)",
      "schema": 1,
      "status": "captured",
      "location": "arXiv:arXiv/arXiv:license",
      "source_url": "https://oaipmh.arxiv.org/oai?verb=GetRecord&identifier=oai:arXiv.org:2602.03779&metadataPrefix=arXiv",
      "asserted_by": "arXiv submitter",
      "captured_at": "2026-10-09T09:53:59+00:00",
      "source_system": "arxiv",
      "observed_value": "http://creativecommons.org/licenses/by-nc-sa/4.0/",
      "documentation_url": "https://info.arxiv.org/help/oa/index.html",
      "responsibility_url": "https://info.arxiv.org/help/license/index.html",
      "documentation_label": "arXiv OAI-PMH metadata documentation",
      "responsibility_note": "The submitter chooses the article-version licence and certifies the right to grant it."
    }
  },
  "descriptive": {
    "contributions": [
      {
        "name": "Lasse Middendorf",
        "role": "author",
        "affiliation": "",
        "identifier": "",
        "scope": "resource"
      },
      {
        "name": "Noelia Ferruz",
        "role": "author",
        "affiliation": "",
        "identifier": "",
        "scope": "resource"
      }
    ],
    "identifiers": [
      {
        "scheme": "arxiv",
        "value": "2602.03779",
        "scope": "resource"
      }
    ],
    "dates": [
      {
        "meaning": "issued",
        "value": "2026-02-03",
        "scope": "resource"
      }
    ],
    "subjects": [
      {
        "value": "q-bio.BM",
        "scheme": "arxiv",
        "scope": "resource"
      }
    ],
    "relations": [],
    "educational": {
      "learning_resource_type": "",
      "intended_end_user_role": "",
      "context": "",
      "difficulty": "",
      "typical_learning_time": "",
      "description": ""
    },
    "container": {
      "kind": "",
      "uri": "",
      "title": "",
      "description": "",
      "identifier": ""
    },
    "declared_language": "en",
    "declared_type": "preprint",
    "rights_holder": "",
    "access_rights": "open",
    "publisher": "",
    "version": "v1",
    "citation": "",
    "notes": "",
    "lifecycle_status": "",
    "structure_role": "",
    "snapshot": {
      "resource": {
        "title": "Generative AI for Enzyme Design and Biocatalysis",
        "authors": [
          "Lasse Middendorf",
          "Noelia Ferruz"
        ],
        "summary": "Sparked by innovations in generative artificial intelligence (AI), the field of protein design has undergone a paradigm shift with an explosion of new models for optimizing existing enzymes or creating them from scratch. After more than one decade of low success rates for computationally designed enzymes, generative AI models are now frequently used for designing proficient enzymes. Here, we provide a comprehensive overview and classification of generative AI models for enzyme design, highlighting models with experimental validation relevant to real-world settings and outlining their respective limitations. We argue that generative AI models now have the maturity to create and optimize enzymes for industrial applications. Wider adoption of generative AI models with experimental feedback loops can speed up the development of biocatalysts and serve as a community assessment to inform the next generation of models.",
        "updated": "2026-02-03T17:40:20Z",
        "version": 1,
        "arxiv_id": "2602.03779",
        "published": "2026-02-03T17:40:20Z",
        "categories": [
          "q-bio.BM"
        ],
        "affiliations": [
          "",
          ""
        ],
        "primary_category": "q-bio.BM"
      }
    }
  },
  "representations": [
    {
      "role": "extracted",
      "media_type": "text/markdown",
      "size_bytes": 47309,
      "filename": "",
      "location": "",
      "source_format": "latexml-html",
      "converter": "arxiv-html"
    }
  ],
  "observed": {
    "language": {
      "method": "declared",
      "reason": "declared English",
      "accepted": true,
      "declared": "en",
      "detected": "en",
      "confidence": null,
      "review_required": false
    }
  },
  "collection": {
    "source": "arxiv",
    "source_label": "arXiv",
    "collected_at": "2026-10-09T09:54:10.999738+00:00",
    "query": "(all:\"artificial intelligence\" OR all:\"machine learning\" OR all:\"generative AI\" OR all:\"deep learning\" OR all:\"reinforcement learning\" OR all:\"large language model\") AND (all:\"AI concepts\" OR all:\"types of AI\" OR all:\"AI fundamentals\" OR all:\"recognizing AI\" OR all:\"recognising AI\" OR all:\"general versus narrow AI\" OR all:\"narrow AI\" OR all:\"general AI\" OR all:\"machine intelligence\" OR all:\"AI strengths and weaknesses\" OR all:\"traditional software\" OR all:\"rule-based systems\" OR all:\"introduction to AI\" OR all:\"introduction to artificial intelligence\" OR all:\"artificial intelligence introduction\" OR all:\"AI primer\" OR all:\"foundations of artificial intelligence\" OR all:\"overview of AI\" OR all:\"understanding AI\" OR all:\"history of AI\" OR all:\"AI essentials\" OR all:\"AI terminology\" OR all:\"metaphors for AI\" OR all:\"AI fundamental concepts\" OR all:\"AI key concepts\" OR all:\"philosophy of AI\" OR all:\"critical AI literacy\")",
    "note": "where this was collected from. Not a claim that the provider published or authored it"
  },
  "provenance": [
    {
      "field": "resource_id",
      "scope": "resource",
      "method": "engine",
      "evidence_ref": "engine#/resource_id"
    },
    {
      "field": "query",
      "scope": "resource",
      "method": "engine",
      "evidence_ref": "engine#/query"
    },
    {
      "field": "collected_from",
      "scope": "resource",
      "method": "engine",
      "evidence_ref": "engine#/source"
    },
    {
      "field": "title",
      "scope": "resource",
      "method": "source_metadata",
      "evidence_ref": "snapshot#/resource/title"
    },
    {
      "field": "description",
      "scope": "resource",
      "method": "source_metadata",
      "evidence_ref": "snapshot#/resource/summary"
    },
    {
      "field": "version",
      "scope": "resource",
      "method": "source_metadata",
      "evidence_ref": "snapshot#/resource"
    },
    {
      "field": "subjects",
      "scope": "resource",
      "method": "source_metadata",
      "evidence_ref": "snapshot#/resource/categories/0"
    },
    {
      "field": "contributions",
      "scope": "resource",
      "method": "source_metadata",
      "evidence_ref": "snapshot#/resource/authors/0"
    },
    {
      "field": "contributions",
      "scope": "resource",
      "method": "source_metadata",
      "evidence_ref": "snapshot#/resource/authors/1"
    },
    {
      "field": "dates",
      "scope": "resource",
      "method": "source_metadata",
      "evidence_ref": "snapshot#/resource"
    },
    {
      "field": "identifiers",
      "scope": "resource",
      "method": "source_metadata",
      "evidence_ref": "snapshot#/resource/arxiv_id"
    },
    {
      "field": "content_language",
      "scope": "resource",
      "method": "gate_observation",
      "evidence_ref": "gate#/language/declared"
    },
    {
      "field": "declared_language",
      "scope": "resource",
      "method": "source_metadata",
      "evidence_ref": "snapshot#/resource"
    },
    {
      "field": "licence",
      "scope": "resource",
      "method": "gate_observation",
      "evidence_ref": "gate#/licence/evidence"
    },
    {
      "field": "access_rights",
      "scope": "resource",
      "method": "source_metadata",
      "evidence_ref": "snapshot#/resource"
    },
    {
      "field": "representations",
      "scope": "resource",
      "method": "conversion",
      "evidence_ref": "conversion#/latexml-html"
    },
    {
      "field": "declared_type",
      "scope": "resource",
      "method": "source_metadata",
      "evidence_ref": "snapshot#/resource"
    },
    {
      "field": "educational",
      "scope": "resource",
      "method": "declared_type_mapping",
      "evidence_ref": "profile#/learning_resource_type/preprint"
    }
  ],
  "incidents": [
    {
      "code": "absent",
      "field": "rights_holder",
      "detail": "no rights holder is named at source; the licence is recorded without one rather than attributed to the platform that served it"
    },
    {
      "code": "absent",
      "field": "publisher",
      "detail": "the source named no publisher of the work; where it was collected from is recorded as collection provenance instead, which is a different claim"
    },
    {
      "code": "absent",
      "field": "educational",
      "detail": "the source declared no educational metadata — no resource type, audience, context, difficulty or learning time. Nothing here estimates them"
    }
  ],
  "inferred": [
    {
      "rule": "purpose.declared_type",
      "field": "purpose",
      "value": "reference",
      "method": "inferred",
      "evidence": {
        "declared_type": "preprint"
      },
      "rule_version": "purpose/1"
    },
    {
      "field": "references",
      "value": "https://doi.org/10.1038/s41467-025-61209-y",
      "label": "doi:10.1038/s41467-025-61209-y",
      "resource_id": "",
      "method": "inferred",
      "rule": "citation",
      "rule_version": "links/1",
      "evidence": {
        "links": [
          {
            "how": "citation",
            "line": 126,
            "basis": "reference",
            "literal": "doi:10.1038/s41467-025-61209-y"
          }
        ],
        "kind": "citation"
      }
    },
    {
      "field": "references",
      "value": "https://arxiv.org/abs/2412.12979",
      "label": "arXiv:2412.12979",
      "resource_id": "",
      "method": "inferred",
      "rule": "citation",
      "rule_version": "links/1",
      "evidence": {
        "links": [
          {
            "how": "citation",
            "line": 145,
            "basis": "reference",
            "literal": "arXiv:2412.12979"
          }
        ],
        "kind": "citation"
      }
    },
    {
      "field": "references",
      "value": "https://arxiv.org/abs/2511.21476",
      "label": "arXiv:2511.21476",
      "resource_id": "",
      "method": "inferred",
      "rule": "citation",
      "rule_version": "links/1",
      "evidence": {
        "links": [
          {
            "how": "citation",
            "line": 146,
            "basis": "reference",
            "literal": "arXiv:2511.21476"
          }
        ],
        "kind": "citation"
      }
    },
    {
      "field": "references",
      "value": "https://doi.org/10.1016/j.greenca.2025.03.005",
      "label": "doi:10.1016/j.greenca.2025.03.005",
      "resource_id": "",
      "method": "inferred",
      "rule": "citation",
      "rule_version": "links/1",
      "evidence": {
        "links": [
          {
            "how": "citation",
            "line": 173,
            "basis": "reference",
            "literal": "doi:10.1016/j.greenca.2025.03.005"
          }
        ],
        "kind": "citation"
      }
    },
    {
      "field": "references",
      "value": "https://arxiv.org/abs/2410.21127",
      "label": "arXiv:2410.21127",
      "resource_id": "",
      "method": "inferred",
      "rule": "citation",
      "rule_version": "links/1",
      "evidence": {
        "links": [
          {
            "how": "citation",
            "line": 183,
            "basis": "reference",
            "literal": "arXiv:2410.21127"
          }
        ],
        "kind": "citation"
      }
    }
  ]
}