{"id":"https://openalex.org/W2125702140","doi":"https://doi.org/10.1109/bibe.2003.1188971","title":"MotifMiner: a general toolkit for efficiently identifying common substructures in molecules","display_name":"MotifMiner: a general toolkit for efficiently identifying common substructures in molecules","publication_year":2003,"publication_date":"2003-11-20","ids":{"openalex":"https://openalex.org/W2125702140","doi":"https://doi.org/10.1109/bibe.2003.1188971","mag":"2125702140"},"language":"en","primary_location":{"id":"doi:10.1109/bibe.2003.1188971","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibe.2003.1188971","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Third IEEE Symposium on Bioinformatics and Bioengineering, 2003. 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/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"]}]},{"author_position":"last","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"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.3442,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.90066738,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"336","last_page":"340"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9760000109672546,"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"}},"topics":[{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9760000109672546,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9749000072479248,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9689000248908997,"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":0.7733925580978394},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6262373328208923},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.550351083278656},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.5186668634414673},{"id":"https://openalex.org/keywords/extensibility","display_name":"Extensibility","score":0.501683235168457},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.49099376797676086},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.44407689571380615},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4375721216201782},{"id":"https://openalex.org/keywords/substructure","display_name":"Substructure","score":0.4201495051383972},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3944503664970398},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.3924764394760132},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.17151927947998047},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.12053987383842468},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.09643450379371643},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0856776237487793}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7733925580978394},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6262373328208923},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.550351083278656},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.5186668634414673},{"id":"https://openalex.org/C32833848","wikidata":"https://www.wikidata.org/wiki/Q4115054","display_name":"Extensibility","level":2,"score":0.501683235168457},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.49099376797676086},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.44407689571380615},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4375721216201782},{"id":"https://openalex.org/C99679407","wikidata":"https://www.wikidata.org/wiki/Q56761637","display_name":"Substructure","level":2,"score":0.4201495051383972},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3944503664970398},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.3924764394760132},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.17151927947998047},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.12053987383842468},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.09643450379371643},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0856776237487793},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bibe.2003.1188971","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibe.2003.1188971","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Third IEEE Symposium on Bioinformatics and Bioengineering, 2003. Proceedings.","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W21533455","https://openalex.org/W64137754","https://openalex.org/W202299441","https://openalex.org/W1484413656","https://openalex.org/W1550545076","https://openalex.org/W2033534831","https://openalex.org/W2119148238","https://openalex.org/W2133452849","https://openalex.org/W2135453151","https://openalex.org/W2136593687","https://openalex.org/W2138024338","https://openalex.org/W2141842526","https://openalex.org/W2158454296","https://openalex.org/W2175099847","https://openalex.org/W2522853541","https://openalex.org/W6600849518","https://openalex.org/W6608186361","https://openalex.org/W6628750762","https://openalex.org/W6633119159","https://openalex.org/W6679771225","https://openalex.org/W6680115189"],"related_works":["https://openalex.org/W3153444835","https://openalex.org/W2153916713","https://openalex.org/W2023846184","https://openalex.org/W2703419385","https://openalex.org/W2329056228","https://openalex.org/W2284584236","https://openalex.org/W2950955148","https://openalex.org/W1979083399","https://openalex.org/W2344320748","https://openalex.org/W2374530195"],"abstract_inverted_index":{"Scientific":[0],"research":[1],"often":[2],"involves":[3],"examining":[4],"structural":[5,65,115],"relationships":[6],"in":[7,13,67,133],"molecules":[8],"since":[9],"scientists":[10],"strongly":[11],"believe":[12],"the":[14,35,43,93,154],"causal":[15],"relationship":[16],"between":[17],"structure":[18],"and":[19,42,60,82,145,167],"function.":[20],"Traditionally,":[21],"researchers":[22],"have":[23,74,83],"identified":[24],"these":[25],"patterns,":[26],"or":[27,108],"motifs,":[28,149],"manually":[29],"using":[30],"biochemical":[31,40],"expertise.":[32],"However,":[33],"with":[34],"massive":[36],"influx":[37],"of":[38,78,156],"new":[39],"data":[41,47],"ability":[44],"to":[45,99],"gather":[46],"for":[48,56,92,113,128,147],"very":[49],"large":[50],"molecules,":[51],"there":[52],"is":[53,111],"great":[54],"need":[55],"techniques":[57,81],"that":[58],"automatically":[59,129],"efficiently":[61],"identify":[62],"commonly":[63],"occurring":[64],"patterns":[66],"molecules.":[68],"Previous":[69],"automated":[70],"substructure":[71],"discovery":[72],"approaches":[73],"each":[75],"introduced":[76],"variations":[77],"similar":[79],"underlying":[80],"embedded":[84],"domain":[85],"knowledge.":[86],"While":[87],"doing":[88],"so":[89],"improves":[90],"performance":[91],"particular":[94],"domain,":[95],"this":[96,120],"complicates":[97],"extensibility":[98],"other":[100],"domains.":[101],"Also,":[102],"they":[103],"do":[104],"not":[105],"address":[106],"scalability":[107],"noise,":[109],"which":[110],"critical":[112],"certain":[114],"domains":[116],"like":[117],"macromolecules.":[118],"In":[119],"paper,":[121],"we":[122],"present":[123],"MotifMiner,":[124],"a":[125],"general":[126],"toolkit":[127],"identifying":[130,148],"common":[131],"motifs":[132],"most":[134],"any":[135],"scientific":[136],"molecular":[137],"dataset.":[138],"We":[139],"describe":[140],"both":[141],"our":[142,157],"application":[143],"framework":[144],"services":[146],"as":[150,152],"well":[151],"demonstrate":[153],"flexibility":[155],"system":[158],"by":[159],"analyzing":[160],"several":[161],"disparate":[162],"domains,":[163],"including":[164],"protein,":[165],"drug,":[166],"MD":[168],"simulation":[169],"datasets.":[170]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2013,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}