{"id":"https://openalex.org/W1967893020","doi":"https://doi.org/10.1021/ci600552n","title":"Molecular Basis SetsA General Similarity-Based Approach for Representing Chemical Spaces","display_name":"Molecular Basis SetsA General Similarity-Based Approach for Representing Chemical Spaces","publication_year":2007,"publication_date":"2007-06-07","ids":{"openalex":"https://openalex.org/W1967893020","doi":"https://doi.org/10.1021/ci600552n","mag":"1967893020","pmid":"https://pubmed.ncbi.nlm.nih.gov/17552511"},"language":"en","primary_location":{"id":"doi:10.1021/ci600552n","is_oa":false,"landing_page_url":"https://doi.org/10.1021/ci600552n","pdf_url":null,"source":{"id":"https://openalex.org/S167262187","display_name":"Journal of Chemical Information and Modeling","issn_l":"1549-9596","issn":["1549-9596","1549-960X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320006","host_organization_name":"American Chemical Society","host_organization_lineage":["https://openalex.org/P4310320006"],"host_organization_lineage_names":["American Chemical Society"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Chemical Information and Modeling","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Akshay S. Raghavendra","orcid":null},"institutions":[{"id":"https://openalex.org/I138006243","display_name":"University of Arizona","ror":"https://ror.org/03m2x1q45","country_code":"US","type":"education","lineage":["https://openalex.org/I138006243"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Akshay S. Raghavendra","raw_affiliation_strings":["Electrical & Computer Engineering, BIO5 Institute, and College of Pharmacy, University of Arizona, Tucson, Arizona 85721"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electrical & Computer Engineering, BIO5 Institute, and College of Pharmacy, University of Arizona, Tucson, Arizona 85721","institution_ids":["https://openalex.org/I138006243"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055069582","display_name":"Gerald M. Maggiora","orcid":"https://orcid.org/0000-0002-1839-2650"},"institutions":[{"id":"https://openalex.org/I138006243","display_name":"University of Arizona","ror":"https://ror.org/03m2x1q45","country_code":"US","type":"education","lineage":["https://openalex.org/I138006243"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Gerald M. Maggiora","raw_affiliation_strings":["Electrical & Computer Engineering, BIO5 Institute, and College of Pharmacy, University of Arizona, Tucson, Arizona 85721"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electrical & Computer Engineering, BIO5 Institute, and College of Pharmacy, University of Arizona, Tucson, Arizona 85721","institution_ids":["https://openalex.org/I138006243"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5055069582"],"corresponding_institution_ids":["https://openalex.org/I138006243"],"apc_list":null,"apc_paid":null,"fwci":1.1225,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.77071546,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"47","issue":"4","first_page":"1328","last_page":"1340"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9995999932289124,"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":0.9995999932289124,"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/T10640","display_name":"Spectroscopy and Chemometric Analyses","score":0.9907000064849854,"subfield":{"id":"https://openalex.org/subfields/1602","display_name":"Analytical 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/T10908","display_name":"Analytical Chemistry and Chromatography","score":0.9793999791145325,"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/orthonormal-basis","display_name":"Orthonormal basis","score":0.8067110776901245},{"id":"https://openalex.org/keywords/basis","display_name":"Basis (linear algebra)","score":0.7973859906196594},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.693600058555603},{"id":"https://openalex.org/keywords/orthonormality","display_name":"Orthonormality","score":0.6263784170150757},{"id":"https://openalex.org/keywords/orthogonal-basis","display_name":"Orthogonal basis","score":0.6018452048301697},{"id":"https://openalex.org/keywords/orthogonalization","display_name":"Orthogonalization","score":0.5090172290802002},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5060033202171326},{"id":"https://openalex.org/keywords/basis-function","display_name":"Basis function","score":0.477448046207428},{"id":"https://openalex.org/keywords/norm","display_name":"Norm (philosophy)","score":0.4676764905452728},{"id":"https://openalex.org/keywords/sto-ng-basis-sets","display_name":"STO-nG basis sets","score":0.45963627099990845},{"id":"https://openalex.org/keywords/vector-space","display_name":"Vector space","score":0.41643714904785156},{"id":"https://openalex.org/keywords/basis-set","display_name":"Basis set","score":0.1951391100883484},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1843472719192505},{"id":"https://openalex.org/keywords/pure-mathematics","display_name":"Pure mathematics","score":0.16890981793403625},{"id":"https://openalex.org/keywords/mathematical-analysis","display_name":"Mathematical analysis","score":0.16665393114089966},{"id":"https://openalex.org/keywords/geometry","display_name":"Geometry","score":0.15746033191680908},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.12156590819358826},{"id":"https://openalex.org/keywords/molecule","display_name":"Molecule","score":0.10073825716972351},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.09763669967651367},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.08893713355064392}],"concepts":[{"id":"https://openalex.org/C5806529","wikidata":"https://www.wikidata.org/wiki/Q2365325","display_name":"Orthonormal basis","level":2,"score":0.8067110776901245},{"id":"https://openalex.org/C12426560","wikidata":"https://www.wikidata.org/wiki/Q189569","display_name":"Basis (linear algebra)","level":2,"score":0.7973859906196594},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.693600058555603},{"id":"https://openalex.org/C92951342","wikidata":"https://www.wikidata.org/wiki/Q1411166","display_name":"Orthonormality","level":3,"score":0.6263784170150757},{"id":"https://openalex.org/C187064257","wikidata":"https://www.wikidata.org/wiki/Q3306808","display_name":"Orthogonal basis","level":2,"score":0.6018452048301697},{"id":"https://openalex.org/C47559304","wikidata":"https://www.wikidata.org/wiki/Q1702189","display_name":"Orthogonalization","level":2,"score":0.5090172290802002},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5060033202171326},{"id":"https://openalex.org/C5917680","wikidata":"https://www.wikidata.org/wiki/Q2621825","display_name":"Basis function","level":2,"score":0.477448046207428},{"id":"https://openalex.org/C191795146","wikidata":"https://www.wikidata.org/wiki/Q3878446","display_name":"Norm (philosophy)","level":2,"score":0.4676764905452728},{"id":"https://openalex.org/C150279259","wikidata":"https://www.wikidata.org/wiki/Q2886427","display_name":"STO-nG basis sets","level":5,"score":0.45963627099990845},{"id":"https://openalex.org/C13336665","wikidata":"https://www.wikidata.org/wiki/Q125977","display_name":"Vector space","level":2,"score":0.41643714904785156},{"id":"https://openalex.org/C65956243","wikidata":"https://www.wikidata.org/wiki/Q2664086","display_name":"Basis set","level":3,"score":0.1951391100883484},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1843472719192505},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.16890981793403625},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.16665393114089966},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.15746033191680908},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.12156590819358826},{"id":"https://openalex.org/C32909587","wikidata":"https://www.wikidata.org/wiki/Q11369","display_name":"Molecule","level":2,"score":0.10073825716972351},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.09763669967651367},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.08893713355064392},{"id":"https://openalex.org/C53848692","wikidata":"https://www.wikidata.org/wiki/Q900666","display_name":"Linear combination of atomic orbitals","level":4,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1021/ci600552n","is_oa":false,"landing_page_url":"https://doi.org/10.1021/ci600552n","pdf_url":null,"source":{"id":"https://openalex.org/S167262187","display_name":"Journal of Chemical Information and Modeling","issn_l":"1549-9596","issn":["1549-9596","1549-960X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320006","host_organization_name":"American Chemical Society","host_organization_lineage":["https://openalex.org/P4310320006"],"host_organization_lineage_names":["American Chemical Society"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Chemical Information and Modeling","raw_type":"journal-article"},{"id":"pmid:17552511","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/17552511","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 chemical information and modeling","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320310160","display_name":"University of Arizona","ror":"https://ror.org/03m2x1q45"},{"id":"https://openalex.org/F4320334347","display_name":"BIO5 Institute, University of Arizona","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W204885769","https://openalex.org/W636881225","https://openalex.org/W1510073064","https://openalex.org/W1534408902","https://openalex.org/W1562327279","https://openalex.org/W1575639801","https://openalex.org/W1964347042","https://openalex.org/W1971458166","https://openalex.org/W1974373855","https://openalex.org/W1974697910","https://openalex.org/W1976160686","https://openalex.org/W1995560543","https://openalex.org/W1999597013","https://openalex.org/W2001141328","https://openalex.org/W2006690943","https://openalex.org/W2053186076","https://openalex.org/W2056823697","https://openalex.org/W2082612735","https://openalex.org/W2096729078","https://openalex.org/W2134407776","https://openalex.org/W2134738108","https://openalex.org/W2167816765","https://openalex.org/W2170456712","https://openalex.org/W2492427238","https://openalex.org/W2797597138","https://openalex.org/W4205380271","https://openalex.org/W4240525777"],"related_works":["https://openalex.org/W1981742685","https://openalex.org/W2071357880","https://openalex.org/W2141709668","https://openalex.org/W3200964664","https://openalex.org/W2004773025","https://openalex.org/W2038713466","https://openalex.org/W1508503670","https://openalex.org/W1508132973","https://openalex.org/W3106443019","https://openalex.org/W2078597522"],"abstract_inverted_index":{"A":[0,103],"new":[1],"method,":[2],"based":[3],"on":[4,170],"generalized":[5],"Fourier":[6],"analysis,":[7],"is":[8,94,120,210,298,307],"described":[9,281],"that":[10,48,64,77,280,288,306],"utilizes":[11],"the":[12,40,62,78,87,96,110,113,149,152,159,164,176,188,193,206,220,250,256,261,289,299],"concept":[13],"of":[14,54,68,89,112,116,137,151,166,173,183,222,232,249],"\"molecular":[15],"basis":[16,28,41,81,118,126,140,167,207,230],"sets\"":[17],"to":[18,101,122,229,279],"represent":[19],"chemical":[20,262],"space":[21,32,153],"within":[22,142],"an":[23,46],"abstract":[24,34,79,275],"vector":[25,146,276],"space.":[26,147],"The":[27],"vectors":[29,42,82,98,141,185],"in":[30,71,133,187,196,202,268,301,309],"this":[31,302],"are":[33,43,83,99,215],"molecular":[35,50,80,97,117,184],"vectors.":[36],"Inner":[37],"products":[38,292],"among":[39],"determined":[44],"using":[45],"ansatz":[47],"associates":[49],"similarities":[51,65],"between":[52,66],"pairs":[53,67],"molecules":[55,69],"with":[56,92,227],"their":[57,225],"corresponding":[58],"inner":[59,291],"products.":[60],"Moreover,":[61],"fact":[63],"are,":[70],"essentially":[72],"all":[73],"cases,":[74],"nonzero":[75],"implies":[76],"nonorthogonal,":[84],"but":[85],"since":[86],"similarity":[88],"a":[90,143,171,269,304],"molecule":[91],"itself":[93],"unity,":[95],"normalized":[100],"unity.":[102],"symmetric":[104],"orthogonalization":[105],"procedure,":[106],"which":[107],"optimally":[108],"preserves":[109],"character":[111],"original":[114],"set":[115,168,208],"vectors,":[119],"used":[121],"construct":[123],"appropriate":[124,290],"orthonormal":[125,138],"sets.":[127],"Molecules":[128],"can":[129,154,258,283,293],"then":[130],"be":[131,259,285,294],"represented,":[132],"general,":[134],"by":[135],"sets":[136,231],"\"molecule-like\"":[139],"proper":[144],"Euclidean":[145],"However,":[148],"dimension":[150,257],"become":[155],"quite":[156],"large.":[157],"Thus,":[158],"work":[160],"presented":[161],"here":[162,282],"assesses":[163],"effect":[165],"size":[169,209,234],"number":[172],"properties":[174],"including":[175],"average":[177,181,197,203],"squared":[178,198],"error":[179,199],"and":[180,200,224,235,245,271],"norm":[182,204],"represented":[186],"space-the":[189],"results":[190],"clearly":[191],"show":[192,252],"expected":[194],"reduction":[195],"increase":[201],"as":[205,241,297],"increased.":[211],"Several":[212],"distance-based":[213],"statistics":[214],"also":[216,284],"considered.":[217],"These":[218],"include":[219],"distribution":[221],"distances":[223],"differences":[226],"respect":[228],"differing":[233],"several":[236],"comparative":[237],"distance":[238],"measures":[239,251],"such":[240],"Spearman":[242],"rank":[243],"correlation":[244],"Kruscal":[246],"stress.":[247],"All":[248],"that,":[253],"even":[254],"though":[255],"high,":[260],"spaces":[263,277],"they":[264],"represent,":[265],"nonetheless,":[266],"behave":[267],"well-controlled":[270],"reasonable":[272],"manner.":[273],"Other":[274],"analogous":[278],"constructed":[286],"providing":[287],"directly":[295],"evaluated":[296],"case":[300],"work,":[303],"problem":[305],"well-known":[308],"kernel-based":[310],"machine":[311],"learning.":[312]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-06-15T08:34:33.830935","created_date":"2016-06-24T00:00:00"}