{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T21:12:04Z","timestamp":1776114724190,"version":"3.50.1"},"reference-count":27,"publisher":"Oxford University Press (OUP)","issue":"D1","license":[{"start":{"date-parts":[[2021,12,1]],"date-time":"2021-12-01T00:00:00Z","timestamp":1638316800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["R01-GM073109"],"award-info":[{"award-number":["R01-GM073109"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000015","name":"U.S. Department of Energy","doi-asserted-by":"publisher","award":["DE-AC02-05CH11231"],"award-info":[{"award-number":["DE-AC02-05CH11231"]}],"id":[{"id":"10.13039\/100000015","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,1,7]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>The Structural Classification of Proteins\u2014extended (SCOPe, https:\/\/scop.berkeley.edu) knowledgebase aims to provide an accurate, detailed, and comprehensive description of the structural and evolutionary relationships amongst the majority of proteins of known structure, along with resources for analyzing the protein structures and their sequences. Structures from the PDB are divided into domains and classified using a combination of manual curation and highly precise automated methods. In the current release of SCOPe, 2.08, we have developed search and display tools for analysis of genetic variants we mapped to structures classified in SCOPe. In order to improve the utility of SCOPe to automated methods such as deep learning classifiers that rely on multiple alignment of sequences of homologous proteins, we have introduced new machine-parseable annotations that indicate aberrant structures as well as domains that are distinguished by a smaller repeat unit. We also classified structures from 74 of the largest Pfam families not previously classified in SCOPe, and we improved our algorithm to remove N- and C-terminal cloning, expression and purification sequences from SCOPe domains. SCOPe 2.08-stable classifies 106 976 PDB entries (about 60% of PDB entries).<\/jats:p>","DOI":"10.1093\/nar\/gkab1054","type":"journal-article","created":{"date-parts":[[2021,11,30]],"date-time":"2021-11-30T22:39:01Z","timestamp":1638311941000},"page":"D553-D559","source":"Crossref","is-referenced-by-count":171,"title":["SCOPe: improvements to the structural classification of proteins \u2013 extended database to facilitate variant interpretation and machine learning"],"prefix":"10.1093","volume":"50","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5153-9079","authenticated-orcid":false,"given":"John-Marc","family":"Chandonia","sequence":"first","affiliation":[{"name":"Environmental Genomics and Systems Biology Division, Lawrence Berkeley National Laboratory, Berkeley, CA 94720, USA"},{"name":"Molecular Biophysics and Integrated Bioimaging Division, Lawrence Berkeley National Laboratory, Berkeley, CA 94720, USA"},{"name":"Department of Plant and Microbial Biology, University of California, Berkeley, CA 94720, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8934-0762","authenticated-orcid":false,"given":"Lindsey","family":"Guan","sequence":"additional","affiliation":[{"name":"Department of Plant and Microbial Biology, University of California, Berkeley, CA 94720, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0033-193X","authenticated-orcid":false,"given":"Shiangyi","family":"Lin","sequence":"additional","affiliation":[{"name":"College of Engineering, University of California, Berkeley, CA 94720, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4799-4535","authenticated-orcid":false,"given":"Changhua","family":"Yu","sequence":"additional","affiliation":[{"name":"Department of Plant and Microbial Biology, University of California, Berkeley, CA 94720, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2828-858X","authenticated-orcid":false,"given":"Naomi\u00a0K","family":"Fox","sequence":"additional","affiliation":[{"name":"Environmental Genomics and Systems Biology Division, Lawrence Berkeley National Laboratory, Berkeley, CA 94720, USA"},{"name":"Molecular Biophysics and Integrated Bioimaging Division, Lawrence Berkeley National Laboratory, Berkeley, CA 94720, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7559-6185","authenticated-orcid":false,"given":"Steven\u00a0E","family":"Brenner","sequence":"additional","affiliation":[{"name":"Environmental Genomics and Systems Biology Division, Lawrence Berkeley National Laboratory, Berkeley, CA 94720, USA"},{"name":"Department of Plant and Microbial Biology, University of California, Berkeley, CA 94720, USA"},{"name":"College of Engineering, University of California, Berkeley, CA 94720, USA"}]}],"member":"286","published-online":{"date-parts":[[2021,12,1]]},"reference":[{"key":"2022010507360586200_B1","doi-asserted-by":"crossref","first-page":"536","DOI":"10.1016\/S0022-2836(05)80134-2","article-title":"SCOP: a structural classification of proteins database for the investigation of sequences and structures","volume":"247","author":"Murzin","year":"1995","journal-title":"J. Mol. Biol."},{"key":"2022010507360586200_B2","doi-asserted-by":"crossref","first-page":"264","DOI":"10.1093\/nar\/30.1.264","article-title":"SCOP database in 2002: refinements accommodate structural genomics","volume":"30","author":"Lo\u00a0Conte","year":"2002","journal-title":"Nucleic Acids Res."},{"key":"2022010507360586200_B3","doi-asserted-by":"crossref","first-page":"D226","DOI":"10.1093\/nar\/gkh039","article-title":"SCOP database in 2004: refinements integrate structure and sequence family data","volume":"32","author":"Andreeva","year":"2004","journal-title":"Nucleic Acids Res."},{"key":"2022010507360586200_B4","doi-asserted-by":"crossref","first-page":"D419","DOI":"10.1093\/nar\/gkm993","article-title":"Data growth and its impact on the SCOP database: new developments","volume":"36","author":"Andreeva","year":"2008","journal-title":"Nucleic Acids Res."},{"key":"2022010507360586200_B5","doi-asserted-by":"crossref","first-page":"D304","DOI":"10.1093\/nar\/gkt1240","article-title":"SCOPe: Structural Classification of Proteins\u2013extended, integrating SCOP and ASTRAL data and classification of new structures","volume":"42","author":"Fox","year":"2014","journal-title":"Nucleic Acids Res."},{"key":"2022010507360586200_B6","doi-asserted-by":"crossref","first-page":"348","DOI":"10.1016\/j.jmb.2016.11.023","article-title":"SCOPe: manual curation and artifact removal in the structural classification of proteins - extended database","volume":"429","author":"Chandonia","year":"2017","journal-title":"J. Mol. Biol."},{"key":"2022010507360586200_B7","doi-asserted-by":"crossref","first-page":"D475","DOI":"10.1093\/nar\/gky1134","article-title":"SCOPe: classification of large macromolecular structures in the structural classification of proteins-extended database","volume":"47","author":"Chandonia","year":"2019","journal-title":"Nucleic Acids Res."},{"key":"2022010507360586200_B8","doi-asserted-by":"crossref","first-page":"235","DOI":"10.1093\/nar\/28.1.235","article-title":"The Protein Data Bank","volume":"28","author":"Berman","year":"2000","journal-title":"Nucleic Acids Res."},{"key":"2022010507360586200_B9","doi-asserted-by":"crossref","first-page":"D437","DOI":"10.1093\/nar\/gkaa1038","article-title":"RCSB Protein Data Bank: powerful new tools for exploring 3D structures of biological macromolecules for basic and applied research and education in fundamental biology, biomedicine, biotechnology, bioengineering and energy sciences","volume":"49","author":"Burley","year":"2021","journal-title":"Nucleic Acids Res."},{"key":"2022010507360586200_B10","doi-asserted-by":"crossref","first-page":"D376","DOI":"10.1093\/nar\/gkz1064","article-title":"The SCOP database in 2020: expanded classification of representative family and superfamily domains of known protein structures","volume":"48","author":"Andreeva","year":"2020","journal-title":"Nucleic Acids Res."},{"key":"2022010507360586200_B11","doi-asserted-by":"crossref","first-page":"D266","DOI":"10.1093\/nar\/gkaa1079","article-title":"CATH: increased structural coverage of functional space","volume":"49","author":"Sillitoe","year":"2021","journal-title":"Nucleic Acids Res."},{"key":"2022010507360586200_B12","doi-asserted-by":"crossref","first-page":"e1003926","DOI":"10.1371\/journal.pcbi.1003926","article-title":"ECOD: an evolutionary classification of protein domains","volume":"10","author":"Cheng","year":"2014","journal-title":"PLoS Comput Biol"},{"key":"2022010507360586200_B13","doi-asserted-by":"crossref","first-page":"D412","DOI":"10.1093\/nar\/gkaa913","article-title":"Pfam: The protein families database in 2021","volume":"49","author":"Mistry","year":"2021","journal-title":"Nucleic Acids Res."},{"key":"2022010507360586200_B14","doi-asserted-by":"crossref","first-page":"2025","DOI":"10.1002\/prot.24915","article-title":"The value of protein structure classification information\u2014surveying the scientific literature","volume":"83","author":"Fox","year":"2015","journal-title":"Proteins Struct. Funct. Bioinforma."},{"key":"2022010507360586200_B15","doi-asserted-by":"crossref","first-page":"552","DOI":"10.1038\/261552a0","article-title":"Structural patterns in globular proteins","volume":"261","author":"Levitt","year":"1976","journal-title":"Nature"},{"key":"2022010507360586200_B16","doi-asserted-by":"crossref","first-page":"D189","DOI":"10.1093\/nar\/gkh034","article-title":"The ASTRAL compendium in 2004","volume":"32","author":"Chandonia","year":"2004","journal-title":"Nucleic Acids Res."},{"key":"2022010507360586200_B17","doi-asserted-by":"crossref","first-page":"160018","DOI":"10.1038\/sdata.2016.18","article-title":"The FAIR Guiding Principles for scientific data management and stewardship","volume":"3","author":"Wilkinson","year":"2016","journal-title":"Sci. Data"},{"key":"2022010507360586200_B18","doi-asserted-by":"crossref","first-page":"141","DOI":"10.1038\/nrg2273","article-title":"Understanding the molecular machinery of genetics through 3D structures","volume":"9","author":"Laskowski","year":"2008","journal-title":"Nat. Rev. Genet."},{"key":"2022010507360586200_B19","doi-asserted-by":"crossref","first-page":"155","DOI":"10.1084\/jem.20150888","article-title":"A novel human autoimmune syndrome caused by combined hypomorphic and activating mutations in ZAP-70","volume":"213","author":"Chan","year":"2016","journal-title":"J. Exp. Med."},{"key":"2022010507360586200_B20","doi-asserted-by":"crossref","first-page":"122","DOI":"10.1186\/s13059-016-0974-4","article-title":"The Ensembl Variant Effect Predictor","volume":"17","author":"McLaren","year":"2016","journal-title":"Genome Biol."},{"key":"2022010507360586200_B21","doi-asserted-by":"crossref","first-page":"D480","DOI":"10.1093\/nar\/gkaa1100","article-title":"UniProt: the universal protein knowledgebase in 2021","volume":"49","author":"The UniProt Consortium","year":"2021","journal-title":"Nucleic Acids Res."},{"key":"2022010507360586200_B22","doi-asserted-by":"crossref","first-page":"D482","DOI":"10.1093\/nar\/gky1114","article-title":"SIFTS: updated Structure Integration with Function, Taxonomy and Sequences resource allows 40-fold increase in coverage of structure-based annotations for proteins","volume":"47","author":"Dana","year":"2019","journal-title":"Nucleic Acids Res."},{"key":"2022010507360586200_B23","doi-asserted-by":"crossref","first-page":"254","DOI":"10.1093\/nar\/28.1.254","article-title":"The ASTRAL compendium for protein structure and sequence analysis","volume":"28","author":"Brenner","year":"2000","journal-title":"Nucleic Acids Res."},{"key":"2022010507360586200_B24","doi-asserted-by":"crossref","first-page":"bar042","DOI":"10.1093\/database\/bar042","article-title":"3DSwap: curated knowledgebase of proteins involved in 3D domain swapping","volume":"2011","author":"Shameer","year":"2011","journal-title":"Database"},{"key":"2022010507360586200_B25","doi-asserted-by":"crossref","first-page":"583","DOI":"10.1038\/s41586-021-03819-2","article-title":"Highly accurate protein structure prediction with AlphaFold","volume":"596","author":"Jumper","year":"2021","journal-title":"Nature"},{"key":"2022010507360586200_B26","doi-asserted-by":"crossref","first-page":"871","DOI":"10.1126\/science.abj8754","article-title":"Accurate prediction of protein structures and interactions using a three-track neural network","volume":"373","author":"Baek","year":"2021","journal-title":"Science"},{"key":"2022010507360586200_B27","doi-asserted-by":"crossref","first-page":"260","DOI":"10.1093\/nar\/30.1.260","article-title":"ASTRAL compendium enhancements","volume":"30","author":"Chandonia","year":"2002","journal-title":"Nucleic Acids Res."}],"container-title":["Nucleic Acids Research"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/nar\/article-pdf\/50\/D1\/D553\/42058119\/gkab1054.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/nar\/article-pdf\/50\/D1\/D553\/42058119\/gkab1054.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,5]],"date-time":"2022-01-05T08:05:37Z","timestamp":1641369937000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/nar\/article\/50\/D1\/D553\/6447236"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12,1]]},"references-count":27,"journal-issue":{"issue":"D1","published-online":{"date-parts":[[2021,12,1]]},"published-print":{"date-parts":[[2022,1,7]]}},"URL":"https:\/\/doi.org\/10.1093\/nar\/gkab1054","relation":{},"ISSN":["0305-1048","1362-4962"],"issn-type":[{"value":"0305-1048","type":"print"},{"value":"1362-4962","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2022,1,7]]},"published":{"date-parts":[[2021,12,1]]}}}