{"id":"https://openalex.org/W1979008671","doi":"https://doi.org/10.1021/ci7004065","title":"Definition and Detection of Outliers in Chemical Space","display_name":"Definition and Detection of Outliers in Chemical Space","publication_year":2008,"publication_date":"2008-07-25","ids":{"openalex":"https://openalex.org/W1979008671","doi":"https://doi.org/10.1021/ci7004065","mag":"1979008671","pmid":"https://pubmed.ncbi.nlm.nih.gov/18652445"},"language":"en","primary_location":{"id":"doi:10.1021/ci7004065","is_oa":false,"landing_page_url":"https://doi.org/10.1021/ci7004065","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":"https://openalex.org/A5021012316","display_name":"Mos\u00e8 Casalegno","orcid":"https://orcid.org/0000-0002-4833-2990"},"institutions":[{"id":"https://openalex.org/I189158943","display_name":"University of Milan","ror":"https://ror.org/00wjc7c48","country_code":"IT","type":"education","lineage":["https://openalex.org/I189158943"]},{"id":"https://openalex.org/I19630809","display_name":"Mario Negri Institute for Pharmacological Research","ror":"https://ror.org/05aspc753","country_code":"IT","type":"nonprofit","lineage":["https://openalex.org/I19630809","https://openalex.org/I4210110338","https://openalex.org/I4210153126"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Mos\u00e8 Casalegno","raw_affiliation_strings":["IRFMN, Mario Negri Institute for Pharmacological Research, Via La Masa, 19, 20156 Milano, Italy, and Dipartimento di Chimica Organica e Industriale, Universit\u00e0 degli Studi di Milano, Via Venezian 21, 20133 Milano, Italy"],"affiliations":[{"raw_affiliation_string":"IRFMN, Mario Negri Institute for Pharmacological Research, Via La Masa, 19, 20156 Milano, Italy, and Dipartimento di Chimica Organica e Industriale, Universit\u00e0 degli Studi di Milano, Via Venezian 21, 20133 Milano, Italy","institution_ids":["https://openalex.org/I19630809","https://openalex.org/I189158943"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070893925","display_name":"Guido Sello","orcid":"https://orcid.org/0000-0003-2538-9107"},"institutions":[{"id":"https://openalex.org/I189158943","display_name":"University of Milan","ror":"https://ror.org/00wjc7c48","country_code":"IT","type":"education","lineage":["https://openalex.org/I189158943"]},{"id":"https://openalex.org/I19630809","display_name":"Mario Negri Institute for Pharmacological Research","ror":"https://ror.org/05aspc753","country_code":"IT","type":"nonprofit","lineage":["https://openalex.org/I19630809","https://openalex.org/I4210110338","https://openalex.org/I4210153126"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Guido Sello","raw_affiliation_strings":["IRFMN, Mario Negri Institute for Pharmacological Research, Via La Masa, 19, 20156 Milano, Italy, and Dipartimento di Chimica Organica e Industriale, Universit\u00e0 degli Studi di Milano, Via Venezian 21, 20133 Milano, Italy"],"affiliations":[{"raw_affiliation_string":"IRFMN, Mario Negri Institute for Pharmacological Research, Via La Masa, 19, 20156 Milano, Italy, and Dipartimento di Chimica Organica e Industriale, Universit\u00e0 degli Studi di Milano, Via Venezian 21, 20133 Milano, Italy","institution_ids":["https://openalex.org/I19630809","https://openalex.org/I189158943"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058133879","display_name":"Emilio Benfenati","orcid":"https://orcid.org/0000-0002-3976-5989"},"institutions":[{"id":"https://openalex.org/I189158943","display_name":"University of Milan","ror":"https://ror.org/00wjc7c48","country_code":"IT","type":"education","lineage":["https://openalex.org/I189158943"]},{"id":"https://openalex.org/I19630809","display_name":"Mario Negri Institute for Pharmacological Research","ror":"https://ror.org/05aspc753","country_code":"IT","type":"nonprofit","lineage":["https://openalex.org/I19630809","https://openalex.org/I4210110338","https://openalex.org/I4210153126"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Emilio Benfenati","raw_affiliation_strings":["IRFMN, Mario Negri Institute for Pharmacological Research, Via La Masa, 19, 20156 Milano, Italy, and Dipartimento di Chimica Organica e Industriale, Universit\u00e0 degli Studi di Milano, Via Venezian 21, 20133 Milano, Italy"],"affiliations":[{"raw_affiliation_string":"IRFMN, Mario Negri Institute for Pharmacological Research, Via La Masa, 19, 20156 Milano, Italy, and Dipartimento di Chimica Organica e Industriale, Universit\u00e0 degli Studi di Milano, Via Venezian 21, 20133 Milano, Italy","institution_ids":["https://openalex.org/I19630809","https://openalex.org/I189158943"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5021012316"],"corresponding_institution_ids":["https://openalex.org/I189158943","https://openalex.org/I19630809"],"apc_list":null,"apc_paid":null,"fwci":2.4807,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.88526648,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"48","issue":"8","first_page":"1592","last_page":"1601"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9988999962806702,"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":0.9988999962806702,"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/T11871","display_name":"Advanced Statistical Methods and Models","score":0.9696999788284302,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10640","display_name":"Spectroscopy and Chemometric Analyses","score":0.9592000246047974,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/outlier","display_name":"Outlier","score":0.8610548973083496},{"id":"https://openalex.org/keywords/generality","display_name":"Generality","score":0.7630903720855713},{"id":"https://openalex.org/keywords/chemical-space","display_name":"Chemical space","score":0.7579355835914612},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6387908458709717},{"id":"https://openalex.org/keywords/anomaly-detection","display_name":"Anomaly detection","score":0.6172956824302673},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.600959300994873},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.5217798352241516},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.5049965977668762},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.44553473591804504},{"id":"https://openalex.org/keywords/contrast","display_name":"Contrast (vision)","score":0.4405677318572998},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.42211470007896423},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4075077176094055},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3844081163406372},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.24561083316802979},{"id":"https://openalex.org/keywords/drug-discovery","display_name":"Drug discovery","score":0.2406749129295349},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.12844812870025635},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.12420496344566345}],"concepts":[{"id":"https://openalex.org/C79337645","wikidata":"https://www.wikidata.org/wiki/Q779824","display_name":"Outlier","level":2,"score":0.8610548973083496},{"id":"https://openalex.org/C2780767217","wikidata":"https://www.wikidata.org/wiki/Q5532421","display_name":"Generality","level":2,"score":0.7630903720855713},{"id":"https://openalex.org/C99726746","wikidata":"https://www.wikidata.org/wiki/Q906396","display_name":"Chemical space","level":3,"score":0.7579355835914612},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6387908458709717},{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.6172956824302673},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.600959300994873},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.5217798352241516},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.5049965977668762},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.44553473591804504},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.4405677318572998},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.42211470007896423},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4075077176094055},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3844081163406372},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.24561083316802979},{"id":"https://openalex.org/C74187038","wikidata":"https://www.wikidata.org/wiki/Q1418791","display_name":"Drug discovery","level":2,"score":0.2406749129295349},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.12844812870025635},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.12420496344566345},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C542102704","wikidata":"https://www.wikidata.org/wiki/Q183257","display_name":"Psychotherapist","level":1,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[{"descriptor_ui":"D008956","descriptor_name":"Models, Chemical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008956","descriptor_name":"Models, Chemical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008956","descriptor_name":"Models, Chemical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D015394","descriptor_name":"Molecular Structure","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015394","descriptor_name":"Molecular Structure","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015394","descriptor_name":"Molecular Structure","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1021/ci7004065","is_oa":false,"landing_page_url":"https://doi.org/10.1021/ci7004065","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:18652445","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/18652445","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":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W1540105270","https://openalex.org/W1551729088","https://openalex.org/W1967775878","https://openalex.org/W1968350258","https://openalex.org/W1973410261","https://openalex.org/W1981078752","https://openalex.org/W1985699832","https://openalex.org/W1994681706","https://openalex.org/W1996155506","https://openalex.org/W2005109863","https://openalex.org/W2007602613","https://openalex.org/W2012540065","https://openalex.org/W2031895393","https://openalex.org/W2038584362","https://openalex.org/W2042887495","https://openalex.org/W2043122083","https://openalex.org/W2047509756","https://openalex.org/W2050273205","https://openalex.org/W2060097376","https://openalex.org/W2062292120","https://openalex.org/W2066527689","https://openalex.org/W2066657428","https://openalex.org/W2070246294","https://openalex.org/W2070983531","https://openalex.org/W2071840184","https://openalex.org/W2085890279","https://openalex.org/W2086190989","https://openalex.org/W2092628504","https://openalex.org/W2094796095","https://openalex.org/W2111160323","https://openalex.org/W2113076747","https://openalex.org/W2117416418","https://openalex.org/W2126963804","https://openalex.org/W2137130182","https://openalex.org/W2147470678","https://openalex.org/W2589554797","https://openalex.org/W2950235751","https://openalex.org/W2952798571","https://openalex.org/W4229837141"],"related_works":["https://openalex.org/W2045049461","https://openalex.org/W1978893398","https://openalex.org/W2201908702","https://openalex.org/W4381094582","https://openalex.org/W2499612753","https://openalex.org/W3111802945","https://openalex.org/W2946096271","https://openalex.org/W2295423552","https://openalex.org/W1598471830","https://openalex.org/W3107369729"],"abstract_inverted_index":{"Detection":[0],"of":[1,9,18,31,52,69,97,122],"outliers":[2,19,76],"is":[3,39,63],"a":[4,40,48,60,83,119],"complex":[5],"and":[6,34,74,114],"challenging":[7],"area":[8],"research":[10],"in":[11,20,28,77],"chemical":[12,22,78,106],"theory.":[13],"Among":[14],"current":[15],"notions,":[16],"that":[17,65],"the":[21,29,53,67,95],"space--descriptors--is":[23],"meaningful":[24],"with":[25,125],"multiple":[26],"applications":[27],"field":[30],"drug":[32],"discovery":[33],"predictive":[35],"modeling.":[36],"Presented":[37],"here":[38],"new":[41,120],"framework":[42],"for":[43],"outlier":[44],"detection,":[45],"relying":[46],"on":[47],"discrete,":[49],"fragment-based":[50],"representation":[51],"molecular":[54],"structures.":[55],"From":[56],"this":[57,92],"starting":[58],"point,":[59],"recursive":[61],"method":[62],"developed":[64],"quantifies":[66],"contribution":[68],"fragments":[70],"to":[71,82,88,101,110],"compound":[72],"description":[73],"identifies":[75],"structure":[79],"databases":[80,107],"according":[81],"novel":[84],"definition.":[85],"In":[86],"contrast":[87],"existing":[89],"detection":[90],"routes,":[91],"approach":[93],"avoids":[94],"use":[96],"thresholds":[98],"usually":[99],"required":[100],"quantify":[102],"outlying":[103],"behavior.":[104],"Three":[105],"are":[108],"investigated":[109],"demonstrate":[111],"its":[112],"generality":[113],"flexibility.":[115],"The":[116],"result":[117],"reveals":[118],"species":[121],"outliers,":[123],"compounds":[124],"no":[126],"specific":[127],"structural":[128],"features,":[129],"rather":[130],"than":[131],"unique":[132],"ones.":[133]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2018,"cited_by_count":3},{"year":2016,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-03-26T15:22:09.906841","created_date":"2025-10-10T00:00:00"}