{"id":"https://openalex.org/W2547231910","doi":"https://doi.org/10.1186/s13321-016-0163-1","title":"Similar compounds versus similar conformers: complementarity between PubChem 2-D and 3-D neighboring sets","display_name":"Similar compounds versus similar conformers: complementarity between PubChem 2-D and 3-D neighboring sets","publication_year":2016,"publication_date":"2016-11-04","ids":{"openalex":"https://openalex.org/W2547231910","doi":"https://doi.org/10.1186/s13321-016-0163-1","mag":"2547231910","pmid":"https://pubmed.ncbi.nlm.nih.gov/27872662"},"language":"en","primary_location":{"id":"doi:10.1186/s13321-016-0163-1","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-016-0163-1","pdf_url":"https://jcheminf.biomedcentral.com/track/pdf/10.1186/s13321-016-0163-1","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","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://jcheminf.biomedcentral.com/track/pdf/10.1186/s13321-016-0163-1","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100430147","display_name":"Sunghwan Kim","orcid":"https://orcid.org/0000-0001-9828-2074"},"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":"Sunghwan Kim","raw_affiliation_strings":["National Center for Biotechnology Information, National Library of Medicine, National Institutes of Health, Department of Health and Human Services, 8600 Rockville Pike, Bethesda, MD 20894 USA","National Center for Biotechnology Information, National Library of Medicine, National Institutes of Health, Department of Health and Human Services, 8600 Rockville Pike, Bethesda, MD, 20894, USA"],"raw_orcid":"https://orcid.org/0000-0001-9828-2074","affiliations":[{"raw_affiliation_string":"National Center for Biotechnology Information, National Library of Medicine, National Institutes of Health, Department of Health and Human Services, 8600 Rockville Pike, Bethesda, MD 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, 8600 Rockville Pike, Bethesda, MD, 20894, USA","institution_ids":["https://openalex.org/I1299303238","https://openalex.org/I4210109390"]}]},{"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, 8600 Rockville Pike, Bethesda, MD 20894 USA","National Center for Biotechnology Information, National Library of Medicine, National Institutes of Health, Department of Health and Human Services, 8600 Rockville Pike, Bethesda, MD, 20894, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Center for Biotechnology Information, National Library of Medicine, National Institutes of Health, Department of Health and Human Services, 8600 Rockville Pike, Bethesda, MD 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, 8600 Rockville Pike, Bethesda, MD, 20894, USA","institution_ids":["https://openalex.org/I1299303238","https://openalex.org/I4210109390"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040349721","display_name":"Stephen H. Bryant","orcid":null},"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":"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, 8600 Rockville Pike, Bethesda, MD 20894 USA","National Center for Biotechnology Information, National Library of Medicine, National Institutes of Health, Department of Health and Human Services, 8600 Rockville Pike, Bethesda, MD, 20894, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Center for Biotechnology Information, National Library of Medicine, National Institutes of Health, Department of Health and Human Services, 8600 Rockville Pike, Bethesda, MD 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, 8600 Rockville Pike, Bethesda, MD, 20894, USA","institution_ids":["https://openalex.org/I1299303238","https://openalex.org/I4210109390"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100430147"],"corresponding_institution_ids":["https://openalex.org/I1299303238","https://openalex.org/I4210109390"],"apc_list":{"value":2190,"currency":"USD","value_usd":2190},"apc_paid":{"value":2190,"currency":"USD","value_usd":2190},"fwci":1.6308,"has_fulltext":true,"cited_by_count":21,"citation_normalized_percentile":{"value":0.86108846,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"8","issue":"1","first_page":"62","last_page":"62"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9787999987602234,"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":0.9787999987602234,"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":0.0019000000320374966,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.0017000000225380063,"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/pubchem","display_name":"PubChem","score":0.9461969137191772},{"id":"https://openalex.org/keywords/complementarity","display_name":"Complementarity (molecular biology)","score":0.7053907513618469},{"id":"https://openalex.org/keywords/conformational-isomerism","display_name":"Conformational isomerism","score":0.6221417188644409},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5143090486526489},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.3676599860191345},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3675828278064728},{"id":"https://openalex.org/keywords/organic-chemistry","display_name":"Organic chemistry","score":0.1399661898612976},{"id":"https://openalex.org/keywords/molecule","display_name":"Molecule","score":0.10924637317657471},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.10825538635253906}],"concepts":[{"id":"https://openalex.org/C158180186","wikidata":"https://www.wikidata.org/wiki/Q278487","display_name":"PubChem","level":2,"score":0.9461969137191772},{"id":"https://openalex.org/C202269582","wikidata":"https://www.wikidata.org/wiki/Q2644277","display_name":"Complementarity (molecular biology)","level":2,"score":0.7053907513618469},{"id":"https://openalex.org/C18705241","wikidata":"https://www.wikidata.org/wiki/Q1128023","display_name":"Conformational isomerism","level":3,"score":0.6221417188644409},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5143090486526489},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.3676599860191345},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3675828278064728},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.1399661898612976},{"id":"https://openalex.org/C32909587","wikidata":"https://www.wikidata.org/wiki/Q11369","display_name":"Molecule","level":2,"score":0.10924637317657471},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.10825538635253906},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1186/s13321-016-0163-1","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-016-0163-1","pdf_url":"https://jcheminf.biomedcentral.com/track/pdf/10.1186/s13321-016-0163-1","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Cheminformatics","raw_type":"journal-article"},{"id":"pmid:27872662","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/27872662","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:pubmedcentral.nih.gov:5097428","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/5097428","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":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"J Cheminform","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1186/s13321-016-0163-1","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-016-0163-1","pdf_url":"https://jcheminf.biomedcentral.com/track/pdf/10.1186/s13321-016-0163-1","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Cheminformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306085","display_name":"U.S. Department of Health and Human Services","ror":"https://ror.org/033jnv181"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337372","display_name":"U.S. National Library of Medicine","ror":"https://ror.org/0060t0j89"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2547231910.pdf","grobid_xml":"https://content.openalex.org/works/W2547231910.grobid-xml"},"referenced_works_count":36,"referenced_works":["https://openalex.org/W1917819059","https://openalex.org/W1988909822","https://openalex.org/W2005386196","https://openalex.org/W2013068027","https://openalex.org/W2019538911","https://openalex.org/W2022478977","https://openalex.org/W2024610405","https://openalex.org/W2027065525","https://openalex.org/W2039197391","https://openalex.org/W2060097376","https://openalex.org/W2071234745","https://openalex.org/W2075186867","https://openalex.org/W2077004593","https://openalex.org/W2080886752","https://openalex.org/W2087179087","https://openalex.org/W2094493457","https://openalex.org/W2096525273","https://openalex.org/W2096560421","https://openalex.org/W2099731392","https://openalex.org/W2112990058","https://openalex.org/W2116345848","https://openalex.org/W2127553917","https://openalex.org/W2130479394","https://openalex.org/W2135812506","https://openalex.org/W2144659448","https://openalex.org/W2146844279","https://openalex.org/W2153057704","https://openalex.org/W2157491247","https://openalex.org/W2164045406","https://openalex.org/W2169546341","https://openalex.org/W2170481351","https://openalex.org/W2177317049","https://openalex.org/W2249269905","https://openalex.org/W2260675179","https://openalex.org/W4230466483","https://openalex.org/W4230784961"],"related_works":["https://openalex.org/W4387497383","https://openalex.org/W2948807893","https://openalex.org/W2899084033","https://openalex.org/W2778153218","https://openalex.org/W2748952813","https://openalex.org/W1531601525","https://openalex.org/W4391375266","https://openalex.org/W2104366126","https://openalex.org/W2547231910","https://openalex.org/W2146844279"],"abstract_inverted_index":{"PubChem":[0,22,38,43,58,124,133,184,228,385,414,482],"is":[1,91,108,370,477],"a":[2,199,202,211,231,242,261,267,286,329,390,401,440,446,465],"public":[3],"repository":[4],"for":[5,82,201,226,252,270,300,343,381,432,449],"biological":[6],"activities":[7],"of":[8,15,19,69,102,146,177,198,264,295,303,375,443],"small":[9],"molecules.":[10],"For":[11,150],"the":[12,37,42,49,61,67,100,103,120,123,136,147,151,159,163,220,249,253,275,301,304,354,376,433,454,474,481],"efficient":[13],"use":[14],"its":[16,340],"vast":[17],"amount":[18],"chemical":[20],"information,":[21,158],"performs":[23],"2-dimensional":[24],"(2-D)":[25],"and":[26,48,71,78,126,140,174,241,334,400],"3-dimensional":[27],"(3-D)":[28],"neighborings,":[29,323,424],"which":[30,208,353],"precompute":[31],"\u201cneighbor\u201d":[32],"relationships":[33],"between":[34,122,138,332,411],"molecules":[35,361],"in":[36,85,132,219,306,352,384,413],"Compound":[39],"database,":[40],"using":[41],"subgraph":[44],"fingerprints-based":[45],"2-D":[46,70,96,125,139,185,215,320,333,368,421],"similarity":[47,310,410],"Gaussian-shape":[50],"overlay-based":[51],"3-D":[52,72,89,127,141,187,217,322,335,346,423],"similarity,":[53,188],"respectively.":[54],"These":[55],"neighborings":[56],"allow":[57],"to":[59,66,274,311,453],"provide":[60],"user":[62,355],"with":[63,156,234,257,266,285,393,445,464],"immediate":[64],"access":[65,358],"list":[68],"neighbors":[73,142,178,218],"(also":[74],"called":[75],"\u201cSimilar":[76,79],"Compounds\u201d":[77],"Conformers\u201d,":[80],"respectively)":[81],"each":[83],"compound":[84],"PubChem.":[86],"However,":[87,168,248],"because":[88],"neighboring":[90,105,272,336,347,369,451],"much":[92],"more":[93,214],"time-consuming":[94],"than":[95],"neighboring,":[97],"how":[98],"different":[99,479],"results":[101,294],"two":[104,235,394],"schemes":[106],"are":[107],"an":[109,349],"important":[110],"question,":[111],"considering":[112],"limited":[113],"computational":[114,344],"resources.":[115],"The":[116,193,223,293,372,429],"present":[117],"study":[118,297],"analyzed":[119],"complementarity":[121,331],"neighbors.":[128,149],"When":[129],"all":[130,227,382],"compounds":[131,155,229,256,265,284,305,313,383,412,444,463],"were":[134,179],"considered,":[135],"overlap":[137,160],"was":[143,206],"only":[144,367],"2%":[145],"total":[148],"data":[152,164,204,221],"sets":[153,165],"containing":[154,255],"annotated":[157,258],"increased":[161],"as":[162,281,283,460,462],"became":[166],"smaller.":[167],"it":[169],"did":[170],"not":[171,190,325,426],"exceed":[172],"31%":[173],"substantial":[175],"fractions":[176],"still":[180],"recognized":[181,316,417],"by":[182,191,318,326,419,427],"either":[183,319,420],"or":[186,216,321,422],"but":[189,324,425],"both.":[192,428],"Neighbor":[194],"Preference":[195],"Index":[196],"(NPI)":[197],"molecule":[200,212],"given":[203],"set":[205],"introduced,":[207],"quantified":[209],"whether":[210],"had":[213,230,260],"set.":[222],"NPI":[224,238,245,250,278,290,397,404,430,457,469],"histogram":[225,431],"bimodal":[232,391],"shape":[233,392],"maxima":[236,395],"at":[237,244,396,403],"=":[239,246,279,291,398,405],"\u00b11":[240,399],"minimum":[243,402],"0.":[247],"histograms":[251],"subsets":[254],"information":[259],"greater":[262,441],"fraction":[263,442],"strong":[268,330,447],"preference":[269,288,378,448,467],"one":[271,450],"method":[273,452],"other":[276,312,455],"(at":[277,289,456,468],"\u00b11)":[280,459],"well":[282,461],"neutral":[287,466],"0).":[292],"our":[296],"indicate":[298],"that,":[299],"majority":[302],"PubChem,":[307],"their":[308],"structural":[309,409],"can":[314,356,415],"be":[315,364,416],"predominantly":[317,418],"both,":[327],"showing":[328],"results.":[337],"Therefore,":[338],"despite":[339],"heavy":[341],"requirements":[342],"resources,":[345],"provides":[348],"alternative":[350],"way":[351],"instantly":[357],"structurally":[359],"similar":[360],"that":[362,408,473],"cannot":[363],"detected":[365],"if":[366],"used.":[371],"binned":[373],"distribution":[374],"neighbor":[377],"indices":[379],"(NPIs)":[380],"(":[386,436],"left":[387],")":[388,438],"has":[389,439],"0,":[406],"indicating":[407,472],"drug":[434,475],"space":[435,476],"right":[437],"\u2248":[458,470],"0),":[471],"very":[478],"from":[480],"space.":[483]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":6},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":1}],"updated_date":"2026-08-03T07:22:36.454288","created_date":"2025-10-10T00:00:00"}