{ "schema_version": "2.0", "record_type": "dataset", "tier": "verified", "slug": "pubchem", "name": "PubChem", "summary": { "en": "License: permissive (LicenseRef-PublicDomain); Mdexa hosting: link-only. all parts permissive; conditions are the union of the parts", "zh": "许可证声明：宽松（LicenseRef-PublicDomain）；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" ], "languages": [ "en" ], "modalities": [ "text" ], "size": { "raw": null, "measures": [] }, "publisher": "U.S. National Library of Medicine (NCBI)", "year": { "value": null, "raw": null }, "license": { "legacy_status": "pending", "spdx": "LicenseRef-PublicDomain", "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": "site-policy", "location_detail": { "en": "Statement found in snapshot s02 (page)", "zh": "在快照 s02（page）中找到的声明" }, "excerpt": "Information that is created by or for the US government on this site is within the public domain. Public domain information on the National Library of Medicine (NLM) Web pages may be freely distributed and copied.", "url": "https://www.ncbi.nlm.nih.gov/home/about/policies/", "verified_on": "2026-11-12", "snapshot_id": "s02", "observed": "page", "captured_by": "pipeline" }, { "location": "site-policy", "location_detail": { "en": "Statement found in snapshot s02 (page)", "zh": "在快照 s02（page）中找到的声明" }, "excerpt": "OMIM (see OMIM Copyright Status ), and PubChem. All persons reproducing, redistributing, or making commercial use of this information are expected to adhere to the terms and conditions asserted by the copyright holder.", "url": "https://www.ncbi.nlm.nih.gov/home/about/policies/", "verified_on": "2026-11-12", "snapshot_id": "s02", "observed": "page", "captured_by": "pipeline" }, { "location": "site-policy", "location_detail": { "en": "Statement found in snapshot s02 (page)", "zh": "在快照 s02（page）中找到的声明" }, "excerpt": "They are designed to provide and encourage access within the scientific community to sources of current and comprehensive information. Therefore, NCBI itself places no restrictions on the use or distribution of the data contained therein.", "url": "https://www.ncbi.nlm.nih.gov/home/about/policies/", "verified_on": "2026-11-12", "snapshot_id": "s02", "observed": "page", "captured_by": "pipeline" }, { "location": "site-policy", "location_detail": { "en": "Statement found in snapshot s02 (page)", "zh": "在快照 s02（page）中找到的声明" }, "excerpt": "Nor do we accept data when the submitter has requested restrictions on reuse or redistribution.", "url": "https://www.ncbi.nlm.nih.gov/home/about/policies/", "verified_on": "2026-11-12", "snapshot_id": "s02", "observed": "page", "captured_by": "pipeline" }, { "location": "site-policy", "location_detail": { "en": "Statement found in snapshot s02 (page)", "zh": "在快照 s02（page）中找到的声明" }, "excerpt": "However, some submitters of the original data (or the country of origin of such data) may claim patent, copyright, or other intellectual property rights in all or a portion of the data (that has been submitted).", "url": "https://www.ncbi.nlm.nih.gov/home/about/policies/", "verified_on": "2026-11-12", "snapshot_id": "s02", "observed": "page", "captured_by": "pipeline" }, { "location": "site-policy", "location_detail": { "en": "Statement found in snapshot s02 (page)", "zh": "在快照 s02（page）中找到的声明" }, "excerpt": "Therefore, NCBI cannot provide comment or unrestricted permission concerning the use, copying, or distribution of the information contained in the molecular databases.", "url": "https://www.ncbi.nlm.nih.gov/home/about/policies/", "verified_on": "2026-11-12", "snapshot_id": "s02", "observed": "page", "captured_by": "pipeline" }, { "location": "site-policy", "location_detail": { "en": "Statement found in snapshot s02 (page)", "zh": "在快照 s02（page）中找到的声明" }, "excerpt": "It is the responsibility of the user to examine the copyright and licensing restrictions of linked pages and to secure all necessary permissions.", "url": "https://www.ncbi.nlm.nih.gov/home/about/policies/", "verified_on": "2026-11-12", "snapshot_id": "s02", "observed": "page", "captured_by": "pipeline" }, { "location": "site-policy", "location_detail": { "en": "Statement found in snapshot s02 (page)", "zh": "在快照 s02（page）中找到的声明" }, "excerpt": "Make no more than 3 requests every 1 second.", "url": "https://www.ncbi.nlm.nih.gov/home/about/policies/", "verified_on": "2026-11-12", "snapshot_id": "s02", "observed": "page", "captured_by": "pipeline" } ], "license_parts": [ { "name": { "en": "main data", "zh": "主体数据" }, "spdx": "LicenseRef-PublicDomain", "status": "permissive", "separable": true, "evidence": { "excerpt": "Information that is created by or for the US government on this site is within the public domain. Public domain information on the National Library of Medicine (NLM) Web pages may be freely distributed and copied.", "url": "https://www.ncbi.nlm.nih.gov/home/about/policies/", "snapshot_id": "s02" } }, { "name": { "en": "PubChem", "zh": "PubChem" }, "spdx": "LicenseRef-PublicDomain", "status": "permissive", "separable": true, "evidence": { "excerpt": "OMIM (see OMIM Copyright Status ), and PubChem. All persons reproducing, redistributing, or making commercial use of this information are expected to adhere to the terms and conditions asserted by the copyright holder.", "url": "https://www.ncbi.nlm.nih.gov/home/about/policies/", "snapshot_id": "s02" } } ], "notes": { "en": "agency policy: Information that is created by or for the US government on this site is within the public domain. Public domain informat; national-law caveat: public-domain status follows the law of the publishing country and may differ elsewhere", "zh": "agency policy: Information that is created by or for the US government on this site is within the public domain. Public domain informat; national-law caveat: public-domain status follows the law of the publishing country and may differ elsewhere" } }, "license_status": "permissive", "hosting": "link-only", "hosting_reason": { "en": "License permissive: all parts permissive; conditions are the union of the parts. Link only.", "zh": "许可证宽松：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": [ { "en": "NCBI states it cannot assess third-party intellectual-property claims and cannot grant unrestricted permission to use, copy, or distribute the information in its molecular databases.", "zh": "NCBI 表示无法评估第三方的知识产权主张，也无法就其分子数据库信息的使用、复制或分发给出无限制许可。" } ], "preflight": { "status": "not-run" }, "access": { "mdexa_download": null, "external_urls": [ "https://pubchem.ncbi.nlm.nih.gov/", "https://www.ncbi.nlm.nih.gov/home/about/policies/" ], "notes": null }, "citation": { "text": null, "references": [] }, "verification_level": "partially-verified", "last_verified": "2026-11-14", "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": "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": "compound, substance, and bioassay record", "count": null, "count_as_of": null, "statement": { "text": { "en": "The text refers to PubChem records as Compound Summary, Substance Record, and BioAssay Record entries.", "zh": "文中把PubChem记录称为化合物摘要、物质记录和生物测定记录条目。" }, "evidence": [ { "location": "api-doc", "excerpt": "All or part of the data for an individual PubChem record may be downloaded in various file formats, using the Download button available on the top-right corner of a Compound Summary, Substance Record, or BioAssay Record page.", "url": "https://pubchem.ncbi.nlm.nih.gov/docs/downloads", "snapshot_id": "s08", "char_start": 809, "verified_on": "2026-11-13", "observed": "page", "captured_by": "browser-agent" } ] } } ], "coverage": [ { "text": { "en": "The text states that the data in PubChem comes from hundreds of data contributors.", "zh": "文中说明PubChem的数据来自数百个数据贡献者。" }, "evidence": [ { "location": "api-doc", "excerpt": "The data in PubChem comes from hundreds of data contributors (https://pubchem.ncbi.nlm.nih.gov/source/).", "url": "https://pubchem.ncbi.nlm.nih.gov/docs/downloads", "snapshot_id": "s08", "char_start": 468, "verified_on": "2026-11-13", "observed": "page", "captured_by": "browser-agent" } ] } ] }, "identifiers": { "schemes": [], "crosswalks": [], "mismatch_cases": [], "notes": [ { "text": { "en": "Substance (SID) holds depositor-submitted records; Compound (CID) holds unique structures derived from substances by standardization; BioAssay uses AIDs.", "zh": "Substance（SID）存放提交者原始记录；Compound（CID）是对物质做结构标准化后得到的唯一结构；BioAssay 用 AID。" }, "evidence": [ { "location": "peer-reviewed-paper", "excerpt": "Substance archives chemical descriptions submitted by individual data depositors and Compound stores unique chemical structures extracted from Substance through chemical structure standardization", "url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC11701573/", "snapshot_id": "s10", "char_start": 9512, "verified_on": "2026-11-14", "observed": "page", "source_work": { "title": "PubChem 2025 update", "authors_or_org": "Kim S, Chen J, Cheng T, et al., Bolton EE (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/PMC11701573/" } } ] }, { "text": { "en": "Hähnke, Kim and Bolton: standardization rejects 0.36% of substances (mainly invalid valences) and modifies 44% of the structures that pass, so a CID structure can differ from what the depositor submitted.", "zh": "Hähnke、Kim、Bolton：结构标准化拒收 0.36% 的物质（主要因价态无效），并修改了 44% 的通过结构；CID 的结构可能与提交者原始结构不同。" }, "evidence": [ { "location": "peer-reviewed-paper", "excerpt": "Of all structures that pass standardization, 44% are modified in the process", "url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC6086778/", "snapshot_id": "s15", "char_start": 5590, "verified_on": "2026-11-14", "observed": "page", "source_work": { "title": "PubChem chemical structure standardization", "authors_or_org": "Hähnke VD, Kim S, Bolton EE (Journal of Cheminformatics)", "date": "2018-08-10", "date_as_written": "2018-08-10", "source_type": "peer-reviewed-paper", "open_access": true, "doi_or_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC6086778/" } } ] }, { "text": { "en": "Records without discrete structures (biologics, minerals, UVCBs, polymers, glycans) cannot enter the Compound collection and so have no CID.", "zh": "没有离散结构的记录（生物制品、矿物、UVCB、聚合物、聚糖）无法进入 Compound 集合，因此没有 CID。" }, "evidence": [ { "location": "peer-reviewed-paper", "excerpt": "because some records in the Substance collection (e.g. biologics, minerals, UVCBs, polymers and glycans) do not have discrete chemical structures to standardize, they cannot be entered into the Compound collection.", "url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC11701573/", "snapshot_id": "s10", "char_start": 33944, "verified_on": "2026-11-14", "observed": "page", "source_work": { "title": "PubChem 2025 update", "authors_or_org": "Kim S, Chen J, Cheng T, et al., Bolton EE (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/PMC11701573/" } } ] } ] }, "access_methods": [ { "method": "web-api", "url": "https://pubchem.ncbi.nlm.nih.gov/docs/programmatic-access", "formats": [], "limits": [ { "text": { "en": "The usage policy asks that any user, application, or organization not make more than 5 requests per second to the PubChem web services.", "zh": "使用政策要求任何用户、应用程序或组织对PubChem Web服务的请求不超过每秒5次。" }, "evidence": [ { "location": "api-doc", "excerpt": "USAGE POLICY: Please note that PubChem web services run on a limited pool of servers shared by all PubChem users. We ask that any user, application, or organization not make more than 5 requests per second, in order to avoid overloading these servers.", "url": "https://pubchem.ncbi.nlm.nih.gov/docs/programmatic-access", "snapshot_id": "s07", "char_start": 49, "verified_on": "2026-11-13", "observed": "page", "captured_by": "browser-agent" } ] }, { "text": { "en": "The page states that API keys or whitelists to exceed these limits cannot be offered.", "zh": "该页面说明无法提供用于超出这些限制的API密钥或白名单。" }, "evidence": [ { "location": "api-doc", "excerpt": "We cannot offer API keys or whitelists to exceed these limits.", "url": "https://pubchem.ncbi.nlm.nih.gov/docs/programmatic-access", "snapshot_id": "s07", "char_start": 423, "verified_on": "2026-11-13", "observed": "page", "captured_by": "browser-agent" } ] }, { "text": { "en": "The NCBI page asks that no more than 3 requests be made every 1 second.", "zh": "NCBI页面要求每秒不超过3次请求。" }, "evidence": [ { "location": "terms-page", "excerpt": "Make no more than 3 requests every 1 second.", "url": "https://www.ncbi.nlm.nih.gov/home/about/policies/", "snapshot_id": "s02", "char_start": 8670, "verified_on": "2026-11-12", "observed": "page", "captured_by": "pipeline" } ] } ], "terms": { "same_as_card_license": false, "own_terms": { "commercial_use": "unstated", "redistribution": "unstated", "evidence": [ { "location": "api-doc", "excerpt": "PUG-REST, a Representational State Transfer (REST)-style web service that supplies specific bits of information on one or more PubChem records, and is a good place to start for most users.", "url": "https://pubchem.ncbi.nlm.nih.gov/docs/programmatic-access", "snapshot_id": "s07", "char_start": 797, "verified_on": "2026-11-13", "observed": "page", "captured_by": "browser-agent" } ] } }, "reachable": { "status": 200, "checked_on": "2026-11-14" } }, { "method": "web-api", "url": "https://pubchem.ncbi.nlm.nih.gov/docs/programmatic-access", "formats": [], "limits": [ { "text": { "en": "The usage policy asks that any user, application, or organization not make more than 5 requests per second to the PubChem web services.", "zh": "使用政策要求任何用户、应用程序或组织对PubChem Web服务的请求不超过每秒5次。" }, "evidence": [ { "location": "api-doc", "excerpt": "USAGE POLICY: Please note that PubChem web services run on a limited pool of servers shared by all PubChem users. We ask that any user, application, or organization not make more than 5 requests per second, in order to avoid overloading these servers.", "url": "https://pubchem.ncbi.nlm.nih.gov/docs/programmatic-access", "snapshot_id": "s07", "char_start": 49, "verified_on": "2026-11-13", "observed": "page", "captured_by": "browser-agent" } ] }, { "text": { "en": "The page states that API keys or whitelists to exceed these limits cannot be offered.", "zh": "该页面说明无法提供用于超出这些限制的API密钥或白名单。" }, "evidence": [ { "location": "api-doc", "excerpt": "We cannot offer API keys or whitelists to exceed these limits.", "url": "https://pubchem.ncbi.nlm.nih.gov/docs/programmatic-access", "snapshot_id": "s07", "char_start": 423, "verified_on": "2026-11-13", "observed": "page", "captured_by": "browser-agent" } ] }, { "text": { "en": "The NCBI page asks that no more than 3 requests be made every 1 second.", "zh": "NCBI页面要求每秒不超过3次请求。" }, "evidence": [ { "location": "terms-page", "excerpt": "Make no more than 3 requests every 1 second.", "url": "https://www.ncbi.nlm.nih.gov/home/about/policies/", "snapshot_id": "s02", "char_start": 8670, "verified_on": "2026-11-12", "observed": "page", "captured_by": "pipeline" } ] } ], "terms": { "same_as_card_license": false, "own_terms": { "commercial_use": "unstated", "redistribution": "unstated", "evidence": [ { "location": "api-doc", "excerpt": "PUG-View is a REST-style web service that provides full reports, including third-party textual annotation, for individual PubChem records.", "url": "https://pubchem.ncbi.nlm.nih.gov/docs/programmatic-access", "snapshot_id": "s07", "char_start": 996, "verified_on": "2026-11-13", "observed": "page", "captured_by": "browser-agent" } ] } }, "reachable": { "status": 200, "checked_on": "2026-11-14" } }, { "method": "web-api", "url": "https://pubchem.ncbi.nlm.nih.gov/docs/programmatic-access", "formats": [], "limits": [ { "text": { "en": "The usage policy asks that any user, application, or organization not make more than 5 requests per second to the PubChem web services.", "zh": "使用政策要求任何用户、应用程序或组织对PubChem Web服务的请求不超过每秒5次。" }, "evidence": [ { "location": "api-doc", "excerpt": "USAGE POLICY: Please note that PubChem web services run on a limited pool of servers shared by all PubChem users. We ask that any user, application, or organization not make more than 5 requests per second, in order to avoid overloading these servers.", "url": "https://pubchem.ncbi.nlm.nih.gov/docs/programmatic-access", "snapshot_id": "s07", "char_start": 49, "verified_on": "2026-11-13", "observed": "page", "captured_by": "browser-agent" } ] }, { "text": { "en": "The page states that API keys or whitelists to exceed these limits cannot be offered.", "zh": "该页面说明无法提供用于超出这些限制的API密钥或白名单。" }, "evidence": [ { "location": "api-doc", "excerpt": "We cannot offer API keys or whitelists to exceed these limits.", "url": "https://pubchem.ncbi.nlm.nih.gov/docs/programmatic-access", "snapshot_id": "s07", "char_start": 423, "verified_on": "2026-11-13", "observed": "page", "captured_by": "browser-agent" } ] }, { "text": { "en": "The NCBI page asks that no more than 3 requests be made every 1 second.", "zh": "NCBI页面要求每秒不超过3次请求。" }, "evidence": [ { "location": "terms-page", "excerpt": "Make no more than 3 requests every 1 second.", "url": "https://www.ncbi.nlm.nih.gov/home/about/policies/", "snapshot_id": "s02", "char_start": 8670, "verified_on": "2026-11-12", "observed": "page", "captured_by": "pipeline" } ] } ], "terms": { "same_as_card_license": false, "own_terms": { "commercial_use": "unstated", "redistribution": "unstated", "evidence": [ { "location": "api-doc", "excerpt": "This is a REST-style interface designed to access RDF-encoded PubChem data. See PubChemRDF for more details.", "url": "https://pubchem.ncbi.nlm.nih.gov/docs/programmatic-access", "snapshot_id": "s07", "char_start": 1162, "verified_on": "2026-11-13", "observed": "page", "captured_by": "browser-agent" } ] } }, "reachable": { "status": 200, "checked_on": "2026-11-14" } }, { "method": "bulk-download", "url": "https://pubchem.ncbi.nlm.nih.gov/docs/downloads", "formats": [], "limits": [ { "text": { "en": "The page states that exceptions may exist where licensing agreements prevent data contributors from allowing bulk downloads of some data sets.", "zh": "该页面说明，在许可协议使数据贡献者无法允许批量下载某些数据集的情况下，可能存在例外。" }, "evidence": [ { "location": "api-doc", "excerpt": "Exceptions may exist in cases where licensing agreements prevent our data contributors from allowing bulk downloads of some data sets.", "url": "https://pubchem.ncbi.nlm.nih.gov/docs/downloads", "snapshot_id": "s08", "char_start": 144, "verified_on": "2026-11-13", "observed": "page", "captured_by": "browser-agent" } ] } ], "terms": { "same_as_card_license": true, "own_terms": null }, "reachable": { "status": 200, "checked_on": "2026-11-14" } }, { "method": "web-ui-only", "url": "https://pubchem.ncbi.nlm.nih.gov/docs/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://pmc.ncbi.nlm.nih.gov/articles/PMC6030920/", "formats": [], "limits": [], "terms": { "same_as_card_license": true, "own_terms": null }, "statement": { "text": { "en": "PUG-REST usage limits: no more than 5 requests per second, 400 per minute, and 300 seconds of server running time per minute; violations can lead to temporary blocking.", "zh": "PUG-REST 使用限制：每秒不超过 5 次请求、每分钟不超过 400 次、每分钟服务器运行时间不超过 300 秒；违规可能被临时封禁。" }, "evidence": [ { "location": "peer-reviewed-paper", "excerpt": "No more than five requests per second.", "url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC6030920/", "snapshot_id": "s12", "char_start": 29221, "verified_on": "2026-11-14", "observed": "page", "source_work": { "title": "An update on PUG-REST: RESTful interface for programmatic access to PubChem", "authors_or_org": "Kim S, Thiessen PA, Cheng T, Yu B, Bolton EE (Nucleic Acids Research)", "date": "2018-07-01", "date_as_written": "2018-07-01", "source_type": "peer-reviewed-paper", "open_access": true, "doi_or_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC6030920/" } } ] }, "reachable": { "status": 200, "checked_on": "2026-11-14" } }, { "method": "bulk-download", "url": "https://ftp.ncbi.nlm.nih.gov/pubchem/README", "formats": [], "limits": [], "terms": { "same_as_card_license": true, "own_terms": null }, "statement": { "text": { "en": "Terms: NCBI places no restrictions on use of FTP data, but submitters may claim patent, copyright or other IP rights, which NCBI does not assess.", "zh": "条款：NCBI 自身对 FTP 数据的使用不设限制，但原始提交者可能主张专利、版权等权利，NCBI 不对此评估。" }, "evidence": [ { "location": "dataset-page", "excerpt": "some submitters of the original data may claim patent, copyright, or other intellectual property rights in all or a portion of the data they have submitted.", "url": "https://ftp.ncbi.nlm.nih.gov/pubchem/README", "snapshot_id": "s09", "char_start": 1850, "verified_on": "2026-11-14", "observed": "page", "source_work": { "title": "PubChem FTP Site README (Fair Use Disclaimer)", "authors_or_org": "NCBI / PubChem", "date": null, "date_as_written": null, "source_type": "official-page", "open_access": true, "doi_or_url": "https://ftp.ncbi.nlm.nih.gov/pubchem/README" } } ] }, "reachable": { "status": 200, "checked_on": "2026-11-14" } } ], "versioning": { "latest": null, "update_cycle": { "cycle": "not-stated", "statement": null }, "breaking_changes": [], "history_url": null, "notes": [ { "text": { "en": "PubChem has no numbered data releases; the FTP site provides full and incremental dumps for Compound and Substance.", "zh": "PubChem 没有编号数据版本；FTP 站点为 Compound 与 Substance 提供全量与增量转储。" }, "evidence": [ { "location": "dataset-page", "excerpt": "Full and incremental data dump for PubChem compounds (without annotations and 3-D conformer models).", "url": "https://ftp.ncbi.nlm.nih.gov/pubchem/README", "snapshot_id": "s09", "char_start": 424, "verified_on": "2026-11-14", "observed": "page", "source_work": { "title": "PubChem FTP Site README", "authors_or_org": "NCBI / PubChem", "date": null, "date_as_written": null, "source_type": "official-page", "open_access": true, "doi_or_url": "https://ftp.ncbi.nlm.nih.gov/pubchem/README" } } ] }, { "text": { "en": "The PubChem 2025 update paper reports >1000 data sources, 119 million compounds, 322 million substances and 295 million bioactivities.", "zh": "PubChem 2025 更新论文报告：数据来源 >1000 个，化合物 1.19 亿、物质 3.22 亿、生物活性 2.95 亿条。" }, "evidence": [ { "location": "peer-reviewed-paper", "excerpt": "PubChem contains >1000 data sources, 119 million compounds, 322 million substances and 295 million bioactivities.", "url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC11701573/", "snapshot_id": "s10", "char_start": 7744, "verified_on": "2026-11-14", "observed": "page", "source_work": { "title": "PubChem 2025 update", "authors_or_org": "Kim S, Chen J, Cheng T, et al., Bolton EE (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/PMC11701573/" } } ] }, { "text": { "en": "Some derived content, such as the consolidated literature panel, is updated weekly.", "zh": "部分衍生内容（如整合文献面板）每周更新。" }, "evidence": [ { "location": "peer-reviewed-paper", "excerpt": "The content in the consolidated literature panel is updated weekly.", "url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC11701573/", "snapshot_id": "s10", "char_start": 27620, "verified_on": "2026-11-14", "observed": "page", "source_work": { "title": "PubChem 2025 update", "authors_or_org": "Kim S, Chen J, Cheng T, et al., Bolton EE (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/PMC11701573/" } } ] } ] }, "known_defects": [ { "kind": "other", "statement": { "text": { "en": "Butkiewicz et al.: PubChem primary HTS screens contain many false-positive hits that are inactive in confirmatory assays; they built benchmark sets from confirmatory screens after manual verification.", "zh": "Butkiewicz 等：PubChem 初筛高通量数据含大量在确证实验中无活性的假阳性；他们在人工核验后以确证筛选构建基准集。" }, "evidence": [ { "location": "peer-reviewed-paper", "excerpt": "Primary screens often include many false-positive hit compounds which display a response in initial assay experiments but are inactive in confirmatory experiments.", "url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC3759399/", "snapshot_id": "s16", "char_start": 16335, "verified_on": "2026-11-14", "observed": "page", "source_work": { "title": "Benchmarking ligand-based virtual High-Throughput Screening with the PubChem database", "authors_or_org": "Butkiewicz M, Lowe EW, Mueller R, Mendenhall JL, Teixeira PL, Weaver CD, Meiler J (Molecules)", "date": "2013-01-08", "date_as_written": "2013-01-08", "source_type": "peer-reviewed-paper", "open_access": true, "doi_or_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC3759399/" } } ] }, "source_kind": "peer-reviewed-paper", "scope": null, "attribution": { "who": "Butkiewicz M, Lowe EW, Mueller R, Mendenhall JL, Teixeira PL, Weaver CD, Meiler J (Molecules)", "when": "2013-01-08", "source_type": "peer-reviewed-paper", "title": "Benchmarking ligand-based virtual High-Throughput Screening with the PubChem database" }, "correction_entrance": "Report an error through the publisher or the authors: https://pmc.ncbi.nlm.nih.gov/articles/PMC3759399/" } ], "fit": { "suited_for": [ { "text": { "en": "The molecular databases are described as designed to provide and encourage access within the scientific community to sources of current and comprehensive information.", "zh": "这些分子数据库被描述为旨在为科学界提供并鼓励获取最新且全面的信息来源。" }, "evidence": [ { "location": "terms-page", "excerpt": "They are designed to provide and encourage access within the scientific community to sources of current and comprehensive information.", "url": "https://www.ncbi.nlm.nih.gov/home/about/policies/", "snapshot_id": "s02", "char_start": 4744, "verified_on": "2026-11-12", "observed": "page", "captured_by": "pipeline" } ] } ], "not_suited_for": [] }, "commercial_access": { "route": "contact-publisher", "url": "https://pubchem.ncbi.nlm.nih.gov/docs/downloads", "statement": { "text": { "en": "The page states that a data source may provide explicit data license information and that one should check with the PubChem data source for the most current data licensing information.", "zh": "该页面说明数据来源可能提供明确的数据许可信息，并应就最新的数据许可信息向PubChem数据来源查询。" }, "evidence": [ { "location": "api-doc", "excerpt": "A data source may provide explicit data license information. One should check with the PubChem data source for the most current data licensing information.", "url": "https://pubchem.ncbi.nlm.nih.gov/docs/downloads", "snapshot_id": "s08", "char_start": 573, "verified_on": "2026-11-13", "observed": "page", "captured_by": "browser-agent" } ] } }, "completeness": { "core_complete": false, "literature_defects": 1, "reachable_access": 7, "meets_practical_bar": false, "gaps": [ { "field": "versioning.latest", "note": "未找到有出处的说明 / no sourced statement found" }, { "field": "versioning.update_cycle", "note": "未找到有出处的说明 / no sourced statement found" }, { "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" } ] } }, "access_recipe": { "verified_on": "2026-11-14", "latest_release": null, "files": [], "api": [ { "name": "E-utilities", "url_template": "https://eutils.ncbi.nlm.nih.gov", "required_params": [], "example_request": null, "key_response_fields": [], "evidence": { "excerpt": "Send E-utilities requests to https://eutils.ncbi.nlm.nih.gov , not the standard NCBI Web address.", "snapshot_id": "s02", "url": "https://www.ncbi.nlm.nih.gov/home/about/policies/" } } ], "registration": null, "bulk_download": [], "gaps": [ "no direct file address was found on the official pages we hold", "no latest release/version stated on the 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：BindingDB (https://mdexa.com/zh/datasets/bindingdb/)；ChEMBL (https://mdexa.com/zh/datasets/chembl/)；jablonkagroup/chempile-lift (https://mdexa.com/zh/datasets/chempile-lift/)。", "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": "BindingDB", "url": "https://mdexa.com/zh/datasets/bindingdb/", "json": "https://mdexa.com/zh/datasets/bindingdb.json" }, { "name": "ChEMBL", "url": "https://mdexa.com/zh/datasets/chembl/", "json": "https://mdexa.com/zh/datasets/chembl.json" }, { "name": "jablonkagroup/chempile-lift", "url": "https://mdexa.com/zh/datasets/chempile-lift/", "json": "https://mdexa.com/zh/datasets/chempile-lift.json" } ] } }