{"id":"https://openalex.org/W2066527689","doi":"https://doi.org/10.1021/ci060013h","title":"<i>R</i>-NN Curves:\u2009 An Intuitive Approach to Outlier Detection Using a Distance Based Method","display_name":"<i>R</i>-NN Curves:\u2009 An Intuitive Approach to Outlier Detection Using a Distance Based Method","publication_year":2006,"publication_date":"2006-06-01","ids":{"openalex":"https://openalex.org/W2066527689","doi":"https://doi.org/10.1021/ci060013h","mag":"2066527689","pmid":"https://pubmed.ncbi.nlm.nih.gov/16859303"},"language":"en","primary_location":{"id":"doi:10.1021/ci060013h","is_oa":false,"landing_page_url":"https://doi.org/10.1021/ci060013h","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/A5069062997","display_name":"Rajarshi Guha","orcid":"https://orcid.org/0000-0001-7403-8819"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]},{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Rajarshi Guha","raw_affiliation_strings":["Department of Chemistry, Pennsylvania State University, University Park, Pennsylvania 16802, and Department of Computational Biology, University of Southern California, Los Angeles, California 90089"],"affiliations":[{"raw_affiliation_string":"Department of Chemistry, Pennsylvania State University, University Park, Pennsylvania 16802, and Department of Computational Biology, University of Southern California, Los Angeles, California 90089","institution_ids":["https://openalex.org/I1174212","https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113845539","display_name":"Debojyoti Dutta","orcid":null},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]},{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Debojyoti Dutta","raw_affiliation_strings":["Department of Chemistry, Pennsylvania State University, University Park, Pennsylvania 16802, and Department of Computational Biology, University of Southern California, Los Angeles, California 90089"],"affiliations":[{"raw_affiliation_string":"Department of Chemistry, Pennsylvania State University, University Park, Pennsylvania 16802, and Department of Computational Biology, University of Southern California, Los Angeles, California 90089","institution_ids":["https://openalex.org/I1174212","https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109171233","display_name":"Peter C. Jurs","orcid":null},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]},{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Peter C. Jurs","raw_affiliation_strings":["Department of Chemistry, Pennsylvania State University, University Park, Pennsylvania 16802, and Department of Computational Biology, University of Southern California, Los Angeles, California 90089"],"affiliations":[{"raw_affiliation_string":"Department of Chemistry, Pennsylvania State University, University Park, Pennsylvania 16802, and Department of Computational Biology, University of Southern California, Los Angeles, California 90089","institution_ids":["https://openalex.org/I1174212","https://openalex.org/I130769515"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100443173","display_name":"Ting Chen","orcid":"https://orcid.org/0000-0001-8414-6346"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]},{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ting Chen","raw_affiliation_strings":["Department of Chemistry, Pennsylvania State University, University Park, Pennsylvania 16802, and Department of Computational Biology, University of Southern California, Los Angeles, California 90089"],"affiliations":[{"raw_affiliation_string":"Department of Chemistry, Pennsylvania State University, University Park, Pennsylvania 16802, and Department of Computational Biology, University of Southern California, Los Angeles, California 90089","institution_ids":["https://openalex.org/I1174212","https://openalex.org/I130769515"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5069062997"],"corresponding_institution_ids":["https://openalex.org/I1174212","https://openalex.org/I130769515"],"apc_list":null,"apc_paid":null,"fwci":2.6162,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.89548009,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"46","issue":"4","first_page":"1713","last_page":"1722"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9993000030517578,"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":0.9993000030517578,"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":0.9677000045776367,"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":0.9641000032424927,"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":0.8040186166763306},{"id":"https://openalex.org/keywords/outlier","display_name":"Outlier","score":0.7756941318511963},{"id":"https://openalex.org/keywords/plot","display_name":"Plot (graphics)","score":0.5963126420974731},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5514848232269287},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5290398001670837},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5141952037811279},{"id":"https://openalex.org/keywords/virtual-screening","display_name":"Virtual screening","score":0.5075298547744751},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5029637217521667},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.494099885225296},{"id":"https://openalex.org/keywords/molecular-descriptor","display_name":"Molecular descriptor","score":0.47885963320732117},{"id":"https://openalex.org/keywords/maxima-and-minima","display_name":"Maxima and minima","score":0.46029624342918396},{"id":"https://openalex.org/keywords/anomaly-detection","display_name":"Anomaly detection","score":0.459547221660614},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.4107738435268402},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.37691938877105713},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3684372305870056},{"id":"https://openalex.org/keywords/quantitative-structure\u2013activity-relationship","display_name":"Quantitative structure\u2013activity relationship","score":0.32319381833076477},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.2186739444732666},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.15871131420135498},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.12305188179016113},{"id":"https://openalex.org/keywords/computational-chemistry","display_name":"Computational chemistry","score":0.07728397846221924},{"id":"https://openalex.org/keywords/molecular-dynamics","display_name":"Molecular dynamics","score":0.07249346375465393}],"concepts":[{"id":"https://openalex.org/C68762167","wikidata":"https://www.wikidata.org/wiki/Q910164","display_name":"Cheminformatics","level":2,"score":0.8040186166763306},{"id":"https://openalex.org/C79337645","wikidata":"https://www.wikidata.org/wiki/Q779824","display_name":"Outlier","level":2,"score":0.7756941318511963},{"id":"https://openalex.org/C167651023","wikidata":"https://www.wikidata.org/wiki/Q1474611","display_name":"Plot (graphics)","level":2,"score":0.5963126420974731},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5514848232269287},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5290398001670837},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5141952037811279},{"id":"https://openalex.org/C103697762","wikidata":"https://www.wikidata.org/wiki/Q4112105","display_name":"Virtual screening","level":3,"score":0.5075298547744751},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5029637217521667},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.494099885225296},{"id":"https://openalex.org/C164923092","wikidata":"https://www.wikidata.org/wiki/Q3705921","display_name":"Molecular descriptor","level":3,"score":0.47885963320732117},{"id":"https://openalex.org/C186633575","wikidata":"https://www.wikidata.org/wiki/Q845060","display_name":"Maxima and minima","level":2,"score":0.46029624342918396},{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.459547221660614},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.4107738435268402},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.37691938877105713},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3684372305870056},{"id":"https://openalex.org/C164126121","wikidata":"https://www.wikidata.org/wiki/Q766383","display_name":"Quantitative structure\u2013activity relationship","level":2,"score":0.32319381833076477},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2186739444732666},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.15871131420135498},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.12305188179016113},{"id":"https://openalex.org/C147597530","wikidata":"https://www.wikidata.org/wiki/Q369472","display_name":"Computational chemistry","level":1,"score":0.07728397846221924},{"id":"https://openalex.org/C59593255","wikidata":"https://www.wikidata.org/wiki/Q901663","display_name":"Molecular dynamics","level":2,"score":0.07249346375465393},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1021/ci060013h","is_oa":false,"landing_page_url":"https://doi.org/10.1021/ci060013h","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:16859303","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/16859303","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1967436230","https://openalex.org/W1977340881","https://openalex.org/W1984471054","https://openalex.org/W2004791924","https://openalex.org/W2007602613","https://openalex.org/W2013470095","https://openalex.org/W2031498906","https://openalex.org/W2033844318","https://openalex.org/W2050273205","https://openalex.org/W2058397078","https://openalex.org/W2071678676","https://openalex.org/W2071840184","https://openalex.org/W2077341638","https://openalex.org/W2078115945","https://openalex.org/W2092302310","https://openalex.org/W2113868874","https://openalex.org/W2220102852","https://openalex.org/W2950235751"],"related_works":["https://openalex.org/W4362464865","https://openalex.org/W2098840560","https://openalex.org/W4302604134","https://openalex.org/W2768880727","https://openalex.org/W2113146994","https://openalex.org/W2073081213","https://openalex.org/W2621548818","https://openalex.org/W4283836736","https://openalex.org/W2123676318","https://openalex.org/W2148009427"],"abstract_inverted_index":{"Libraries":[0],"of":[1,9,37,46,56,60,76,81,117,136,155],"chemical":[2],"structures":[3],"are":[4,20],"used":[5],"in":[6,39,63,66,71,132,157],"a":[7,44,50,64,79,93,124,133,137,144,158],"variety":[8],"cheminformatics":[10],"tasks":[11],"such":[12],"as":[13],"virtual":[14],"screening":[15],"and":[16,19,68],"QSAR":[17],"modeling":[18],"generally":[21],"characterized":[22],"using":[23],"molecular":[24],"descriptors.":[25,47],"When":[26],"working":[27],"with":[28],"libraries":[29],"it":[30],"is":[31],"useful":[32],"to":[33,53,91,114,127,146],"understand":[34],"the":[35,40,54,57,61,106,149],"distribution":[36,59],"compounds":[38,62,130],"space":[41],"defined":[42],"by":[43],"set":[45],"We":[48,141],"present":[49,143],"simple":[51],"approach":[52],"analysis":[55],"spatial":[58],"library":[65],"general":[67],"outlier":[69],"detection":[70],"particular":[72],"based":[73],"on":[74],"counts":[75],"neighbors":[77],"within":[78],"series":[80],"increasing":[82],"radii.":[83],"The":[84,109,120],"resultant":[85],"curves,":[86,89],"termed":[87],"R-NN":[88,121,150],"appear":[90],"follow":[92],"logistic":[94],"model":[95],"for":[96,105],"any":[97],"given":[98,138],"descriptor":[99,139],"space,":[100],"which":[101],"we":[102],"justify":[103],"theoretically":[104],"2D":[107],"case.":[108],"method":[110,126,145],"can":[111],"be":[112],"applied":[113],"data":[115],"sets":[116],"arbitrary":[118],"dimensions.":[119],"curves":[122,151],"provide":[123],"visual":[125],"easily":[128],"detect":[129],"lying":[131],"sparse":[134],"region":[135],"space.":[140],"also":[142],"numerically":[147],"characterize":[148],"thus":[152],"allowing":[153],"identification":[154],"outliers":[156],"single":[159],"plot.":[160]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2016,"cited_by_count":4},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2016-06-24T00:00:00"}
