{"id":"https://openalex.org/W7224798654","doi":"https://doi.org/10.57760/sciencedb.0171m","title":"CryoAtlas: A Large Curated Dataset and Unified Benchmark for Cryo-EM Atomic Model Building","display_name":"CryoAtlas: A Large Curated Dataset and Unified Benchmark for Cryo-EM Atomic Model Building","publication_year":2026,"publication_date":"2026-10-23","ids":{"openalex":"https://openalex.org/W7224798654","doi":"https://doi.org/10.57760/sciencedb.0171m"},"language":"en","primary_location":{"id":"doi:10.57760/sciencedb.0171m","doi":"https://doi.org/10.57760/sciencedb.0171m","is_oa":true,"landing_page_url":"https://doi.org/10.57760/sciencedb.0171m","pdf_url":null,"source":{"id":"https://openalex.org/S7407050937","display_name":"ScienceDB","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"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/10.57760/sciencedb.0171m","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5121429540","display_name":"Mingrui Li","orcid":"https://orcid.org/0009-0002-7899-8985","observed_orcids":["https://orcid.org/0009-0002-7899-8985"]},"institutions":[{"id":"https://openalex.org/I30809798","display_name":"ShanghaiTech University","ror":"https://ror.org/030bhh786","country_code":"CN","type":"education","lineage":["https://openalex.org/I30809798"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingrui Li","raw_affiliation_strings":["ShanghaiTech University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ShanghaiTech University","institution_ids":["https://openalex.org/I30809798"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100715458","display_name":"Yuan Pei","orcid":"https://orcid.org/0000-0003-4065-2540","observed_orcids":["https://orcid.org/0000-0003-4065-2540"]},"institutions":[{"id":"https://openalex.org/I30809798","display_name":"ShanghaiTech University","ror":"https://ror.org/030bhh786","country_code":"CN","type":"education","lineage":["https://openalex.org/I30809798"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuan Pei","raw_affiliation_strings":["ShanghaiTech University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ShanghaiTech University","institution_ids":["https://openalex.org/I30809798"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I30809798"],"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/T10857","display_name":"Advanced Electron Microscopy Techniques and Applications","score":0.98580002784729,"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"}},"topics":[{"id":"https://openalex.org/T10857","display_name":"Advanced Electron Microscopy Techniques and Applications","score":0.98580002784729,"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/T10044","display_name":"Protein Structure and Dynamics","score":0.0066999997943639755,"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":0.00559999980032444,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/cryo-em-maps","display_name":"cryo-EM density maps","score":0.8539999723434448},{"id":"https://openalex.org/keywords/protein-structure-prediction","display_name":"protein structure prediction","score":0.6940000057220459},{"id":"https://openalex.org/keywords/benchmark-dataset","display_name":"benchmark dataset","score":0.6729999780654907},{"id":"https://openalex.org/keywords/emdb","display_name":"EMDB","score":0.46399998664855957},{"id":"https://openalex.org/keywords/protein-data-bank","display_name":"Protein Data Bank","score":0.5929999947547913},{"id":"https://openalex.org/keywords/protein-sequences","display_name":"protein sequences","score":0.3779999911785126}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.8169999718666077},{"id":"https://openalex.org/C56666940","wikidata":"https://www.wikidata.org/wiki/Q788790","display_name":"Documentation","level":2,"score":0.7495999932289124},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6809999942779541},{"id":"https://openalex.org/C71901391","wikidata":"https://www.wikidata.org/wiki/Q7126699","display_name":"Upload","level":2,"score":0.6283000111579895},{"id":"https://openalex.org/C174183944","wikidata":"https://www.wikidata.org/wiki/Q334661","display_name":"MIT License","level":3,"score":0.5573999881744385},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5365999937057495},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.524399995803833},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4787999987602234},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.41110000014305115},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.40209999680519104},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.3950999975204468},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3779999911785126},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3702999949455261},{"id":"https://openalex.org/C2984074130","wikidata":"https://www.wikidata.org/wiki/Q73539779","display_name":"R package","level":2,"score":0.349700003862381},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.34850001335144043},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.32359999418258667},{"id":"https://openalex.org/C65556437","wikidata":"https://www.wikidata.org/wiki/Q766195","display_name":"Protein Data Bank (RCSB PDB)","level":2,"score":0.3149999976158142},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.31130000948905945},{"id":"https://openalex.org/C18051474","wikidata":"https://www.wikidata.org/wiki/Q899656","display_name":"Protein structure prediction","level":3,"score":0.29809999465942383},{"id":"https://openalex.org/C3102742","wikidata":"https://www.wikidata.org/wiki/Q6031177","display_name":"Information repository","level":3,"score":0.2957000136375427},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.29409998655319214},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.2935999929904938},{"id":"https://openalex.org/C60478076","wikidata":"https://www.wikidata.org/wiki/Q3036835","display_name":"Reference data","level":2,"score":0.2919999957084656},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.2863999903202057},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.28619998693466187},{"id":"https://openalex.org/C2780560020","wikidata":"https://www.wikidata.org/wiki/Q79719","display_name":"License","level":2,"score":0.28200000524520874},{"id":"https://openalex.org/C45484198","wikidata":"https://www.wikidata.org/wiki/Q827246","display_name":"Sequence alignment","level":4,"score":0.28060001134872437},{"id":"https://openalex.org/C189474733","wikidata":"https://www.wikidata.org/wiki/Q917912","display_name":"Model building","level":2,"score":0.2782999873161316},{"id":"https://openalex.org/C128942645","wikidata":"https://www.wikidata.org/wiki/Q1568346","display_name":"Test case","level":3,"score":0.2685000002384186},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.25600001215934753},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.25049999356269836}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.57760/sciencedb.0171m","doi":"https://doi.org/10.57760/sciencedb.0171m","is_oa":true,"landing_page_url":"https://doi.org/10.57760/sciencedb.0171m","pdf_url":null,"source":{"id":"https://openalex.org/S7407050937","display_name":"ScienceDB","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"}],"best_oa_location":{"id":"doi:10.57760/sciencedb.0171m","doi":"https://doi.org/10.57760/sciencedb.0171m","is_oa":true,"landing_page_url":"https://doi.org/10.57760/sciencedb.0171m","pdf_url":null,"source":{"id":"https://openalex.org/S7407050937","display_name":"ScienceDB","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"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/W7223331551","https://openalex.org/W7223386885","https://openalex.org/W7223327528","https://openalex.org/W4396660070","https://openalex.org/W7223375402","https://openalex.org/W7223223324","https://openalex.org/W2559824272","https://openalex.org/W7222817420","https://openalex.org/W7165732051","https://openalex.org/W7128537459"],"abstract_inverted_index":{"CryoAtlas":[0],"v1.0":[1],"is":[2,192],"a":[3,133,173],"curated":[4,35],"dataset":[5,191],"and":[6,24,42,51,63,87,101,123,153,158,168,181,184,211,216],"unified":[7,174],"benchmark":[8,115,188],"for":[9,117,156,177],"research":[10],"on":[11],"automated":[12],"protein":[13,64,96],"atomic":[14,61,91,146],"model":[15],"building":[16],"from":[17,22],"cryo-EM":[18],"density":[19,59,89],"maps.":[20],"Derived":[21],"EMDB":[23],"PDB":[25],"records":[26],"available":[27,220],"up":[28],"to":[29],"March":[30],"2026,":[31],"it":[32],"contains":[33],"17,809":[34],"map\u2013model\u2013sequence":[36],"entries,":[37],"comprising":[38],"16,657":[39,74],"training":[40,180],"entries":[41,75,86,108],"1,152":[43,107],"test":[44,127,138,182],"entries.":[45,128],"Following":[46],"map\u2013model":[47],"alignment,":[48],"sequence":[49],"mapping,":[50],"quality":[52],"filtering,":[53],"each":[54],"entry":[55,175],"provides":[56,172],"paired":[57],"experimental":[58],"maps,":[60,90],"structures,":[62,147],"sequences.This":[65],"ScienceDB":[66],"Package":[67],"brings":[68],"together":[69],"three":[70],"complementary":[71],"components:Training":[72],"set:":[73,106],"distributed":[76],"across":[77],"four":[78],"non-overlapping":[79],"parts.":[80],"Each":[81],"part":[82],"preserves":[83],"complete":[84,137],"EMD":[85],"includes":[88],"structures":[92],"in":[93,98,120],"CIF":[94],"format,":[95,100],"sequences":[97],"FASTA":[99],"metadata":[102],"identifying":[103],"its":[104],"contents.Test":[105],"organized":[109],"into":[110],"two":[111],"subsets:":[112],"the":[113,121,124,136,160,179,186,195],"618-target":[114],"used":[116],"comparative":[118],"evaluation":[119,149],"paper":[122],"remaining":[125],"534":[126],"The":[129,190],"618":[130],"targets":[131],"are":[132,219],"subset":[134],"of":[135],"set,":[139],"not":[140],"an":[141],"additional":[142],"dataset.Benchmark":[143],"resources:":[144],"Predicted":[145],"per-target":[148],"results,":[150],"split":[151],"definitions,":[152],"supporting":[154],"documentation":[155,215],"reproducing":[157],"analyzing":[159],"benchmark.":[161],"Evaluation":[162],"covers":[163],"structural":[164],"accuracy,":[165],"model-to-map":[166],"agreement,":[167],"stereochemical":[169],"quality.The":[170],"package":[171],"point":[176],"downloading":[178],"data":[183],"accessing":[185],"accompanying":[187],"resources.":[189],"released":[193],"under":[194],"Creative":[196],"Commons":[197],"Attribution\u2013NonCommercial":[198],"4.0":[199],"International":[200],"license":[201],"(CC":[202],"BY-NC":[203],"4.0);":[204],"third-party":[205],"materials":[206],"retain":[207],"their":[208],"original":[209],"licenses":[210],"attribution":[212],"requirements.":[213],"Additional":[214],"code":[217],"links":[218],"at":[221],"https://oulling.github.io/cryoatlas/.":[222]},"counts_by_year":[],"updated_date":"2026-11-10T13:44:29.811591","created_date":"2026-10-31T00:00:00"}
