{"id":"https://openalex.org/W7223386885","doi":"https://doi.org/10.57760/sciencedb.016k5","title":"CryoAtlas: A Large Curated Dataset and Unified Benchmark for Cryo-EM Atomic Model Building (Train Part 1)","display_name":"CryoAtlas: A Large Curated Dataset and Unified Benchmark for Cryo-EM Atomic Model Building (Train Part 1)","publication_year":2026,"publication_date":"2026-10-19","ids":{"openalex":"https://openalex.org/W7223386885","doi":"https://doi.org/10.57760/sciencedb.016k5"},"language":"en","primary_location":{"id":"doi:10.57760/sciencedb.016k5","doi":"https://doi.org/10.57760/sciencedb.016k5","is_oa":true,"landing_page_url":"https://doi.org/10.57760/sciencedb.016k5","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":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","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.016k5","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":true,"raw_author_name":"\u674e\u660e\u745e","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":["https://openalex.org/A5121429540"],"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":0.9945999979972839,"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":0.9945999979972839,"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":0.002400000113993883,"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":0.002199999988079071,"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":0.8460000157356262},{"id":"https://openalex.org/keywords/automatic-model-generation","display_name":"automatic model generation","score":0.7870000004768372},{"id":"https://openalex.org/keywords/benchmark","display_name":"benchmark","score":0.7070000171661377},{"id":"https://openalex.org/keywords/protein-sequences","display_name":"protein sequences","score":0.46799999475479126},{"id":"https://openalex.org/keywords/emdb","display_name":"EMDB","score":0.5649999976158142},{"id":"https://openalex.org/keywords/protein-data-bank","display_name":"Protein Data Bank","score":0.6679999828338623},{"id":"https://openalex.org/keywords/cryo-em-structure-determination","display_name":"cryo-EM structure determination","score":0.5659999847412109}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7870000004768372},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.678600013256073},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6686000227928162},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.578499972820282},{"id":"https://openalex.org/C189474733","wikidata":"https://www.wikidata.org/wiki/Q917912","display_name":"Model building","level":2,"score":0.5318999886512756},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.515999972820282},{"id":"https://openalex.org/C65556437","wikidata":"https://www.wikidata.org/wiki/Q766195","display_name":"Protein Data Bank (RCSB PDB)","level":2,"score":0.5126000046730042},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5023000240325928},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.4909999966621399},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.4900999963283539},{"id":"https://openalex.org/C2984074130","wikidata":"https://www.wikidata.org/wiki/Q73539779","display_name":"R package","level":2,"score":0.4749000072479248},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.4474000036716461},{"id":"https://openalex.org/C45484198","wikidata":"https://www.wikidata.org/wiki/Q827246","display_name":"Sequence alignment","level":4,"score":0.38370001316070557},{"id":"https://openalex.org/C194778546","wikidata":"https://www.wikidata.org/wiki/Q15308119","display_name":"Atomic model","level":2,"score":0.3391000032424927},{"id":"https://openalex.org/C18051474","wikidata":"https://www.wikidata.org/wiki/Q899656","display_name":"Protein structure prediction","level":3,"score":0.33390000462532043},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3312000036239624},{"id":"https://openalex.org/C66153294","wikidata":"https://www.wikidata.org/wiki/Q899291","display_name":"CASP","level":4,"score":0.31869998574256897},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.31619998812675476},{"id":"https://openalex.org/C60478076","wikidata":"https://www.wikidata.org/wiki/Q3036835","display_name":"Reference data","level":2,"score":0.29670000076293945},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2897000014781952},{"id":"https://openalex.org/C21080849","wikidata":"https://www.wikidata.org/wiki/Q13611879","display_name":"Data point","level":2,"score":0.2870999872684479},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2851000130176544},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2831999957561493},{"id":"https://openalex.org/C55037315","wikidata":"https://www.wikidata.org/wiki/Q5421151","display_name":"Experimental data","level":2,"score":0.2818000018596649},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.27630001306533813},{"id":"https://openalex.org/C88031987","wikidata":"https://www.wikidata.org/wiki/Q1377767","display_name":"Multiple sequence alignment","level":5,"score":0.2761000096797943},{"id":"https://openalex.org/C47487241","wikidata":"https://www.wikidata.org/wiki/Q5227230","display_name":"Data access","level":2,"score":0.27480000257492065},{"id":"https://openalex.org/C119145174","wikidata":"https://www.wikidata.org/wiki/Q7251429","display_name":"Protein Data Bank","level":3,"score":0.2685000002384186},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.26579999923706055},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.26170000433921814}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.57760/sciencedb.016k5","doi":"https://doi.org/10.57760/sciencedb.016k5","is_oa":true,"landing_page_url":"https://doi.org/10.57760/sciencedb.016k5","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":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"}],"best_oa_location":{"id":"doi:10.57760/sciencedb.016k5","doi":"https://doi.org/10.57760/sciencedb.016k5","is_oa":true,"landing_page_url":"https://doi.org/10.57760/sciencedb.016k5","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":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7223327528","https://openalex.org/W7223388597","https://openalex.org/W7223258878","https://openalex.org/W4396660070","https://openalex.org/W7165732051","https://openalex.org/W7223375402","https://openalex.org/W2559824272","https://openalex.org/W7223223324","https://openalex.org/W6911312632","https://openalex.org/W4398981103"],"abstract_inverted_index":{"This":[0],"dataset":[1,105],"is":[2,65],"Part":[3],"1":[4],"of":[5,7],"4":[6],"the":[8,96,108,119],"CryoAtlas":[9,109],"v1.0":[10,110],"training":[11,27,98],"set":[12,28],"for":[13,133],"research":[14],"on":[15],"automated":[16],"protein":[17,62,86],"atomic":[18,59,76],"model":[19],"building":[20],"from":[21,34],"cryo-EM":[22],"density":[23,57,73],"maps.":[24],"The":[25,91,126],"complete":[26,68,120],"contains":[29],"16,657":[30],"curated":[31],"entries":[32,70],"derived":[33],"EMDB":[35],"and":[36,49,61,71,81,84,100,123,138],"PDB":[37],"records":[38],"available":[39],"up":[40],"to":[41,107],"March":[42],"2026.":[43],"Following":[44],"map\u2013model":[45],"alignment,":[46],"sequence":[47],"mapping,":[48],"quality":[50],"filtering,":[51],"each":[52],"entry":[53],"provides":[54,128],"paired":[55],"experimental":[56],"maps,":[58,74],"structures,":[60],"sequences.This":[63],"part":[64],"organized":[66],"by":[67],"EMD":[69],"includes":[72],"corresponding":[75],"structures":[77],"in":[78,88],"CIF":[79],"format,":[80],"original,":[82],"aligned,":[83],"terminal-trimmed":[85],"sequences":[87],"FASTA":[89],"format.":[90],"four":[92,116],"parts":[93],"jointly":[94],"constitute":[95],"fixed":[97],"split":[99],"contain":[101],"no":[102],"overlapping":[103],"entries.This":[104],"belongs":[106],"Package,":[111],"which":[112],"brings":[113],"together":[114],"all":[115],"training-set":[117],"parts,":[118],"test":[121],"set,":[122],"benchmark":[124],"results.":[125],"package":[127],"a":[129],"unified":[130],"access":[131],"point":[132],"data":[134],"retrieval,":[135],"method":[136],"development,":[137],"reproducible":[139],"evaluation.":[140]},"counts_by_year":[],"updated_date":"2026-10-25T09:29:13.331239","created_date":"2026-10-24T00:00:00"}