{"id":"https://openalex.org/W7204113544","doi":"https://doi.org/10.5281/zenodo.22074673","title":"Domain structures for 4.9M non-singleton representatives of a provisional classification of the AlphaFold database 200M set","display_name":"Domain structures for 4.9M non-singleton representatives of a provisional classification of the AlphaFold database 200M set","publication_year":2026,"publication_date":"2026-08-24","ids":{"openalex":"https://openalex.org/W7204113544","doi":"https://doi.org/10.5281/zenodo.22074673"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.22074673","doi":"https://doi.org/10.5281/zenodo.22074673","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.22074673","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"},"volume":null,"type":"dataset","is_traditional":false,"indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.22074673","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5025471816","display_name":"Richard Dustin Schaeffer","orcid":"https://orcid.org/0000-0001-6502-1425","observed_orcids":["https://orcid.org/0000-0001-6502-1425"]},"institutions":[{"id":"https://openalex.org/I867280407","display_name":"The University of Texas Southwestern Medical Center","ror":"https://ror.org/05byvp690","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I867280407"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Schaeffer, R. Dustin","raw_affiliation_strings":["University of Texas Southwestern Medical Center"],"raw_orcid":"https://orcid.org/0000-0001-6502-1425","affiliations":[{"raw_affiliation_string":"University of Texas Southwestern Medical Center","institution_ids":["https://openalex.org/I867280407"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089388395","display_name":"Rui Guo","orcid":"https://orcid.org/0000-0002-5294-923X","observed_orcids":["https://orcid.org/0000-0002-5294-923X","https://orcid.org/0000-0002-2111-2867"]},"institutions":[{"id":"https://openalex.org/I867280407","display_name":"The University of Texas Southwestern Medical Center","ror":"https://ror.org/05byvp690","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I867280407"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Guo, Rui","raw_affiliation_strings":["University of Texas Southwestern Medical Center"],"raw_orcid":"https://orcid.org/0000-0002-2111-2867","affiliations":[{"raw_affiliation_string":"University of Texas Southwestern Medical Center","institution_ids":["https://openalex.org/I867280407"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039591575","display_name":"Qian Cong","orcid":"https://orcid.org/0000-0002-8909-0414","observed_orcids":["https://orcid.org/0000-0002-8909-0414"]},"institutions":[{"id":"https://openalex.org/I867280407","display_name":"The University of Texas Southwestern Medical Center","ror":"https://ror.org/05byvp690","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I867280407"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cong, Qian","raw_affiliation_strings":["University of Texas Southwestern Medical Center"],"raw_orcid":"https://orcid.org/0000-0002-8909-0414","affiliations":[{"raw_affiliation_string":"University of Texas Southwestern Medical Center","institution_ids":["https://openalex.org/I867280407"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108096094","display_name":"Nick V. Grishin","orcid":"https://orcid.org/0000-0003-4108-1153","observed_orcids":["https://orcid.org/0000-0003-4108-1153"]},"institutions":[{"id":"https://openalex.org/I867280407","display_name":"The University of Texas Southwestern Medical Center","ror":"https://ror.org/05byvp690","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I867280407"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Grishin, Nick V.","raw_affiliation_strings":["University of Texas Southwestern Medical Center"],"raw_orcid":"https://orcid.org/0000-0003-4108-1153","affiliations":[{"raw_affiliation_string":"University of Texas Southwestern Medical Center","institution_ids":["https://openalex.org/I867280407"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I867280407"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10044","display_name":"Protein Structure and Dynamics","score":0.9829000234603882,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T10044","display_name":"Protein Structure and Dynamics","score":0.9829000234603882,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11162","display_name":"Enzyme Structure and Function","score":0.00860000029206276,"subfield":{"id":"https://openalex.org/subfields/1315","display_name":"Structural Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.0017999999690800905,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/protein-domain-structure","display_name":"protein domain structure","score":0.8519999980926514},{"id":"https://openalex.org/keywords/protein-structure-prediction","display_name":"protein structure prediction","score":0.5979999899864197},{"id":"https://openalex.org/keywords/protein-domain-classification","display_name":"protein domain classification","score":0.5270000100135803}],"concepts":[{"id":"https://openalex.org/C52130261","wikidata":"https://www.wikidata.org/wiki/Q39825","display_name":"Census","level":3,"score":0.7958999872207642},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.6337000131607056},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.6119999885559082},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.535099983215332},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5202000141143799},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.4731000065803528},{"id":"https://openalex.org/C162372511","wikidata":"https://www.wikidata.org/wiki/Q218341","display_name":"Checksum","level":2,"score":0.4440999925136566},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4023999869823456},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3792000114917755},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.3635999858379364},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.3294000029563904},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.3172999918460846},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.31349998712539673},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.2980000078678131},{"id":"https://openalex.org/C53553401","wikidata":"https://www.wikidata.org/wiki/Q47307","display_name":"Genealogy","level":1,"score":0.2831000089645386},{"id":"https://openalex.org/C154504017","wikidata":"https://www.wikidata.org/wiki/Q853614","display_name":"Identifier","level":2,"score":0.2797999978065491},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.2750999927520752},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.25529998540878296},{"id":"https://openalex.org/C59276292","wikidata":"https://www.wikidata.org/wiki/Q580427","display_name":"Database index","level":3,"score":0.25049999356269836}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5281/zenodo.22074673","doi":"https://doi.org/10.5281/zenodo.22074673","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.22074673","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"},{"id":"doi:10.5281/zenodo.22074674","doi":"https://doi.org/10.5281/zenodo.22074674","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.22074674","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"}],"best_oa_location":{"id":"doi:10.5281/zenodo.22074673","doi":"https://doi.org/10.5281/zenodo.22074673","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.22074673","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W6911712428","https://openalex.org/W6950223259","https://openalex.org/W4410775456","https://openalex.org/W4312032102","https://openalex.org/W4403925091","https://openalex.org/W7204107869","https://openalex.org/W7143516912","https://openalex.org/W4401872102","https://openalex.org/W3211795435","https://openalex.org/W4416872515"],"abstract_inverted_index":{"The":[0,42,122,191,205,230,243,259],"predicted":[1,14],"structural":[2],"archive":[3,57],"behind":[4],"A":[5],"topology":[6],"census":[7,187,241,244],"of":[8,25,29,74,82,106,184,239,280],"four-strand":[9],"\u03b2-sheets":[10],"in":[11,127,222,228],"experimental":[12,273,283],"and":[13,109,148,154,161,226,249,275],"protein":[15],"structures:":[16],"4,959,302":[17],"DPAM-parsed":[18],"domain":[19,125],"structures":[20,211],"for":[21],"the":[22,30,64,83,101,107,114,145,172,186,223,233,240,250,255,276],"non-singleton":[23],"representatives":[24],"a":[26,124,182,237],"provisional":[27],"classification":[28,45],"AlphaFold":[31],"database":[32],"200M":[33,44],"set.":[34],"Why":[35],"these":[36,178],"are":[37,87,268,272],"deposited":[38],"rather":[39,175,284],"than":[40,176,285],"cited.":[41],"AFDB":[43],"they":[46,271],"come":[47],"from":[48,131,171,177],"has":[49],"not":[50,129,236,269],"been":[51],"published,":[52],"so":[53],"there":[54],"is":[55,63,128,147,181,197,208,232,254],"no":[56,217],"to":[58,134],"point":[59],"at.":[60],"This":[61,180],"record":[62,146,219,257],"only":[65,100,113],"source.":[66],"Full-atom":[67],"PDB,":[68],"packed":[69],"as":[70,282],"20":[71],"xz":[72],"archives":[73],"roughly":[75],"1.6":[76],"GB,":[77],"each":[78,164],"covering":[79],"five":[80],"shards":[81],"source":[84,173],"store.":[85],"Members":[86],"named":[88],"{ACC}_D{n}.pdb":[89],"or":[90],"dpam_{ACC}_nD{n}.pdb":[91],"--":[92],"both":[93],"spellings":[94],"occur;":[95],"an":[96,167],"index":[97],"built":[98,111],"on":[99,112],"dpam_":[102],"form":[103,116],"returns":[104],"1.22%":[105],"store,":[108],"one":[110,136],"bare":[115],"silently":[117],"drops":[118],"that":[119,266],"same":[120],"1.22%.":[121],"shard":[123],"falls":[126],"derivable":[130],"its":[132,150],"accession;":[133],"find":[135],"domain,":[137],"look":[138],"across":[139],"all":[140],"shards.":[141],"README.md":[142],"states":[143],"what":[144,185],"how":[149],"counts":[151,252,278],"reconcile;":[152],"MANIFEST.md":[153],"SHA256SUMS":[155],"give":[156],"per-archive":[157],"checksums":[158],"with":[159],"source-tarball":[160],"member":[162],"counts,":[163],"verified":[165],"against":[166],"independent":[168],"count":[169],"read":[170],"tarballs":[174],"archives.":[179],"superset":[183],"searched,":[188],"by":[189],"0.91%.":[190],"paper":[192,277],"reports":[193],"4,914,196":[194],"representatives,":[195],"which":[196,215],"meta-matrix":[198,218],"records":[199],"minus":[200],"7,735":[201,279],"seeded":[202,264],"ECOD":[203,261],"references.":[204],"45,106":[206],"difference":[207],"domains":[209,263],"whose":[210],"exist":[212],"here":[213],"but":[214],"produced":[216],"\u2014":[220,246,253],"44,978":[221],"new/":[224],"tree":[225],"128":[227],"dpam/.":[229],"store":[231],"classification's":[234],"structures,":[235,274],"transcript":[238],"input.":[242],"itself":[245],"code,":[247],"artifacts":[248],"per-topology":[251],"companion":[256],"10.5281/zenodo.21814885.":[258],"7,746":[260],"reference":[262],"into":[265],"clustering":[267],"included:":[270],"them":[281],"predicted.":[286]},"counts_by_year":[],"updated_date":"2026-10-14T16:39:01.820549","created_date":"2026-08-25T00:00:00"}
