{"id":"https://openalex.org/W7225126331","doi":"https://doi.org/10.48550/arxiv.2610.41411","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":"2026-10-30","ids":{"openalex":"https://openalex.org/W7225126331","doi":"https://doi.org/10.48550/arxiv.2610.41411"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.41411","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.41411","pdf_url":"https://arxiv.org/pdf/2610.41411","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2610.41411","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5160382565","display_name":"Mingrui Li","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Mingrui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160365052","display_name":"Minzhang Li","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Minzhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139780386","display_name":"Weichen Qin","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qin, Weichen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160381639","display_name":"Yufan Xie","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xie, Yufan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128271669","display_name":"Zhangzhi Xiong","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiong, Zhangzhi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036643323","display_name":"Sixian Shen","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shen, Sixian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160365197","display_name":"Jiakai Zhang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Jiakai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160382275","display_name":"Yuan Pei","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pei, Yuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5160362486","display_name":"Jingyi Yu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu, Jingyi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"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":0.986299991607666,"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":0.986299991607666,"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":0.008500000461935997,"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":0.002899999963119626,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/protein-structure-prediction","display_name":"protein structure prediction","score":0.45899999141693115},{"id":"https://openalex.org/keywords/benchmark-dataset","display_name":"benchmark dataset","score":0.5139999985694885},{"id":"https://openalex.org/keywords/emdb","display_name":"EMDB","score":0.44200000166893005},{"id":"https://openalex.org/keywords/protein-data-bank","display_name":"Protein Data Bank","score":0.7990000247955322},{"id":"https://openalex.org/keywords/alphafold-3","display_name":"AlphaFold3","score":0.7279999852180481},{"id":"https://openalex.org/keywords/phenix","display_name":"PHENIX","score":0.8939999938011169},{"id":"https://openalex.org/keywords/map-resolution","display_name":"map resolution","score":0.5299999713897705},{"id":"https://openalex.org/keywords/sequence-identity","display_name":"sequence identity","score":0.9179999828338623}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.8948000073432922},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6782000064849854},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.671500027179718},{"id":"https://openalex.org/C189474733","wikidata":"https://www.wikidata.org/wiki/Q917912","display_name":"Model building","level":2,"score":0.5435000061988831},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5001999735832214},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.49000000953674316},{"id":"https://openalex.org/C2780385302","wikidata":"https://www.wikidata.org/wiki/Q367158","display_name":"Protocol (science)","level":3,"score":0.48919999599456787},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.48730000853538513},{"id":"https://openalex.org/C2778712577","wikidata":"https://www.wikidata.org/wiki/Q3505966","display_name":"Retraining","level":2,"score":0.4799000024795532},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.4602999985218048},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39969998598098755},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36820000410079956},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.3301999866962433},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.2906999886035919},{"id":"https://openalex.org/C2776505523","wikidata":"https://www.wikidata.org/wiki/Q4785468","display_name":"Plan (archaeology)","level":2,"score":0.28380000591278076},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.27889999747276306},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.26759999990463257},{"id":"https://openalex.org/C18051474","wikidata":"https://www.wikidata.org/wiki/Q899656","display_name":"Protein structure prediction","level":3,"score":0.2639999985694885},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.2621999979019165},{"id":"https://openalex.org/C71901391","wikidata":"https://www.wikidata.org/wiki/Q7126699","display_name":"Upload","level":2,"score":0.25540000200271606},{"id":"https://openalex.org/C194778546","wikidata":"https://www.wikidata.org/wiki/Q15308119","display_name":"Atomic model","level":2,"score":0.2500999867916107}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2610.41411","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.41411","pdf_url":"https://arxiv.org/pdf/2610.41411","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2610.41411","doi":"https://doi.org/10.48550/arxiv.2610.41411","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.41411","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2610.41411","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.41411","pdf_url":"https://arxiv.org/pdf/2610.41411","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"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/W4396660070","https://openalex.org/W4408220653","https://openalex.org/W4412351891","https://openalex.org/W4416199605","https://openalex.org/W7128537459","https://openalex.org/W4388826960","https://openalex.org/W2559824272","https://openalex.org/W4416827057","https://openalex.org/W4396800657","https://openalex.org/W4404408757"],"abstract_inverted_index":{"Deep":[0],"learning":[1],"has":[2],"accelerated":[3],"automated":[4],"atomic":[5,42,148],"model":[6,43,149],"building":[7,44,150],"from":[8],"cryo-EM":[9,147],"maps,":[10],"yet":[11],"progress":[12],"remains":[13],"limited":[14],"by":[15,30],"the":[16,108,128,137],"lack":[17],"of":[18,45,110],"large,":[19],"high-quality":[20],"datasets":[21],"and":[22,37,50,53,91,104,117,154],"standardized":[23],"evaluation":[24,82],"benchmarks.":[25],"We":[26],"address":[27],"this":[28,72,95],"gap":[29],"introducing":[31],"CryoAtlas,":[32],"a":[33,66,76,80,124],"rigorously":[34],"curated":[35,67],"dataset":[36],"unified":[38],"benchmark":[39,78,98],"for":[40,145],"density-guided":[41],"protein":[46,115],"chains.":[47],"By":[48],"integrating":[49],"filtering":[51],"EMDB":[52],"PDB":[54],"entries":[55],"(up":[56],"to":[57],"March":[58],"2026),":[59],"CryoAtlas":[60,133,139],"provides":[61,140],"17,809":[62],"map-model-sequence":[63],"entries,":[64],"including":[65],"16,657-entry":[68],"training":[69],"split.":[70],"From":[71],"resource,":[73],"we":[74,97],"construct":[75],"618-target":[77],"with":[79],"shared":[81],"protocol":[83],"that":[84],"jointly":[85],"assesses":[86],"structural":[87],"accuracy,":[88],"model-to-map":[89],"fit,":[90],"stereochemical":[92],"validity.":[93],"Using":[94],"framework,":[96],"state-of-the-art":[99],"learning-based":[100],"methods":[101],"against":[102],"Phenix":[103],"AlphaFold3,":[105],"comprehensively":[106],"analyzing":[107],"impact":[109],"map":[111],"resolution,":[112],"sequence":[113,118],"length,":[114],"category":[116],"identity":[119],"on":[120,132,136],"modeling":[121],"accuracy.":[122],"As":[123],"case":[125],"study,":[126],"retraining":[127],"ModelAngelo":[129],"CNN":[130],"component":[131],"improves":[134],"performance":[135],"benchmark.":[138],"an":[141],"open,":[142],"reproducible":[143],"foundation":[144],"future":[146],"research.":[151],"Project":[152],"details":[153],"resource":[155],"release":[156],"updates":[157],"are":[158],"available":[159],"at":[160],"https://oulling.github.io/cryoatlas/.":[161]},"counts_by_year":[],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2026-11-03T00:00:00"}