{"id":"https://openalex.org/W1970550359","doi":"https://doi.org/10.1186/1758-2946-5-s1-p38","title":"PubChem: atom environments for molecule standardization","display_name":"PubChem: atom environments for molecule standardization","publication_year":2013,"publication_date":"2013-03-01","ids":{"openalex":"https://openalex.org/W1970550359","doi":"https://doi.org/10.1186/1758-2946-5-s1-p38","mag":"1970550359"},"language":"en","primary_location":{"id":"doi:10.1186/1758-2946-5-s1-p38","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1758-2946-5-s1-p38","pdf_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/1758-2946-5-S1-P38","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"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/1758-2946-5-S1-P38","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5044443830","display_name":"Volker H\u00e4hnke","orcid":"https://orcid.org/0000-0002-4032-7601"},"institutions":[{"id":"https://openalex.org/I1299303238","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88","country_code":"US","type":"government","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238"]},{"id":"https://openalex.org/I4210109390","display_name":"National Center for Biotechnology Information","ror":"https://ror.org/02meqm098","country_code":"US","type":"facility","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238","https://openalex.org/I2800548410","https://openalex.org/I4210109390"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Volker H\u00e4hnke","raw_affiliation_strings":["National Center for Biotechnology Information, National Library of Medicine, National Institutes of Health, Department of Health and Human Services, Bethesda, Maryland, 20894, USA","National Center for Biotechnology Information National Library of Medicine, National Institutes of Health Department of Health and Human Services, Bethesda, USA"],"affiliations":[{"raw_affiliation_string":"National Center for Biotechnology Information, National Library of Medicine, National Institutes of Health, Department of Health and Human Services, Bethesda, Maryland, 20894, USA","institution_ids":["https://openalex.org/I4210109390"]},{"raw_affiliation_string":"National Center for Biotechnology Information National Library of Medicine, National Institutes of Health Department of Health and Human Services, Bethesda, USA","institution_ids":["https://openalex.org/I1299303238"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015494748","display_name":"Evan Bolton","orcid":"https://orcid.org/0000-0002-5959-6190"},"institutions":[{"id":"https://openalex.org/I1299303238","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88","country_code":"US","type":"government","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238"]},{"id":"https://openalex.org/I4210109390","display_name":"National Center for Biotechnology Information","ror":"https://ror.org/02meqm098","country_code":"US","type":"facility","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238","https://openalex.org/I2800548410","https://openalex.org/I4210109390"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Evan E Bolton","raw_affiliation_strings":["National Center for Biotechnology Information, National Library of Medicine, National Institutes of Health, Department of Health and Human Services, Bethesda, Maryland, 20894, USA","National Center for Biotechnology Information National Library of Medicine, National Institutes of Health Department of Health and Human Services, Bethesda, USA"],"affiliations":[{"raw_affiliation_string":"National Center for Biotechnology Information, National Library of Medicine, National Institutes of Health, Department of Health and Human Services, Bethesda, Maryland, 20894, USA","institution_ids":["https://openalex.org/I4210109390"]},{"raw_affiliation_string":"National Center for Biotechnology Information National Library of Medicine, National Institutes of Health Department of Health and Human Services, Bethesda, USA","institution_ids":["https://openalex.org/I1299303238"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040349721","display_name":"Stephen H. Bryant","orcid":null},"institutions":[{"id":"https://openalex.org/I4210109390","display_name":"National Center for Biotechnology Information","ror":"https://ror.org/02meqm098","country_code":"US","type":"facility","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238","https://openalex.org/I2800548410","https://openalex.org/I4210109390"]},{"id":"https://openalex.org/I1299303238","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88","country_code":"US","type":"government","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Stephen H Bryant","raw_affiliation_strings":["National Center for Biotechnology Information, National Library of Medicine, National Institutes of Health, Department of Health and Human Services, Bethesda, Maryland, 20894, USA","National Center for Biotechnology Information National Library of Medicine, National Institutes of Health Department of Health and Human Services, Bethesda, USA"],"affiliations":[{"raw_affiliation_string":"National Center for Biotechnology Information, National Library of Medicine, National Institutes of Health, Department of Health and Human Services, Bethesda, Maryland, 20894, USA","institution_ids":["https://openalex.org/I4210109390"]},{"raw_affiliation_string":"National Center for Biotechnology Information National Library of Medicine, National Institutes of Health Department of Health and Human Services, Bethesda, USA","institution_ids":["https://openalex.org/I1299303238"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5044443830"],"corresponding_institution_ids":["https://openalex.org/I1299303238","https://openalex.org/I4210109390"],"apc_list":{"value":1290,"currency":"GBP","value_usd":1582},"apc_paid":{"value":1290,"currency":"GBP","value_usd":1582},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.05942427,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"5","issue":"S1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9994000196456909,"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":0.9994000196456909,"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/T11948","display_name":"Machine Learning in Materials Science","score":0.9965999722480774,"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"}},{"id":"https://openalex.org/T10908","display_name":"Analytical Chemistry and Chromatography","score":0.9660000205039978,"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/pubchem","display_name":"PubChem","score":0.9717510938644409},{"id":"https://openalex.org/keywords/standardization","display_name":"Standardization","score":0.9011204838752747},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6148776412010193},{"id":"https://openalex.org/keywords/atom","display_name":"Atom (system on chip)","score":0.5138502717018127},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3601769208908081},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.2567570209503174},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.12019473314285278}],"concepts":[{"id":"https://openalex.org/C158180186","wikidata":"https://www.wikidata.org/wiki/Q278487","display_name":"PubChem","level":2,"score":0.9717510938644409},{"id":"https://openalex.org/C188087704","wikidata":"https://www.wikidata.org/wiki/Q369577","display_name":"Standardization","level":2,"score":0.9011204838752747},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6148776412010193},{"id":"https://openalex.org/C58312451","wikidata":"https://www.wikidata.org/wiki/Q4817200","display_name":"Atom (system on chip)","level":2,"score":0.5138502717018127},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3601769208908081},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.2567570209503174},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.12019473314285278},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1186/1758-2946-5-s1-p38","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1758-2946-5-s1-p38","pdf_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/1758-2946-5-S1-P38","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":"pmh:oai:europepmc.org:2605484","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/3606221","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"}],"best_oa_location":{"id":"doi:10.1186/1758-2946-5-s1-p38","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1758-2946-5-s1-p38","pdf_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/1758-2946-5-S1-P38","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":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1970550359.pdf","grobid_xml":"https://content.openalex.org/works/W1970550359.grobid-xml"},"referenced_works_count":1,"referenced_works":["https://openalex.org/W1601495365"],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2104366126","https://openalex.org/W2547231910","https://openalex.org/W2235675062","https://openalex.org/W2177317049","https://openalex.org/W4293208996","https://openalex.org/W2169546341","https://openalex.org/W2127553917","https://openalex.org/W2013068027"],"abstract_inverted_index":{"PubChem":[0,180],"is":[1,126],"an":[2],"open":[3],"repository":[4],"for":[5,75,85,130,196],"molecular":[6],"structures,":[7],"their":[8],"properties":[9],"and":[10,52,62,71,93,112,160,194,219],"biological":[11],"activities":[12],"[1].":[13],"The":[14],"number":[15],"of":[16,49,54,88,142,176,190,199],"deposited":[17,192],"structures":[18,193],"has":[19],"been":[20],"steadily":[21],"increasing":[22],"since":[23],"its":[24],"creation":[25],"in":[26,95],"2004.":[27],"Today,":[28],"it":[29],"contains":[30],"more":[31],"than":[32],"92":[33],"million":[34,40],"substances":[35],"(PubChem":[36,44],"Substance)":[37],"with":[38,147,211],"32":[39],"unique":[41],"small":[42],"molecules":[43],"Compound).":[45],"Consequently,":[46],"visual":[47],"inspection":[48],"every":[50],"structure":[51,60],"correction":[53],"errors":[55,92],"by":[56,99,169],"hand":[57,170],"to":[58,63,83,179],"detect":[59],"equivalencies":[61],"ensure":[64],"data":[65,105],"quality":[66],"are":[67,77,119,136,167],"not":[68],"feasible.":[69],"Efficient":[70],"reliable":[72],"automated":[73,113],"methods":[74],"standardization":[76,123],"necessary":[78],"during":[79],"the":[80,173,191,197,207,215],"registration":[81],"process":[82],"compensate":[84],"alternating":[86],"representations":[87,97],"as":[89,91,202],"well":[90],"artifacts":[94],"(sub)structure":[96],"caused":[98],"diverging":[100],"business":[101],"rules,":[102],"personal":[103],"preferences,":[104],"format":[106],"conversion,":[107],"disagreements":[108],"between":[109],"aromaticity":[110,161],"definitions":[111],"library":[114],"generation.":[115],"At":[116],"PubChem,":[117],"we":[118,181,205],"developing":[120],"a":[121,139,148],"new":[122],"approach":[124],"that":[125],"based":[127],"on":[128,183],"rules":[129,135],"atom":[131,143,164,200],"environment":[132,144,165],"transformation.":[133],"Those":[134,187],"obtained":[137,210],"from":[138],"statistical":[140],"analysis":[141],"transformations":[145],"observed":[146],"reference":[149],"workflow":[150],"combining":[151],"chemical":[152],"reasonability":[153],"checks,":[154],"valence":[155],"filters,":[156],"canonical":[157],"tautomer":[158],"determination":[159],"normalization.":[162],"Additional":[163],"mappings":[166],"provided":[168],"curation.":[171],"In":[172],"first":[174,208],"application":[175],"our":[177,212],"technique":[178],"concentrate":[182],"purely":[184],"organic":[185],"compounds.":[186],"represent":[188],"97%":[189],"account":[195],"majority":[198],"environments":[201],"well.":[203],"Here,":[204],"present":[206],"results":[209],"approach,":[213],"highlighting":[214],"methodology,":[216],"challenges,":[217],"benefits":[218],"future":[220],"possibilities.":[221]},"counts_by_year":[],"updated_date":"2026-03-17T17:19:04.345684","created_date":"2025-10-10T00:00:00"}