{"id":"https://openalex.org/W2172533829","doi":"https://doi.org/10.1186/s13321-015-0102-6","title":"Ambiguity of non-systematic chemical identifiers within and between small-molecule databases","display_name":"Ambiguity of non-systematic chemical identifiers within and between small-molecule databases","publication_year":2015,"publication_date":"2015-11-16","ids":{"openalex":"https://openalex.org/W2172533829","doi":"https://doi.org/10.1186/s13321-015-0102-6","mag":"2172533829","pmid":"https://pubmed.ncbi.nlm.nih.gov/26579214","pmcid":"https://www.ncbi.nlm.nih.gov/pmc/articles/4646925"},"language":"en","primary_location":{"is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-015-0102-6","pdf_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-015-0102-6","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_indexed_in_scopus":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/s13321-015-0102-6","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5023359433","display_name":"Saber A. Akhondi","orcid":"https://orcid.org/0000-0003-2855-5633"},"institutions":[],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Saber A. Akhondi","raw_affiliation_strings":["Department of Medical Informatics, Erasmus University Medical Centre, P.O. Box 2040, 3000 CA, Rotterdam, The Netherlands"],"affiliations":[{"raw_affiliation_string":"Department of Medical Informatics, Erasmus University Medical Centre, P.O. Box 2040, 3000 CA, Rotterdam, The Netherlands","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056365720","display_name":"Sorel Mure\u015fan","orcid":"https://orcid.org/0000-0003-2386-0436"},"institutions":[{"id":"https://openalex.org/I85920734","display_name":"Univesity of Life Science \"King Mihai I\" from Timisoara","ror":"https://ror.org/02pjx9m11","country_code":"RO","type":"education","lineage":["https://openalex.org/I85920734"]}],"countries":["RO"],"is_corresponding":false,"raw_author_name":"Sorel Muresan","raw_affiliation_strings":["Food Control Department, Banat University of Agricultural Sciences and Veterinary Medicine, Calea Aradului 119, 300645, Timisoara, Romania"],"affiliations":[{"raw_affiliation_string":"Food Control Department, Banat University of Agricultural Sciences and Veterinary Medicine, Calea Aradului 119, 300645, Timisoara, Romania","institution_ids":["https://openalex.org/I85920734"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062051745","display_name":"Antony Williams","orcid":"https://orcid.org/0000-0002-2668-4821"},"institutions":[],"countries":["US"],"is_corresponding":false,"raw_author_name":"Antony J. Williams","raw_affiliation_strings":["ChemConnector Inc., 904 Tamaras Circle, Wake Forest, NC, 27587, USA"],"affiliations":[{"raw_affiliation_string":"ChemConnector Inc., 904 Tamaras Circle, Wake Forest, NC, 27587, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005077862","display_name":"Jan A. Kors","orcid":"https://orcid.org/0000-0002-4929-026X"},"institutions":[],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Jan A. Kors","raw_affiliation_strings":["Department of Medical Informatics, Erasmus University Medical Centre, P.O. Box 2040, 3000 CA, Rotterdam, The Netherlands"],"affiliations":[{"raw_affiliation_string":"Department of Medical Informatics, Erasmus University Medical Centre, P.O. Box 2040, 3000 CA, Rotterdam, The Netherlands","institution_ids":[]}]}],"institution_assertions":[],"countries_distinct_count":3,"institutions_distinct_count":1,"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":1.286,"has_fulltext":true,"fulltext_origin":"pdf","cited_by_count":18,"citation_normalized_percentile":{"value":0.897963,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":91},"biblio":{"volume":"7","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9996,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T10211","display_name":"Computational Drug Discovery Methods","score":0.9996,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T10836","display_name":"Metabolomics and Mass Spectrometry Studies","score":0.9978,"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/T10908","display_name":"Analytical Chemistry and Chromatography","score":0.9963,"subfield":{"id":"https://openalex.org/subfields/1607","display_name":"Spectroscopy"},"field":{"id":"https://openalex.org/fields/16","display_name":"Chemistry"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/unique-identifier","display_name":"Unique identifier","score":0.60123783},{"id":"https://openalex.org/keywords/chemical-database","display_name":"Chemical database","score":0.5145066}],"concepts":[{"id":"https://openalex.org/C154504017","wikidata":"https://www.wikidata.org/wiki/Q853614","display_name":"Identifier","level":2,"score":0.93170774},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.84674746},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7203675},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.6850236},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6727052},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.6462433},{"id":"https://openalex.org/C188087704","wikidata":"https://www.wikidata.org/wiki/Q369577","display_name":"Standardization","level":2,"score":0.6271267},{"id":"https://openalex.org/C119839945","wikidata":"https://www.wikidata.org/wiki/Q6545185","display_name":"Unique identifier","level":3,"score":0.60123783},{"id":"https://openalex.org/C203394866","wikidata":"https://www.wikidata.org/wiki/Q2881060","display_name":"Chemical database","level":2,"score":0.5145066},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4411242},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.15997285},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.14328143},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-015-0102-6","pdf_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-015-0102-6","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_indexed_in_scopus":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/pmc4646925","pdf_url":"https://europepmc.org/articles/pmc4646925?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_indexed_in_scopus":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":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4646925","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_indexed_in_scopus":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/26579214","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_indexed_in_scopus":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/s13321-015-0102-6","pdf_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-015-0102-6","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_indexed_in_scopus":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":[],"grants":[{"funder":"https://openalex.org/F4320307770","funder_display_name":"AstraZeneca","award_id":"102695"}],"datasets":[],"versions":[],"referenced_works_count":38,"referenced_works":["https://openalex.org/W1557395197","https://openalex.org/W1572194202","https://openalex.org/W1601495365","https://openalex.org/W1975147762","https://openalex.org/W1976892175","https://openalex.org/W1998442020","https://openalex.org/W2017222169","https://openalex.org/W2018518196","https://openalex.org/W2020859943","https://openalex.org/W2023164253","https://openalex.org/W2027708456","https://openalex.org/W2029912875","https://openalex.org/W2034354062","https://openalex.org/W2034537627","https://openalex.org/W2041610798","https://openalex.org/W2051810242","https://openalex.org/W2053385401","https://openalex.org/W2057069496","https://openalex.org/W2069676201","https://openalex.org/W2076018790","https://openalex.org/W2080848531","https://openalex.org/W2087563523","https://openalex.org/W2096541451","https://openalex.org/W2097186436","https://openalex.org/W2108492672","https://openalex.org/W2122709242","https://openalex.org/W2125904022","https://openalex.org/W2132320273","https://openalex.org/W2133993935","https://openalex.org/W2135505477","https://openalex.org/W2137052779","https://openalex.org/W2145870108","https://openalex.org/W2146538435","https://openalex.org/W2161568599","https://openalex.org/W2165681080","https://openalex.org/W2166468803","https://openalex.org/W2170146596","https://openalex.org/W2431109715"],"related_works":["https://openalex.org/W4301062032","https://openalex.org/W3130054399","https://openalex.org/W2413664130","https://openalex.org/W2413568490","https://openalex.org/W2390627310","https://openalex.org/W2343500026","https://openalex.org/W2319837024","https://openalex.org/W2172533829","https://openalex.org/W2033159440","https://openalex.org/W1913624564"],"abstract_inverted_index":{"A":[0,151],"wide":[1,152],"range":[2,153],"of":[3,47,51,96,112,120,125,154,168,188,199],"chemical":[4,23,105,113,192],"compound":[5,15,43],"databases":[6,24,129,164,181,193],"are":[7,29,38,161,203],"currently":[8],"available":[9],"for":[10,148,157],"pharmaceutical":[11],"research.":[12],"To":[13],"retrieve":[14],"information,":[16],"including":[17],"structures,":[18],"researchers":[19],"can":[20,62,221],"query":[21],"these":[22],"using":[25],"non-systematic":[26,52,97,121,126,158,189,200],"identifiers.":[27,122],"These":[28],"source-dependent":[30],"identifiers":[31,53,98,127,159,190,201],"(e.g.,":[32],"brand":[33],"names,":[34],"generic":[35],"names),":[36],"which":[37,67],"usually":[39],"assigned":[40],"to":[41,74,133,144,215,223],"the":[42,45,59,94,110,118,141,175,213],"at":[44],"point":[46],"registration.":[48],"The":[49,123],"correctness":[50],"(i.e.,":[54,79],"whether":[55,80],"an":[56,81],"identifier":[57,82],"matches":[58,83],"associated":[60],"structure)":[61],"only":[63,143],"be":[64],"assessed":[65],"manually,":[66],"is":[68,72,194,207],"cumbersome,":[69],"but":[70,197],"it":[71],"possible":[73],"automatically":[75],"check":[76],"their":[77],"ambiguity":[78,95,119,124,142,155,179,198,214],"more":[84],"than":[85],"one":[86],"structure).":[87],"In":[88],"this":[89],"study":[90],"we":[91],"have":[92],"quantified":[93],"within":[99,128,191],"and":[100,228],"between":[101,163,205],"eight":[102],"widely":[103],"used":[104],"databases.":[106,150],"We":[107],"also":[108],"studied":[109],"effect":[111],"structure":[114,210],"standardization":[115,211],"on":[116],"reducing":[117],"varied":[130],"from":[131],"0.1":[132],"15.2":[134],"%":[135],"(median":[136,182],"2.5":[137],"%).":[138,170],"Standardization":[139],"reduced":[140],"a":[145,216],"small":[146],"extent":[147],"most":[149],"existed":[156],"that":[160,202],"shared":[162,204],"(17.7\u201360.2":[165],"%,":[166],"median":[167],"40.3":[169],"Removing":[171],"stereochemistry":[172],"information":[173],"provided":[174],"largest":[176],"reduction":[177,183],"in":[178],"across":[180],"13.7":[184],"percentage":[185],"points).":[186],"Ambiguity":[187],"generally":[195],"low,":[196],"databases,":[206],"high.":[208],"Chemical":[209],"reduces":[212],"limited":[217],"extent.":[218],"Our":[219],"findings":[220],"help":[222],"improve":[224],"database":[225],"integration,":[226],"curation,":[227],"maintenance.":[229]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W2172533829","counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2}],"updated_date":"2025-01-20T08:38:29.425123","created_date":"2016-06-24"}