{"id":"https://openalex.org/W6893156585","doi":"https://doi.org/10.5281/zenodo.14288439","title":"The QCML dataset, Quantum chemistry reference data from 33.5M DFT and 14.7B semi-empirical calculations","display_name":"The QCML dataset, Quantum chemistry reference data from 33.5M DFT and 14.7B semi-empirical calculations","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W6893156585","doi":"https://doi.org/10.5281/zenodo.14288439"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.14288439","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.14288439","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,"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"},"type":"dataset","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.14288439","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Ganscha, Stefan","orcid":"https://orcid.org/0009-0009-1640-9576"},"institutions":[{"id":"https://openalex.org/I4210100430","display_name":"Google (Switzerland)","ror":"https://ror.org/014f9c269","country_code":"CH","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210100430","https://openalex.org/I4210128969"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Ganscha, Stefan","raw_affiliation_strings":["Google (Switzerland)"],"raw_orcid":"https://orcid.org/0009-0009-1640-9576","affiliations":[{"raw_affiliation_string":"Google (Switzerland)","institution_ids":["https://openalex.org/I4210100430"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Unke, Oliver T.","orcid":"https://orcid.org/0000-0001-7503-406X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Unke, Oliver T.","raw_affiliation_strings":["Google (Germany)"],"raw_orcid":"https://orcid.org/0000-0001-7503-406X","affiliations":[{"raw_affiliation_string":"Google (Germany)","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Ahlin, Daniel","orcid":"https://orcid.org/0009-0008-7528-1712"},"institutions":[{"id":"https://openalex.org/I4210100430","display_name":"Google (Switzerland)","ror":"https://ror.org/014f9c269","country_code":"CH","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210100430","https://openalex.org/I4210128969"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Ahlin, Daniel","raw_affiliation_strings":["Google (Switzerland)"],"raw_orcid":"https://orcid.org/0009-0008-7528-1712","affiliations":[{"raw_affiliation_string":"Google (Switzerland)","institution_ids":["https://openalex.org/I4210100430"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Maennel, Hartmut","orcid":"https://orcid.org/0000-0002-4833-3387"},"institutions":[{"id":"https://openalex.org/I4210100430","display_name":"Google (Switzerland)","ror":"https://ror.org/014f9c269","country_code":"CH","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210100430","https://openalex.org/I4210128969"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Maennel, Hartmut","raw_affiliation_strings":["Google (Switzerland)"],"raw_orcid":"https://orcid.org/0000-0002-4833-3387","affiliations":[{"raw_affiliation_string":"Google (Switzerland)","institution_ids":["https://openalex.org/I4210100430"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Kashubin, Sergii","orcid":"https://orcid.org/0009-0001-5498-5939"},"institutions":[{"id":"https://openalex.org/I4210100430","display_name":"Google (Switzerland)","ror":"https://ror.org/014f9c269","country_code":"CH","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210100430","https://openalex.org/I4210128969"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Kashubin, Sergii","raw_affiliation_strings":["Google (Switzerland)"],"raw_orcid":"https://orcid.org/0009-0001-5498-5939","affiliations":[{"raw_affiliation_string":"Google (Switzerland)","institution_ids":["https://openalex.org/I4210100430"]}]},{"author_position":"last","author":{"id":null,"display_name":"Mueller, Klaus-Robert","orcid":"https://orcid.org/0000-0002-3861-7685"},"institutions":[{"id":"https://openalex.org/I4210109712","display_name":"Max Planck Institute for Informatics","ror":"https://ror.org/01w19ak89","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210109712"]},{"id":"https://openalex.org/I4577782","display_name":"Technische Universit\u00e4t Berlin","ror":"https://ror.org/03v4gjf40","country_code":"DE","type":"education","lineage":["https://openalex.org/I4577782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Mueller, Klaus-Robert","raw_affiliation_strings":["Technische Universit\u00e4t Berlin","Google (Germany)","Korea University","Max Planck Institute for Informatics"],"raw_orcid":"https://orcid.org/0000-0002-3861-7685","affiliations":[{"raw_affiliation_string":"Technische Universit\u00e4t Berlin","institution_ids":["https://openalex.org/I4577782"]},{"raw_affiliation_string":"Google (Germany)","institution_ids":[]},{"raw_affiliation_string":"Korea University","institution_ids":[]},{"raw_affiliation_string":"Max Planck Institute for Informatics","institution_ids":["https://openalex.org/I4210109712"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"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":true,"primary_topic":null,"topics":[],"keywords":[{"id":"https://openalex.org/keywords/chemical-space","display_name":"Chemical space","score":0.5950999855995178},{"id":"https://openalex.org/keywords/quantum-chemistry","display_name":"Quantum chemistry","score":0.5777999758720398},{"id":"https://openalex.org/keywords/reference-data","display_name":"Reference data","score":0.5559999942779541},{"id":"https://openalex.org/keywords/ab-initio","display_name":"Ab initio","score":0.5270000100135803},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.46959999203681946},{"id":"https://openalex.org/keywords/quantum-chemical","display_name":"Quantum chemical","score":0.46299999952316284},{"id":"https://openalex.org/keywords/density-functional-theory","display_name":"Density functional theory","score":0.4510999917984009},{"id":"https://openalex.org/keywords/molecule","display_name":"Molecule","score":0.38850000500679016},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.3628000020980835}],"concepts":[{"id":"https://openalex.org/C99726746","wikidata":"https://www.wikidata.org/wiki/Q906396","display_name":"Chemical space","level":3,"score":0.5950999855995178},{"id":"https://openalex.org/C22994065","wikidata":"https://www.wikidata.org/wiki/Q188403","display_name":"Quantum chemistry","level":4,"score":0.5777999758720398},{"id":"https://openalex.org/C60478076","wikidata":"https://www.wikidata.org/wiki/Q3036835","display_name":"Reference data","level":2,"score":0.5559999942779541},{"id":"https://openalex.org/C2781442258","wikidata":"https://www.wikidata.org/wiki/Q46310","display_name":"Ab initio","level":2,"score":0.5270000100135803},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5234000086784363},{"id":"https://openalex.org/C121864883","wikidata":"https://www.wikidata.org/wiki/Q677916","display_name":"Statistical physics","level":1,"score":0.4973999857902527},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.46959999203681946},{"id":"https://openalex.org/C2991951333","wikidata":"https://www.wikidata.org/wiki/Q188403","display_name":"Quantum chemical","level":3,"score":0.46299999952316284},{"id":"https://openalex.org/C152365726","wikidata":"https://www.wikidata.org/wiki/Q1048589","display_name":"Density functional theory","level":2,"score":0.4510999917984009},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.3926999866962433},{"id":"https://openalex.org/C32909587","wikidata":"https://www.wikidata.org/wiki/Q11369","display_name":"Molecule","level":2,"score":0.38850000500679016},{"id":"https://openalex.org/C147597530","wikidata":"https://www.wikidata.org/wiki/Q369472","display_name":"Computational chemistry","level":1,"score":0.3634999990463257},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.3628000020980835},{"id":"https://openalex.org/C84114770","wikidata":"https://www.wikidata.org/wiki/Q46344","display_name":"Quantum","level":2,"score":0.3528999984264374},{"id":"https://openalex.org/C52765159","wikidata":"https://www.wikidata.org/wiki/Q1027847","display_name":"Multipole expansion","level":2,"score":0.3472000062465668},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.34549999237060547},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.3452000021934509},{"id":"https://openalex.org/C86025842","wikidata":"https://www.wikidata.org/wiki/Q5358432","display_name":"Electronic structure","level":2,"score":0.33500000834465027},{"id":"https://openalex.org/C48677424","wikidata":"https://www.wikidata.org/wiki/Q6888088","display_name":"Mode (computer interface)","level":2,"score":0.33410000801086426},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.33169999718666077},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.32519999146461487},{"id":"https://openalex.org/C149629883","wikidata":"https://www.wikidata.org/wiki/Q660926","display_name":"Fraction (chemistry)","level":2,"score":0.32089999318122864},{"id":"https://openalex.org/C55037315","wikidata":"https://www.wikidata.org/wiki/Q5421151","display_name":"Experimental data","level":2,"score":0.30720001459121704},{"id":"https://openalex.org/C10803110","wikidata":"https://www.wikidata.org/wiki/Q1341441","display_name":"Force field (fiction)","level":2,"score":0.3037000000476837},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.29580000042915344},{"id":"https://openalex.org/C183971685","wikidata":"https://www.wikidata.org/wiki/Q547605","display_name":"Ab initio quantum chemistry methods","level":3,"score":0.2879999876022339},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.28769999742507935},{"id":"https://openalex.org/C59593255","wikidata":"https://www.wikidata.org/wiki/Q901663","display_name":"Molecular dynamics","level":2,"score":0.2822999954223633},{"id":"https://openalex.org/C18705241","wikidata":"https://www.wikidata.org/wiki/Q1128023","display_name":"Conformational isomerism","level":3,"score":0.2603999972343445},{"id":"https://openalex.org/C132459708","wikidata":"https://www.wikidata.org/wiki/Q744069","display_name":"Extrapolation","level":2,"score":0.2581999897956848},{"id":"https://openalex.org/C21080849","wikidata":"https://www.wikidata.org/wiki/Q13611879","display_name":"Data point","level":2,"score":0.25690001249313354},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.2508000135421753},{"id":"https://openalex.org/C32758168","wikidata":"https://www.wikidata.org/wiki/Q900488","display_name":"Normal mode","level":3,"score":0.25029999017715454}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5281/zenodo.14288439","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.14288439","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,"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Dataset"}],"best_oa_location":{"id":"doi:10.5281/zenodo.14288439","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.14288439","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,"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.4378923773765564}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Machine":[0],"learning":[1],"(ML)":[2],"methods":[3,115],"enable":[4],"prediction":[5],"of":[6,9,20,64,77,145,148,176],"the":[7,25,33,40,78,146,157,169,177],"properties":[8,110,128],"chemical":[10,58,89],"structures":[11],"without":[12],"computationally":[13],"expensive":[14],"ab":[15],"initio":[16],"calculations.":[17],"The":[18,53,126],"quality":[19],"such":[21],"predictions":[22],"depends":[23],"on":[24,156],"reference":[26],"data":[27,158],"that":[28],"was":[29],"used":[30,98],"to":[31,66,99,162],"train":[32],"model.":[34],"In":[35],"this":[36],"work,":[37],"we":[38],"introduce":[39],"QCML":[41,54],"dataset:":[42],"A":[43],"comprehensive":[44],"dataset":[45,55,150,171],"for":[46,50,107,173],"training":[47,152],"ML":[48],"models":[49],"quantum":[51],"chemistry.":[52],"systematically":[56],"covers":[57],"space":[59],"with":[60,113],"small":[61],"molecules":[62],"consisting":[63],"up":[65],"8":[67],"heavy":[68],"atoms":[69],"and":[70,93,103,119,134,159,180],"includes":[71],"elements":[72],"from":[73,88],"a":[74,142,174],"large":[75],"fraction":[76],"periodic":[79],"table,":[80],"as":[81,83],"well":[82],"different":[84],"electronic":[85],"states.":[86],"Starting":[87],"graphs,":[90],"conformer":[91],"search":[92],"normal":[94],"mode":[95],"sampling":[96],"are":[97,111],"generate":[100],"both":[101],"equilibrium":[102],"off-equilibrium":[104],"3D":[105],"structures,":[106],"which":[108],"various":[109],"calculated":[112],"semi-empirical":[114],"(14.7":[116],"billion":[117],"entries)":[118],"density":[120],"functional":[121],"theory":[122],"(33.5":[123],"million":[124],"entries).":[125],"covered":[127],"include":[129],"energies,":[130],"forces,":[131],"multipole":[132],"moments,":[133],"other":[135],"quantities,":[136],"e.g.":[137],"Kohn-Sham":[138],"matrices.":[139],"We":[140],"provide":[141],"first":[143],"demonstration":[144],"utility":[147],"our":[149],"by":[151],"ML-based":[153],"force":[154],"fields":[155],"applying":[160],"them":[161],"run":[163],"molecular":[164],"dynamics":[165],"simulations.":[166],"Please":[167],"see":[168],"latest":[170],"version":[172],"description":[175],"directory":[178],"structure":[179],"available":[181],"data.":[182]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2025-10-10T00:00:00"}
