{"id":"https://openalex.org/W1902120158","doi":"https://doi.org/10.1186/s13321-015-0093-3","title":"Standards-based curation of a decade-old digital repository dataset of molecular information","display_name":"Standards-based curation of a decade-old digital repository dataset of molecular information","publication_year":2015,"publication_date":"2015-08-26","ids":{"openalex":"https://openalex.org/W1902120158","doi":"https://doi.org/10.1186/s13321-015-0093-3","mag":"1902120158","pmid":"https://pubmed.ncbi.nlm.nih.gov/26322133"},"language":"en","primary_location":{"id":"doi:10.1186/s13321-015-0093-3","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-015-0093-3","pdf_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-015-0093-3","source":{"id":"https://openalex.org/S180838163","display_name":"Journal of Cheminformatics","issn_l":"1758-2946","issn":["1758-2946"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Cheminformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-015-0093-3","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Matthew J Harvey","orcid":null},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Matthew J Harvey","raw_affiliation_strings":["High Performance Computing Service, Imperial College London, London, SW7 2AZ UK","High Performance Computing Service, Imperial College London, London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"High Performance Computing Service, Imperial College London, London, SW7 2AZ UK","institution_ids":["https://openalex.org/I47508984"]},{"raw_affiliation_string":"High Performance Computing Service, Imperial College London, London, UK","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030197216","display_name":"Nicholas Mason","orcid":"https://orcid.org/0000-0001-9475-0328"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Nicholas J Mason","raw_affiliation_strings":["Department of Chemistry, Imperial College London, South Kensington Campus, London, SW7 2AZ UK","Department of Chemistry, Imperial College London, London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Chemistry, Imperial College London, South Kensington Campus, London, SW7 2AZ UK","institution_ids":["https://openalex.org/I47508984"]},{"raw_affiliation_string":"Department of Chemistry, Imperial College London, London, UK","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039525933","display_name":"Andrew Mclean","orcid":"https://orcid.org/0000-0002-1653-7430"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Andrew McLean","raw_affiliation_strings":["High Performance Computing Service, Imperial College London, London, SW7 2AZ UK","High Performance Computing Service, Imperial College London, London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"High Performance Computing Service, Imperial College London, London, SW7 2AZ UK","institution_ids":["https://openalex.org/I47508984"]},{"raw_affiliation_string":"High Performance Computing Service, Imperial College London, London, UK","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041092827","display_name":"Peter Murray\u2010Rust","orcid":"https://orcid.org/0000-0003-3386-3972"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Peter Murray-Rust","raw_affiliation_strings":["Department of Chemistry, Centre for Molecular Informatics, Lensfield Road, Cambridge, CB2 1EW UK","Department of Chemistry, Centre for Molecular Informatics, Cambridge, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Chemistry, Centre for Molecular Informatics, Lensfield Road, Cambridge, CB2 1EW UK","institution_ids":["https://openalex.org/I241749"]},{"raw_affiliation_string":"Department of Chemistry, Centre for Molecular Informatics, Cambridge, UK","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072164503","display_name":"Henry S. Rzepa","orcid":"https://orcid.org/0000-0002-8635-8390"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Henry S Rzepa","raw_affiliation_strings":["Department of Chemistry, Imperial College London, South Kensington Campus, London, SW7 2AZ UK","Department of Chemistry, Imperial College London, London, UK"],"raw_orcid":"https://orcid.org/0000-0002-8635-8390","affiliations":[{"raw_affiliation_string":"Department of Chemistry, Imperial College London, South Kensington Campus, London, SW7 2AZ UK","institution_ids":["https://openalex.org/I47508984"]},{"raw_affiliation_string":"Department of Chemistry, Imperial College London, London, UK","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060242817","display_name":"James J. P. Stewart","orcid":"https://orcid.org/0000-0001-6280-8695"},"institutions":[{"id":"https://openalex.org/I4210115059","display_name":"Green Circle","ror":"https://ror.org/028pb7349","country_code":"CZ","type":"nonprofit","lineage":["https://openalex.org/I4210115059"]},{"id":"https://openalex.org/I888729015","display_name":"University of Colorado Colorado Springs","ror":"https://ror.org/054spjc55","country_code":"US","type":"education","lineage":["https://openalex.org/I888729015"]}],"countries":["CZ","US"],"is_corresponding":false,"raw_author_name":"James J P Stewart","raw_affiliation_strings":["Stewart Computational Chemistry, 15210 Paddington Circle, Colorado Springs, CO 80921 USA","Stewart Computational Chemistry, Colorado Springs, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stewart Computational Chemistry, 15210 Paddington Circle, Colorado Springs, CO 80921 USA","institution_ids":["https://openalex.org/I4210115059"]},{"raw_affiliation_string":"Stewart Computational Chemistry, Colorado Springs, USA","institution_ids":["https://openalex.org/I888729015"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5072164503"],"corresponding_institution_ids":["https://openalex.org/I47508984"],"apc_list":{"value":2390,"currency":"USD","value_usd":2390},"apc_paid":{"value":2390,"currency":"USD","value_usd":2390},"fwci":9.8843,"has_fulltext":true,"cited_by_count":13,"citation_normalized_percentile":{"value":0.97687678,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"7","issue":"1","first_page":"43","last_page":"43"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11937","display_name":"Research Data Management Practices","score":0.3540000021457672,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11937","display_name":"Research Data Management Practices","score":0.3540000021457672,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.2046000063419342,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.14810000360012054,"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/computer-science","display_name":"Computer science","score":0.807685911655426},{"id":"https://openalex.org/keywords/data-curation","display_name":"Data curation","score":0.7875298261642456},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.6778446435928345},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6464196443557739},{"id":"https://openalex.org/keywords/xml","display_name":"XML","score":0.5580508708953857},{"id":"https://openalex.org/keywords/schema","display_name":"Schema (genetic algorithms)","score":0.4827346205711365},{"id":"https://openalex.org/keywords/metadata-modeling","display_name":"Metadata modeling","score":0.4736434519290924},{"id":"https://openalex.org/keywords/identifier","display_name":"Identifier","score":0.46315422654151917},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3479011654853821},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3371451497077942},{"id":"https://openalex.org/keywords/metadata-repository","display_name":"Metadata repository","score":0.3209308385848999},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.2689211666584015},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1062573492527008}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.807685911655426},{"id":"https://openalex.org/C91632574","wikidata":"https://www.wikidata.org/wiki/Q15088675","display_name":"Data curation","level":2,"score":0.7875298261642456},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.6778446435928345},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6464196443557739},{"id":"https://openalex.org/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.5580508708953857},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.4827346205711365},{"id":"https://openalex.org/C110326360","wikidata":"https://www.wikidata.org/wiki/Q17149476","display_name":"Metadata modeling","level":4,"score":0.4736434519290924},{"id":"https://openalex.org/C154504017","wikidata":"https://www.wikidata.org/wiki/Q853614","display_name":"Identifier","level":2,"score":0.46315422654151917},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3479011654853821},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3371451497077942},{"id":"https://openalex.org/C153048206","wikidata":"https://www.wikidata.org/wiki/Q3454922","display_name":"Metadata repository","level":3,"score":0.3209308385848999},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2689211666584015},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1062573492527008}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1186/s13321-015-0093-3","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-015-0093-3","pdf_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-015-0093-3","source":{"id":"https://openalex.org/S180838163","display_name":"Journal of Cheminformatics","issn_l":"1758-2946","issn":["1758-2946"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Cheminformatics","raw_type":"journal-article"},{"id":"pmid:26322133","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/26322133","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of cheminformatics","raw_type":"Journal Article"},{"id":"pmh:oai:europepmc.org:3524593","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/4550659","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Text"},{"id":"pmh:oai:spiral.imperial.ac.uk:10044/1/52606","is_oa":true,"landing_page_url":"http://hdl.handle.net/10044/1/52606","pdf_url":null,"source":{"id":"https://openalex.org/S4306401396","display_name":"Spiral (Imperial College London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I47508984","host_organization_name":"Imperial College London","host_organization_lineage":["https://openalex.org/I47508984"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Journal Article"}],"best_oa_location":{"id":"doi:10.1186/s13321-015-0093-3","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-015-0093-3","pdf_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-015-0093-3","source":{"id":"https://openalex.org/S180838163","display_name":"Journal of Cheminformatics","issn_l":"1758-2946","issn":["1758-2946"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Cheminformatics","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.4399999976158142,"id":"https://metadata.un.org/sdg/17","display_name":"Partnerships for the goals"}],"awards":[{"id":"https://openalex.org/G1105467142","display_name":null,"funder_award_id":"R44 GM108085","funder_id":"https://openalex.org/F4320337354","funder_display_name":"National Institute of General Medical Sciences"}],"funders":[{"id":"https://openalex.org/F4320320283","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337354","display_name":"National Institute of General Medical Sciences","ror":"https://ror.org/04q48ey07"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1902120158.pdf","grobid_xml":"https://content.openalex.org/works/W1902120158.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W643289902","https://openalex.org/W1902120158","https://openalex.org/W1961830156","https://openalex.org/W1970377702","https://openalex.org/W1978815802","https://openalex.org/W1992633332","https://openalex.org/W1994628115","https://openalex.org/W2011703027","https://openalex.org/W2011805684","https://openalex.org/W2024754921","https://openalex.org/W2028046413","https://openalex.org/W2030645341","https://openalex.org/W2032084435","https://openalex.org/W2033917497","https://openalex.org/W2041971736","https://openalex.org/W2047600440","https://openalex.org/W2048715559","https://openalex.org/W2063945640","https://openalex.org/W2071513876","https://openalex.org/W2080635178","https://openalex.org/W2087563523","https://openalex.org/W2105144209","https://openalex.org/W2134164499","https://openalex.org/W2159790018","https://openalex.org/W2169678694","https://openalex.org/W2581300917","https://openalex.org/W4212894242","https://openalex.org/W4285719527","https://openalex.org/W6904756944","https://openalex.org/W6960938144"],"related_works":["https://openalex.org/W2367786714","https://openalex.org/W2807292920","https://openalex.org/W4289754504","https://openalex.org/W202512329","https://openalex.org/W3084772717","https://openalex.org/W4224036053","https://openalex.org/W4245065899","https://openalex.org/W2373484614","https://openalex.org/W2147434489","https://openalex.org/W1773645839"],"abstract_inverted_index":{"BACKGROUND:":[0],"The":[1,45],"desirable":[2],"curation":[3,50,173],"of":[4,13,53,64,144,174,180],"158,122":[5],"molecular":[6,181],"geometries":[7],"derived":[8],"from":[9],"the":[10,22,34,49,54,62,65,71,82,92,99,138,145],"NCI":[11],"set":[12],"reference":[14],"molecules":[15],"together":[16,84],"with":[17,85,152],"associated":[18,151],"properties":[19],"computed":[20],"using":[21,57,131],"MOPAC":[23,59],"semi-empirical":[24],"quantum":[25],"mechanical":[26],"method":[27],"and":[28,77,125,147,171],"originally":[29],"deposited":[30],"in":[31,48,108,161],"2005":[32],"into":[33],"Cambridge":[35],"DSpace":[36],"repository":[37,178],"as":[38],"a":[39,86,105,110,162,175],"data":[40,56,72,123,126,141,149],"collection":[41],"is":[42,115],"reported.":[43],"RESULTS:":[44],"procedures":[46],"involved":[47],"included":[51],"annotation":[52],"original":[55],"new":[58,79],"methods,":[60],"updating":[61],"syntax":[63],"CML":[66],"documents":[67],"used":[68,97],"to":[69,73,90,95,121],"express":[70],"ensure":[74],"schema":[75,88,94],"conformance":[76],"adding":[78],"metadata":[80,93],"describing":[81],"entries":[83],"XML":[87],"transformation":[89],"map":[91],"that":[96,137,164],"by":[98],"DataCite":[100,111,132],"organisation.":[101],"We":[102,135],"have":[103],"adopted":[104],"granularity":[106],"model":[107],"which":[109],"persistent":[112],"identifier":[113],"(DOI)":[114],"created":[116],"for":[117],"each":[118],"individual":[119],"molecule":[120],"enable":[122],"discovery":[124],"metrics":[127],"at":[128],"this":[129],"level":[130],"tools.":[133],"CONCLUSIONS:":[134],"recommend":[136],"future":[139],"research":[140],"management":[142],"(RDM)":[143],"scientific":[146],"chemical":[148],"components":[150],"journal":[153],"articles":[154],"(the":[155],"\"supporting":[156],"information\")":[157],"should":[158],"be":[159],"conducted":[160],"manner":[163],"facilitates":[165],"automatic":[166],"periodic":[167],"curation.":[168],"Graphical":[169],"abstractStandards":[170],"metadata-based":[172],"decade-old":[176],"digital":[177],"dataset":[179],"information.":[182]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":2}],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2025-10-10T00:00:00"}
