{
  "schema_version": "2.0",
  "record_type": "dataset",
  "tier": "practical",
  "slug": "uniprot",
  "name": "UniProt",
  "summary": {
    "en": "License: permissive (CC-BY-4.0); Mdexa hosting: link-only. first-hand data-scope statement(s) allow commercial use and redistribution",
    "zh": "许可证声明：宽松（CC-BY-4.0）；本站处理：只链接原出处。针对数据的声明允许商用和再分发。"
  },
  "systems": [
    "modern-medicine"
  ],
  "domains": [
    "genomics-omics"
  ],
  "content_types": [
    "database"
  ],
  "content_description": {
    "en": "UniProt (Universal Protein Resource) is a comprehensive catalog of information on proteins.",
    "zh": "UniProt（通用蛋白质资源）是一个全面的蛋白质信息目录。"
  },
  "languages": [
    "en"
  ],
  "modalities": [
    "text"
  ],
  "size": {
    "raw": "154,222,205 entries",
    "measures": []
  },
  "publisher": "UniProt Consortium",
  "year": {
    "value": 2026,
    "raw": "2026_04"
  },
  "license": {
    "legacy_status": "pending",
    "spdx": "CC-BY-4.0",
    "commercial_use": "yes",
    "derivatives": "yes",
    "redistribution": "yes",
    "rationale": {
      "en": "first-hand data-scope statement(s) allow commercial use and redistribution",
      "zh": "针对数据的声明允许商用和再分发"
    },
    "evidence": [
      {
        "location": "terms-page",
        "location_detail": {
          "en": "Statement found in snapshot s10 (terms-page)",
          "zh": "在快照 s10（terms-page）中找到的声明"
        },
        "excerpt": "We have chosen to apply the Creative Commons Attribution 4.0 International (CC BY 4.0) License to all copyrightable parts of our databases.",
        "spdx": "CC-BY-4.0",
        "url": "https://www.uniprot.org/help/license",
        "verified_on": "2026-11-13",
        "snapshot_id": "s10",
        "observed": "page",
        "captured_by": "browser-agent",
        "capturer": "browser-agent",
        "captured_at": "2026-11-13",
        "page_title": "License & disclaimer | UniProt help",
        "final_url": "https://www.uniprot.org/help/license",
        "text_sha256": "b457467dc9526e615356393a3f67ef8fd6860bbb912a3e84853c878d4893d90c"
      },
      {
        "location": "terms-page",
        "location_detail": {
          "en": "Statement found in snapshot s10 (terms-page)",
          "zh": "在快照 s10（terms-page）中找到的声明"
        },
        "excerpt": "We cannot provide unrestricted permission regarding the use of the data, as some data may be covered by patents or other rights.",
        "url": "https://www.uniprot.org/help/license",
        "verified_on": "2026-11-13",
        "snapshot_id": "s10",
        "observed": "page",
        "captured_by": "browser-agent",
        "capturer": "browser-agent",
        "captured_at": "2026-11-13",
        "page_title": "License & disclaimer | UniProt help",
        "final_url": "https://www.uniprot.org/help/license",
        "text_sha256": "b457467dc9526e615356393a3f67ef8fd6860bbb912a3e84853c878d4893d90c"
      },
      {
        "location": "terms-page",
        "location_detail": {
          "en": "Statement found in snapshot s10 (terms-page)",
          "zh": "在快照 s10（terms-page）中找到的声明"
        },
        "excerpt": "Any medical or genetic information is provided for research, educational and informational purposes only.",
        "url": "https://www.uniprot.org/help/license",
        "verified_on": "2026-11-13",
        "snapshot_id": "s10",
        "observed": "page",
        "captured_by": "browser-agent",
        "capturer": "browser-agent",
        "captured_at": "2026-11-13",
        "page_title": "License & disclaimer | UniProt help",
        "final_url": "https://www.uniprot.org/help/license",
        "text_sha256": "b457467dc9526e615356393a3f67ef8fd6860bbb912a3e84853c878d4893d90c"
      }
    ],
    "license_conditions": [
      "attribution"
    ],
    "check_exceptions": true,
    "third_party_rights_notice": true,
    "review": {
      "method": "rules-plus-second-pass-model",
      "method_label": {
        "en": "Judged by public rules and checked a second time before listing.",
        "zh": "按公开规则判定，经二次核对后收录。"
      },
      "readings": [
        {
          "restatement": {
            "en": "first-hand data-scope statement(s) allow commercial use and redistribution",
            "zh": "针对数据的声明允许商用和再分发"
          },
          "quotes": [
            {
              "excerpt": "We have chosen to apply the Creative Commons Attribution 4.0 International (CC BY 4.0) License to all copyrightable parts of our databases.",
              "snapshot_id": "s10",
              "url": "https://www.uniprot.org/help/license"
            },
            {
              "excerpt": "We cannot provide unrestricted permission regarding the use of the data, as some data may be covered by patents or other rights.",
              "snapshot_id": "s10",
              "url": "https://www.uniprot.org/help/license"
            },
            {
              "excerpt": "Any medical or genetic information is provided for research, educational and informational purposes only.",
              "snapshot_id": "s10",
              "url": "https://www.uniprot.org/help/license"
            }
          ],
          "values": {
            "license_status": "permissive",
            "commercial_use": "yes",
            "derivatives": "yes",
            "redistribution": "yes"
          },
          "source": "rules"
        }
      ],
      "adopted": 0,
      "second_pass": {
        "reviewer": "model-second-pass",
        "reviewed_at": "2026-11-13",
        "overall": "stricter",
        "agreed": true,
        "disagreement": null,
        "missed_restrictions": [
          {
            "excerpt": "Any medical or genetic information is provided for research, educational and informational purposes only.",
            "snapshot_id": "s10",
            "effect": "含\"research, educational ... purposes only\"：按第10条限定用途类别为使用限制，\"educational/informational\"部分在免责语境中；无法确定，应列为拿不准的点进人工清单，较严读法下医学/遗传信息限研究与教育用途，影响 commercial_use。",
            "class": "D"
          }
        ],
        "routing": [
          "license_status: the reviewer's quote is not a class A sentence (Article 23), so the value is not changed",
          "commercial_use: the reviewer's quote is not a class A sentence (Article 23), so the value is not changed",
          "derivatives: the reviewer's quote is not a class A sentence (Article 23), so the value is not changed",
          "redistribution: the reviewer's quote is not a class A sentence (Article 23), so the value is not changed",
          "missed sentence, class D: Any medical or genetic information is provided for research, educational and informational"
        ]
      }
    },
    "notes": {
      "en": "These pages could not be retrieved: the UniProt FTP knowledge base README and the UniRef README (connection timed out), and the help pages on API access and downloads (they returned only a script shell). The conclusion rests on the pages that were retrieved: the UniProt license page and the release notes.",
      "zh": "以下页面未能取到：UniProt FTP 知识库 README 与 UniRef README（连接超时），以及 API 与下载帮助页（只返回脚本外壳）。结论依据已取到的页面：UniProt 许可页与发布说明。"
    }
  },
  "license_status": "permissive",
  "hosting": "link-only",
  "hosting_reason": {
    "en": "License permissive, judged by public rules and checked by a second-pass model. Link only.",
    "zh": "许可证状态：permissive，按公开规则判定并经第二遍模型复核。仅链接。"
  },
  "signoff": null,
  "risk_flags": [],
  "provenance": {
    "source_description": null,
    "upstream": []
  },
  "known_issues": [
    {
      "en": "Publisher states it makes no warranties about the correctness of the data and disclaims liability for damages resulting from its use.",
      "zh": "发布方声明不对数据正确性作任何担保，并拒绝承担因使用数据造成的损害责任。"
    },
    {
      "en": "The license help page snapshot shows only a generic fallback message, not the license text.",
      "zh": "许可帮助页快照仅显示通用回退提示，未包含许可正文。"
    }
  ],
  "usage_notes": [
    {
      "kind": "disclaimer",
      "excerpt": "Any medical or genetic information is provided for research, educational and informational purposes only.",
      "url": "https://www.uniprot.org/help/license",
      "snapshot_id": "s10"
    }
  ],
  "preflight": {
    "status": "not-run"
  },
  "access": {
    "mdexa_download": null,
    "external_urls": [
      "https://www.uniprot.org/",
      "https://www.uniprot.org/help/license"
    ],
    "notes": null
  },
  "citation": {
    "text": null,
    "references": []
  },
  "verification_level": "partially-verified",
  "last_verified": "2026-11-13",
  "changelog": [
    {
      "date": "2026-11-13",
      "change": {
        "en": "Listed on 2026-11-13. Judged by public rules and checked a second time before listing. These pages could not be retrieved: the UniProt FTP knowledge base README and the UniRef README (connection timed out), and the help pages on API access and downloads (they returned only a script shell). The conclusion rests on the pages that were retrieved: the UniProt license page and the release notes.",
        "zh": "2026-11-13 上架。按公开规则判定，经二次核对后收录。 以下页面未能取到：UniProt FTP 知识库 README 与 UniRef README（连接超时），以及 API 与下载帮助页（只返回脚本外壳）。结论依据已取到的页面：UniProt 许可页与发布说明。"
      }
    },
    {
      "date": "2026-11-14",
      "change": {
        "en": "Known defects, version notes and access statements from cited sources (papers, release notes, official pages) were added; each shows who said it, when, and what kind of source it is.",
        "zh": "补入来自所引来源（论文、发布说明、官方页面）的已知缺陷、版本说明与取用方式，每条标明出自谁、何时、来源类型。"
      }
    },
    {
      "date": "2026-11-14",
      "change": {
        "en": "Known defects, version notes and access statements from cited sources (papers, release notes, official pages) were added; each shows who said it, when, and what kind of source it is.",
        "zh": "补入来自所引来源（论文、发布说明、官方页面）的已知缺陷、版本说明与取用方式，每条标明出自谁、何时、来源类型。"
      }
    },
    {
      "date": "2026-11-14",
      "change": {
        "en": "Known defects, version notes and access statements from cited sources (papers, release notes, official pages) were added; each shows who said it, when, and what kind of source it is.",
        "zh": "补入来自所引来源（论文、发布说明、官方页面）的已知缺陷、版本说明与取用方式，每条标明出自谁、何时、来源类型。"
      }
    },
    {
      "date": "2026-11-14",
      "change": {
        "en": "Known defects, version notes and access statements from cited sources (papers, release notes, official pages) were added; each shows who said it, when, and what kind of source it is.",
        "zh": "补入来自所引来源（论文、发布说明、官方页面）的已知缺陷、版本说明与取用方式，每条标明出自谁、何时、来源类型。"
      }
    },
    {
      "date": "2026-11-14",
      "change": {
        "en": "Known defects, version notes and access statements from cited sources (papers, release notes, official pages) were added; each shows who said it, when, and what kind of source it is.",
        "zh": "补入来自所引来源（论文、发布说明、官方页面）的已知缺陷、版本说明与取用方式，每条标明出自谁、何时、来源类型。"
      }
    },
    {
      "date": "2026-11-14",
      "change": {
        "en": "Practical fields (scope, identifiers, access methods, versions, known defects) were added by the automated pipeline from stored page snapshots; every statement carries a verbatim quote.",
        "zh": "实用卡字段（内容范围、标识符、取用方式、版本、已知缺陷）由自动流水线根据已存快照添加，每条陈述带逐字引文。"
      }
    },
    {
      "date": "2026-11-14",
      "change": {
        "en": "Known defects, version notes and access statements from cited sources (papers, release notes, official pages) were added; each shows who said it, when, and what kind of source it is.",
        "zh": "补入来自所引来源（论文、发布说明、官方页面）的已知缺陷、版本说明与取用方式，每条标明出自谁、何时、来源类型。"
      }
    }
  ],
  "practical": {
    "content_scope": {
      "entities": [
        {
          "kind": "protein (UniProtKB entry)",
          "count": 154222205,
          "count_as_of": "2026-11-04",
          "statement": {
            "text": {
              "en": "UniProtKB Release 2026_04 consists of 154,222,205 entries, with 576,073 entries in UniProtKB/Swiss-Prot and 153,646,132 entries in UniProtKB/TrEMBL.",
              "zh": "UniProtKB 2026_04 版包含 154,222,205 条条目，其中 UniProtKB/Swiss-Prot 有 576,073 条，UniProtKB/TrEMBL 有 153,646,132 条。"
            },
            "evidence": [
              {
                "location": "release-notes",
                "excerpt": "UniProtKB Release 2026_04 consists of 154,222,205 entries (UniProtKB/Swiss-Prot: 576,073 entries and UniProtKB/TrEMBL: 153,646,132 entries)",
                "url": "https://ftp.uniprot.org/pub/databases/uniprot/current_release/relnotes.txt",
                "snapshot_id": "s09",
                "char_start": 352,
                "verified_on": "2026-11-13",
                "observed": "page",
                "captured_by": "browser-agent"
              }
            ]
          }
        }
      ],
      "coverage": [
        {
          "text": {
            "en": "The UniRef100 part of Release 2026_04 consists of 227,086,028 entries.",
            "zh": "2026_04 版的 UniRef100 部分包含 227,086,028 条条目。"
          },
          "evidence": [
            {
              "location": "release-notes",
              "excerpt": "UniRef100 Release 2026_04 consists of 227,086,028 entries",
              "url": "https://ftp.uniprot.org/pub/databases/uniprot/current_release/relnotes.txt",
              "snapshot_id": "s09",
              "char_start": 493,
              "verified_on": "2026-11-13",
              "observed": "page",
              "captured_by": "browser-agent"
            }
          ]
        }
      ]
    },
    "identifiers": {
      "schemes": [],
      "crosswalks": [],
      "mismatch_cases": [],
      "notes": [
        {
          "text": {
            "en": "UniProtKB accessions are 6 or 10 alphanumeric characters and are the stable, citable identifier.",
            "zh": "UniProtKB 登录号为 6 位或 10 位字母数字，是稳定、可引用的标识。"
          },
          "evidence": [
            {
              "location": "dataset-page",
              "excerpt": "UniProtKB accession numbers consist of 6 or 10 alphanumerical characters in the format:",
              "url": "https://rest.uniprot.org/help/accession_numbers",
              "snapshot_id": "s13",
              "char_start": 409,
              "verified_on": "2026-11-13",
              "observed": "page",
              "source_work": {
                "title": "Accession",
                "authors_or_org": "UniProt Consortium",
                "date": "2026-06-12",
                "date_as_written": "2026-06-12",
                "source_type": "official-page",
                "open_access": true,
                "doi_or_url": "https://rest.uniprot.org/help/accession_numbers"
              }
            }
          ]
        },
        {
          "text": {
            "en": "When an entry is demerged, all parts get new primary accessions and the old accession survives only as a secondary accession, so an old accession can map to several current entries.",
            "zh": "条目拆分时，各部分都获得新的主登录号，原登录号只作为次要登录号保留；因此旧登录号可能对应多个现行条目。"
          },
          "evidence": [
            {
              "location": "dataset-page",
              "excerpt": "If an existing entry is split into two or more entries ('demerged'), new 'primary' accession numbers are attributed to all the split entries while all original accession numbers are retained as 'secondary' accession numbers.",
              "url": "https://rest.uniprot.org/help/accession_numbers",
              "snapshot_id": "s13",
              "char_start": 1909,
              "verified_on": "2026-11-13",
              "observed": "page",
              "source_work": {
                "title": "Accession",
                "authors_or_org": "UniProt Consortium",
                "date": "2026-06-12",
                "date_as_written": "2026-06-12",
                "source_type": "official-page",
                "open_access": true,
                "doi_or_url": "https://rest.uniprot.org/help/accession_numbers"
              }
            }
          ]
        },
        {
          "text": {
            "en": "The entry name (e.g. XXX_HUMAN) is not stable: it can change for consistency or when an entry moves from TrEMBL to Swiss-Prot.",
            "zh": "条目名（如 XXX_HUMAN）不稳定：可能为保持一致或从 TrEMBL 升入 Swiss-Prot 而改变。"
          },
          "evidence": [
            {
              "location": "dataset-page",
              "excerpt": "It is sometimes necessary, for reasons of consistency, to change IDs (for example to ensure that related entries have similar names).",
              "url": "https://rest.uniprot.org/help/difference_accession_entryname",
              "snapshot_id": "s14",
              "char_start": 631,
              "verified_on": "2026-11-13",
              "observed": "page",
              "source_work": {
                "title": "What is the difference between an accession number (AC) and the entry name?",
                "authors_or_org": "UniProt Consortium",
                "date": "2022-04-20",
                "date_as_written": "2022-04-20",
                "source_type": "official-page",
                "open_access": true,
                "doi_or_url": "https://rest.uniprot.org/help/difference_accession_entryname"
              }
            }
          ]
        },
        {
          "text": {
            "en": "UniRef cluster identifiers are not permanent, although most do not change between releases (FAQ). The ID-mapping help page describes them as stable; the two help pages differ in wording.",
            "zh": "UniRef 簇 ID 不是永久的，但大多数跨版本不变（FAQ 原文）；而 ID 映射帮助页称其为“stable”，两处官方表述不一致。"
          },
          "evidence": [
            {
              "location": "dataset-page",
              "excerpt": "No. However, the vast majority do not change from release to release even if clusters are recomputed, and the representative entry usually remains the same.",
              "url": "https://rest.uniprot.org/help/linking_to_uniref",
              "snapshot_id": "s15",
              "char_start": null,
              "verified_on": "2026-11-13",
              "observed": "page",
              "source_work": {
                "title": "Are UniRef cluster identifiers permanent? How can I link to UniRef clusters?",
                "authors_or_org": "UniProt Consortium",
                "date": "2022-04-29",
                "date_as_written": "2022-04-29",
                "source_type": "official-page",
                "open_access": true,
                "doi_or_url": "https://rest.uniprot.org/help/linking_to_uniref"
              }
            }
          ]
        },
        {
          "text": {
            "en": "The ID-mapping service describes each UniRef cluster as having a stable ID derived from a representative entry, and accepts up to 100,000 IDs per job.",
            "zh": "ID 映射页称每个 UniRef 簇的 ID 由代表条目派生且稳定；单次最多提交 100,000 个 ID。"
          },
          "evidence": [
            {
              "location": "dataset-page",
              "excerpt": "You may submit up to a maximum of 100,000 IDs for mapping.",
              "url": "https://rest.uniprot.org/help/id_mapping",
              "snapshot_id": "s16",
              "char_start": 2857,
              "verified_on": "2026-11-13",
              "observed": "page",
              "source_work": {
                "title": "ID Mapping",
                "authors_or_org": "UniProt Consortium",
                "date": "2026-04-24",
                "date_as_written": "2026-04-24",
                "source_type": "official-page",
                "open_access": true,
                "doi_or_url": "https://rest.uniprot.org/help/id_mapping"
              }
            }
          ]
        }
      ]
    },
    "access_methods": [
      {
        "method": "bulk-download",
        "url": "https://www.uniprot.org/downloads",
        "formats": [],
        "limits": [],
        "terms": {
          "same_as_card_license": true,
          "own_terms": null
        },
        "reachable": {
          "status": 200,
          "checked_on": "2026-11-14"
        }
      },
      {
        "method": "web-ui-only",
        "url": "https://www.uniprot.org",
        "formats": [],
        "limits": [],
        "terms": {
          "same_as_card_license": true,
          "own_terms": null
        },
        "reachable": {
          "status": 200,
          "checked_on": "2026-11-14"
        }
      },
      {
        "method": "web-api",
        "url": "https://rest.uniprot.org/help/programmatic_access",
        "formats": [],
        "limits": [],
        "terms": {
          "same_as_card_license": true,
          "own_terms": null
        },
        "statement": {
          "text": {
            "en": "Programmatic access: website REST API (text, XML, RDF, FASTA, GFF, TSV), Proteins REST API (genomic coordinates, variation, proteomics), SPARQL endpoint and a Java API.",
            "zh": "程序化访问：网站 REST API（text、XML、RDF、FASTA、GFF、TSV）、Proteins REST API（基因组坐标、变异、蛋白组学）、SPARQL 端点与 Java API。"
          },
          "evidence": [
            {
              "location": "dataset-page",
              "excerpt": "UniProt provides several application programming interfaces (APIs) to query and access its data programmatically:",
              "url": "https://rest.uniprot.org/help/programmatic_access",
              "snapshot_id": "s17",
              "char_start": 113,
              "verified_on": "2026-11-13",
              "observed": "page",
              "source_work": {
                "title": "Programmatic access",
                "authors_or_org": "UniProt Consortium",
                "date": "2024-11-27",
                "date_as_written": "2024-11-27",
                "source_type": "official-page",
                "open_access": true,
                "doi_or_url": "https://rest.uniprot.org/help/programmatic_access"
              }
            }
          ]
        },
        "reachable": {
          "status": 200,
          "checked_on": "2026-11-14"
        }
      },
      {
        "method": "web-api",
        "url": "https://rest.uniprot.org/help/license",
        "formats": [],
        "limits": [],
        "terms": {
          "same_as_card_license": true,
          "own_terms": null
        },
        "statement": {
          "text": {
            "en": "Data are licensed CC BY 4.0 for all copyrightable parts.",
            "zh": "数据中可受版权保护部分统一适用 CC BY 4.0。"
          },
          "evidence": [
            {
              "location": "dataset-page",
              "excerpt": "to all copyrightable parts of our databases.",
              "url": "https://rest.uniprot.org/help/license",
              "snapshot_id": "s18",
              "char_start": 258,
              "verified_on": "2026-11-13",
              "observed": "page",
              "source_work": {
                "title": "License & disclaimer",
                "authors_or_org": "UniProt Consortium",
                "date": "2024-12-18",
                "date_as_written": "2024-12-18",
                "source_type": "official-page",
                "open_access": true,
                "doi_or_url": "https://rest.uniprot.org/help/license"
              }
            }
          ]
        },
        "reachable": {
          "status": 200,
          "checked_on": "2026-11-14"
        }
      }
    ],
    "versioning": {
      "latest": {
        "label": "UniProt Release 2026_04",
        "released_on": "2026-11-04",
        "statement": {
          "text": {
            "en": "The announced UniProt Knowledgebase (UniProtKB) release is Release 2026_04, dated 04-Nov-2026.",
            "zh": "所宣布的 UniProt 知识库（UniProtKB）版本为 2026_04 版，日期为 2026 年 11 月 4 日。"
          },
          "evidence": [
            {
              "location": "release-notes",
              "excerpt": "is pleased to announce UniProt Knowledgebase (UniProtKB) Release 2026_04 (04-Nov-2026).",
              "url": "https://ftp.uniprot.org/pub/databases/uniprot/current_release/relnotes.txt",
              "snapshot_id": "s09",
              "char_start": 169,
              "verified_on": "2026-11-13",
              "observed": "page",
              "captured_by": "browser-agent"
            }
          ]
        }
      },
      "update_cycle": {
        "cycle": "not-stated",
        "statement": null
      },
      "breaking_changes": [
        {
          "version": "in 2025",
          "date": "2025-01-01",
          "kind": "license",
          "statement": {
            "text": {
              "en": "UniProt announced in its 2025 NAR paper the intention to restrict unreviewed (TrEMBL) entries to reference proteomes, expecting an initial drop in unreviewed entry counts; excluded sequences remain in UniParc.",
              "zh": "UniProt 在 2025 年 NAR 论文中宣布拟将未审阅（TrEMBL）条目限于参考蛋白质组，预计未审阅条目数先下降；被排除的序列仍保留在 UniParc。"
            },
            "evidence": [
              {
                "location": "peer-reviewed-paper",
                "excerpt": "It is our intention in 2025 to limit the unreviewed sequences in UniProtKB/TrEMBL to only those derived from reference proteomes",
                "url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC11701636/",
                "snapshot_id": "s22",
                "char_start": 10110,
                "verified_on": "2026-11-13",
                "observed": "page",
                "source_work": {
                  "title": "UniProt: the Universal Protein Knowledgebase in 2025",
                  "authors_or_org": "UniProt Consortium (Nucleic Acids Research)",
                  "date": "2025-01-01",
                  "date_as_written": "2025-01-01",
                  "source_type": "peer-reviewed-paper",
                  "open_access": true,
                  "doi_or_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC11701636/"
                }
              }
            ]
          }
        },
        {
          "version": "unspecified",
          "date": "2026-06-10",
          "kind": "content-removed",
          "statement": {
            "text": {
              "en": "Earlier, proteome-redundancy reduction has removed proteins from redundant proteomes since release 2015_04.",
              "zh": "此前自 2015_04 版起已执行蛋白质组去冗余，删去冗余蛋白质组中的蛋白。"
            },
            "evidence": [
              {
                "location": "dataset-page",
                "excerpt": "Methods to reduce proteome redundancy have been in effect since release 2015_04.",
                "url": "https://rest.uniprot.org/help/proteome_redundancy",
                "snapshot_id": "s19",
                "char_start": 122,
                "verified_on": "2026-11-13",
                "observed": "page",
                "source_work": {
                  "title": "Reducing proteome redundancy",
                  "authors_or_org": "UniProt Consortium",
                  "date": "2026-06-10",
                  "date_as_written": "2026-06-10",
                  "source_type": "official-page",
                  "open_access": true,
                  "doi_or_url": "https://rest.uniprot.org/help/proteome_redundancy"
                }
              }
            ]
          }
        },
        {
          "version": "to 2013",
          "date": "2025-11-26",
          "kind": "other",
          "statement": {
            "text": {
              "en": "UniRef clustering changed in 2013: before then there was no 80% overlap threshold, so older clusters were more length-heterogeneous.",
              "zh": "UniRef 聚类规则在 2013 年变更：此前没有 80% 覆盖度阈值，旧簇内长度差异更大。"
            },
            "evidence": [
              {
                "location": "dataset-page",
                "excerpt": "Prior to 2013 there was no overlap threshold, so clusters were more heterogeneous in length.",
                "url": "https://rest.uniprot.org/help/uniref",
                "snapshot_id": "s20",
                "char_start": 1503,
                "verified_on": "2026-11-13",
                "observed": "page",
                "source_work": {
                  "title": "UniRef",
                  "authors_or_org": "UniProt Consortium",
                  "date": "2025-11-26",
                  "date_as_written": "2025-11-26",
                  "source_type": "official-page",
                  "open_access": true,
                  "doi_or_url": "https://rest.uniprot.org/help/uniref"
                }
              }
            ]
          }
        }
      ],
      "history_url": null,
      "notes": [
        {
          "text": {
            "en": "UniProt releases every 2–3 months, with possible gaps in January and summer.",
            "zh": "UniProt 每 2–3 个月发布一次，1 月与夏季可能例外。"
          },
          "evidence": [
            {
              "location": "dataset-page",
              "excerpt": "UniProt releases are published every 2-3 months, with possible exceptions in January and summer due to reduced staff during holiday periods.",
              "url": "https://rest.uniprot.org/help/synchronization",
              "snapshot_id": "s12",
              "char_start": 152,
              "verified_on": "2026-11-13",
              "observed": "page",
              "source_work": {
                "title": "UniProt release cycle",
                "authors_or_org": "UniProt Consortium",
                "date": "2026-06-12",
                "date_as_written": "2026-06-12",
                "source_type": "official-page",
                "open_access": true,
                "doi_or_url": "https://rest.uniprot.org/help/synchronization"
              }
            }
          ]
        },
        {
          "text": {
            "en": "Data are frozen well before each public release, so updates in a linked database can take 8 to 16 weeks to appear in UniProtKB.",
            "zh": "每版数据在公开发布前很早就冻结，关联数据库的更新可能要 8–16 周才出现在 UniProtKB 中。"
          },
          "evidence": [
            {
              "location": "dataset-page",
              "excerpt": "significantly earlier than the public release date, which can result in a delay of 8 to 16 weeks between the update of a related database and the appearance of relevant data in the public version of UniProtKB.",
              "url": "https://rest.uniprot.org/help/synchronization",
              "snapshot_id": "s12",
              "char_start": 929,
              "verified_on": "2026-11-13",
              "observed": "page",
              "source_work": {
                "title": "UniProt release cycle",
                "authors_or_org": "UniProt Consortium",
                "date": "2026-06-12",
                "date_as_written": "2026-06-12",
                "source_type": "official-page",
                "open_access": true,
                "doi_or_url": "https://rest.uniprot.org/help/synchronization"
              }
            }
          ]
        }
      ]
    },
    "known_defects": [
      {
        "kind": "other",
        "statement": {
          "text": {
            "en": "Schnoes et al. found Swiss-Prot near 0% misannotation for most of 37 enzyme families, while TrEMBL, GenBank NR and KEGG showed 5%–63% average misannotation across six superfamilies.",
            "zh": "Schnoes 等发现：在 37 个酶家族中 Swiss-Prot 多数家族误注释接近 0%，而 TrEMBL、GenBank NR、KEGG 在六个超家族中平均误注释为 5%–63%。"
          },
          "evidence": [
            {
              "location": "peer-reviewed-paper",
              "excerpt": "the two other protein sequence databases (GenBank NR and TrEMBL) and the protein sequences in the KEGG pathways database exhibit similar and surprisingly high levels of misannotation that average 5%–63% across the six superfamilies studied.",
              "url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC2781113/",
              "snapshot_id": "s23",
              "char_start": 5918,
              "verified_on": "2026-11-13",
              "observed": "page",
              "source_work": {
                "title": "Annotation error in public databases: misannotation of molecular function in enzyme superfamilies",
                "authors_or_org": "Schnoes AM, Brown SD, Dodevski I, Babbitt PC (PLoS Computational Biology)",
                "date": "2009-12-11",
                "date_as_written": "2009-12-11",
                "source_type": "peer-reviewed-paper",
                "open_access": true,
                "doi_or_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC2781113/"
              }
            }
          ]
        },
        "source_kind": "peer-reviewed-paper",
        "scope": null,
        "attribution": {
          "who": "Schnoes AM, Brown SD, Dodevski I, Babbitt PC (PLoS Computational Biology)",
          "when": "2009-12-11",
          "source_type": "peer-reviewed-paper",
          "title": "Annotation error in public databases: misannotation of molecular function in enzyme superfamilies"
        },
        "correction_entrance": "Report an error through the publisher or the authors: https://pmc.ncbi.nlm.nih.gov/articles/PMC2781113/"
      },
      {
        "kind": "other",
        "statement": {
          "text": {
            "en": "UniProt states TrEMBL entries are computationally annotated by automated systems, unlike reviewed Swiss-Prot entries.",
            "zh": "UniProt 说明 TrEMBL 条目由自动系统计算注释，不同于经人工审阅的 Swiss-Prot。"
          },
          "evidence": [
            {
              "location": "peer-reviewed-paper",
              "excerpt": "In the latter, entries are computationally annotated by automated systems.",
              "url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC11701636/",
              "snapshot_id": "s22",
              "char_start": 5657,
              "verified_on": "2026-11-13",
              "observed": "page",
              "source_work": {
                "title": "UniProt: the Universal Protein Knowledgebase in 2025",
                "authors_or_org": "UniProt Consortium (Nucleic Acids Research)",
                "date": "2025-01-01",
                "date_as_written": "2025-01-01",
                "source_type": "peer-reviewed-paper",
                "open_access": true,
                "doi_or_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC11701636/"
              }
            }
          ]
        },
        "source_kind": "peer-reviewed-paper",
        "scope": null,
        "attribution": {
          "who": "UniProt Consortium (Nucleic Acids Research)",
          "when": "2025-01-01",
          "source_type": "peer-reviewed-paper",
          "title": "UniProt: the Universal Protein Knowledgebase in 2025"
        },
        "correction_entrance": "Report an error through the publisher or the authors: https://pmc.ncbi.nlm.nih.gov/articles/PMC11701636/"
      }
    ],
    "fit": {
      "suited_for": [
        {
          "text": {
            "en": "UniProt recommends UniRef90/UniRef50 for similarity searches because they reduce redundancy while keeping full sequence-space coverage (about 58% and 79% size reduction).",
            "zh": "UniProt 推荐用 UniRef90/UniRef50 做相似性检索：在保留序列空间完整覆盖的同时降低冗余（体积约减少 58% 与 79%）。"
          },
          "evidence": [
            {
              "location": "dataset-page",
              "excerpt": "UniRef, especially UniRef90 and UniRef50, decreases sequence redundancy compared to UniProtKB and UniParc, while maintaining complete coverage of the sequence space.",
              "url": "https://rest.uniprot.org/help/uniref_blast_use",
              "snapshot_id": "s21",
              "char_start": 146,
              "verified_on": "2026-11-13",
              "observed": "page",
              "source_work": {
                "title": "Why can it make sense to use UniRef for BLAST searches?",
                "authors_or_org": "UniProt Consortium",
                "date": "2022-04-28",
                "date_as_written": "2022-04-28",
                "source_type": "official-page",
                "open_access": true,
                "doi_or_url": "https://rest.uniprot.org/help/uniref_blast_use"
              }
            }
          ]
        }
      ],
      "not_suited_for": []
    },
    "commercial_access": {
      "route": "unknown",
      "url": null,
      "statement": null
    },
    "completeness": {
      "core_complete": true,
      "literature_defects": 2,
      "reachable_access": 4,
      "meets_practical_bar": true,
      "gaps": [
        {
          "field": "versioning.update_cycle",
          "note": "未找到有出处的说明 / no sourced statement found"
        },
        {
          "field": "fit.not_suited_for",
          "note": "未找到有出处的说明 / no sourced statement found"
        },
        {
          "field": "commercial_access",
          "note": "未找到有出处的说明 / no sourced statement found"
        }
      ]
    }
  },
  "access_recipe": {
    "verified_on": "2026-11-14",
    "latest_release": {
      "version": "2026_04",
      "date": "04-Nov-2026",
      "evidence": {
        "excerpt": "2026_04 (04-Nov-2026).",
        "snapshot_id": "s09",
        "url": "https://ftp.uniprot.org/pub/databases/uniprot/current_release/relnotes.txt"
      }
    },
    "files": [
      {
        "name": "Swiss-Prot xml",
        "url": "https://ftp.uniprot.org/pub/databases/uniprot/current_release/knowledgebase/complete/uniprot_sprot.xml.gz",
        "size_text": null,
        "checksum": null,
        "format": "xml",
        "version": null,
        "evidence": {
          "excerpt": "Swiss-Prot xml: https://ftp.uniprot.org/pub/databases/uniprot/current_release/knowledgebase/complete/uniprot_sprot.xml.gz",
          "snapshot_id": "s24",
          "url": "https://www.uniprot.org/help/downloads"
        }
      },
      {
        "name": "Swiss-Prot fasta",
        "url": "https://ftp.uniprot.org/pub/databases/uniprot/current_release/knowledgebase/complete/uniprot_sprot.fasta.gz",
        "size_text": null,
        "checksum": null,
        "format": "fasta",
        "version": null,
        "evidence": {
          "excerpt": "Swiss-Prot fasta: https://ftp.uniprot.org/pub/databases/uniprot/current_release/knowledgebase/complete/uniprot_sprot.fasta.gz",
          "snapshot_id": "s24",
          "url": "https://www.uniprot.org/help/downloads"
        }
      },
      {
        "name": "Swiss-Prot text",
        "url": "https://ftp.uniprot.org/pub/databases/uniprot/current_release/knowledgebase/complete/uniprot_sprot.dat.gz",
        "size_text": null,
        "checksum": null,
        "format": "text",
        "version": null,
        "evidence": {
          "excerpt": "Swiss-Prot text: https://ftp.uniprot.org/pub/databases/uniprot/current_release/knowledgebase/complete/uniprot_sprot.dat.gz",
          "snapshot_id": "s24",
          "url": "https://www.uniprot.org/help/downloads"
        }
      },
      {
        "name": "TrEMBL xml",
        "url": "https://ftp.uniprot.org/pub/databases/uniprot/current_release/knowledgebase/complete/uniprot_trembl.xml.gz",
        "size_text": null,
        "checksum": null,
        "format": "xml",
        "version": null,
        "evidence": {
          "excerpt": "TrEMBL xml: https://ftp.uniprot.org/pub/databases/uniprot/current_release/knowledgebase/complete/uniprot_trembl.xml.gz",
          "snapshot_id": "s24",
          "url": "https://www.uniprot.org/help/downloads"
        }
      },
      {
        "name": "TrEMBL fasta",
        "url": "https://ftp.uniprot.org/pub/databases/uniprot/current_release/knowledgebase/complete/uniprot_trembl.fasta.gz",
        "size_text": null,
        "checksum": null,
        "format": "fasta",
        "version": null,
        "evidence": {
          "excerpt": "TrEMBL fasta: https://ftp.uniprot.org/pub/databases/uniprot/current_release/knowledgebase/complete/uniprot_trembl.fasta.gz",
          "snapshot_id": "s24",
          "url": "https://www.uniprot.org/help/downloads"
        }
      },
      {
        "name": "TrEMBL text",
        "url": "https://ftp.uniprot.org/pub/databases/uniprot/current_release/knowledgebase/complete/uniprot_trembl.dat.gz",
        "size_text": null,
        "checksum": null,
        "format": "text",
        "version": null,
        "evidence": {
          "excerpt": "TrEMBL text: https://ftp.uniprot.org/pub/databases/uniprot/current_release/knowledgebase/complete/uniprot_trembl.dat.gz",
          "snapshot_id": "s24",
          "url": "https://www.uniprot.org/help/downloads"
        }
      },
      {
        "name": "Isoform sequences fasta",
        "url": "https://ftp.uniprot.org/pub/databases/uniprot/current_release/knowledgebase/complete/uniprot_sprot_varsplic.fasta.gz",
        "size_text": null,
        "checksum": null,
        "format": "fasta",
        "version": null,
        "evidence": {
          "excerpt": "Isoform sequences fasta: https://ftp.uniprot.org/pub/databases/uniprot/current_release/knowledgebase/complete/uniprot_sprot_varsplic.fasta.gz",
          "snapshot_id": "s24",
          "url": "https://www.uniprot.org/help/downloads"
        }
      },
      {
        "name": "UniRef100 xml",
        "url": "https://ftp.uniprot.org/pub/databases/uniprot/uniref/uniref100/uniref100.xml.gz",
        "size_text": null,
        "checksum": null,
        "format": "xml",
        "version": null,
        "evidence": {
          "excerpt": "UniRef100 xml: https://ftp.uniprot.org/pub/databases/uniprot/uniref/uniref100/uniref100.xml.gz",
          "snapshot_id": "s24",
          "url": "https://www.uniprot.org/help/downloads"
        }
      },
      {
        "name": "UniRef100 fasta",
        "url": "https://ftp.uniprot.org/pub/databases/uniprot/uniref/uniref100/uniref100.fasta.gz",
        "size_text": null,
        "checksum": null,
        "format": "fasta",
        "version": null,
        "evidence": {
          "excerpt": "UniRef100 fasta: https://ftp.uniprot.org/pub/databases/uniprot/uniref/uniref100/uniref100.fasta.gz",
          "snapshot_id": "s24",
          "url": "https://www.uniprot.org/help/downloads"
        }
      },
      {
        "name": "UniRef90 xml",
        "url": "https://ftp.uniprot.org/pub/databases/uniprot/uniref/uniref90/uniref90.xml.gz",
        "size_text": null,
        "checksum": null,
        "format": "xml",
        "version": null,
        "evidence": {
          "excerpt": "UniRef90 xml: https://ftp.uniprot.org/pub/databases/uniprot/uniref/uniref90/uniref90.xml.gz",
          "snapshot_id": "s24",
          "url": "https://www.uniprot.org/help/downloads"
        }
      },
      {
        "name": "UniRef90 fasta",
        "url": "https://ftp.uniprot.org/pub/databases/uniprot/uniref/uniref90/uniref90.fasta.gz",
        "size_text": null,
        "checksum": null,
        "format": "fasta",
        "version": null,
        "evidence": {
          "excerpt": "UniRef90 fasta: https://ftp.uniprot.org/pub/databases/uniprot/uniref/uniref90/uniref90.fasta.gz",
          "snapshot_id": "s24",
          "url": "https://www.uniprot.org/help/downloads"
        }
      },
      {
        "name": "UniRef50 fasta",
        "url": "https://ftp.uniprot.org/pub/databases/uniprot/uniref/uniref50/uniref50.fasta.gz",
        "size_text": null,
        "checksum": null,
        "format": "fasta",
        "version": null,
        "evidence": {
          "excerpt": "UniRef50 fasta: https://ftp.uniprot.org/pub/databases/uniprot/uniref/uniref50/uniref50.fasta.gz",
          "snapshot_id": "s24",
          "url": "https://www.uniprot.org/help/downloads"
        }
      }
    ],
    "api": [],
    "registration": null,
    "bulk_download": [],
    "gaps": [
      "the official pages we hold publish no checksum for the files; none was computed (we do not download data files)"
    ],
    "license_note": {
      "license_status": "permissive",
      "text": "Use according to the terms of the official source; this recipe does not say the data can be used freely."
    }
  },
  "_links": {
    "text": "在本库继续查找。本条目是 109 条已处理并核实的记录之一（数据集、数据资源与开源模型）。查找其他条目：调用 `https://mcp.mdexa.com/v1/datasets?q=<关键词>`，或连接 MCP 服务 `https://mcp.mdexa.com/mcp`；每分钟 20 次以内无需密钥。每行返回不到 1 KB；空结果即\"数据库未收录\"。核对一份清单：一次批量核对（免费账号）即返回报告。说明：/agents.md。相似条目：AlphaFold Protein Structure Database (https://mdexa.com/zh/datasets/alphafold-db/)；GEO (https://mdexa.com/zh/datasets/geo/)；gnomAD (https://mdexa.com/zh/datasets/gnomad/)。",
    "records": 109,
    "search": {
      "template": "https://mcp.mdexa.com/v1/datasets?q={words}",
      "example": "https://mcp.mdexa.com/v1/datasets?q=%E7%BB%93%E5%90%88%E4%BA%B2%E5%92%8C%E5%8A%9B"
    },
    "mcp": "https://mcp.mdexa.com/mcp",
    "anonymous_calls_per_minute": 20,
    "guide": "https://mdexa.com/zh/agents.md",
    "faq": "https://mdexa.com/zh/developers/faq/",
    "similar": [
      {
        "name": "AlphaFold Protein Structure Database",
        "url": "https://mdexa.com/zh/datasets/alphafold-db/",
        "json": "https://mdexa.com/zh/datasets/alphafold-db.json"
      },
      {
        "name": "GEO",
        "url": "https://mdexa.com/zh/datasets/geo/",
        "json": "https://mdexa.com/zh/datasets/geo.json"
      },
      {
        "name": "gnomAD",
        "url": "https://mdexa.com/zh/datasets/gnomad/",
        "json": "https://mdexa.com/zh/datasets/gnomad.json"
      }
    ]
  }
}