{"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","pmcid":"https://www.ncbi.nlm.nih.gov/pmc/articles/4550659"},"language":"en","primary_location":{"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/P4310319965","https://openalex.org/P4310320256"],"host_organization_lineage_names":["Springer Nature","BioMed Central"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true},"type":"article","type_crossref":"journal-article","indexed_in":["crossref","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":"https://openalex.org/A5083345049","display_name":"M J Harvey","orcid":"https://orcid.org/0000-0003-1797-3186"},"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, UK"],"affiliations":[{"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, London, UK."],"affiliations":[{"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, UK"],"affiliations":[{"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":[],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Peter Murray-Rust","raw_affiliation_strings":["Department of Chemistry, Centre for Molecular Informatics, Cambridge, UK"],"affiliations":[{"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":false,"raw_author_name":"Henry S Rzepa","raw_affiliation_strings":["Department of Chemistry, Imperial College London, London, UK."],"affiliations":[{"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/I888729015","display_name":"University of Colorado Colorado Springs","ror":"https://ror.org/054spjc55","country_code":"US","type":"education","lineage":["https://openalex.org/I888729015"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"James J P Stewart","raw_affiliation_strings":["Stewart Computational Chemistry, Colorado Springs, USA"],"affiliations":[{"raw_affiliation_string":"Stewart Computational Chemistry, Colorado Springs, USA","institution_ids":["https://openalex.org/I888729015"]}]}],"institution_assertions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1290,"currency":"GBP","value_usd":1582,"provenance":"doaj"},"apc_paid":{"value":1290,"currency":"GBP","value_usd":1582,"provenance":"doaj"},"fwci":4.508,"has_fulltext":true,"fulltext_origin":"pdf","cited_by_count":8,"citation_normalized_percentile":{"value":0.879062,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":84,"max":85},"biblio":{"volume":"7","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9863,"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"}},"topics":[{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9863,"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/T11937","display_name":"Research Data Management Practices","score":0.9801,"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/T11948","display_name":"Machine Learning in Materials Science","score":0.9725,"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/schema","display_name":"Schema (genetic algorithms)","score":0.48273462},{"id":"https://openalex.org/keywords/metadata-modeling","display_name":"Metadata modeling","score":0.47364345}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8076859},{"id":"https://openalex.org/C91632574","wikidata":"https://www.wikidata.org/wiki/Q15088675","display_name":"Data curation","level":2,"score":0.7875298},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.67784464},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.64641964},{"id":"https://openalex.org/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.5580509},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.48273462},{"id":"https://openalex.org/C110326360","wikidata":"https://www.wikidata.org/wiki/Q17149476","display_name":"Metadata modeling","level":4,"score":0.47364345},{"id":"https://openalex.org/C154504017","wikidata":"https://www.wikidata.org/wiki/Q853614","display_name":"Identifier","level":2,"score":0.46315423},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.34790117},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.33714515},{"id":"https://openalex.org/C153048206","wikidata":"https://www.wikidata.org/wiki/Q3454922","display_name":"Metadata repository","level":3,"score":0.32093084},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.26892117},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10625735}],"mesh":[],"locations_count":5,"locations":[{"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/P4310319965","https://openalex.org/P4310320256"],"host_organization_lineage_names":["Springer Nature","BioMed Central"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true},{"is_oa":true,"landing_page_url":"https://europepmc.org/articles/pmc4550659","pdf_url":"https://europepmc.org/articles/pmc4550659?pdf=render","source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":true,"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":["European Bioinformatics Institute"],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true},{"is_oa":true,"landing_page_url":"http://hdl.handle.net/10044/1/52606","pdf_url":"http://spiral.imperial.ac.uk/bitstream/10044/1/52606/2/Standards-based%20curation%20of%20a%20decade-old%20digital%20repository%20dataset%20of%20molecular%20information.pdf","source":{"id":"https://openalex.org/S4306401396","display_name":"Spiral (Imperial College London)","issn_l":null,"issn":null,"is_oa":true,"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":["Imperial College London"],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true},{"is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4550659","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"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":["National Institutes of Health"],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true},{"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":["National Institutes of Health"],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false}],"best_oa_location":{"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/P4310319965","https://openalex.org/P4310320256"],"host_organization_lineage_names":["Springer Nature","BioMed Central"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true},"sustainable_development_goals":[{"display_name":"Partnerships for the goals","score":0.44,"id":"https://metadata.un.org/sdg/17"}],"grants":[],"datasets":[],"versions":[],"referenced_works_count":28,"referenced_works":["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/W643289902"],"related_works":["https://openalex.org/W4289754504","https://openalex.org/W4245065899","https://openalex.org/W4224036053","https://openalex.org/W3084772717","https://openalex.org/W2807292920","https://openalex.org/W2373484614","https://openalex.org/W2367786714","https://openalex.org/W2147434489","https://openalex.org/W202512329","https://openalex.org/W1773645839"],"abstract_inverted_index":{"The":[0,43],"desirable":[1],"curation":[2,48],"of":[3,12,51,62,141],"158,122":[4],"molecular":[5],"geometries":[6],"derived":[7],"from":[8],"the":[9,21,33,47,52,60,63,69,80,90,97,135,142],"NCI":[10],"set":[11],"reference":[13],"molecules":[14],"together":[15,82],"with":[16,83,149],"associated":[17,148],"properties":[18],"computed":[19],"using":[20,55,129],"MOPAC":[22,57],"semi-empirical":[23],"quantum":[24],"mechanical":[25],"method":[26],"and":[27,75,123,144],"originally":[28],"deposited":[29],"in":[30,46,106,158],"2005":[31],"into":[32],"Cambridge":[34],"DSpace":[35],"repository":[36],"as":[37],"a":[38,84,103,108,159],"data":[39,54,70,121,124,138,146],"collection":[40],"is":[41,113],"reported.":[42],"procedures":[44],"involved":[45],"included":[49],"annotation":[50],"original":[53],"new":[56,77],"methods,":[58],"updating":[59],"syntax":[61],"CML":[64],"documents":[65],"used":[66,95],"to":[67,71,88,93,119],"express":[68],"ensure":[72],"schema":[73,86,92],"conformance":[74],"adding":[76],"metadata":[78,91],"describing":[79],"entries":[81],"XML":[85],"transformation":[87],"map":[89],"that":[94,134,161],"by":[96],"DataCite":[98,109,130],"organisation.":[99],"We":[100,132],"have":[101],"adopted":[102],"granularity":[104],"model":[105],"which":[107],"persistent":[110],"identifier":[111],"(DOI)":[112],"created":[114],"for":[115],"each":[116],"individual":[117],"molecule":[118],"enable":[120],"discovery":[122],"metrics":[125],"at":[126],"this":[127],"level":[128],"tools.":[131],"recommend":[133],"future":[136],"research":[137],"management":[139],"(RDM)":[140],"scientific":[143],"chemical":[145],"components":[147],"journal":[150],"articles":[151],"(the":[152],"\u201csupporting":[153],"information\u201d)":[154],"should":[155],"be":[156],"conducted":[157],"manner":[160],"facilitates":[162],"automatic":[163],"periodic":[164],"curation.":[165]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W1902120158","counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":2}],"updated_date":"2025-01-07T10:34:26.644852","created_date":"2016-06-24"}