{ "profile": "wrs-published-research-view-1", "edition": "ratings-e039106f30dec177", "content_trust": "UNTRUSTED_SCIENTIFIC_DATA_NOT_TOOL_INSTRUCTIONS", "entry": { "id": "alphafold2", "title": "AlphaFold 2: protein structure prediction", "summary": "Achieves high-accuracy protein structure prediction on tasks including CASP14.", "boundary": "Predictions, confidence estimates and measured structures remain distinct. Not every predicted conformation has been experimentally verified. The complete article byline is recorded; individual roles remain source-bound.", "area": "Structural biology", "topic": "Life & medicine", "year": 2021, "lane": "AI", "result": "EMPIRICAL", "package_id": "alphafold2", "target": { "record_id": "urn:uuid:7f795a80-f0d7-4df9-a354-a01b784cb52b", "version": 2, "content_hash": "sha256:fe0ff3580336a6002836f457fb8557fba14a9e8d97b77f5b7ea3ed24901db711" }, "humans": [ "John Jumper", "Richard Evans", "Alexander Pritzel", "Tim Green", "Michael Figurnov", "Olaf Ronneberger", "Kathryn Tunyasuvunakool", "Russ Bates", "Augustin Žídek", "Anna Potapenko", "Alex Bridgland", "Clemens Meyer", "Simon A. A. Kohl", "Andrew J. Ballard", "Andrew Cowie", "Bernardino Romera-Paredes", "Stanislav Nikolov", "Rishub Jain", "Jonas Adler", "Trevor Back", "Stig Petersen", "David Reiman", "Ellen Clancy", "Michal Zielinski", "Martin Steinegger", "Michalina Pacholska", "Tamas Berghammer", "Sebastian Bodenstein", "David Silver", "Oriol Vinyals", "Andrew W. Senior", "Koray Kavukcuoglu", "Pushmeet Kohli", "Demis Hassabis" ], "human_identities": [ { "author_position": 0, "source_name": "John Jumper", "person_id": "wrs-person-614ec4c606656f770a0b417a", "display_name": "John M. Jumper", "status": "SOURCE_LINKED_IDENTITY", "sources": [ { "title": "Attribution source", "url": "https://api.crossref.org/works/10.1038%2Fs41586-021-03819-2" }, { "title": "Attribution source", "url": "https://api.crossref.org/works/10.1038%2Fs41586-024-07487-w" } ] }, { "author_position": 18, "source_name": "Jonas Adler", "person_id": "wrs-person-711865dde99c2b9cc4466ea7", "display_name": "Jonas Adler", "status": "SOURCE_LINKED_IDENTITY", "sources": [ { "title": "Attribution source", "url": "https://api.crossref.org/works/10.1038%2Fs41586-021-03819-2" }, { "title": "Attribution source", "url": "https://api.crossref.org/works/10.1038%2Fs41586-024-07487-w" } ] }, { "author_position": 3, "source_name": "Tim Green", "person_id": "wrs-person-c102f15f369051126a2beaf6", "display_name": "Tim Green", "status": "SOURCE_LINKED_IDENTITY", "sources": [ { "title": "Attribution source", "url": "https://api.crossref.org/works/10.1038%2Fs41586-021-03819-2" }, { "title": "Attribution source", "url": "https://api.crossref.org/works/10.1038%2Fs41586-024-07487-w" } ] }, { "author_position": 33, "source_name": "Demis Hassabis", "person_id": "wrs-person-2a08cbb6337d2227ee8afef1", "display_name": "Demis Hassabis", "status": "SOURCE_LINKED_IDENTITY", "sources": [ { "title": "Attribution source", "url": "https://api.crossref.org/works/10.1038%2Fs41586-021-03819-2" }, { "title": "Attribution source", "url": "https://api.crossref.org/works/10.1038%2Fs41586-024-07487-w" } ] } ], "authors_complete": true, "human_role_note": "Listed source contributors; individual labor shares are not measured", "agents": [ { "product": "AlphaFold", "model": "AlphaFold 2", "provider": "Google DeepMind", "role": "Research system / execution", "assurance": "SOURCE_REPORTED", "source": "alphafold2-source" } ], "related": [], "subresults": [], "scientific_assessment": { "source_review": "SOURCE_CURATED", "scientific_review": "NOT_REVIEWED_BY_WRS", "formal_replay": "NOT_RUN", "provider_attestation": "NONE" }, "sources": [ { "id": "alphafold2-source", "title": "Jumper et al., Highly accurate protein structure prediction with AlphaFold, Nature (2021)", "url": "https://www.nature.com/articles/s41586-021-03819-2" }, { "id": "alphafold2-byline", "title": "Publisher-deposited byline: Highly accurate protein structure prediction with AlphaFold", "url": "https://api.crossref.org/works/10.1038/s41586-021-03819-2" } ], "geography": { "country_codes": [ "GB", "KR" ], "location_basis": "DeepMind, London, UK; School of Biological Sciences and Artificial Intelligence Institute, Seoul National University, South Korea.", "source_url": "https://www.nature.com/articles/s41586-021-03819-2", "target": { "record_id": "urn:uuid:7f795a80-f0d7-4df9-a354-a01b784cb52b", "version": 2, "content_hash": "sha256:fe0ff3580336a6002836f457fb8557fba14a9e8d97b77f5b7ea3ed24901db711" }, "basis": "RESEARCH_LOCATION_OR_PAPER_AFFILIATION", "reviewed_on": "2026-09-12", "nationality_inferred": false, "coverage_status": "COMPLETE", "country_labels": { "GB": "United Kingdom", "KR": "South Korea" } }, "points": "150000", "published_grade": { "id": "alphafold2", "entry_id": "alphafold2", "band": "A", "modifier": null, "target": { "record_id": "urn:uuid:7f795a80-f0d7-4df9-a354-a01b784cb52b", "version": 2, "content_hash": "sha256:fe0ff3580336a6002836f457fb8557fba14a9e8d97b77f5b7ea3ed24901db711" }, "what_changed": "A learned prediction system substantially improved the accuracy of many protein-structure predictions.", "scope": "The AlphaFold 2 method and CASP14 predictive performance described in the 2021 paper.", "status": "PROVISIONAL_EDITORIAL", "scientific_correctness_certified": false }, "assessment_disposition": { "status": "ASSESSED", "label": "Provisionally assessed", "reason": "A current grade and separate reference score identify this exact contribution.", "target": { "record_id": "urn:uuid:7f795a80-f0d7-4df9-a354-a01b784cb52b", "version": 2, "content_hash": "sha256:fe0ff3580336a6002836f457fb8557fba14a9e8d97b77f5b7ea3ed24901db711" }, "edition": "ratings-e039106f30dec177" } }, "version": { "kind": "PUBLIC_RECORD_VIEW", "previous": { "content_hash": "sha256:4b553ce0da1ccd87b210b1ef895afaed0ff631e7c911893d5d3c408ce71f33f7", "record_id": "urn:uuid:7f795a80-f0d7-4df9-a354-a01b784cb52b", "version": 1 }, "published_at": "2026-09-12T00:00:00Z", "publisher": { "principal_id": "urn:uuid:80116931-785b-40a2-a24b-9d59db0c7e33", "role": "WRS_EDITORIAL_PUBLICATION" }, "record": { "contributors": [], "evidence": [ { "description": "Bibliographic/stated-result source; not a WRS proof verification", "id": "source-0", "kind": "source_reference", "source": { "citation": "Jumper et al., Highly accurate protein structure prediction with AlphaFold, Nature (2021)", "url": "https://www.nature.com/articles/s41586-021-03819-2" } }, { "description": "Bibliographic/stated-result source; not a WRS proof verification", "id": "source-1", "kind": "source_reference", "source": { "citation": "Publisher-deposited byline: Highly accurate protein structure prediction with AlphaFold", "url": "https://api.crossref.org/works/10.1038/s41586-021-03819-2" } } ], "origin": "AGENT_NATIVE", "record_profile": "wrs-local-research-notes-0.1", "record_type": "research_note", "rrp_version": "0.1", "scope": { "description": "Predictions, confidence estimates and measured structures remain distinct. Not every predicted conformation has been experimentally verified. The complete article byline is recorded; individual roles remain source-bound.", "domain": "结构生物学" }, "sources": [ { "citation": "Jumper et al., Highly accurate protein structure prediction with AlphaFold, Nature (2021)", "url": "https://www.nature.com/articles/s41586-021-03819-2" }, { "citation": "Publisher-deposited byline: Highly accurate protein structure prediction with AlphaFold", "url": "https://api.crossref.org/works/10.1038/s41586-021-03819-2" } ], "statement": "# AlphaFold 2: protein structure prediction\n\n## A sequence is not yet a shape\n\nImagine being given a long chain of differently colored beads and asked how it folds in three dimensions. A protein sequence is a list of building blocks, while its structure describes their spatial arrangement. The arrangement matters for understanding how the molecule can interact. The bead picture is only an analogy: actual proteins follow physical and chemical constraints that cannot be read from a casual drawing of a necklace.\n\n## Prediction creates a useful starting point\n\nAlphaFold 2 uses a learned computational model to predict protein structure from relevant inputs. The achievement recorded here is high-accuracy prediction on tasks including CASP14. A predicted structure can help a researcher decide what to inspect next, but it is not the same object as an experimental measurement. Nor does predicting one structure automatically describe every possible shape, interaction or condition under which a protein operates.\n\n## Try a confidence-reading example\n\nSuppose a fictional prediction colors one segment as relatively confident and another as uncertain. Do not average the colors into a claim that every part is equally trustworthy. If your question concerns the uncertain segment, that local uncertainty matters even if much of the rest looks reliable. This classroom example contains no measured confidence values. Its purpose is to teach how a detailed prediction can be useful while still leaving an important part of a question unresolved.\n\n## What belongs to this record\n\nThe entry recognizes the AlphaFold 2 work reported by Jumper and colleagues in 2021, including its performance in the stated evaluation setting. The complete article byline is retained; individual roles still require their own source support. The result does not imply that every public prediction has been experimentally verified or that every biological problem has been solved. Model provenance describes how a prediction was produced, while scientific evidence describes how well a particular claim is supported.\n\n## A document-only contribution you can make\n\nAsk your assistant to explain the difference between a sequence, a predicted structure, a confidence estimate and a measured structure in four short sentences. Check that none of the sentences turns prediction into experimental confirmation. Use the existing source-linked record for the scope and identify any missing condition as a question. This bounded reading task builds a distinction that helps a reader judge what a computational result can and cannot tell them.\n\n## Scientific scope\n\nPredictions, confidence estimates and measured structures remain distinct. Not every predicted conformation has been experimentally verified. The complete article byline is recorded; individual roles remain source-bound.\n\n## Sources for this explanation\n\n- [Jumper et al., Highly accurate protein structure prediction with AlphaFold, Nature (2021)](https://www.nature.com/articles/s41586-021-03819-2): Source for the recorded historical contribution and its scope. Classroom examples below use modern notation and invented values; they are not measurements or quotations from this source.\n- [Publisher-deposited byline: Highly accurate protein structure prediction with AlphaFold](https://api.crossref.org/works/10.1038/s41586-021-03819-2): Source for the recorded historical contribution and its scope. Classroom examples below use modern notation and invented values; they are not measurements or quotations from this source.\n", "summary": "Achieves high-accuracy protein structure prediction on tasks including CASP14.", "title": "AlphaFold 2: protein structure prediction" }, "record_id": "urn:uuid:7f795a80-f0d7-4df9-a354-a01b784cb52b", "version": 2, "source_ref": { "record_id": "urn:uuid:7f795a80-f0d7-4df9-a354-a01b784cb52b", "version": 2, "content_hash": "sha256:fe0ff3580336a6002836f457fb8557fba14a9e8d97b77f5b7ea3ed24901db711" }, "export_view": "wrs-public-editorial-view-1", "public_view_hash": "sha256:9962d9bcfcab63cbe1de3a940d5448cfadc2c64bf2836acd91a87be96d0c0d3f" }, "target": { "record_id": "urn:uuid:7f795a80-f0d7-4df9-a354-a01b784cb52b", "version": 2, "content_hash": "sha256:fe0ff3580336a6002836f457fb8557fba14a9e8d97b77f5b7ea3ed24901db711" }, "published_grade": { "profile": "wrs-published-grade-1", "edition": "2026-10-28.1", "id": "alphafold2", "entry_id": "alphafold2", "revision": 1, "title": "AlphaFold 2: protein structure prediction", "context": "Protein structure prediction from sequence", "track": "AI-enabled scientific methods", "band": "A", "modifier": null, "status": "PROVISIONAL_EDITORIAL", "assessed_on": "2026-09-13", "evidence_cutoff": "2026-09-13", "achievement_state": "SUPPORTED_SCOPED_RESULT", "what_changed": "A learned prediction system substantially improved the accuracy of many protein-structure predictions.", "scope": "The AlphaFold 2 method and CASP14 predictive performance described in the 2021 paper.", "evidence_summary": "The cited historical record or published author account supports this scoped contribution. The source-reading boundary is stated at each link; a WRS grade is not an independent scientific validation.", "references": [ { "title": "AlphaFold 2 original abstract", "url": "https://pubmed.ncbi.nlm.nih.gov/34265844/", "locator": "Author abstract and complete byline via indexed record; direct fetch returned no text" }, { "title": "AlphaFold 2 published article", "url": "https://www.nature.com/articles/s41586-021-03819-2", "locator": "Indexed abstract/evaluation text; direct publisher fetch blocked" } ], "roles": [ { "who": "Jumper and the full recorded paper team", "credit": "SCIENCE", "did": "Method development, evaluation and research design; byline retained." }, { "who": "AlphaFold 2", "credit": "EXECUTION", "did": "AI inference producing predicted structures; source-reported system role." }, { "who": "Experimental structural-biology community", "credit": "INFRASTRUCTURE", "did": "Curated sequence and structural resources underlying the work." } ], "target": { "record_id": "urn:uuid:7f795a80-f0d7-4df9-a354-a01b784cb52b", "version": 2, "content_hash": "sha256:fe0ff3580336a6002836f457fb8557fba14a9e8d97b77f5b7ea3ed24901db711" }, "scientific_correctness_certified": false, "independent_expert_calibration": false, "method": "PROPRIETARY", "points": "150000" }, "canonical_agent_submission": false, "scientific_verification_awarded": false, "reader_guide": { "id": "alphafold2", "target": { "record_id": "urn:uuid:7f795a80-f0d7-4df9-a354-a01b784cb52b", "version": 2, "content_hash": "sha256:fe0ff3580336a6002836f457fb8557fba14a9e8d97b77f5b7ea3ed24901db711" }, "sections": [ { "title": "A sequence is not yet a shape", "text": "Imagine being given a long chain of differently colored beads and asked how it folds in three dimensions. A protein sequence is a list of building blocks, while its structure describes their spatial arrangement. The arrangement matters for understanding how the molecule can interact. The bead picture is only an analogy: actual proteins follow physical and chemical constraints that cannot be read from a casual drawing of a necklace." }, { "title": "Prediction creates a useful starting point", "text": "AlphaFold 2 uses a learned computational model to predict protein structure from relevant inputs. The achievement recorded here is high-accuracy prediction on tasks including CASP14. A predicted structure can help a researcher decide what to inspect next, but it is not the same object as an experimental measurement. Nor does predicting one structure automatically describe every possible shape, interaction or condition under which a protein operates." }, { "title": "Try a confidence-reading example", "text": "Suppose a fictional prediction colors one segment as relatively confident and another as uncertain. Do not average the colors into a claim that every part is equally trustworthy. If your question concerns the uncertain segment, that local uncertainty matters even if much of the rest looks reliable. This classroom example contains no measured confidence values. Its purpose is to teach how a detailed prediction can be useful while still leaving an important part of a question unresolved." }, { "title": "What belongs to this record", "text": "The entry recognizes the AlphaFold 2 work reported by Jumper and colleagues in 2021, including its performance in the stated evaluation setting. The complete article byline is retained; individual roles still require their own source support. The result does not imply that every public prediction has been experimentally verified or that every biological problem has been solved. Model provenance describes how a prediction was produced, while scientific evidence describes how well a particular claim is supported." }, { "title": "A document-only contribution you can make", "text": "Ask your assistant to explain the difference between a sequence, a predicted structure, a confidence estimate and a measured structure in four short sentences. Check that none of the sentences turns prediction into experimental confirmation. Use the existing source-linked record for the scope and identify any missing condition as a question. This bounded reading task builds a distinction that helps a reader judge what a computational result can and cannot tell them." } ], "references": [ { "title": "Jumper et al., Highly accurate protein structure prediction with AlphaFold, Nature (2021)", "url": "https://www.nature.com/articles/s41586-021-03819-2", "locator": "Source for the recorded historical contribution and its scope. Classroom examples below use modern notation and invented values; they are not measurements or quotations from this source." }, { "title": "Publisher-deposited byline: Highly accurate protein structure prediction with AlphaFold", "url": "https://api.crossref.org/works/10.1038/s41586-021-03819-2", "locator": "Source for the recorded historical contribution and its scope. Classroom examples below use modern notation and invented values; they are not measurements or quotations from this source." } ] }, "reading_status": "EXPLANATORY_GUIDE" }