{"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"},"language":"en","primary_location":{"id":"doi:10.1186/s13321-015-0102-6","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-015-0102-6","pdf_url":"https://link.springer.com/content/pdf/10.1186/s13321-015-0102-6.pdf","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://link.springer.com/content/pdf/10.1186/s13321-015-0102-6.pdf","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":[{"id":"https://openalex.org/I2801952686","display_name":"Erasmus MC","ror":"https://ror.org/018906e22","country_code":"NL","type":"healthcare","lineage":["https://openalex.org/I2801952686"]},{"id":"https://openalex.org/I913958620","display_name":"Erasmus University Rotterdam","ror":"https://ror.org/057w15z03","country_code":"NL","type":"education","lineage":["https://openalex.org/I913958620"]}],"countries":["NL"],"is_corresponding":true,"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","Department of Medical Informatics, Erasmus University Medical Centre, P.O. Box 2040, 3000 CA, Rotterdam, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Medical Informatics, Erasmus University Medical Centre, P.O. Box 2040, 3000 CA Rotterdam, The Netherlands","institution_ids":["https://openalex.org/I2801952686","https://openalex.org/I913958620"]},{"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","Food Control Department, Banat University of Agricultural Sciences and Veterinary Medicine, Calea Aradului 119, 300645, Timisoara, Romania"],"raw_orcid":null,"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"]},{"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":null},"institutions":[{"id":"https://openalex.org/I2751430930","display_name":"Royal Society of Chemistry","ror":"https://ror.org/025sbr097","country_code":"GB","type":"nonprofit","lineage":["https://openalex.org/I2751430930"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Antony J. Williams","raw_affiliation_strings":["ChemConnector Inc., 904 Tamaras Circle, Wake Forest, NC 27587 USA","ChemConnector Inc., 904 Tamaras Circle, Wake Forest, NC, 27587, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ChemConnector Inc., 904 Tamaras Circle, Wake Forest, NC 27587 USA","institution_ids":["https://openalex.org/I2751430930"]},{"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":[{"id":"https://openalex.org/I2801952686","display_name":"Erasmus MC","ror":"https://ror.org/018906e22","country_code":"NL","type":"healthcare","lineage":["https://openalex.org/I2801952686"]},{"id":"https://openalex.org/I913958620","display_name":"Erasmus University Rotterdam","ror":"https://ror.org/057w15z03","country_code":"NL","type":"education","lineage":["https://openalex.org/I913958620"]}],"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","Department of Medical Informatics, Erasmus University Medical Centre, P.O. Box 2040, 3000 CA, Rotterdam, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Medical Informatics, Erasmus University Medical Centre, P.O. Box 2040, 3000 CA Rotterdam, The Netherlands","institution_ids":["https://openalex.org/I2801952686","https://openalex.org/I913958620"]},{"raw_affiliation_string":"Department of Medical Informatics, Erasmus University Medical Centre, P.O. Box 2040, 3000 CA, Rotterdam, The Netherlands","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5023359433"],"corresponding_institution_ids":["https://openalex.org/I2801952686","https://openalex.org/I913958620"],"apc_list":{"value":2190,"currency":"USD","value_usd":2190},"apc_paid":{"value":2190,"currency":"USD","value_usd":2190},"fwci":1.6735,"has_fulltext":true,"cited_by_count":21,"citation_normalized_percentile":{"value":0.85374659,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"7","issue":"1","first_page":"54","last_page":"54"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.8863999843597412,"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":0.8863999843597412,"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/T12527","display_name":"Chemistry and Stereochemistry Studies","score":0.023099999874830246,"subfield":{"id":"https://openalex.org/subfields/1605","display_name":"Organic Chemistry"},"field":{"id":"https://openalex.org/fields/16","display_name":"Chemistry"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.008899999782443047,"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/identifier","display_name":"Identifier","score":0.7348864674568176},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6899710297584534},{"id":"https://openalex.org/keywords/ambiguity","display_name":"Ambiguity","score":0.6703166365623474},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.5842998623847961},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4969682991504669},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4288698434829712},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.40412479639053345},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.082282155752182}],"concepts":[{"id":"https://openalex.org/C154504017","wikidata":"https://www.wikidata.org/wiki/Q853614","display_name":"Identifier","level":2,"score":0.7348864674568176},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6899710297584534},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.6703166365623474},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.5842998623847961},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4969682991504669},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4288698434829712},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.40412479639053345},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.082282155752182}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.1186/s13321-015-0102-6","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-015-0102-6","pdf_url":"https://link.springer.com/content/pdf/10.1186/s13321-015-0102-6.pdf","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:26579214","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_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":null},{"id":"pmh:oai:pure.eur.nl:openaire_cris_publications/46da1fee-9dfd-43f3-8d2f-0ad985a29b61","is_oa":false,"landing_page_url":"https://pure.eur.nl/en/publications/46da1fee-9dfd-43f3-8d2f-0ad985a29b61","pdf_url":null,"source":{"id":"https://openalex.org/S4306401266","display_name":"EUR Research Repository (Erasmus University Rotterdam)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I913958620","host_organization_name":"Erasmus University Rotterdam","host_organization_lineage":["https://openalex.org/I913958620"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Ahmad Akhondi, S, Muresan, S, Williams, AJ & Kors, J 2015, 'Ambiguity of non-systematic chemical identifiers within and between small-molecule databases', Journal of Cheminformatics, vol. 7. https://doi.org/10.1186/s13321-015-0102-6","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:eur:oai:repub.eur.nl:79177","is_oa":true,"landing_page_url":"http://hdl.handle.net/1765/79177","pdf_url":null,"source":{"id":"https://openalex.org/S4306401843","display_name":"Data Archiving and Networked Services (DANS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1322597698","host_organization_name":"Royal Netherlands Academy of Arts and Sciences","host_organization_lineage":["https://openalex.org/I1322597698"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:europepmc.org:3619033","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/4646925","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:repub.eur.nl:79177","is_oa":true,"landing_page_url":"http://repub.eur.nl/pub/79177","pdf_url":null,"source":{"id":"https://openalex.org/S4377196287","display_name":"RePub (Erasmus University Rotterdam)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I913958620","host_organization_name":"Erasmus University Rotterdam","host_organization_lineage":["https://openalex.org/I913958620"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Journal of Cheminformatics vol. 7 no. 1","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1186/s13321-015-0102-6","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-015-0102-6","pdf_url":"https://link.springer.com/content/pdf/10.1186/s13321-015-0102-6.pdf","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":[],"awards":[{"id":"https://openalex.org/G8849530879","display_name":null,"funder_award_id":"102695","funder_id":"https://openalex.org/F4320307770","funder_display_name":"AstraZeneca"}],"funders":[{"id":"https://openalex.org/F4320307770","display_name":"AstraZeneca","ror":"https://ror.org/04r9x1a08"},{"id":"https://openalex.org/F4320320006","display_name":"Royal Society","ror":"https://ror.org/03wnrjx87"},{"id":"https://openalex.org/F4320320251","display_name":"Royal Society of Chemistry","ror":"https://ror.org/025sbr097"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2172533829.pdf","grobid_xml":"https://content.openalex.org/works/W2172533829.grobid-xml"},"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/W2353179089","https://openalex.org/W4378651134","https://openalex.org/W2923538289","https://openalex.org/W2353125546","https://openalex.org/W2470643824","https://openalex.org/W4400595174","https://openalex.org/W2349635380","https://openalex.org/W4353089801","https://openalex.org/W2353819554","https://openalex.org/W2359488321"],"abstract_inverted_index":{"BACKGROUND:":[0],"A":[1,153],"wide":[2,154],"range":[3,155],"of":[4,48,52,97,113,121,127,156,170,191,202],"chemical":[5,24,106,114,195],"compound":[6,16,44],"databases":[7,25,131,166,183,196],"are":[8,30,39,163,206],"currently":[9],"available":[10],"for":[11,150,159],"pharmaceutical":[12],"research.":[13],"To":[14],"retrieve":[15],"information,":[17],"including":[18],"structures,":[19],"researchers":[20],"can":[21,63,224],"query":[22],"these":[23],"using":[26],"non-systematic":[27,53,98,122,128,160,192,203],"identifiers.":[28,123],"These":[29],"source-dependent":[31],"identifiers":[32,54,99,129,161,193,204],"(e.g.,":[33],"brand":[34],"names,":[35],"generic":[36],"names),":[37],"which":[38,68],"usually":[40],"assigned":[41],"to":[42,75,135,146,218,226],"the":[43,46,60,95,111,119,143,177,216],"at":[45],"point":[47],"registration.":[49],"The":[50,125],"correctness":[51],"(i.e.,":[55,80],"whether":[56,81],"an":[57,82],"identifier":[58,83],"matches":[59,84],"associated":[61],"structure)":[62],"only":[64,145],"be":[65],"assessed":[66],"manually,":[67],"is":[69,73,197,210],"cumbersome,":[70],"but":[71,200],"it":[72],"possible":[74],"automatically":[76],"check":[77],"their":[78],"ambiguity":[79,96,120,126,144,157,181,201,217],"more":[85],"than":[86],"one":[87],"structure).":[88],"In":[89],"this":[90],"study":[91],"we":[92],"have":[93],"quantified":[94],"within":[100,130,194],"and":[101,231],"between":[102,165,208],"eight":[103],"widely":[104],"used":[105],"databases.":[107,152],"We":[108],"also":[109],"studied":[110],"effect":[112],"structure":[115,213],"standardization":[116,214],"on":[117],"reducing":[118],"RESULTS:":[124],"varied":[132],"from":[133],"0.1":[134],"15.2":[136],"%":[137],"(median":[138,184],"2.5":[139],"%).":[140,172],"Standardization":[141],"reduced":[142],"a":[147,219],"small":[148],"extent":[149],"most":[151],"existed":[158],"that":[162,205],"shared":[164,207],"(17.7-60.2":[167],"%,":[168],"median":[169],"40.3":[171],"Removing":[173],"stereochemistry":[174],"information":[175],"provided":[176],"largest":[178],"reduction":[179,185],"in":[180],"across":[182],"13.7":[186],"percentage":[187],"points).":[188],"CONCLUSIONS:":[189],"Ambiguity":[190],"generally":[198],"low,":[199],"databases,":[209],"high.":[211],"Chemical":[212],"reduces":[215],"limited":[220],"extent.":[221],"Our":[222],"findings":[223],"help":[225],"improve":[227],"database":[228],"integration,":[229],"curation,":[230],"maintenance.":[232]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"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":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}
