{"id":"https://openalex.org/W2135133508","doi":"https://doi.org/10.1093/bioinformatics/btl637","title":"MinSet: a general approach to derive maximally representative database subsets by using fragment dictionaries and its application to the SCOP database","display_name":"MinSet: a general approach to derive maximally representative database subsets by using fragment dictionaries and its application to the SCOP database","publication_year":2007,"publication_date":"2007-01-03","ids":{"openalex":"https://openalex.org/W2135133508","doi":"https://doi.org/10.1093/bioinformatics/btl637","mag":"2135133508","pmid":"https://pubmed.ncbi.nlm.nih.gov/17204463"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btl637","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btl637","pdf_url":null,"source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","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/A5079015407","display_name":"Alessandro Pandini","orcid":"https://orcid.org/0000-0002-4158-233X"},"institutions":[{"id":"https://openalex.org/I66752286","display_name":"University of Milano-Bicocca","ror":"https://ror.org/01ynf4891","country_code":"IT","type":"education","lineage":["https://openalex.org/I66752286"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Alessandro Pandini","raw_affiliation_strings":["Dipartimento di Scienze dell'Ambiente e del Territorio, Universit\u00e0 degli Studi di Milano-Bicocca 1 \u00a0 1 \u00a0 \u00a0 Milano, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dipartimento di Scienze dell'Ambiente e del Territorio, Universit\u00e0 degli Studi di Milano-Bicocca 1 \u00a0 1 \u00a0 \u00a0 Milano, Italy","institution_ids":["https://openalex.org/I66752286"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045019644","display_name":"Laura Bonati","orcid":"https://orcid.org/0000-0003-3028-0368"},"institutions":[{"id":"https://openalex.org/I66752286","display_name":"University of Milano-Bicocca","ror":"https://ror.org/01ynf4891","country_code":"IT","type":"education","lineage":["https://openalex.org/I66752286"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Laura Bonati","raw_affiliation_strings":["Dipartimento di Scienze dell'Ambiente e del Territorio, Universit\u00e0 degli Studi di Milano-Bicocca 1 \u00a0 1 \u00a0 \u00a0 Milano, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dipartimento di Scienze dell'Ambiente e del Territorio, Universit\u00e0 degli Studi di Milano-Bicocca 1 \u00a0 1 \u00a0 \u00a0 Milano, Italy","institution_ids":["https://openalex.org/I66752286"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049119135","display_name":"Franca Fraternali","orcid":"https://orcid.org/0000-0002-3143-6574"},"institutions":[{"id":"https://openalex.org/I183935753","display_name":"King's College London","ror":"https://ror.org/0220mzb33","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I183935753"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Franca Fraternali","raw_affiliation_strings":["Bioinformatics Unit, King's College 2 \u00a0 2 \u00a0 \u00a0 London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bioinformatics Unit, King's College 2 \u00a0 2 \u00a0 \u00a0 London, UK","institution_ids":["https://openalex.org/I183935753"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063875453","display_name":"Jens Kleinjung","orcid":"https://orcid.org/0000-0002-7875-5724"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Jens Kleinjung","raw_affiliation_strings":["Division of Mathematical Biology, National Institute for Medical Research 3 \u00a0 3 \u00a0 \u00a0 The Ridgeway, London NW7 1AA, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Division of Mathematical Biology, National Institute for Medical Research 3 \u00a0 3 \u00a0 \u00a0 The Ridgeway, London NW7 1AA, UK","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5063875453"],"corresponding_institution_ids":[],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":null,"fwci":2.769,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.91952062,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"23","issue":"4","first_page":"515","last_page":"516"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.31439998745918274,"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":0.31439998745918274,"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/T10519","display_name":"Advanced Proteomics Techniques and Applications","score":0.10040000081062317,"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"}},{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.09440000355243683,"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":0.6916741132736206},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.6770552396774292},{"id":"https://openalex.org/keywords/string","display_name":"String (physics)","score":0.5431808829307556},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.4762064218521118},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4689856171607971},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.43393486738204956},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.37959104776382446},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.20732802152633667}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6916741132736206},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.6770552396774292},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.5431808829307556},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.4762064218521118},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4689856171607971},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.43393486738204956},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.37959104776382446},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.20732802152633667},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D003628","descriptor_name":"Database Management Systems","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D003628","descriptor_name":"Database Management Systems","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D003628","descriptor_name":"Database Management Systems","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D003628","descriptor_name":"Database Management Systems","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D004015","descriptor_name":"Dictionaries, Chemical as Topic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D004015","descriptor_name":"Dictionaries, Chemical as Topic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D004015","descriptor_name":"Dictionaries, Chemical as Topic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D004015","descriptor_name":"Dictionaries, Chemical as Topic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010446","descriptor_name":"Peptide Fragments","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":false},{"descriptor_ui":"D010446","descriptor_name":"Peptide Fragments","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":false},{"descriptor_ui":"D010446","descriptor_name":"Peptide Fragments","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":false},{"descriptor_ui":"D010446","descriptor_name":"Peptide Fragments","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":false},{"descriptor_ui":"D010446","descriptor_name":"Peptide Fragments","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D010446","descriptor_name":"Peptide Fragments","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D010446","descriptor_name":"Peptide Fragments","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D010446","descriptor_name":"Peptide Fragments","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D044962","descriptor_name":"Data Compression","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D044962","descriptor_name":"Data Compression","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D044962","descriptor_name":"Data Compression","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D044962","descriptor_name":"Data Compression","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false}],"locations_count":4,"locations":[{"id":"doi:10.1093/bioinformatics/btl637","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btl637","pdf_url":null,"source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:17204463","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/17204463","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":"Bioinformatics (Oxford, England)","raw_type":null},{"id":"pmh:oai:boa.unimib.it:10281/3233","is_oa":false,"landing_page_url":"http://hdl.handle.net/10281/3233","pdf_url":null,"source":{"id":"https://openalex.org/S4306401259","display_name":"BOA (University of Milano-Bicocca)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I66752286","host_organization_name":"University of Milano-Bicocca","host_organization_lineage":["https://openalex.org/I66752286"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:kclpure.kcl.ac.uk:publications/f01020cd-0984-4cb0-88eb-8d11f12a85b5","is_oa":false,"landing_page_url":"https://kclpure.kcl.ac.uk/portal/en/publications/f01020cd-0984-4cb0-88eb-8d11f12a85b5","pdf_url":null,"source":{"id":"https://openalex.org/S4306400216","display_name":"Research Portal (King's College London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I183935753","host_organization_name":"King's College London","host_organization_lineage":["https://openalex.org/I183935753"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Pandini, A, Bonati, L, Fraternali, F & Kleinjung, J 2007, 'MinSet: a general approach to derive maximally representative database subsets by using fragment dictionaries and its application to the SCOP database', BIOINFORMATICS, vol. 23, no. 4, pp. 515 - 516. https://doi.org/10.1093/bioinformatics/btl637","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7400000095367432}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":2,"referenced_works":["https://openalex.org/W2101386484","https://openalex.org/W2133657429"],"related_works":["https://openalex.org/W1495042958","https://openalex.org/W2494338568","https://openalex.org/W2122678784","https://openalex.org/W2282510344","https://openalex.org/W139987158","https://openalex.org/W2183994405","https://openalex.org/W1875646599","https://openalex.org/W2349023125","https://openalex.org/W4253006236","https://openalex.org/W1976807322"],"abstract_inverted_index":{"MOTIVATION:":[0],"The":[1,41,64],"size":[2,83],"of":[3,17,33,47,61,72,80,87,99,105,127,160,167,175,179],"current":[4],"protein":[5,106,120],"databases":[6],"is":[7,66,142],"a":[8,36,45,48,52,77,103,128,145,173],"challenge":[9],"for":[10,55,76,155,177],"many":[11],"Bioinformatics":[12,191],"applications,":[13],"both":[14],"in":[15,91],"terms":[16],"processing":[18],"speed":[19],"and":[20,51,59,131,158],"information":[21,89],"redundancy.":[22],"It":[23],"may":[24],"be":[25],"therefore":[26],"desirable":[27],"to":[28,35,69,137],"efficiently":[29],"reduce":[30],"the":[31,56,81,88,92,97,100,114,156,168],"database":[32,62,82,104,117],"interest":[34],"maximally":[37,153],"representative":[38,154],"subset.":[39],"RESULTS:":[40],"MinSet":[42],"method":[43,101],"employs":[44],"combination":[46],"Suffix":[49],"Tree":[50],"Genetic":[53],"Algorithm":[54],"generation,":[57],"selection":[58],"assessment":[60],"subsets.":[63],"approach":[65],"generally":[67],"applicable":[68],"any":[70],"type":[71],"string-encoded":[73],"data,":[74],"allowing":[75],"drastic":[78],"reduction":[79],"whilst":[84],"retaining":[85],"most":[86],"contained":[90],"original":[93],"set.":[94],"We":[95,112],"demonstrate":[96],"performance":[98],"on":[102,144],"domain":[107,116],"structures":[108,121],"encoded":[109],"as":[110],"strings.":[111],"used":[113],"SCOP40":[115],"by":[118,125,132],"translating":[119],"into":[122],"character":[123],"strings":[124],"means":[126],"structural":[129],"alphabet":[130],"extracting":[133],"optimized":[134,150],"subsets":[135,151],"according":[136],"an":[138],"entropy":[139],"score":[140],"that":[141],"based":[143],"constant-length":[146],"fragment":[147],"dictionary.":[148],"Therefore,":[149],"are":[152,188],"distribution":[157],"range":[159],"local":[161],"structures.":[162],"Subsets":[163],"containing":[164],"only":[165],"10%":[166],"SCOP":[169],"structure":[170],"classes":[171],"show":[172],"coverage":[174],">90%":[176],"fragments":[178],"length":[180],"1-4.":[181],"AVAILABILITY:":[182],"http://mathbio.nimr.mrc.ac.uk/~jkleinj/MinSet.":[183],"SUPPLEMENTARY":[184],"INFORMATION:":[185],"Supplementary":[186],"data":[187],"available":[189],"at":[190],"online.":[192]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":1}],"updated_date":"2026-08-14T07:06:38.338062","created_date":"2025-10-10T00:00:00"}