{"id":"https://openalex.org/W2141842526","doi":"https://doi.org/10.1109/icdm.2002.1183924","title":"Efficient discovery of common substructures in macromolecules","display_name":"Efficient discovery of common substructures in macromolecules","publication_year":2003,"publication_date":"2003-06-26","ids":{"openalex":"https://openalex.org/W2141842526","doi":"https://doi.org/10.1109/icdm.2002.1183924","mag":"2141842526"},"language":"en","primary_location":{"id":"doi:10.1109/icdm.2002.1183924","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdm.2002.1183924","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2002 IEEE International Conference on Data Mining, 2002. Proceedings.","raw_type":"proceedings-article"},"type":"article","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/A5100755351","display_name":"Srinivasan Parthasarathy","orcid":"https://orcid.org/0000-0002-6062-6449"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"S. Parthasarathy","raw_affiliation_strings":["Computer and Information Science, Ohio State Uinversity, USA","Dept of Comput. & Inf. Sci., Ohio State Univ., Columbus, OH, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer and Information Science, Ohio State Uinversity, USA","institution_ids":[]},{"raw_affiliation_string":"Dept of Comput. & Inf. Sci., Ohio State Univ., Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002709371","display_name":"Matt Coatney","orcid":null},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"M. Coatney","raw_affiliation_strings":["Computer and Information Science, Ohio State Uinversity, USA","Dept of Comput. & Inf. Sci., Ohio State Univ., Columbus, OH, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer and Information Science, Ohio State Uinversity, USA","institution_ids":[]},{"raw_affiliation_string":"Dept of Comput. & Inf. Sci., Ohio State Univ., Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.0622,"has_fulltext":false,"cited_by_count":26,"citation_normalized_percentile":{"value":0.86741769,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"362","last_page":"369"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9962000250816345,"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"}},"topics":[{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9962000250816345,"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"}},{"id":"https://openalex.org/T10044","display_name":"Protein Structure and Dynamics","score":0.9919000267982483,"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"}},{"id":"https://openalex.org/T10602","display_name":"Glycosylation and Glycoproteins Research","score":0.9818000197410583,"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/computer-science","display_name":"Computer science","score":0.6740932464599609},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.603813886642456},{"id":"https://openalex.org/keywords/macromolecule","display_name":"Macromolecule","score":0.5568171143531799},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5495185852050781},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.532943844795227},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.4781306982040405},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4561942219734192},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.43823009729385376},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33786100149154663},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.15898162126541138},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12717783451080322}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6740932464599609},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.603813886642456},{"id":"https://openalex.org/C204389451","wikidata":"https://www.wikidata.org/wiki/Q178593","display_name":"Macromolecule","level":2,"score":0.5568171143531799},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5495185852050781},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.532943844795227},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.4781306982040405},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4561942219734192},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.43823009729385376},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33786100149154663},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.15898162126541138},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12717783451080322},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","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},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icdm.2002.1183924","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdm.2002.1183924","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2002 IEEE International Conference on Data Mining, 2002. Proceedings.","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W7180117","https://openalex.org/W14258228","https://openalex.org/W21533455","https://openalex.org/W58080530","https://openalex.org/W64137754","https://openalex.org/W202299441","https://openalex.org/W1484413656","https://openalex.org/W1550545076","https://openalex.org/W1641039719","https://openalex.org/W1678889691","https://openalex.org/W1971784203","https://openalex.org/W2000488027","https://openalex.org/W2033534831","https://openalex.org/W2039379906","https://openalex.org/W2089967664","https://openalex.org/W2118727666","https://openalex.org/W2133452849","https://openalex.org/W2135453151","https://openalex.org/W2141842526","https://openalex.org/W2149706766","https://openalex.org/W2158454296","https://openalex.org/W2175099847","https://openalex.org/W2319660501","https://openalex.org/W2522853541","https://openalex.org/W4236137412","https://openalex.org/W4285719527","https://openalex.org/W6600311773","https://openalex.org/W6600571477","https://openalex.org/W6600849518","https://openalex.org/W6602383291","https://openalex.org/W6608186361","https://openalex.org/W6628750762","https://openalex.org/W6633119159","https://openalex.org/W6678115988","https://openalex.org/W6679771225","https://openalex.org/W6680115189","https://openalex.org/W6817491142"],"related_works":["https://openalex.org/W2044014390","https://openalex.org/W1846316342","https://openalex.org/W1964725291","https://openalex.org/W4210447090","https://openalex.org/W1984670152","https://openalex.org/W2083665351","https://openalex.org/W2043468722","https://openalex.org/W2123419409","https://openalex.org/W2003172604","https://openalex.org/W3151146928"],"abstract_inverted_index":{"Biological":[0],"macromolecules":[1],"play":[2],"a":[3,70],"fundamental":[4],"role":[5],"in":[6,118],"disease;":[7],"therefore,":[8],"they":[9],"are":[10],"of":[11,28,125],"great":[12],"interest":[13],"to":[14,24,62,74,107,138],"fields":[15],"such":[16],"as":[17],"pharmacology":[18],"and":[19,98,127,131,144],"chemical":[20],"genomics.":[21],"Yet":[22],"due":[23],"macromolecules'":[25],"complexity,":[26],"development":[27],"effective":[29],"techniques":[30,41],"for":[31],"elucidating":[32],"structure-function":[33,51],"macromolecular":[34],"relationships":[35],"has":[36],"been":[37],"ill":[38],"explored.":[39],"Previous":[40],"have":[42],"either":[43],"focused":[44],"on":[45,54,80],"sequence":[46],"analysis,":[47],"which":[48,58],"only":[49],"approximates":[50],"relationships,":[52],"or":[53,65],"small":[55],"coordinate":[56,82,99],"datasets,":[57],"does":[59],"not":[60],"scale":[61],"large":[63],"datasets":[64],"handle":[66],"noise.":[67],"We":[68,102],"present":[69],"novel":[71],"scalable":[72],"approach":[73,88,113],"efficiently":[75],"discover":[76,115],"macromolecule":[77,120],"substructures":[78,117],"based":[79],"three-dimensional":[81],"data,":[83],"without":[84],"domain-specific":[85],"knowledge.":[86],"The":[87],"combines":[89],"structure-based":[90],"frequent":[91],"pattern":[92],"discovery":[93,124],"with":[94],"search":[95],"space":[96],"reduction":[97],"noise":[100],"handling.":[101],"analyze":[103],"computational":[104],"performance":[105],"compared":[106],"traditional":[108],"approaches,":[109],"validate":[110],"that":[111,133],"our":[112,134],"can":[114],"meaningful":[116],"noisy":[119],"data":[121],"by":[122],"automated":[123],"primary":[126],"secondary":[128],"protein":[129],"structures,":[130],"show":[132],"technique":[135],"is":[136],"superior":[137],"sequence-based":[139],"approaches":[140],"at":[141],"determining":[142],"structural,":[143],"thus":[145],"functional,":[146],"similarity":[147],"between":[148],"proteins.":[149]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2014,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}