{"id":"https://openalex.org/W2084903757","doi":"https://doi.org/10.1145/2554850.2555063","title":"Structural clustering of millions of molecular graphs","display_name":"Structural clustering of millions of molecular graphs","publication_year":2014,"publication_date":"2014-03-24","ids":{"openalex":"https://openalex.org/W2084903757","doi":"https://doi.org/10.1145/2554850.2555063","mag":"2084903757"},"language":"en","primary_location":{"id":"doi:10.1145/2554850.2555063","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2554850.2555063","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th Annual ACM Symposium on Applied Computing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"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/A5056807104","display_name":"Madeleine Seeland","orcid":null},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Madeleine Seeland","raw_affiliation_strings":["Technische Universit\u00e4t M\u00fcnchen, Germany","Technische Universitat, Munchen, Germany#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technische Universit\u00e4t M\u00fcnchen, Germany","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"Technische Universitat, Munchen, Germany#TAB#","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026210150","display_name":"Andreas Karwath","orcid":"https://orcid.org/0000-0002-6942-3760"},"institutions":[{"id":"https://openalex.org/I197323543","display_name":"Johannes Gutenberg University Mainz","ror":"https://ror.org/023b0x485","country_code":"DE","type":"education","lineage":["https://openalex.org/I197323543"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Andreas Karwath Johannes","raw_affiliation_strings":["Johannes Gutenberg-Universit\u00e4t Mainz, Mainz, Germany","Johannes Gutenberg Universitat Mainz, Mainz, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johannes Gutenberg-Universit\u00e4t Mainz, Mainz, Germany","institution_ids":["https://openalex.org/I197323543"]},{"raw_affiliation_string":"Johannes Gutenberg Universitat Mainz, Mainz, Germany","institution_ids":["https://openalex.org/I197323543"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102744434","display_name":"Stefan Kr\u00e4mer","orcid":"https://orcid.org/0000-0003-0136-2540"},"institutions":[{"id":"https://openalex.org/I197323543","display_name":"Johannes Gutenberg University Mainz","ror":"https://ror.org/023b0x485","country_code":"DE","type":"education","lineage":["https://openalex.org/I197323543"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Stefan Kramer","raw_affiliation_strings":["Johannes Gutenberg-Universit\u00e4t Mainz, Mainz, Germany","Johannes Gutenberg Universitat Mainz, Mainz, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johannes Gutenberg-Universit\u00e4t Mainz, Mainz, Germany","institution_ids":["https://openalex.org/I197323543"]},{"raw_affiliation_string":"Johannes Gutenberg Universitat Mainz, Mainz, Germany","institution_ids":["https://openalex.org/I197323543"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"121","last_page":"128"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10064","display_name":"Complex Network Analysis Techniques","score":0.9961000084877014,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10064","display_name":"Complex Network Analysis Techniques","score":0.9961000084877014,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9842000007629395,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10211","display_name":"Computational Drug Discovery Methods","score":0.9819999933242798,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.802619457244873},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6887812614440918},{"id":"https://openalex.org/keywords/single-linkage-clustering","display_name":"Single-linkage clustering","score":0.5661000609397888},{"id":"https://openalex.org/keywords/correlation-clustering","display_name":"Correlation clustering","score":0.5378732681274414},{"id":"https://openalex.org/keywords/cluster","display_name":"Cluster (spacecraft)","score":0.5317180156707764},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.48873353004455566},{"id":"https://openalex.org/keywords/fuzzy-clustering","display_name":"Fuzzy clustering","score":0.4738234281539917},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.44863998889923096},{"id":"https://openalex.org/keywords/disjoint-sets","display_name":"Disjoint sets","score":0.44791728258132935},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.42505255341529846},{"id":"https://openalex.org/keywords/clustering-coefficient","display_name":"Clustering coefficient","score":0.4105924069881439},{"id":"https://openalex.org/keywords/cure-data-clustering-algorithm","display_name":"CURE data clustering algorithm","score":0.3927377462387085},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2215409278869629},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2079804539680481},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.13299015164375305}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.802619457244873},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6887812614440918},{"id":"https://openalex.org/C22648726","wikidata":"https://www.wikidata.org/wiki/Q7523744","display_name":"Single-linkage clustering","level":5,"score":0.5661000609397888},{"id":"https://openalex.org/C94641424","wikidata":"https://www.wikidata.org/wiki/Q5172845","display_name":"Correlation clustering","level":3,"score":0.5378732681274414},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.5317180156707764},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.48873353004455566},{"id":"https://openalex.org/C17212007","wikidata":"https://www.wikidata.org/wiki/Q5511111","display_name":"Fuzzy clustering","level":3,"score":0.4738234281539917},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.44863998889923096},{"id":"https://openalex.org/C45340560","wikidata":"https://www.wikidata.org/wiki/Q215382","display_name":"Disjoint sets","level":2,"score":0.44791728258132935},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.42505255341529846},{"id":"https://openalex.org/C22047676","wikidata":"https://www.wikidata.org/wiki/Q898680","display_name":"Clustering coefficient","level":3,"score":0.4105924069881439},{"id":"https://openalex.org/C33704608","wikidata":"https://www.wikidata.org/wiki/Q5014717","display_name":"CURE data clustering algorithm","level":4,"score":0.3927377462387085},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2215409278869629},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2079804539680481},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.13299015164375305},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2554850.2555063","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2554850.2555063","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th Annual ACM Symposium on Applied Computing","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.atira.dk:openaire_cris_publications/9a6dc69f-2e94-470b-9bf8-8b0838f86820","is_oa":false,"landing_page_url":"https://research.birmingham.ac.uk/en/publications/9a6dc69f-2e94-470b-9bf8-8b0838f86820","pdf_url":null,"source":{"id":"https://openalex.org/S4306402634","display_name":"University of Birmingham Research Portal (University of Birmingham)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79619799","host_organization_name":"University of Birmingham","host_organization_lineage":["https://openalex.org/I79619799"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Seeland, M, Karwath, A & Kramer, S 2014, 'Structural clustering of millions of molecular graphs', pp. 121-128. https://doi.org/10.1145/2554850.2555063","raw_type":"conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W87060577","https://openalex.org/W1529345033","https://openalex.org/W1679913846","https://openalex.org/W1952713189","https://openalex.org/W2000184633","https://openalex.org/W2047260621","https://openalex.org/W2083888914","https://openalex.org/W2100005623","https://openalex.org/W2110668502","https://openalex.org/W2117228324","https://openalex.org/W2129893339","https://openalex.org/W2133286004","https://openalex.org/W2141245797","https://openalex.org/W2148781711","https://openalex.org/W2153037537","https://openalex.org/W2170726034","https://openalex.org/W2172024214","https://openalex.org/W2952213121","https://openalex.org/W4237222446"],"related_works":["https://openalex.org/W2406185607","https://openalex.org/W2389934482","https://openalex.org/W4308301473","https://openalex.org/W4298005308","https://openalex.org/W3140018618","https://openalex.org/W2599570117","https://openalex.org/W4241252752","https://openalex.org/W3209217468","https://openalex.org/W2374506950","https://openalex.org/W2409936277"],"abstract_inverted_index":{"We":[0],"propose":[1],"an":[2,49,62,188],"algorithm":[3,55,159,205],"for":[4,101],"clustering":[5,38,54,136,180],"very":[6,149],"large":[7,15,150],"molecular":[8,167],"graph":[9,168,179,193],"databases":[10],"according":[11],"to":[12,74,82,162,174,186],"scaffolds":[13],"(i.e.,":[14],"structural":[16],"overlaps)":[17],"that":[18,138,157,203],"are":[19,97,122],"common":[20],"between":[21],"cluster":[22,59,88,94,103,110,163,187],"members.":[23],"Our":[24],"approach":[25,39,137,183],"first":[26,221],"partitions":[27],"the":[28,57,67,71,93,199,209],"original":[29],"dataset":[30],"into":[31,125],"several":[32],"smaller":[33],"datasets":[34,151],"using":[35,131],"a":[36,83,87,109,115,126,132,175,196,220],"greedy":[37],"named":[40],"APreClus":[41,47,91],"based":[42,113],"on":[43,114,148],"dynamic":[44],"seed":[45],"clustering.":[46],"is":[48,80,89,160,184,206],"online":[50],"and":[51,79,142,219],"instance":[52,63,72],"incremental":[53],"delaying":[56],"final":[58],"assignment":[60],"of":[61,66,117,129,152,190,198,211,214],"until":[64],"one":[65],"so-called":[68],"pending":[69],"clusters":[70,121],"belongs":[73],"has":[75],"reached":[76],"significant":[77],"size":[78],"converted":[81],"fixed":[84],"cluster.":[85],"Once":[86],"fixed,":[90],"recalculates":[92],"centers,":[95],"which":[96],"used":[98],"as":[99],"representatives":[100],"further":[102,123],"assignments.":[104],"The":[105,119],"pre-clustering":[106],"methodology":[107],"employs":[108],"membership":[111],"test":[112],"set-abstraction":[116],"graphs.":[118],"resulting":[120],"partitioned":[124],"finer":[127],"level":[128],"granularity":[130],"highly":[133],"parallelized":[134],"scaffold-based":[135,178],"produces":[139],"overlapping":[140],"(non-disjoint)":[141],"non-exhaustive":[143],"clusters.":[144],"In":[145],"our":[146,158,182,204],"experiments":[147],"chemical":[153,225],"structures,":[154],"we":[155],"show":[156],"able":[161,185],"at":[164],"least":[165],"3,000,000":[166],"structures":[169,194],"within":[170],"reasonable":[171],"time.":[172,200],"Compared":[173],"recently":[176],"proposed":[177],"algorithm,":[181],"order":[189],"magnitude":[191],"more":[192],"in":[195,208],"fraction":[197],"This":[201],"demonstrates":[202],"applicable":[207],"context":[210],"virtual":[212],"screening":[213],"realistically":[215],"sized":[216],"compound":[217],"libraries":[218],"step":[222],"towards":[223],"structuring":[224],"space.":[226]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}