{"id":"https://openalex.org/W1546956326","doi":"https://doi.org/10.1186/s13321-015-0072-8","title":"The Chemical Validation and Standardization Platform (CVSP): large-scale automated validation of chemical structure datasets","display_name":"The Chemical Validation and Standardization Platform (CVSP): large-scale automated validation of chemical structure datasets","publication_year":2015,"publication_date":"2015-06-18","ids":{"openalex":"https://openalex.org/W1546956326","doi":"https://doi.org/10.1186/s13321-015-0072-8","mag":"1546956326","pmid":"https://pubmed.ncbi.nlm.nih.gov/26155308","pmcid":"https://www.ncbi.nlm.nih.gov/pmc/articles/4494041"},"language":"en","primary_location":{"is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-015-0072-8","pdf_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-015-0072-8","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/s13321-015-0072-8","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5032678781","display_name":"K. V. Karapetyan","orcid":"https://orcid.org/0000-0003-2052-5034"},"institutions":[],"countries":["US"],"is_corresponding":false,"raw_author_name":"Karen Karapetyan","raw_affiliation_strings":["Royal Society of Chemistry, Wake Forest, USA"],"affiliations":[{"raw_affiliation_string":"Royal Society of Chemistry, Wake Forest, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052275685","display_name":"Colin Batchelor","orcid":"https://orcid.org/0000-0001-5985-7429"},"institutions":[],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Colin Batchelor","raw_affiliation_strings":["Thomas Graham House, Cambridge, UK"],"affiliations":[{"raw_affiliation_string":"Thomas Graham House, Cambridge, UK","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039700952","display_name":"D R Sharpe","orcid":"https://orcid.org/0000-0001-5543-2503"},"institutions":[],"countries":["GB"],"is_corresponding":false,"raw_author_name":"David Sharpe","raw_affiliation_strings":["Thomas Graham House, Cambridge, UK"],"affiliations":[{"raw_affiliation_string":"Thomas Graham House, Cambridge, UK","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112237087","display_name":"Valery Tkachenko","orcid":null},"institutions":[],"countries":["US"],"is_corresponding":false,"raw_author_name":"Valery Tkachenko","raw_affiliation_strings":["Royal Society of Chemistry, Wake Forest, USA"],"affiliations":[{"raw_affiliation_string":"Royal Society of Chemistry, Wake Forest, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062051745","display_name":"Antony Williams","orcid":"https://orcid.org/0000-0002-2668-4821"},"institutions":[{"id":"https://openalex.org/I1302368450","display_name":"Environmental Protection Agency","ror":"https://ror.org/03tns0030","country_code":"US","type":"government","lineage":["https://openalex.org/I1302368450"]},{"id":"https://openalex.org/I1309191912","display_name":"Research Triangle Park Foundation","ror":"https://ror.org/03eqttr49","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1309191912"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Antony J Williams","raw_affiliation_strings":["Environmental Protection Agency, Research Triangle Park, USA","Royal Society of Chemistry, Wake Forest, USA"],"affiliations":[{"raw_affiliation_string":"Environmental Protection Agency, Research Triangle Park, USA","institution_ids":["https://openalex.org/I1302368450","https://openalex.org/I1309191912"]},{"raw_affiliation_string":"Royal Society of Chemistry, Wake Forest, USA","institution_ids":[]}]}],"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":3.598,"has_fulltext":true,"fulltext_origin":"pdf","cited_by_count":27,"citation_normalized_percentile":{"value":0.838998,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":92,"max":93},"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":0.9999,"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":0.9999,"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":0.9973,"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":0.99,"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/cheminformatics","display_name":"Cheminformatics","score":0.91338253},{"id":"https://openalex.org/keywords/chemical-database","display_name":"Chemical database","score":0.47394824}],"concepts":[{"id":"https://openalex.org/C68762167","wikidata":"https://www.wikidata.org/wiki/Q910164","display_name":"Cheminformatics","level":2,"score":0.91338253},{"id":"https://openalex.org/C188087704","wikidata":"https://www.wikidata.org/wiki/Q369577","display_name":"Standardization","level":2,"score":0.78337395},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.77852947},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.55987364},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.55053324},{"id":"https://openalex.org/C203394866","wikidata":"https://www.wikidata.org/wiki/Q2881060","display_name":"Chemical database","level":2,"score":0.47394824},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4705755},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.43519908},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.39481127},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.34264222},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.18135041},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.17780277},{"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":3,"locations":[{"is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-015-0072-8","pdf_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-015-0072-8","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://www.ncbi.nlm.nih.gov/pmc/articles/PMC4494041","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/26155308","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/s13321-015-0072-8","pdf_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-015-0072-8","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":[{"id":"https://metadata.un.org/sdg/17","score":0.51,"display_name":"Partnerships for the goals"}],"grants":[],"datasets":[],"versions":[],"referenced_works_count":26,"referenced_works":["https://openalex.org/W1493980486","https://openalex.org/W1518253129","https://openalex.org/W1835740130","https://openalex.org/W1975147762","https://openalex.org/W1976892175","https://openalex.org/W1984678368","https://openalex.org/W1989405983","https://openalex.org/W2009313526","https://openalex.org/W2033377040","https://openalex.org/W2041610798","https://openalex.org/W2084254228","https://openalex.org/W2087563523","https://openalex.org/W2096541451","https://openalex.org/W2116238734","https://openalex.org/W2137052779","https://openalex.org/W2143392414","https://openalex.org/W2155741020","https://openalex.org/W2169678694","https://openalex.org/W2170146596","https://openalex.org/W2487152033","https://openalex.org/W2505382393","https://openalex.org/W2912724381","https://openalex.org/W2976869771","https://openalex.org/W4285719527","https://openalex.org/W45940268","https://openalex.org/W71547456"],"related_works":["https://openalex.org/W3143892890","https://openalex.org/W2988249053","https://openalex.org/W2903373627","https://openalex.org/W2561309435","https://openalex.org/W2317928565","https://openalex.org/W2185159477","https://openalex.org/W2153037537","https://openalex.org/W2127121938","https://openalex.org/W2066666235","https://openalex.org/W158734140"],"abstract_inverted_index":{"There":[0],"are":[1,50],"presently":[2],"hundreds":[3],"of":[4,9,18,21,45,53,71,92],"online":[5],"databases":[6],"hosting":[7],"millions":[8],"chemical":[10,59,72,93],"compounds":[11],"and":[12,69],"associated":[13],"data.":[14],"As":[15],"a":[16,51,81],"result":[17],"the":[19,31,36,43,46,87,90],"number":[20],"cheminformatics":[22,38],"software":[23,47],"tools":[24],"that":[25,55],"can":[26,56],"be":[27],"used":[28],"to":[29,65,86],"produce":[30],"data,":[32],"subtle":[33],"differences":[34],"between":[35],"various":[37,76],"platforms,":[39],"as":[40,42],"well":[41],"naivety":[44],"users,":[48],"there":[49],"myriad":[52],"issues":[54],"exist":[57],"with":[58],"structure":[60,73],"representations":[61],"online.":[62],"In":[63],"order":[64],"help":[66],"facilitate":[67],"validation":[68],"standardization":[70],"datasets":[74],"from":[75],"sources":[77],"we":[78],"have":[79],"delivered":[80],"freely":[82],"available":[83],"internet-based":[84],"platform":[85],"community":[88],"for":[89],"processing":[91],"compound":[94],"datasets.":[95]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W1546956326","counts_by_year":[{"year":2024,"cited_by_count":4},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":1}],"updated_date":"2025-01-03T03:53:04.896796","created_date":"2016-06-24"}