{
  "schema_version": "2.0",
  "record_type": "dataset",
  "tier": "practical",
  "slug": "tdc",
  "name": "Therapeutics Data Commons",
  "summary": {
    "en": "License: unstated (NOASSERTION); Mdexa hosting: pending. the source says licenses differ per subset and does not list them",
    "zh": "许可证声明：未声明（NOASSERTION）；本站处理：待确认，暂只链接原出处。来源写明各子集许可各自不同，没有列出。"
  },
  "systems": [
    "modern-medicine"
  ],
  "domains": [
    "pharmacy-drugs",
    "clinical-medicine"
  ],
  "content_types": [
    "database"
  ],
  "content_description": {
    "en": "A coordinated initiative and resource offering AI-solvable tasks, AI-ready datasets and curated benchmarks for therapeutic science, with tools, libraries, leaderboards and community resources.",
    "zh": "面向治疗科学的协调项目与资源，提供可被AI解决的任务、AI就绪数据集和精选基准，并配有工具、库、排行榜与社区资源。"
  },
  "languages": [
    "en"
  ],
  "modalities": [
    "text",
    "tabular"
  ],
  "size": {
    "raw": null,
    "measures": []
  },
  "publisher": "Zitnik Lab, Harvard",
  "year": {
    "value": 2020,
    "raw": "2020"
  },
  "license": {
    "legacy_status": "pending",
    "spdx": "NOASSERTION",
    "commercial_use": "unstated",
    "derivatives": "unstated",
    "redistribution": "unstated",
    "rationale": {
      "en": "the source says licenses differ per subset and does not list them",
      "zh": "来源写明各子集许可各自不同，没有列出"
    },
    "evidence": [
      {
        "location": "repo-license",
        "location_detail": {
          "en": "GitHub repository license found in snapshot s08 (api-license)",
          "zh": "在快照 s08（api-license）中找到：GitHub repository license"
        },
        "excerpt": "\"spdx_id\": \"MIT\"",
        "spdx": "MIT",
        "url": "https://github.com/mims-harvard/TDC",
        "verified_on": "2026-11-13",
        "snapshot_id": "s08",
        "observed": "page",
        "captured_by": "pipeline"
      },
      {
        "location": "terms-page",
        "location_detail": {
          "en": "Statement found in snapshot s05 (readme)",
          "zh": "在快照 s05（readme）中找到的声明"
        },
        "excerpt": "The TDC codebase is licensed under the MIT license.",
        "spdx": "MIT",
        "url": "https://github.com/mims-harvard/TDC",
        "verified_on": "2026-11-13",
        "snapshot_id": "s05",
        "observed": "page",
        "captured_by": "pipeline"
      },
      {
        "location": "terms-page",
        "location_detail": {
          "en": "Statement found in snapshot s05 (readme)",
          "zh": "在快照 s05（readme）中找到的声明"
        },
        "excerpt": "For individual dataset usage, please refer to the dataset license on the website.",
        "url": "https://github.com/mims-harvard/TDC",
        "verified_on": "2026-11-13",
        "snapshot_id": "s05",
        "observed": "page",
        "captured_by": "pipeline"
      },
      {
        "location": "terms-page",
        "location_detail": {
          "en": "Statement found in snapshot s06 (license)",
          "zh": "在快照 s06（license）中找到的声明"
        },
        "excerpt": "Permission is hereby granted, free of charge, to any person obtaining a copy",
        "spdx": "MIT",
        "url": "https://github.com/mims-harvard/TDC",
        "verified_on": "2026-11-13",
        "snapshot_id": "s06",
        "observed": "page",
        "captured_by": "pipeline"
      },
      {
        "location": "terms-page",
        "location_detail": {
          "en": "Statement found in snapshot s07 (page)",
          "zh": "在快照 s07（page）中找到的声明"
        },
        "excerpt": "The TDC codebase is licensed under the MIT license. For individual dataset usage, please refer to the dataset license on the website.",
        "spdx": "MIT",
        "url": "https://github.com/mims-harvard/TDC",
        "verified_on": "2026-11-13",
        "snapshot_id": "s07",
        "observed": "page",
        "captured_by": "pipeline"
      }
    ],
    "per_component_license": true,
    "notes": {
      "en": "Licenses are specified per subset; check each subset page.",
      "zh": "许可按子集分别规定，需到各子集页面查看"
    }
  },
  "license_status": "unstated",
  "hosting": "pending",
  "hosting_reason": {
    "en": "License unstated: the source says licenses differ per subset and does not list them. Link only.",
    "zh": "许可证未声明：来源写明各子集许可各自不同，没有列出。只链接原出处。"
  },
  "signoff": null,
  "repo_license": {
    "spdx": "MIT",
    "source": "license-file",
    "verified": true,
    "snapshot_id": "s08",
    "url": "https://github.com/mims-harvard/TDC"
  },
  "risk_flags": [],
  "provenance": {
    "source_description": null,
    "upstream": []
  },
  "known_issues": [
    {
      "en": "The README defers per-dataset licensing to the website, so the license of the individual datasets is not stated here.",
      "zh": "README把各数据集的许可指向网站，此处未说明各数据集本身的许可。"
    },
    {
      "en": "The release is a beta release, so the local copy should be updated regularly.",
      "zh": "该版本为beta版，需要定期更新本地副本。"
    }
  ],
  "preflight": {
    "status": "not-run"
  },
  "access": {
    "mdexa_download": null,
    "external_urls": [
      "https://tdcommons.ai/",
      "https://github.com/mims-harvard/TDC"
    ],
    "notes": null
  },
  "citation": {
    "text": null,
    "references": [
      "arXiv:2102.09548"
    ]
  },
  "verification_level": "verified",
  "last_verified": "2026-11-14",
  "tags": [
    {
      "facet": "intended_use",
      "value": "evaluation",
      "basis": "author-stated",
      "excerpt": "It supports the development of AI methods and aims to establish the foundation of which AI methods are most suitable for drug discovery applications and why.",
      "snapshot_id": "s05"
    },
    {
      "facet": "specialty",
      "value": "pharmacy",
      "basis": "author-stated",
      "excerpt": "TDC covers a wide range of learning tasks, including target discovery, activity screening, efficacy, safety, and manufacturing across biomedical products, including small molecules, antibodies, and vaccines.",
      "snapshot_id": "s05"
    },
    {
      "facet": "benchmark_status",
      "value": "public-leaderboard",
      "basis": "author-stated",
      "excerpt": "TDC provides benchmarks for fair model comparison and systematic model development and evaluation.",
      "snapshot_id": "s05"
    },
    {
      "facet": "official_split",
      "value": "full-split",
      "basis": "inferred",
      "inferred_from": "card-content-description",
      "excerpt": "TDC provides extensive data functions, including data evaluators, meaningful data splits, data processors, and molecule generation oracles.",
      "snapshot_id": "s05"
    }
  ],
  "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": "2026-11-14",
      "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": "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": "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": "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": "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": "dataset",
          "count": 66,
          "count_as_of": null,
          "statement": {
            "text": {
              "en": "The text states that TDC includes 66 AI-ready datasets spread across 22 learning tasks and spanning the discovery and development of safe and effective medicines.",
              "zh": "文中说明，TDC 包含 66 个可供 AI 使用的数据集，分布在 22 个学习任务上，覆盖安全有效药物的发现与开发。"
            },
            "evidence": [
              {
                "location": "preprint",
                "excerpt": "To date, TDC includes 66 AI-ready datasets spread across 22 learning tasks and spanning the discovery and development of safe and effective medicines.",
                "url": "https://arxiv.org/abs/2102.09548",
                "snapshot_id": "s01",
                "char_start": 1120,
                "verified_on": "2026-11-13",
                "observed": "page",
                "captured_by": "pipeline"
              }
            ]
          }
        }
      ],
      "coverage": [
        {
          "text": {
            "en": "The text states that TDC covers learning tasks including target discovery, activity screening, efficacy, safety and manufacturing across biomedical products such as small molecules, antibodies and vaccines.",
            "zh": "文中说明，TDC 覆盖靶点发现、活性筛选、有效性、安全性和生产等学习任务，涉及小分子、抗体和疫苗等生物医学产品。"
          },
          "evidence": [
            {
              "location": "dataset-page",
              "excerpt": "TDC covers a wide range of learning tasks, including target discovery, activity screening, efficacy, safety, and manufacturing across biomedical products, including small molecules, antibodies, and vaccines.",
              "url": "https://tdcommons.ai/",
              "snapshot_id": "s03",
              "char_start": 3567,
              "verified_on": "2026-11-13",
              "observed": "page",
              "captured_by": "pipeline"
            }
          ]
        }
      ]
    },
    "identifiers": {
      "schemes": [
        {
          "name": "dataset name within a task class",
          "bioregistry_prefix": null,
          "applies_to": "datasets",
          "statement": {
            "text": {
              "en": "The text shows a dataset retrieved by the name HIA_Hou from the ADME therapeutic learning task under single-instance prediction.",
              "zh": "文中显示，通过名称 HIA_Hou 从单实例预测问题下的 ADME 治疗学习任务中获取一个数据集。"
            },
            "evidence": [
              {
                "location": "readme",
                "excerpt": "For a concrete example, to obtain the HIA dataset from the ADME therapeutic learning task in the single-instance prediction problem:",
                "url": "https://raw.githubusercontent.com/mims-harvard/TDC/HEAD/README.md",
                "snapshot_id": "s05",
                "char_start": 11422,
                "verified_on": "2026-11-13",
                "observed": "page",
                "captured_by": "pipeline"
              }
            ]
          }
        }
      ],
      "crosswalks": [],
      "mismatch_cases": []
    },
    "access_methods": [
      {
        "method": "web-ui-only",
        "url": "https://github.com/mims-harvard/TDC",
        "formats": [],
        "limits": [],
        "terms": {
          "same_as_card_license": true,
          "own_terms": null
        },
        "statement": {
          "text": {
            "en": "Data are loaded through the PyTDC library, which provides data functions, splits (e.g. scaffold split) and leaderboards; many datasets are fetched from Harvard Dataverse, so they are unavailable when Dataverse is under maintenance.",
            "zh": "数据通过 PyTDC 库加载，库内提供数据函数、切分方式（如骨架切分）与排行榜；许多数据集从 Harvard Dataverse 拉取，Dataverse 维护期间无法获取。"
          },
          "evidence": [
            {
              "location": "dataset-page",
              "excerpt": "When Dataverse is under maintenance, TDC datasets cannot be retrieved.",
              "url": "https://github.com/mims-harvard/TDC",
              "snapshot_id": "s11",
              "char_start": 17058,
              "verified_on": "2026-11-13",
              "observed": "page",
              "source_work": {
                "title": "mims-harvard/TDC README",
                "authors_or_org": "TDC team (Harvard, mims-harvard)",
                "date": null,
                "date_as_written": null,
                "source_type": "official-page",
                "open_access": true,
                "doi_or_url": "https://github.com/mims-harvard/TDC"
              }
            }
          ]
        },
        "reachable": {
          "status": 200,
          "checked_on": "2026-11-14"
        }
      }
    ],
    "versioning": {
      "latest": {
        "label": "2025-03",
        "released_on": "2025-03-31",
        "statement": {
          "text": {
            "en": "TDC is versioned as the PyTDC Python package; the latest PyPI release is 1.1.15, uploaded 2025-03-31. No separate data-release numbering was found.",
            "zh": "TDC 以 Python 包 PyTDC 的版本号区分；PyPI 最新版本为 1.1.15，上传于 2025-03-31。未见独立的数据版本编号。"
          },
          "evidence": [
            {
              "location": "official-release-notes",
              "excerpt": "\"upload_time\":\"2025-03-31T15:20:14\"",
              "url": "https://pypi.org/pypi/PyTDC/json",
              "snapshot_id": "s10",
              "char_start": 64578,
              "verified_on": "2026-11-13",
              "observed": "page",
              "source_work": {
                "title": "PyTDC package metadata (PyPI JSON API)",
                "authors_or_org": "PyPI / TDC maintainers",
                "date": "2025-03-31",
                "date_as_written": "2025-03-31",
                "source_type": "official-release-notes",
                "open_access": true,
                "doi_or_url": "https://pypi.org/pypi/PyTDC/json"
              }
            }
          ]
        }
      },
      "update_cycle": {
        "cycle": "irregular",
        "statement": {
          "text": {
            "en": "The text states that TDC is regularly updated with new datasets and tasks, such as antibody therapeutics and gene editing.",
            "zh": "文中说明，TDC 会定期更新，加入新的数据集和任务，例如抗体疗法和基因编辑。"
          },
          "evidence": [
            {
              "location": "dataset-page",
              "excerpt": "TDC is regularly updated with novel datasets and tasks, such as antibody therapeutics and gene editing.",
              "url": "https://tdcommons.ai/overview/",
              "snapshot_id": "s04",
              "char_start": 932,
              "verified_on": "2026-11-13",
              "observed": "page",
              "captured_by": "pipeline"
            }
          ]
        }
      },
      "breaking_changes": [],
      "history_url": null
    },
    "known_defects": [
      {
        "kind": "misuse",
        "statement": {
          "text": {
            "en": "The author writes that TDC is \"equally flawed\" as MoleculeNet, judged by the criteria he sets out in the article.",
            "zh": "作者在文中写道：按他列出的标准，TDC 与 MoleculeNet“同样有缺陷”。"
          },
          "evidence": [
            {
              "location": "practitioner-article",
              "excerpt": "other widely used benchmarks like the Therapeutic Data Commons (TDC) are equally flawed.",
              "url": "https://practicalcheminformatics.blogspot.com/2023/08/we-need-better-benchmarks-for-machine.html",
              "snapshot_id": "s12",
              "char_start": 3272,
              "verified_on": "2026-11-13",
              "observed": "page",
              "source_work": {
                "title": "We Need Better Benchmarks for Machine Learning in Drug Discovery",
                "authors_or_org": "Pat Walters (Practical Cheminformatics blog)",
                "date": "2023-08-03",
                "date_as_written": "2023-08-03",
                "source_type": "practitioner-article",
                "open_access": true,
                "doi_or_url": "https://practicalcheminformatics.blogspot.com/2023/08/we-need-better-benchmarks-for-machine.html"
              }
            }
          ]
        },
        "source_kind": "practitioner-article",
        "scope": null,
        "attribution": {
          "who": "Pat Walters (Practical Cheminformatics blog)",
          "when": "2023-08-03",
          "source_type": "practitioner-article",
          "title": "We Need Better Benchmarks for Machine Learning in Drug Discovery"
        },
        "correction_entrance": "Report an error through the publisher or the authors: https://practicalcheminformatics.blogspot.com/2023/08/we-need-better-benchmarks-for-machine.html"
      },
      {
        "kind": "duplicate",
        "statement": {
          "text": {
            "en": "Walters: the MoleculeNet BBB set contains 59 duplicate structures, 10 of which carry conflicting labels, plus 11 SMILES RDKit cannot parse.",
            "zh": "Walters：MoleculeNet 的 BBB 数据集含 59 个重复结构，其中 10 对标签相互矛盾，另有 11 个 RDKit 无法解析的 SMILES。"
          },
          "evidence": [
            {
              "location": "practitioner-article",
              "excerpt": "First, the dataset contains 59 duplicate structures. This is not the sort of thing we want to have in a benchmark. But wait, it gets worse, 10 of these duplicate structures have different labels.",
              "url": "https://practicalcheminformatics.blogspot.com/2023/08/we-need-better-benchmarks-for-machine.html",
              "snapshot_id": "s12",
              "char_start": 10507,
              "verified_on": "2026-11-13",
              "observed": "page",
              "source_work": {
                "title": "We Need Better Benchmarks for Machine Learning in Drug Discovery",
                "authors_or_org": "Pat Walters (Practical Cheminformatics blog)",
                "date": "2023-08-03",
                "date_as_written": "2023-08-03",
                "source_type": "practitioner-article",
                "open_access": true,
                "doi_or_url": "https://practicalcheminformatics.blogspot.com/2023/08/we-need-better-benchmarks-for-machine.html"
              }
            }
          ]
        },
        "source_kind": "practitioner-article",
        "scope": null,
        "attribution": {
          "who": "Pat Walters (Practical Cheminformatics blog)",
          "when": "2023-08-03",
          "source_type": "practitioner-article",
          "title": "We Need Better Benchmarks for Machine Learning in Drug Discovery"
        },
        "correction_entrance": "Report an error through the publisher or the authors: https://practicalcheminformatics.blogspot.com/2023/08/we-need-better-benchmarks-for-machine.html"
      },
      {
        "kind": "other",
        "statement": {
          "text": {
            "en": "Walters: in the MoleculeNet BACE set 71% of molecules have at least one undefined stereocenter.",
            "zh": "Walters：MoleculeNet 的 BACE 数据集中 71% 的分子至少有一个未定义的立体中心。"
          },
          "evidence": [
            {
              "location": "practitioner-article",
              "excerpt": "71% of the molecules have at least one undefined stereocenter, 222 molecules have 3 undefined stereocenters, and one molecule has a whopping 12 undefined stereocenters.",
              "url": "https://practicalcheminformatics.blogspot.com/2023/08/we-need-better-benchmarks-for-machine.html",
              "snapshot_id": "s12",
              "char_start": 6292,
              "verified_on": "2026-11-13",
              "observed": "page",
              "source_work": {
                "title": "We Need Better Benchmarks for Machine Learning in Drug Discovery",
                "authors_or_org": "Pat Walters (Practical Cheminformatics blog)",
                "date": "2023-08-03",
                "date_as_written": "2023-08-03",
                "source_type": "practitioner-article",
                "open_access": true,
                "doi_or_url": "https://practicalcheminformatics.blogspot.com/2023/08/we-need-better-benchmarks-for-machine.html"
              }
            }
          ]
        },
        "source_kind": "practitioner-article",
        "scope": null,
        "attribution": {
          "who": "Pat Walters (Practical Cheminformatics blog)",
          "when": "2023-08-03",
          "source_type": "practitioner-article",
          "title": "We Need Better Benchmarks for Machine Learning in Drug Discovery"
        },
        "correction_entrance": "Report an error through the publisher or the authors: https://practicalcheminformatics.blogspot.com/2023/08/we-need-better-benchmarks-for-machine.html"
      }
    ],
    "fit": {
      "suited_for": [
        {
          "text": {
            "en": "The text states that TDC is a resource to access and evaluate AI methods and supports the development of AI methods for drug discovery applications.",
            "zh": "文中说明，TDC 是一个用于访问和评估 AI 方法的资源，支持面向药物发现应用的 AI 方法开发。"
          },
          "evidence": [
            {
              "location": "dataset-page",
              "excerpt": "Therapeutics Data Commons is a resource to access and evaluate AI methods, supporting the development of AI methods, with a strong bent towards establishing the foundation of which AI methods are most suitable for drug discovery applications and why.",
              "url": "https://tdcommons.ai/",
              "snapshot_id": "s03",
              "char_start": 1581,
              "verified_on": "2026-11-13",
              "observed": "page",
              "captured_by": "pipeline"
            }
          ]
        },
        {
          "text": {
            "en": "TDC authors state their experiments show even the strongest algorithms fall short on distribution shift and generalisation to novel data.",
            "zh": "TDC 作者称其实验显示最强算法在真实分布偏移与对新数据的泛化上仍有不足。"
          },
          "evidence": [
            {
              "location": "preprint",
              "excerpt": "demonstrating that even the strongest algorithms fall short of solving key therapeutics challenges, including real dataset distributional shifts, multi-scale modeling of heterogeneous data, and robust generalization to novel data points.",
              "url": "https://arxiv.org/abs/2102.09548",
              "snapshot_id": "s13",
              "char_start": 1760,
              "verified_on": "2026-11-13",
              "observed": "page",
              "source_work": {
                "title": "Therapeutics Data Commons: Machine Learning Datasets and Tasks for Drug Discovery and Development",
                "authors_or_org": "Huang K, Fu T, Gao W, Zhao Y, Roohani Y, Leskovec J, Coley CW, Xiao C, Sun J, Zitnik M",
                "date": "2021-02-18",
                "date_as_written": "2021-02-18 (v2 2021-08-28)",
                "source_type": "preprint",
                "open_access": true,
                "doi_or_url": "https://arxiv.org/abs/2102.09548"
              }
            }
          ]
        },
        {
          "text": {
            "en": "Walters: MoleculeNet physiology datasets (BBB, toxicology) have complex endpoints that make them less than ideal for benchmark comparisons.",
            "zh": "Walters：MoleculeNet 的生理类数据集（BBB、毒性）终点复杂，不太适合做基准比较。"
          },
          "evidence": [
            {
              "location": "practitioner-article",
              "excerpt": "The complexity of these endpoints makes the data less than ideal for benchmark comparisons.",
              "url": "https://practicalcheminformatics.blogspot.com/2023/08/we-need-better-benchmarks-for-machine.html",
              "snapshot_id": "s12",
              "char_start": 2172,
              "verified_on": "2026-11-13",
              "observed": "page",
              "source_work": {
                "title": "We Need Better Benchmarks for Machine Learning in Drug Discovery",
                "authors_or_org": "Pat Walters (Practical Cheminformatics blog)",
                "date": "2023-08-03",
                "date_as_written": "2023-08-03",
                "source_type": "practitioner-article",
                "open_access": true,
                "doi_or_url": "https://practicalcheminformatics.blogspot.com/2023/08/we-need-better-benchmarks-for-machine.html"
              }
            }
          ]
        }
      ],
      "not_suited_for": []
    },
    "commercial_access": {
      "route": "unknown",
      "url": null,
      "statement": null
    },
    "completeness": {
      "core_complete": true,
      "literature_defects": 3,
      "reachable_access": 1,
      "meets_practical_bar": true,
      "gaps": [
        {
          "field": "versioning.breaking_changes",
          "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",
    "platform": "github",
    "repo_id": "mims-harvard/TDC",
    "source": {
      "api_url": "https://api.github.com/repos/mims-harvard/TDC",
      "fetched_on": "2026-11-14"
    },
    "access_state": "open",
    "files": [],
    "files_truncated": false,
    "commands": [
      {
        "command": "git clone https://github.com/mims-harvard/TDC",
        "evidence": {
          "excerpt": "git clone https://github.com/YOUR-USERNAME/YOUR-REPOSITORY",
          "doc": "github-clone",
          "url": "https://docs.github.com/en/repositories/creating-and-managing-repositories/cloning-a-repository",
          "fetched_on": "2026-11-14"
        }
      }
    ],
    "registration": null,
    "version": {
      "commit": null,
      "last_modified": "2025-07-13T17:44:10Z",
      "default_branch": "main"
    },
    "license_note": {
      "license_status": "unstated",
      "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": "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：TopU-LBVS: Multi-Target Benchmark for Ligand-Based Virtual Screening (https://mdexa.com/zh/datasets/topu-lbvs/)；BindingDB (https://mdexa.com/zh/datasets/bindingdb/)；DrugCentral (https://mdexa.com/zh/datasets/drugcentral/)。",
    "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": "TopU-LBVS: Multi-Target Benchmark for Ligand-Based Virtual Screening",
        "url": "https://mdexa.com/zh/datasets/topu-lbvs/",
        "json": "https://mdexa.com/zh/datasets/topu-lbvs.json"
      },
      {
        "name": "BindingDB",
        "url": "https://mdexa.com/zh/datasets/bindingdb/",
        "json": "https://mdexa.com/zh/datasets/bindingdb.json"
      },
      {
        "name": "DrugCentral",
        "url": "https://mdexa.com/zh/datasets/drugcentral/",
        "json": "https://mdexa.com/zh/datasets/drugcentral.json"
      }
    ]
  }
}