{ "schema_version": "2.0", "record_type": "dataset", "tier": "practical", "slug": "chembl", "name": "ChEMBL", "summary": { "en": "License: permissive, share-alike (CC-BY-SA-3.0); Mdexa hosting: link-only. all parts permissive; conditions are the union of the parts", "zh": "许可证声明：宽松，须相同方式共享（CC-BY-SA-3.0）；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。" }, "systems": [ "modern-medicine" ], "domains": [ "pharmacy-drugs" ], "content_types": [ "database" ], "content_description": { "en": "Database of bioactive drug-like small molecules with 2-D structures, calculated properties, and curated bioactivities such as binding constants, pharmacology and ADMET data.", "zh": "收录生物活性类药小分子的数据库，含二维结构、计算属性，以及结合常数、药理学和ADMET等生物活性数据。" }, "languages": [ "en" ], "modalities": [ "tabular" ], "size": { "raw": null, "measures": [] }, "publisher": "EMBL-EBI", "year": { "value": null, "raw": null }, "license": { "legacy_status": "pending", "spdx": "CC-BY-SA-3.0", "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": "terms-page", "location_detail": { "en": "Statement found in snapshot s01 (page)", "zh": "在快照 s01（page）中找到的声明" }, "excerpt": "Access to the web interface of ChEMBL is made under the EBI's Terms of Use .", "url": "https://chembl.gitbook.io/chembl-interface-documentation/about", "verified_on": "2026-11-13", "snapshot_id": "s01", "observed": "page", "captured_by": "pipeline" }, { "location": "terms-page", "location_detail": { "en": "Statement found in snapshot s01 (page)", "zh": "在快照 s01（page）中找到的声明" }, "excerpt": "The ChEMBL data is made available on a Creative Commons Attribution-Share Alike 3.0 Unported License.", "spdx": "CC-BY-SA-3.0", "url": "https://chembl.gitbook.io/chembl-interface-documentation/about", "verified_on": "2026-11-13", "snapshot_id": "s01", "observed": "page", "captured_by": "pipeline" } ], "license_conditions": [ "attribution", "share-alike" ], "license_parts": [ { "name": { "en": "ChEMBL data", "zh": "ChEMBL data" }, "spdx": "CC-BY-SA-3.0", "status": "permissive", "separable": true, "license_conditions": [ "attribution", "share-alike" ], "evidence": { "excerpt": "The ChEMBL data is made available on a Creative Commons Attribution-Share Alike 3.0 Unported License.", "url": "https://chembl.gitbook.io/chembl-interface-documentation/about", "snapshot_id": "s01" } } ] }, "license_status": "permissive", "hosting": "link-only", "hosting_reason": { "en": "License permissive, share-alike: all parts permissive; conditions are the union of the parts. 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。只链接原出处。" }, "signoff": null, "risk_flags": [], "provenance": { "source_description": null, "upstream": [] }, "known_issues": [], "preflight": { "status": "not-run" }, "access": { "mdexa_download": null, "external_urls": [ "https://www.ebi.ac.uk/chembl/", "https://chembl.gitbook.io/chembl-interface-documentation/about" ], "notes": null }, "citation": { "text": null, "references": [] }, "verification_level": "verified", "last_verified": "2026-11-14", "tags": [ { "facet": "intended_use", "value": "retrieval-kb", "basis": "inferred", "inferred_from": "card-content-description", "excerpt": "ChEMBL is a database of bioactive drug-like small molecules", "snapshot_id": "s01" }, { "facet": "specialty", "value": "pharmacy", "basis": "inferred", "inferred_from": "card-content-description", "excerpt": "abstracted bioactivities (e.g. binding constants, pharmacology and ADMET data)", "snapshot_id": "s01" }, { "facet": "source_type", "value": "literature", "basis": "author-stated", "excerpt": "The data is abstracted and curated from the primary scientific literature", "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": "2026-11-14", "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": "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": "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": "bioactive drug-like small molecule", "count": null, "count_as_of": null, "statement": { "text": { "en": "The page describes ChEMBL as a database of bioactive drug-like small molecules containing 2-D structures, calculated properties such as logP and molecular weight, and abstracted bioactivities.", "zh": "该页面称 ChEMBL 是一个生物活性类药小分子数据库，包含二维结构、计算属性（如 logP、分子量）以及抽取的生物活性数据。" }, "evidence": [ { "location": "dataset-page", "excerpt": "ChEMBL is a database of bioactive drug-like small molecules, it contains 2-D structures, calculated properties (e.g. logP, Molecular Weight, Lipinski Parameters, etc.) and abstracted bioactivities (e.g. binding constants, pharmacology and ADMET data).", "url": "https://chembl.gitbook.io/chembl-interface-documentation/about", "snapshot_id": "s01", "char_start": 415, "verified_on": "2026-11-13", "observed": "page", "captured_by": "pipeline" } ] } } ], "coverage": [ { "text": { "en": "The text states the data is abstracted and curated from the primary scientific literature and covers a significant fraction of the SAR and discovery of modern drugs.", "zh": "文本说明这些数据从原始科学文献中抽取和整理，覆盖现代药物构效关系（SAR）与发现的相当一部分。" }, "evidence": [ { "location": "dataset-page", "excerpt": "The data is abstracted and curated from the primary scientific literature, and cover a significant fraction of the SAR and discovery of modern drugs", "url": "https://chembl.gitbook.io/chembl-interface-documentation/about", "snapshot_id": "s01", "char_start": 667, "verified_on": "2026-11-13", "observed": "page", "captured_by": "pipeline" } ] } ] }, "identifiers": { "schemes": [ { "name": "ChEMBL_ID", "bioregistry_prefix": null, "applies_to": "molecules/compounds in chemical searches", "statement": { "text": { "en": "The text states that the Substructure and Similarity services accept SMILES, InChI Key and molecule ChEMBL_ID as arguments.", "zh": "文本说明子结构与相似性服务接受 SMILES、InChI Key 和分子 ChEMBL_ID 作为参数。" }, "evidence": [ { "location": "dataset-page", "excerpt": "These methods accept SMILES, InChI Key and molecule ChEMBL_ID as arguments and in the case of similarity searches an additional identity cut-off is needed.", "url": "https://chembl.gitbook.io/chembl-interface-documentation/web-services/chembl-data-web-services", "snapshot_id": "s06", "char_start": 11393, "verified_on": "2026-11-13", "observed": "page", "captured_by": "pipeline" } ] } } ], "crosswalks": [ { "to": "other resources (unspecified)", "to_slug": null, "statement": { "text": { "en": "The X-Ref endpoint is described as providing cross references to other resources for compounds.", "zh": "X-Ref 端点被描述为提供化合物与其他资源之间的交叉引用。" }, "evidence": [ { "location": "dataset-page", "excerpt": "Cross references to other resources for compounds", "url": "https://chembl.gitbook.io/chembl-interface-documentation/web-services/chembl-data-web-services", "snapshot_id": "s06", "char_start": 6162, "verified_on": "2026-11-13", "observed": "page", "captured_by": "pipeline" } ] } } ], "mismatch_cases": [], "notes": [ { "text": { "en": "ChEMBL 37 merged about 400 tautomer duplicates that InChI did not catch but a SMILES tautomer hash did.", "zh": "ChEMBL 37 合并了约 400 个 InChI 未识别、由 SMILES 互变异构哈希识别出的重复结构。" }, "evidence": [ { "location": "official-release-notes", "excerpt": "merged ~400 tautomer duplicates which were not identified by InChI, but were found via a SMILES tautomer hash", "url": "https://ftp.ebi.ac.uk/pub/databases/chembl/ChEMBLdb/latest/chembl_37_release_notes.txt", "snapshot_id": "s07", "char_start": 7995, "verified_on": "2026-11-13", "observed": "page", "source_work": { "title": "ChEMBL database version ChEMBL37 release notes", "authors_or_org": "ChEMBL team, EMBL-EBI", "date": null, "date_as_written": "01/05/2026 (as written)", "source_type": "official-release-notes", "open_access": true, "doi_or_url": "https://ftp.ebi.ac.uk/pub/databases/chembl/ChEMBLdb/latest/chembl_37_release_notes.txt" } } ] }, { "text": { "en": "In ChEMBL 37 legacy organism-based assays were remapped to about 400 new organism targets, aligned to NCBI taxonomy, while original assay descriptions were left unchanged.", "zh": "ChEMBL 37 把旧的以生物体为对象的测定重新映射到约 400 个新的生物体靶点（对齐 NCBI 分类），原始测定描述保持不变。" }, "evidence": [ { "location": "official-release-notes", "excerpt": "Legacy organism-based assays (mostly antimicrobial assays) were remapped to specific organism targets resulting in ~ 400 new organism entries in the TARGET_DICTIONARY.", "url": "https://ftp.ebi.ac.uk/pub/databases/chembl/ChEMBLdb/latest/chembl_37_release_notes.txt", "snapshot_id": "s07", "char_start": 6049, "verified_on": "2026-11-13", "observed": "page", "source_work": { "title": "ChEMBL database version ChEMBL37 release notes", "authors_or_org": "ChEMBL team, EMBL-EBI", "date": null, "date_as_written": "01/05/2026 (as written)", "source_type": "official-release-notes", "open_access": true, "doi_or_url": "https://ftp.ebi.ac.uk/pub/databases/chembl/ChEMBLdb/latest/chembl_37_release_notes.txt" } } ] } ] }, "access_methods": [ { "method": "bulk-download", "url": "https://ftp.ebi.ac.uk/pub/databases/chembl/ChEMBLdb/latest/README", "formats": [ "SDF", "FASTA", "MySQL", "PostgreSQL", "SQLite", "FP", "H5", "XML", "TXT", "PNG" ], "limits": [ { "text": { "en": "ChEMBL flags questionable activity values in ACTIVITIES.data_validity_comment (e.g. 'Outside typical range', 'Non standard unit for type', 'Potential transcription error', 'Potential author error'); ChEMBL leaves it to users to decide whether to keep them.", "zh": "ChEMBL 在 ACTIVITIES.data_validity_comment 中标记可疑活性值（如“超出典型范围”“该类型的非标准单位”“可能的转录错误”“可能的作者错误”），由用户决定是否保留。" }, "evidence": [ { "location": "dataset-page", "excerpt": "The use of the flag will allow users to decide whether or not to retain those values in their results set after running a search on the interface or using the downloaded database.", "url": "https://chembl.gitbook.io/chembl-interface-documentation/frequently-asked-questions/chembl-data-questions", "snapshot_id": "s11", "char_start": 9708, "verified_on": "2026-11-13", "observed": "page", "source_work": { "title": "ChEMBL Data Questions — FAQ", "authors_or_org": "ChEMBL team, EMBL-EBI", "date": null, "date_as_written": null, "source_type": "official-page", "open_access": true, "doi_or_url": "https://chembl.gitbook.io/chembl-interface-documentation/frequently-asked-questions/chembl-data-questions" } } ] } ], "terms": { "same_as_card_license": false, "own_terms": { "commercial_use": "unstated", "redistribution": "conditional", "evidence": [ { "location": "readme", "excerpt": "The data content in ChEMBL is licensed under a highly permissive Creative Commons license - specifically the \"CC Attribution-ShareAlike 3.0 Unported license\", see LICENSE file. The required attribution should contain the url of the ChEMBL resource, and also the release version, e.g.:", "url": "https://ftp.ebi.ac.uk/pub/databases/chembl/ChEMBLdb/latest/README", "snapshot_id": "s03", "char_start": 251, "verified_on": "2026-11-13", "observed": "page", "captured_by": "pipeline" } ] } }, "reachable": { "status": 200, "checked_on": "2026-11-14" } }, { "method": "web-api", "url": "https://www.ebi.ac.uk/chembl/api/data/molecule", "formats": [ "XML", "JSON", "YAML", "SVG", "SDF" ], "limits": [ { "text": { "en": "The text states that GET parameters must be encoded into the URL and that URL length is limited, so POST requests are often more convenient.", "zh": "文本说明 GET 参数必须编码进 URL，且 URL 长度有限，因此 POST 请求通常更方便。" }, "evidence": [ { "location": "dataset-page", "excerpt": "In GET request all the parameters has to be encoded into URL. Because there is a limitation of how long a URL can be it's often more convenient to use POST requests instead.", "url": "https://chembl.gitbook.io/chembl-interface-documentation/web-services/chembl-data-web-services", "snapshot_id": "s06", "char_start": 13431, "verified_on": "2026-11-13", "observed": "page", "captured_by": "pipeline" } ] } ], "terms": { "same_as_card_license": true, "own_terms": null }, "reachable": { "status": 200, "checked_on": "2026-11-14" } }, { "method": "bulk-download", "url": "https://chembl.gitbook.io/chembl-interface-documentation/downloads", "formats": [ "turtle" ], "limits": [], "terms": { "same_as_card_license": true, "own_terms": null }, "reachable": { "status": 200, "checked_on": "2026-11-14" } }, { "method": "web-api", "url": "https://chembl.gitbook.io/chembl-interface-documentation/web-services", "formats": [], "limits": [], "terms": { "same_as_card_license": true, "own_terms": null }, "statement": { "text": { "en": "ChEMBL offers two web services, the Data Web Services and the Cheminformatic Utils ('Beaker'), each with interactive documentation.", "zh": "ChEMBL 提供两套网络服务：数据服务与化学信息工具服务（Beaker），各有交互式文档。" }, "evidence": [ { "location": "dataset-page", "excerpt": "Online interactive documentation is available for both ChEMBL web services:", "url": "https://chembl.gitbook.io/chembl-interface-documentation/web-services", "snapshot_id": "s10", "char_start": 612, "verified_on": "2026-11-13", "observed": "page", "source_work": { "title": "Web Services — ChEMBL Interface Documentation", "authors_or_org": "ChEMBL team, EMBL-EBI", "date": null, "date_as_written": null, "source_type": "official-page", "open_access": true, "doi_or_url": "https://chembl.gitbook.io/chembl-interface-documentation/web-services" } } ] }, "reachable": { "status": 200, "checked_on": "2026-11-14" } }, { "method": "database-dump", "url": "https://ftp.ebi.ac.uk/pub/databases/chembl/ChEMBLdb/latest/", "formats": [], "limits": [], "terms": { "same_as_card_license": true, "own_terms": null }, "statement": { "text": { "en": "Each release is distributed as dumps (MySQL, PostgreSQL, SQLite), SDF, FASTA and other files; ChEMBL 37 also ships a ChEMBL-to-UniProt mapping file.", "zh": "每个版本以 MySQL、PostgreSQL、SQLite 转储及 SDF、FASTA 等文件分发；ChEMBL 37 目录另附 ChEMBL 与 UniProt 的映射文件。" }, "evidence": [ { "location": "dataset-page", "excerpt": "chembl_uniprot_mapping.txt", "url": "https://ftp.ebi.ac.uk/pub/databases/chembl/ChEMBLdb/latest/", "snapshot_id": "s08", "char_start": 926, "verified_on": "2026-11-13", "observed": "page", "source_work": { "title": "Index of /pub/databases/chembl/ChEMBLdb/latest", "authors_or_org": "EMBL-EBI", "date": null, "date_as_written": null, "source_type": "official-page", "open_access": true, "doi_or_url": "https://ftp.ebi.ac.uk/pub/databases/chembl/ChEMBLdb/latest/" } } ] }, "reachable": { "status": 200, "checked_on": "2026-11-14" } }, { "method": "web-ui-only", "url": "https://chembl.gitbook.io/chembl-interface-documentation/about", "formats": [], "limits": [], "terms": { "same_as_card_license": true, "own_terms": null }, "statement": { "text": { "en": "Terms differ by channel: the web interface is used under EBI's Terms of Use, while the data are licensed CC BY-SA 3.0 Unported (share-alike).", "zh": "不同取用渠道条款不同：网页界面适用 EBI 使用条款，数据本身为 CC BY-SA 3.0 Unported（相同方式共享）。" }, "evidence": [ { "location": "dataset-page", "excerpt": "Access to the web interface of ChEMBL is made under the EBI's Terms of Use . The ChEMBL data is made available on a Creative Commons Attribution-Share Alike 3.0 Unported License.", "url": "https://chembl.gitbook.io/chembl-interface-documentation/about", "snapshot_id": "s09", "char_start": 1825, "verified_on": "2026-11-13", "observed": "page", "source_work": { "title": "About — ChEMBL Interface Documentation", "authors_or_org": "ChEMBL team, EMBL-EBI", "date": null, "date_as_written": null, "source_type": "official-page", "open_access": true, "doi_or_url": "https://chembl.gitbook.io/chembl-interface-documentation/about" } } ] }, "reachable": { "status": 200, "checked_on": "2026-11-14" } } ], "versioning": { "latest": { "label": "chembl_37", "released_on": "2026-05-01", "statement": { "text": { "en": "The text states the version of ChEMBL is chembl_37.", "zh": "文本说明 ChEMBL 的版本为 chembl_37。" }, "evidence": [ { "location": "readme", "excerpt": "ChEMBL data is from http://www.ebi.ac.uk/chembl - the version of ChEMBL is chembl_37.", "url": "https://ftp.ebi.ac.uk/pub/databases/chembl/ChEMBLdb/latest/README", "snapshot_id": "s03", "char_start": 537, "verified_on": "2026-11-13", "observed": "page", "captured_by": "pipeline" } ] } }, "update_cycle": { "cycle": "not-stated", "statement": null }, "breaking_changes": [ { "version": "ChEMBL 36", "date": null, "kind": "format", "statement": { "text": { "en": "Schema changes between releases: ChEMBL 37 deprecated tables CURATION_LOOKUP and PROTEIN_CLASS_SYNONYMS and fields CELL_DICTIONARY.CL_LINCS_ID and ASSAYS.CURATED_BY, and added ACTIVITIES.MODALITY.", "zh": "版本间存在表结构变更：ChEMBL 37 弃用 CURATION_LOOKUP、PROTEIN_CLASS_SYNONYMS 两张表及 CELL_DICTIONARY.CL_LINCS_ID、ASSAYS.CURATED_BY 两个字段，新增 ACTIVITIES.MODALITY。" }, "evidence": [ { "location": "official-release-notes", "excerpt": "# Tables that have been deprecated since ChEMBL 36: CURATION_LOOKUP PROTEIN_CLASS_SYNONYMS", "url": "https://ftp.ebi.ac.uk/pub/databases/chembl/ChEMBLdb/latest/chembl_37_release_notes.txt", "snapshot_id": "s07", "char_start": null, "verified_on": "2026-11-13", "observed": "page", "source_work": { "title": "ChEMBL database version ChEMBL37 release notes", "authors_or_org": "ChEMBL team, EMBL-EBI", "date": null, "date_as_written": "01/05/2026 (as written)", "source_type": "official-release-notes", "open_access": true, "doi_or_url": "https://ftp.ebi.ac.uk/pub/databases/chembl/ChEMBLdb/latest/chembl_37_release_notes.txt" } } ] } }, { "version": "unspecified", "date": null, "kind": "other", "statement": { "text": { "en": "Approved-drug status (MAX_PHASE) changed markedly in ChEMBL 36 after a stricter reading of ATC and BNF sources; 169 compounds were restored to MAX_PHASE 4 in ChEMBL 37, and ChEMBL says differences between recent releases will persist.", "zh": "ChEMBL 36 因对 ATC、BNF 来源采用更严格的“已批准”解释，已上市药物（MAX_PHASE）数量大幅变化；ChEMBL 37 经人工核对又将 169 个化合物恢复为 MAX_PHASE 4，官方称近期版本间仍会有差异。" }, "evidence": [ { "location": "official-release-notes", "excerpt": "Differences in ATC MAX_PHASE will still exist between recent ChEMBL releases, as this curation effort is ongoing.", "url": "https://ftp.ebi.ac.uk/pub/databases/chembl/ChEMBLdb/latest/chembl_37_release_notes.txt", "snapshot_id": "s07", "char_start": 9360, "verified_on": "2026-11-13", "observed": "page", "source_work": { "title": "ChEMBL database version ChEMBL37 release notes", "authors_or_org": "ChEMBL team, EMBL-EBI", "date": null, "date_as_written": "01/05/2026 (as written)", "source_type": "official-release-notes", "open_access": true, "doi_or_url": "https://ftp.ebi.ac.uk/pub/databases/chembl/ChEMBLdb/latest/chembl_37_release_notes.txt" } } ] } } ], "history_url": null, "notes": [ { "text": { "en": "The latest release on the EBI FTP 'latest' directory is ChEMBL 37; its release notes give 2,921,148 compounds, 24,527,044 activities, 1,970,438 assays and 18,552 targets, with preparation date written as 01/05/2026.", "zh": "EBI FTP 的 latest 目录当前为 ChEMBL 37；其发布说明列出化合物 2,921,148 个、活性数据 24,527,044 条、测定 1,970,438 个、靶点 18,552 个，准备日期原文写作 01/05/2026。" }, "evidence": [ { "location": "official-release-notes", "excerpt": "This version of the database, prepared on 01/05/2026 contains:", "url": "https://ftp.ebi.ac.uk/pub/databases/chembl/ChEMBLdb/latest/chembl_37_release_notes.txt", "snapshot_id": "s07", "char_start": 102, "verified_on": "2026-11-13", "observed": "page", "source_work": { "title": "ChEMBL database version ChEMBL37 release notes", "authors_or_org": "ChEMBL team, EMBL-EBI", "date": null, "date_as_written": "01/05/2026 (as written; day/month order not stated)", "source_type": "official-release-notes", "open_access": true, "doi_or_url": "https://ftp.ebi.ac.uk/pub/databases/chembl/ChEMBLdb/latest/chembl_37_release_notes.txt" } } ] }, { "text": { "en": "Each ChEMBL release can be cited by its own DOI, listed on the Downloads page.", "zh": "每个 ChEMBL 版本都有独立 DOI，可在下载页查到并用于引用特定版本。" }, "evidence": [ { "location": "dataset-page", "excerpt": "You may also use a DOI to reference a specific release of the ChEMBL database", "url": "https://chembl.gitbook.io/chembl-interface-documentation/about", "snapshot_id": "s09", "char_start": 2085, "verified_on": "2026-11-13", "observed": "page", "source_work": { "title": "About — ChEMBL Interface Documentation", "authors_or_org": "ChEMBL team, EMBL-EBI", "date": null, "date_as_written": null, "source_type": "official-page", "open_access": true, "doi_or_url": "https://chembl.gitbook.io/chembl-interface-documentation/about" } } ] }, { "text": { "en": "ChEMBL's 2023 NAR update reports that ChEMBL now holds slightly more bioactivity data from deposited datasets than from literature extraction.", "zh": "ChEMBL 2023 年 NAR 更新论文称，库中来自直接提交数据集的活性数据已略多于文献抽取数据。" }, "evidence": [ { "location": "peer-reviewed-paper", "excerpt": "ChEMBL now contains slightly more bioactivity data from deposited data vs data extracted from literature.", "url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC10767899/", "snapshot_id": "s12", "char_start": 11343, "verified_on": "2026-11-13", "observed": "page", "source_work": { "title": "The ChEMBL Database in 2023: a drug discovery platform spanning multiple bioactivity data types and time periods", "authors_or_org": "Zdrazil B, Felix E, Hunter F, et al., Leach AR (Nucleic Acids Research)", "date": "2024-01-01", "date_as_written": "2024-01-01", "source_type": "peer-reviewed-paper", "open_access": true, "doi_or_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC10767899/" } } ] } ] }, "known_defects": [ { "kind": "duplicate", "statement": { "text": { "en": "ChEMBL flags likely repeat citations of an earlier measurement in the potential_duplicate column.", "zh": "ChEMBL 在 potential_duplicate 列中标记可能是对早先测量的重复引用。" }, "evidence": [ { "location": "dataset-page", "excerpt": "Identification of potential duplicate values - where an activity measurement is likely to be a repeat citation of an earlier measurement, rather than an independent measurement (flagged using the potential_duplicate column).", "url": "https://chembl.gitbook.io/chembl-interface-documentation/frequently-asked-questions/chembl-data-questions", "snapshot_id": "s11", "char_start": 10896, "verified_on": "2026-11-13", "observed": "page", "source_work": { "title": "ChEMBL Data Questions — FAQ", "authors_or_org": "ChEMBL team, EMBL-EBI", "date": null, "date_as_written": null, "source_type": "official-page", "open_access": true, "doi_or_url": "https://chembl.gitbook.io/chembl-interface-documentation/frequently-asked-questions/chembl-data-questions" } } ] }, "source_kind": "official-note", "scope": null, "attribution": { "who": "ChEMBL team, EMBL-EBI", "when": "date not stated (page read 2026-11-13)", "source_type": "official-page", "title": "ChEMBL Data Questions — FAQ" }, "correction_entrance": "Report an error through the publisher or the authors: https://chembl.gitbook.io/chembl-interface-documentation/frequently-asked-questions/chembl-data-questions" }, { "kind": "data-quality", "statement": { "text": { "en": "Landrum and Riniker: combining ChEMBL IC50 values from different assays with minimal curation gives poor agreement (about 65% of pairs differ by >0.3 log units, 27% by >1 log unit); stricter metadata matching reduces but does not remove the noise, and Ki shows similar noise.", "zh": "Landrum 与 Riniker：以最低限度筛选合并 ChEMBL 不同测定的 IC50，一致性差（约 65% 的成对数据相差 >0.3 个对数单位，27% 相差 >1）；严格匹配测定元数据可减轻但不能消除噪声，Ki 也有类似噪声。" }, "evidence": [ { "location": "peer-reviewed-paper", "excerpt": "IC 50 assays selected using minimal curation settings have poor agreement with each other: almost 65% of the points differ by more than 0.3 log units, 27% differ by more than one log unit", "url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC10934815/", "snapshot_id": "s13", "char_start": null, "verified_on": "2026-11-13", "observed": "page", "source_work": { "title": "Combining IC50 or Ki Values from Different Sources Is a Source of Significant Noise", "authors_or_org": "Landrum GA, Riniker S (Journal of Chemical Information and Modeling)", "date": "2024-02-23", "date_as_written": "2024-02-23", "source_type": "peer-reviewed-paper", "open_access": true, "doi_or_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC10934815/" } } ] }, "source_kind": "peer-reviewed-paper", "scope": null, "attribution": { "who": "Landrum GA, Riniker S (Journal of Chemical Information and Modeling)", "when": "2024-02-23", "source_type": "peer-reviewed-paper", "title": "Combining IC50 or Ki Values from Different Sources Is a Source of Significant Noise" }, "correction_entrance": "Report an error through the publisher or the authors: https://pmc.ncbi.nlm.nih.gov/articles/PMC10934815/" }, { "kind": "data-quality", "statement": { "text": { "en": "Kalliokoski et al. reached a milder conclusion: the standard deviation of ChEMBL IC50 data is only about 25% larger than for Ki, so mixing IC50 from different assays adds a moderate amount of noise.", "zh": "Kalliokoski 等结论较温和：ChEMBL IC50 数据的标准差只比 Ki 大约 25%，混合不同测定的 IC50 只增加中等程度的噪声。" }, "evidence": [ { "location": "peer-reviewed-paper", "excerpt": "The standard deviation of IC 50 data is only 25% larger than the standard deviation of K i data, suggesting that mixing IC 50 data from different assays, even not knowing assay conditions details, only adds a moderate amount of noise to the overall data.", "url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC3628986/", "snapshot_id": "s15", "char_start": 5469, "verified_on": "2026-11-13", "observed": "page", "source_work": { "title": "Comparability of mixed IC50 data - a statistical analysis", "authors_or_org": "Kalliokoski T, Kramer C, Vulpetti A, Gedeck P (PLoS ONE)", "date": "2013-04-16", "date_as_written": "2013-04-16", "source_type": "peer-reviewed-paper", "open_access": true, "doi_or_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC3628986/" } } ] }, "source_kind": "peer-reviewed-paper", "scope": null, "attribution": { "who": "Kalliokoski T, Kramer C, Vulpetti A, Gedeck P (PLoS ONE)", "when": "2013-04-16", "source_type": "peer-reviewed-paper", "title": "Comparability of mixed IC50 data - a statistical analysis" }, "correction_entrance": "Report an error through the publisher or the authors: https://pmc.ncbi.nlm.nih.gov/articles/PMC3628986/" }, { "kind": "data-quality", "statement": { "text": { "en": "Kramer et al. found ChEMBL Ki data contain unit-transcription errors, undifferentiated stereoisomers and repeated citations (90% of all pairs), and estimated an experimental-uncertainty ceiling of R² about 0.81.", "zh": "Kramer 等发现 ChEMBL 的 Ki 数据含单位转录错误、未区分的立体异构体与重复引用（占全部成对数据的 90%），估计实验不确定性决定的 R² 上限约 0.81。" }, "evidence": [ { "location": "peer-reviewed-paper", "excerpt": "Careful filtering of the data was required because ChEMBL contains unit-transcription errors, undifferentiated stereoisomers, and repeated citations of single measurements (90% of all pairs).", "url": "https://pubmed.ncbi.nlm.nih.gov/22643060/", "snapshot_id": "s14", "char_start": 176, "verified_on": "2026-11-13", "observed": "page", "source_work": { "title": "The experimental uncertainty of heterogeneous public K(i) data", "authors_or_org": "Kramer C, Kalliokoski T, Gedeck P, Vulpetti A (Journal of Medicinal Chemistry)", "date": "2012-05-29", "date_as_written": "2012-05-29", "source_type": "peer-reviewed-paper", "open_access": false, "doi_or_url": "https://pubmed.ncbi.nlm.nih.gov/22643060/" } } ] }, "source_kind": "peer-reviewed-paper", "scope": null, "attribution": { "who": "Kramer C, Kalliokoski T, Gedeck P, Vulpetti A (Journal of Medicinal Chemistry)", "when": "2012-05-29", "source_type": "peer-reviewed-paper", "title": "The experimental uncertainty of heterogeneous public K(i) data" }, "correction_entrance": "Report an error through the publisher or the authors: https://pubmed.ncbi.nlm.nih.gov/22643060/" }, { "kind": "duplicate", "statement": { "text": { "en": "ChEMBL 37 removed 13 duplicate documents found within and across the BindingDB and SureChEMBL patent sources.", "zh": "ChEMBL 37 在 BindingDB 与 SureChEMBL 专利来源内部及之间发现并去除 13 份重复文献。" }, "evidence": [ { "location": "official-release-notes", "excerpt": "13 intra-source and inter-source duplicate documents were identified.", "url": "https://ftp.ebi.ac.uk/pub/databases/chembl/ChEMBLdb/latest/chembl_37_release_notes.txt", "snapshot_id": "s07", "char_start": 5602, "verified_on": "2026-11-13", "observed": "page", "source_work": { "title": "ChEMBL database version ChEMBL37 release notes", "authors_or_org": "ChEMBL team, EMBL-EBI", "date": null, "date_as_written": "01/05/2026 (as written)", "source_type": "official-release-notes", "open_access": true, "doi_or_url": "https://ftp.ebi.ac.uk/pub/databases/chembl/ChEMBLdb/latest/chembl_37_release_notes.txt" } } ] }, "source_kind": "official-note", "scope": null, "attribution": { "who": "ChEMBL team, EMBL-EBI", "when": "01/05/2026 (as written)", "source_type": "official-release-notes", "title": "ChEMBL database version ChEMBL37 release notes" }, "correction_entrance": "Report an error through the publisher or the authors: https://ftp.ebi.ac.uk/pub/databases/chembl/ChEMBLdb/latest/chembl_37_release_notes.txt" } ], "fit": { "suited_for": [ { "text": { "en": "The text states that the Substructure and Similarity web service resources allow the chemical content of ChEMBL to be searched.", "zh": "文本说明子结构与相似性 Web 服务资源可用于检索 ChEMBL 的化学内容。" }, "evidence": [ { "location": "dataset-page", "excerpt": "The 'Substructure' and 'Similarity' web service resources allow for the chemical content of ChEMBL to be searched.", "url": "https://chembl.gitbook.io/chembl-interface-documentation/web-services/chembl-data-web-services", "snapshot_id": "s06", "char_start": 11168, "verified_on": "2026-11-13", "observed": "page", "captured_by": "pipeline" } ] }, { "text": { "en": "Landrum and Riniker caution that combining literature IC50 data from different assays into one ML set is scientifically risky, more so for large literature collections like ChEMBL.", "zh": "Landrum 与 Riniker 提醒：把不同测定的文献 IC50 合并成一个机器学习数据集在科学上有风险，对 ChEMBL 这类大型文献集合尤甚。" }, "evidence": [ { "location": "peer-reviewed-paper", "excerpt": "the risks of assays being incompatible are even higher when pulling data from large collections of literature data like ChEMBL.", "url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC10934815/", "snapshot_id": "s13", "char_start": null, "verified_on": "2026-11-13", "observed": "page", "source_work": { "title": "Combining IC50 or Ki Values from Different Sources Is a Source of Significant Noise", "authors_or_org": "Landrum GA, Riniker S (Journal of Chemical Information and Modeling)", "date": "2024-02-23", "date_as_written": "2024-02-23", "source_type": "peer-reviewed-paper", "open_access": true, "doi_or_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC10934815/" } } ] } ], "not_suited_for": [ { "text": { "en": "The text states that the Image resource, unlike the other resources, does not accept filtering and paging arguments.", "zh": "文本说明 Image 资源与其他资源不同，不接受过滤和分页参数。" }, "evidence": [ { "location": "dataset-page", "excerpt": "Unlike the other resources it does not except filtering and paging arguments, but does accept image specific arguments.", "url": "https://chembl.gitbook.io/chembl-interface-documentation/web-services/chembl-data-web-services", "snapshot_id": "s06", "char_start": 12772, "verified_on": "2026-11-13", "observed": "page", "captured_by": "pipeline" } ] } ] }, "commercial_access": { "route": "unknown", "url": null, "statement": null }, "completeness": { "core_complete": true, "literature_defects": 4, "reachable_access": 6, "meets_practical_bar": true, "gaps": [ { "field": "versioning.update_cycle", "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": "chembl_37", "date": "01/05/2026", "evidence": { "excerpt": "* Release: chembl_37 * * Date: 01/05/2026", "snapshot_id": "s03", "url": "https://ftp.ebi.ac.uk/pub/databases/chembl/ChEMBLdb/latest/README" } }, "files": [], "api": [ { "name": "Molecule", "url_template": "https://www.ebi.ac.uk/chembl/api/data/molecule", "required_params": [], "example_request": "https://www.ebi.ac.uk/chembl/api/data/molecule?molecule_properties__mw_freebase__lte=300", "key_response_fields": [], "evidence": { "excerpt": "Molecule Molecule information, including properties, structural representations and synonyms https://www.ebi.ac.uk/chembl/api/data/molecule", "snapshot_id": "s06", "url": "https://chembl.gitbook.io/chembl-interface-documentation/web-services/chembl-data-web-services" } }, { "name": "Target", "url_template": "https://www.ebi.ac.uk/chembl/api/data/target", "required_params": [], "example_request": "https://www.ebi.ac.uk/chembl/api/data/target?pref_name__contains=cyclin", "key_response_fields": [], "evidence": { "excerpt": "Target Targets (protein and non-protein) defined in Assay https://www.ebi.ac.uk/chembl/api/data/target", "snapshot_id": "s06", "url": "https://chembl.gitbook.io/chembl-interface-documentation/web-services/chembl-data-web-services" } }, { "name": "Activity", "url_template": "https://www.ebi.ac.uk/chembl/api/data/activity", "required_params": [], "example_request": "https://www.ebi.ac.uk/chembl/api/data/activity?limit=20&offset=20", "key_response_fields": [], "evidence": { "excerpt": "Activity Activity values recorded in an Assay https://www.ebi.ac.uk/chembl/api/data/activity", "snapshot_id": "s06", "url": "https://chembl.gitbook.io/chembl-interface-documentation/web-services/chembl-data-web-services" } }, { "name": "Assay", "url_template": "https://www.ebi.ac.uk/chembl/api/data/assay", "required_params": [], "example_request": "https://www.ebi.ac.uk/chembl/api/data/assay.xml", "key_response_fields": [], "evidence": { "excerpt": "Assay Assay details as reported in source Document/Dataset https://www.ebi.ac.uk/chembl/api/data/assay", "snapshot_id": "s06", "url": "https://chembl.gitbook.io/chembl-interface-documentation/web-services/chembl-data-web-services" } }, { "name": "Document", "url_template": "https://www.ebi.ac.uk/chembl/api/data/document", "required_params": [], "example_request": "https://www.ebi.ac.uk/chembl/api/data/document.yaml", "key_response_fields": [], "evidence": { "excerpt": "Document Document/Dataset from which Assays have been extracted https://www.ebi.ac.uk/chembl/api/data/document", "snapshot_id": "s06", "url": "https://chembl.gitbook.io/chembl-interface-documentation/web-services/chembl-data-web-services" } }, { "name": "Drug", "url_template": "https://www.ebi.ac.uk/chembl/api/data/drug", "required_params": [], "example_request": null, "key_response_fields": [], "evidence": { "excerpt": "Approved drugs information, including (but not limited to) applicants, patent numbers and research codes.", "snapshot_id": "s06", "url": "https://chembl.gitbook.io/chembl-interface-documentation/web-services/chembl-data-web-services" } }, { "name": "Mechanism", "url_template": "https://www.ebi.ac.uk/chembl/api/data/mechanism", "required_params": [], "example_request": null, "key_response_fields": [], "evidence": { "excerpt": "Mechanism Mechanism of action information for approved drugs.", "snapshot_id": "s06", "url": "https://chembl.gitbook.io/chembl-interface-documentation/web-services/chembl-data-web-services" } }, { "name": "Status", "url_template": "https://www.ebi.ac.uk/chembl/api/data/status", "required_params": [], "example_request": "https://www.ebi.ac.uk/chembl/api/data/status", "key_response_fields": [], "evidence": { "excerpt": "Status API status with ChEMBL DB version number and API software version number https://www.ebi.ac.uk/chembl/api/data/status", "snapshot_id": "s06", "url": "https://chembl.gitbook.io/chembl-interface-documentation/web-services/chembl-data-web-services" } }, { "name": "Image", "url_template": "https://www.ebi.ac.uk/chembl/api/data/image/CHEMBL1", "required_params": [], "example_request": "https://www.ebi.ac.uk/chembl/api/data/image/CHEMBL25?format=svg", "key_response_fields": [], "evidence": { "excerpt": "Image Graphical (svg) representation of Molecule https://www.ebi.ac.uk/chembl/api/data/image/CHEMBL1", "snapshot_id": "s06", "url": "https://chembl.gitbook.io/chembl-interface-documentation/web-services/chembl-data-web-services" } }, { "name": "Cell Line", "url_template": "https://www.ebi.ac.uk/chembl/api/data/cell_line", "required_params": [], "example_request": "https://www.ebi.ac.uk/chembl/api/data/cell_line?cell_source_tissue__iendswith=carcinoma", "key_response_fields": [], "evidence": { "excerpt": "Cell Line Cell line information https://www.ebi.ac.uk/chembl/api/data/cell_line", "snapshot_id": "s06", "url": "https://chembl.gitbook.io/chembl-interface-documentation/web-services/chembl-data-web-services" } }, { "name": "Organism", "url_template": "https://www.ebi.ac.uk/chembl/api/data/organism", "required_params": [], "example_request": null, "key_response_fields": [], "evidence": { "excerpt": "Organism Simple organism classification https://www.ebi.ac.uk/chembl/api/data/organism", "snapshot_id": "s06", "url": "https://chembl.gitbook.io/chembl-interface-documentation/web-services/chembl-data-web-services" } }, { "name": "Target Component", "url_template": "https://www.ebi.ac.uk/chembl/api/data/target_component", "required_params": [], "example_request": null, "key_response_fields": [], "evidence": { "excerpt": "Target Component Target sequence information (a Target may have 1 or more sequences) https://www.ebi.ac.uk/chembl/api/data/target_component", "snapshot_id": "s06", "url": "https://chembl.gitbook.io/chembl-interface-documentation/web-services/chembl-data-web-services" } }, { "name": "X-Ref (Cross references)", "url_template": "https://www.ebi.ac.uk/chembl/api/data/xref_source", "required_params": [], "example_request": null, "key_response_fields": [], "evidence": { "excerpt": "X-Ref (Cross references) Cross references to other resources for compounds https://www.ebi.ac.uk/chembl/api/data/xref_source", "snapshot_id": "s06", "url": "https://chembl.gitbook.io/chembl-interface-documentation/web-services/chembl-data-web-services" } } ], "registration": null, "bulk_download": [ { "command_text": "https://www.ebi.ac.uk/chembl/api/data/activity", "evidence": { "excerpt": "To download all ChEMBL activity endpoints (>13 million), the following URL can be used: https://www.ebi.ac.uk/chembl/api/data/activity .", "snapshot_id": "s06", "url": "https://chembl.gitbook.io/chembl-interface-documentation/web-services/chembl-data-web-services" } } ], "gaps": [ "no direct file address was found on the official pages we hold", "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：DDInter (https://mdexa.com/zh/datasets/ddinter/)；ClinPGx/PharmGKB (https://mdexa.com/zh/datasets/pharmgkb/)；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": "DDInter", "url": "https://mdexa.com/zh/datasets/ddinter/", "json": "https://mdexa.com/zh/datasets/ddinter.json" }, { "name": "ClinPGx/PharmGKB", "url": "https://mdexa.com/zh/datasets/pharmgkb/", "json": "https://mdexa.com/zh/datasets/pharmgkb.json" }, { "name": "DrugCentral", "url": "https://mdexa.com/zh/datasets/drugcentral/", "json": "https://mdexa.com/zh/datasets/drugcentral.json" } ] } }