{
  "schema_version": "2.0",
  "record_type": "dataset",
  "tier": "verified",
  "slug": "topu-lbvs",
  "name": "TopU-LBVS: Multi-Target Benchmark for Ligand-Based Virtual Screening",
  "summary": {
    "en": "License: permissive, share-alike (CC-BY-SA-4.0); Mdexa hosting: link-only. all parts permissive; conditions are the union of the parts Risk flag(s): derived.",
    "zh": "许可证声明：宽松，须相同方式共享（CC-BY-SA-4.0）；本站处理：只链接原出处。各部分均宽松，条件取各部分的并集。来源风险标记：derived。"
  },
  "systems": [
    "modern-medicine"
  ],
  "domains": [
    "pharmacy-drugs"
  ],
  "content_types": [
    "database"
  ],
  "content_description": {
    "en": "Multi-target benchmark for ligand-based virtual screening (LBVS) under hard-negative screening conditions: 93 protein targets across 7 protein classes, curated from ChEMBL 35.",
    "zh": "基于配体的虚拟筛选多靶点基准，采用困难负样本条件：覆盖7个蛋白质类别的93个蛋白质靶点，数据整理自ChEMBL 35。"
  },
  "languages": [
    "en"
  ],
  "modalities": [
    "text",
    "graph",
    "tabular"
  ],
  "size": {
    "raw": "100K<n<1M",
    "measures": []
  },
  "publisher": "introvoyz042",
  "year": {
    "value": null,
    "raw": null
  },
  "license": {
    "legacy_status": "pending",
    "spdx": "CC-BY-SA-4.0",
    "commercial_use": "yes",
    "derivatives": "yes",
    "redistribution": "yes",
    "rationale": {
      "en": "all parts permissive; conditions are the union of the parts",
      "zh": "各部分均宽松，条件取各部分的并集"
    },
    "evidence": [
      {
        "location": "hf-card-metadata",
        "location_detail": {
          "en": "Statement found in snapshot s01 (readme)",
          "zh": "在快照 s01（readme）中找到的声明"
        },
        "excerpt": "license: cc-by-sa-4.0",
        "spdx": "CC-BY-SA-4.0",
        "url": "https://huggingface.co/datasets/introvoyz042/topu-lbvs",
        "verified_on": "2026-11-12",
        "snapshot_id": "s01",
        "observed": "page",
        "captured_by": "pipeline"
      },
      {
        "location": "readme",
        "location_detail": {
          "en": "Statement found in snapshot s01 (readme)",
          "zh": "在快照 s01（readme）中找到的声明"
        },
        "excerpt": "📜 **License**: CC-BY-SA-4.0",
        "spdx": "CC-BY-SA-4.0",
        "url": "https://huggingface.co/datasets/introvoyz042/topu-lbvs",
        "verified_on": "2026-11-12",
        "snapshot_id": "s01",
        "observed": "page",
        "captured_by": "pipeline"
      },
      {
        "location": "readme",
        "location_detail": {
          "en": "Statement found in snapshot s01 (readme)",
          "zh": "在快照 s01（readme）中找到的声明"
        },
        "excerpt": "The TopU-LBVS dataset is released under **CC-BY-SA-4.0**.",
        "spdx": "CC-BY-SA-4.0",
        "url": "https://huggingface.co/datasets/introvoyz042/topu-lbvs",
        "verified_on": "2026-11-12",
        "snapshot_id": "s01",
        "observed": "page",
        "captured_by": "pipeline"
      },
      {
        "location": "readme",
        "location_detail": {
          "en": "Statement found in snapshot s01 (readme)",
          "zh": "在快照 s01（readme）中找到的声明"
        },
        "excerpt": "The companion code (https://github.com/topu-benchmark/topu-lbvs) is released under the **MIT License**.",
        "spdx": "MIT",
        "url": "https://huggingface.co/datasets/introvoyz042/topu-lbvs",
        "verified_on": "2026-11-12",
        "snapshot_id": "s01",
        "observed": "page",
        "captured_by": "pipeline"
      },
      {
        "location": "readme",
        "location_detail": {
          "en": "Statement found in snapshot s01 (readme)",
          "zh": "在快照 s01（readme）中找到的声明"
        },
        "excerpt": "ChEMBL is released under CC-BY-SA-3.0.",
        "spdx": "CC-BY-SA-3.0",
        "url": "https://huggingface.co/datasets/introvoyz042/topu-lbvs",
        "verified_on": "2026-11-12",
        "snapshot_id": "s01",
        "observed": "page",
        "captured_by": "pipeline"
      },
      {
        "location": "readme",
        "location_detail": {
          "en": "Statement found in snapshot s01 (readme)",
          "zh": "在快照 s01（readme）中找到的声明"
        },
        "excerpt": "The curated TopU-LBVS data inherits a compatible CC-BY-SA-4.0 license.",
        "spdx": "CC-BY-SA-4.0",
        "url": "https://huggingface.co/datasets/introvoyz042/topu-lbvs",
        "verified_on": "2026-11-12",
        "snapshot_id": "s01",
        "observed": "page",
        "captured_by": "pipeline"
      },
      {
        "location": "readme",
        "location_detail": {
          "en": "Statement found in snapshot s01 (readme)",
          "zh": "在快照 s01（readme）中找到的声明"
        },
        "excerpt": "Users redistributing the data or derived works must preserve the CC-BY-SA terms and provide attribution to both ChEMBL and this dataset.",
        "url": "https://huggingface.co/datasets/introvoyz042/topu-lbvs",
        "verified_on": "2026-11-12",
        "snapshot_id": "s01",
        "observed": "page",
        "captured_by": "pipeline"
      },
      {
        "location": "dataset-page",
        "location_detail": {
          "en": "Statement found in snapshot s02 (page)",
          "zh": "在快照 s02（page）中找到的声明"
        },
        "excerpt": "📜 License : CC-BY-SA-4.0",
        "spdx": "CC-BY-SA-4.0",
        "url": "https://huggingface.co/datasets/introvoyz042/topu-lbvs",
        "verified_on": "2026-11-12",
        "snapshot_id": "s02",
        "observed": "page",
        "captured_by": "pipeline"
      }
    ],
    "license_conditions": [
      "attribution",
      "share-alike",
      "notice-required"
    ],
    "license_parts": [
      {
        "name": {
          "en": "main data",
          "zh": "主体数据"
        },
        "spdx": "CC-BY-SA-4.0",
        "status": "permissive",
        "separable": true,
        "license_conditions": [
          "attribution",
          "share-alike"
        ],
        "evidence": {
          "excerpt": "license: cc-by-sa-4.0",
          "url": "https://huggingface.co/datasets/introvoyz042/topu-lbvs",
          "snapshot_id": "s01"
        }
      },
      {
        "name": {
          "en": "companion code",
          "zh": "companion code"
        },
        "spdx": "MIT",
        "status": "permissive",
        "separable": true,
        "license_conditions": [
          "notice-required"
        ],
        "evidence": {
          "excerpt": "The companion code (https://github.com/topu-benchmark/topu-lbvs) is released under the **MIT License**.",
          "url": "https://huggingface.co/datasets/introvoyz042/topu-lbvs",
          "snapshot_id": "s01"
        }
      },
      {
        "name": {
          "en": "ChEMBL source data",
          "zh": "ChEMBL source data"
        },
        "spdx": "CC-BY-SA-3.0",
        "status": "permissive",
        "separable": true,
        "license_conditions": [
          "attribution",
          "share-alike"
        ],
        "evidence": {
          "excerpt": "ChEMBL is released under CC-BY-SA-3.0.",
          "url": "https://huggingface.co/datasets/introvoyz042/topu-lbvs",
          "snapshot_id": "s01"
        }
      }
    ],
    "notes": {
      "en": "risk flag(s) derived: never eligible or hosted",
      "zh": "risk flag(s) derived: never eligible or hosted"
    }
  },
  "license_status": "permissive",
  "hosting": "link-only",
  "hosting_reason": {
    "en": "License permissive, share-alike: all parts permissive; conditions are the union of the parts. Risk flag(s): derived. Link only.",
    "zh": "许可证宽松，须相同方式共享：各部分均宽松，条件取各部分的并集。来源风险标记：derived。只链接原出处。"
  },
  "signoff": null,
  "risk_flags": [
    "derived"
  ],
  "provenance": {
    "source_description": null,
    "upstream": [
      {
        "slug": null,
        "name": "ChEMBL 35",
        "relation": "derived-from"
      }
    ]
  },
  "known_issues": [],
  "preflight": {
    "status": "not-run"
  },
  "access": {
    "mdexa_download": null,
    "external_urls": [
      "https://huggingface.co/datasets/introvoyz042/topu-lbvs"
    ],
    "notes": null
  },
  "citation": {
    "text": null,
    "references": []
  },
  "verification_level": "verified",
  "last_verified": "2026-11-14",
  "tags": [
    {
      "facet": "task_format",
      "value": "text-classification",
      "basis": "author-stated",
      "excerpt": "**`tabular-classification`** — Per-target binary classification of compounds as active or inactive against a fixed protein target.",
      "snapshot_id": "s01"
    },
    {
      "facet": "intended_use",
      "value": "evaluation",
      "basis": "author-stated",
      "excerpt": "The benchmark is organised into **three evaluation protocols**:",
      "snapshot_id": "s01"
    },
    {
      "facet": "specialty",
      "value": "pharmacy",
      "basis": "inferred",
      "inferred_from": "card-content-description",
      "excerpt": "**Multi-target benchmark for ligand-based virtual screening (LBVS) under hard-negative screening conditions.**",
      "snapshot_id": "s01"
    },
    {
      "facet": "source_type",
      "value": "knowledge-base",
      "basis": "inferred",
      "inferred_from": "card-content-description",
      "excerpt": "curated from ChEMBL 35.",
      "snapshot_id": "s01"
    },
    {
      "facet": "data_format",
      "value": "parquet",
      "basis": "inferred",
      "inferred_from": "card-content-description",
      "excerpt": "path: \"flat/topu-lbvs-full/train.parquet\"",
      "snapshot_id": "s01"
    },
    {
      "facet": "data_format",
      "value": "csv",
      "basis": "inferred",
      "inferred_from": "card-content-description",
      "excerpt": "Companion `*.csv` files contain the same compounds in plain tabular form for inspection.",
      "snapshot_id": "s01"
    },
    {
      "facet": "data_format",
      "value": "json",
      "basis": "inferred",
      "inferred_from": "card-content-description",
      "excerpt": "`split_info.json`",
      "snapshot_id": "s01"
    },
    {
      "facet": "official_split",
      "value": "full-split",
      "basis": "author-stated",
      "excerpt": "For each target, the ChEMBL\\* training pool is split 85% / 15% (stratified random, seed 2026/2027/2028) at a fixed 1:10 active-to-decoy ratio. The full TopU library is the test set at 1:40 active-to-decoy ratio.",
      "snapshot_id": "s01"
    }
  ],
  "changelog": [
    {
      "date": "2026-11-13",
      "change": {
        "en": "Added via the automated pipeline and passed all checks (gates, verbatim quotes, rule engine, two independent extractions).",
        "zh": "经自动流水线收录并通过全部校验（门禁、逐字引用、判定引擎、两轮独立抽取）。"
      }
    },
    {
      "date": "2026-11-13",
      "change": {
        "en": "Re-adjudicated under the current rules; all machine checks still pass.",
        "zh": "按当前规则重新判定；机器检查仍全部通过。"
      }
    },
    {
      "date": "2026-11-13",
      "change": {
        "en": "Re-adjudicated under the current rules; all machine checks still pass.",
        "zh": "按当前规则重新判定；机器检查仍全部通过。"
      }
    },
    {
      "date": "2026-11-13",
      "change": {
        "en": "Re-adjudicated under the current rules; all machine checks still pass.",
        "zh": "按当前规则重新判定；机器检查仍全部通过。"
      }
    },
    {
      "date": "2026-11-13",
      "change": {
        "en": "Re-adjudicated under the current rules; all machine checks still pass.",
        "zh": "按当前规则重新判定；机器检查仍全部通过。"
      }
    },
    {
      "date": "2026-11-13",
      "change": {
        "en": "Re-adjudicated under the current rules; all machine checks still pass.",
        "zh": "按当前规则重新判定；机器检查仍全部通过。"
      }
    },
    {
      "date": "2026-11-13",
      "change": {
        "en": "Re-adjudicated under the current rules; all machine checks still pass.",
        "zh": "按当前规则重新判定；机器检查仍全部通过。"
      }
    },
    {
      "date": "2026-11-13",
      "change": {
        "en": "Re-adjudicated under the current rules; all machine checks still pass.",
        "zh": "按当前规则重新判定；机器检查仍全部通过。"
      }
    },
    {
      "date": "2026-11-13",
      "change": {
        "en": "Re-adjudicated under the current rules; all machine checks still pass.",
        "zh": "按当前规则重新判定；机器检查仍全部通过。"
      }
    },
    {
      "date": "2026-11-14",
      "change": {
        "en": "Re-adjudicated under the current rules; all machine checks still pass.",
        "zh": "按当前规则重新判定；机器检查仍全部通过。"
      }
    },
    {
      "date": "2026-11-14",
      "change": {
        "en": "Re-adjudicated under the current rules; all machine checks still pass.",
        "zh": "按当前规则重新判定；机器检查仍全部通过。"
      }
    }
  ],
  "access_recipe": {
    "verified_on": "2026-11-14",
    "platform": "huggingface",
    "repo_id": "introvoyz042/topu-lbvs",
    "source": {
      "api_url": "https://huggingface.co/api/datasets/introvoyz042/topu-lbvs",
      "fetched_on": "2026-11-14"
    },
    "access_state": "open",
    "files": [],
    "files_truncated": false,
    "commands": [
      {
        "command": "hf download introvoyz042/topu-lbvs --repo-type dataset",
        "evidence": {
          "excerpt": "You can use the hf download command from the terminal to directly download files from the Hub.",
          "doc": "hf-download",
          "url": "https://huggingface.co/docs/huggingface_hub/guides/download",
          "fetched_on": "2026-11-14"
        }
      }
    ],
    "registration": null,
    "version": {
      "commit": "1ef722eb4b9710b3bf509d3c68442c8190f633ed",
      "last_modified": "2026-10-03T01:40:16.000Z"
    },
    "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."
    },
    "gaps": [
      "the platform publishes no checksum for these files; none was computed (we do not download data files)"
    ]
  },
  "_links": {
    "text": "Continue in this database. This record is one of 109 processed and verified records (datasets, data resources and open models). To find others, call `https://mcp.mdexa.com/v1/datasets?q=<words>` or connect the MCP server at `https://mcp.mdexa.com/mcp`; no key is needed for 20 calls per minute. Rows are under 1 KB; an empty result means \"not listed\". For a list of items, one batch check (free account) returns a report. Guide: /agents.md. Similar records: BindingDB (https://mdexa.com/datasets/bindingdb/); Therapeutics Data Commons (https://mdexa.com/datasets/tdc/); CBLUE (https://mdexa.com/datasets/cblue/).",
    "records": 109,
    "search": {
      "template": "https://mcp.mdexa.com/v1/datasets?q={words}",
      "example": "https://mcp.mdexa.com/v1/datasets?q=binding%20affinity"
    },
    "mcp": "https://mcp.mdexa.com/mcp",
    "anonymous_calls_per_minute": 20,
    "guide": "https://mdexa.com/agents.md",
    "faq": "https://mdexa.com/developers/faq/",
    "similar": [
      {
        "name": "BindingDB",
        "url": "https://mdexa.com/datasets/bindingdb/",
        "json": "https://mdexa.com/datasets/bindingdb.json"
      },
      {
        "name": "Therapeutics Data Commons",
        "url": "https://mdexa.com/datasets/tdc/",
        "json": "https://mdexa.com/datasets/tdc.json"
      },
      {
        "name": "CBLUE",
        "url": "https://mdexa.com/datasets/cblue/",
        "json": "https://mdexa.com/datasets/cblue.json"
      }
    ]
  }
}