{"id":"https://openalex.org/W2102660584","doi":"https://doi.org/10.1186/1471-2105-10-446","title":"Data mining of enzymes using specific peptides","display_name":"Data mining of enzymes using specific peptides","publication_year":2009,"publication_date":"2009-12-01","ids":{"openalex":"https://openalex.org/W2102660584","doi":"https://doi.org/10.1186/1471-2105-10-446","mag":"2102660584","pmid":"https://pubmed.ncbi.nlm.nih.gov/20034383"},"language":"en","primary_location":{"id":"doi:10.1186/1471-2105-10-446","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-10-446","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-10-446","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-10-446","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5069478161","display_name":"Uri Weingart","orcid":null},"institutions":[{"id":"https://openalex.org/I16391192","display_name":"Tel Aviv University","ror":"https://ror.org/04mhzgx49","country_code":"IL","type":"education","lineage":["https://openalex.org/I16391192"]}],"countries":["IL"],"is_corresponding":true,"raw_author_name":"Uri Weingart","raw_affiliation_strings":["School of Physics and Astronomy, Tel Aviv University, Tel Aviv 69978, Israel. uriweing@tau.ac.il","School of Physics and Astronomy, Tel Aviv University, Tel Aviv, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Physics and Astronomy, Tel Aviv University, Tel Aviv 69978, Israel. uriweing@tau.ac.il","institution_ids":["https://openalex.org/I16391192"]},{"raw_affiliation_string":"School of Physics and Astronomy, Tel Aviv University, Tel Aviv, Israel","institution_ids":["https://openalex.org/I16391192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021102674","display_name":"Yair Lavi","orcid":null},"institutions":[{"id":"https://openalex.org/I16391192","display_name":"Tel Aviv University","ror":"https://ror.org/04mhzgx49","country_code":"IL","type":"education","lineage":["https://openalex.org/I16391192"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Yair Lavi","raw_affiliation_strings":["School of Physics and Astronomy, Tel Aviv University, Tel Aviv, 69978, Israel","School of Physics and Astronomy, Tel Aviv University, Tel Aviv, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Physics and Astronomy, Tel Aviv University, Tel Aviv, 69978, Israel","institution_ids":["https://openalex.org/I16391192"]},{"raw_affiliation_string":"School of Physics and Astronomy, Tel Aviv University, Tel Aviv, Israel","institution_ids":["https://openalex.org/I16391192"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001249894","display_name":"D. Horn","orcid":"https://orcid.org/0000-0003-2708-186X"},"institutions":[{"id":"https://openalex.org/I16391192","display_name":"Tel Aviv University","ror":"https://ror.org/04mhzgx49","country_code":"IL","type":"education","lineage":["https://openalex.org/I16391192"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"David Horn","raw_affiliation_strings":["School of Physics and Astronomy, Tel Aviv University, Tel Aviv, 69978, Israel","School of Physics and Astronomy, Tel Aviv University, Tel Aviv, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Physics and Astronomy, Tel Aviv University, Tel Aviv, 69978, Israel","institution_ids":["https://openalex.org/I16391192"]},{"raw_affiliation_string":"School of Physics and Astronomy, Tel Aviv University, Tel Aviv, Israel","institution_ids":["https://openalex.org/I16391192"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5069478161"],"corresponding_institution_ids":["https://openalex.org/I16391192"],"apc_list":{"value":1690,"currency":"GBP","value_usd":2072},"apc_paid":{"value":1690,"currency":"GBP","value_usd":2072},"fwci":0.8343,"has_fulltext":true,"cited_by_count":13,"citation_normalized_percentile":{"value":0.7185528,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"10","issue":"1","first_page":"446","last_page":"446"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10519","display_name":"Advanced Proteomics Techniques and Applications","score":0.4341000020503998,"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"}},"topics":[{"id":"https://openalex.org/T10519","display_name":"Advanced Proteomics Techniques and Applications","score":0.4341000020503998,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.4092000126838684,"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/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.027300000190734863,"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/computational-biology","display_name":"Computational biology","score":0.6220746636390686},{"id":"https://openalex.org/keywords/dna-microarray","display_name":"DNA microarray","score":0.5878592133522034},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4206016957759857},{"id":"https://openalex.org/keywords/enzyme","display_name":"Enzyme","score":0.4110051393508911},{"id":"https://openalex.org/keywords/bioinformatics","display_name":"Bioinformatics","score":0.4028635025024414},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.39358827471733093},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.3579244613647461},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.2595670819282532},{"id":"https://openalex.org/keywords/biochemistry","display_name":"Biochemistry","score":0.22723111510276794},{"id":"https://openalex.org/keywords/gene-expression","display_name":"Gene expression","score":0.14546102285385132},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.13390305638313293}],"concepts":[{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.6220746636390686},{"id":"https://openalex.org/C95371953","wikidata":"https://www.wikidata.org/wiki/Q591745","display_name":"DNA microarray","level":4,"score":0.5878592133522034},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4206016957759857},{"id":"https://openalex.org/C181199279","wikidata":"https://www.wikidata.org/wiki/Q8047","display_name":"Enzyme","level":2,"score":0.4110051393508911},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.4028635025024414},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.39358827471733093},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.3579244613647461},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.2595670819282532},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.22723111510276794},{"id":"https://openalex.org/C150194340","wikidata":"https://www.wikidata.org/wiki/Q26972","display_name":"Gene expression","level":3,"score":0.14546102285385132},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.13390305638313293}],"mesh":[{"descriptor_ui":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010455","descriptor_name":"Peptides","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D010455","descriptor_name":"Peptides","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D010455","descriptor_name":"Peptides","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":"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":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","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":"D057225","descriptor_name":"Data Mining","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false}],"locations_count":4,"locations":[{"id":"doi:10.1186/1471-2105-10-446","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-10-446","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-10-446","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},{"id":"pmid:20034383","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/20034383","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":"BMC bioinformatics","raw_type":null},{"id":"pmh:oai:doaj.org/article:9d07a07c9c96407bb07995d0e5629698","is_oa":false,"landing_page_url":"https://doaj.org/article/9d07a07c9c96407bb07995d0e5629698","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Bioinformatics, Vol 10, Iss 1, p 446 (2009)","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:2811123","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/2811123","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Bioinformatics","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1186/1471-2105-10-446","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-10-446","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-10-446","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.8600000143051147,"display_name":"Life below water","id":"https://metadata.un.org/sdg/14"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320322596","display_name":"Tel Aviv University","ror":"https://ror.org/04mhzgx49"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2102660584.pdf","grobid_xml":"https://content.openalex.org/works/W2102660584.grobid-xml"},"referenced_works_count":15,"referenced_works":["https://openalex.org/W1995614275","https://openalex.org/W2000622980","https://openalex.org/W2021380741","https://openalex.org/W2049349724","https://openalex.org/W2055043387","https://openalex.org/W2057508801","https://openalex.org/W2075623226","https://openalex.org/W2100179836","https://openalex.org/W2100320834","https://openalex.org/W2113601822","https://openalex.org/W2117019496","https://openalex.org/W2120143417","https://openalex.org/W2126809954","https://openalex.org/W2143296986","https://openalex.org/W2145336165"],"related_works":["https://openalex.org/W2415545834","https://openalex.org/W2069695727","https://openalex.org/W1802639773","https://openalex.org/W2118505788","https://openalex.org/W4254166511","https://openalex.org/W2150084125","https://openalex.org/W1542823905","https://openalex.org/W1490878237","https://openalex.org/W2990314835","https://openalex.org/W2131319730"],"abstract_inverted_index":{"BACKGROUND:":[0],"Predicting":[1],"the":[2,26,43,51,78,109,123,136,146,164,204,207,257,297,301,304],"function":[3],"of":[4,14,32,42,54,97,103,112,126,132,153,194,206,222,249,259,279,290,300,307,321],"a":[5,11,71,94,192,239],"protein":[6,72,137],"from":[7,67,89,143],"its":[8,68],"sequence":[9,69],"is":[10,73,140,265],"long-standing":[12],"challenge":[13],"bioinformatic":[15],"research,":[16],"typically":[17],"addressed":[18],"using":[19],"either":[20],"sequence-similarity":[21],"or":[22],"sequence-motifs.":[23],"We":[24,49,84,187],"employ":[25],"novel":[27,86,240],"motif":[28],"method":[29,190],"that":[30,36,58,108,158,220],"consists":[31],"Specific":[33],"Peptides":[34],"(SPs)":[35],"are":[37],"unique":[38],"to":[39,197,210,268,338],"specific":[40],"branches":[41],"Enzyme":[44],"Commission":[45],"(EC)":[46],"functional":[47],"classification.":[48],"devise":[50],"Data":[52],"Mining":[53],"Enzymes":[55],"(DME)":[56],"methodology":[57],"allows":[59],"for":[60,115,171,236,310,317],"searching":[61],"SPs":[62,316],"on":[63,122,135,148,191,244],"arbitrary":[64],"proteins,":[65,276],"determining":[66],"whether":[70],"an":[74,149],"enzyme":[75,91,150],"and":[76,100,118,283],"what":[77],"enzyme's":[79],"EC":[80,312],"classification":[81],"is.":[82],"RESULTS:":[83],"extract":[85],"SP":[87,128,241,263],"sets":[88,102],"Swiss-Prot":[90,228,246],"data.":[92],"Using":[93],"training":[95],"set":[96,152,193,242,254,264],"July":[98,104,154,201,231,250],"2006,":[99],"test":[101,151,188],"2008,":[105,155,202],"we":[106,156,218,234],"find":[107,157,219],"predictive":[110],"power":[111],"SPs,":[113],"both":[114],"true-positives":[116],"(enzymes)":[117],"true-negatives":[119],"(non-enzymes),":[120],"depends":[121],"coverage":[124],"length":[125],"all":[127,245],"matches":[129],"(the":[130],"number":[131],"amino-acids":[133],"matched":[134],"sequence).":[138],"DME":[139,159,167],"quite":[141],"different":[142,311],"BLAST.":[144],"Comparing":[145],"two":[147,284],"has":[160,336],"lower":[161],"recall.":[162],"On":[163],"other":[165],"hand,":[166],"can":[168,293],"provide":[169],"predictions":[170,217,278],"proteins":[172,195,322],"regarded":[173],"by":[174,227,230,296],"BLAST":[175],"as":[176,248],"having":[177],"low":[178],"homologies":[179],"with":[180,273],"known":[181],"enzymes,":[182,282],"thus":[183],"supplying":[184],"complementary":[185],"information.":[186],"our":[189,216,331],"belonging":[196],"10":[198],"bacteria,":[199],"dated":[200],"establishing":[203],"usefulness":[205],"coverage-length":[208,328],"cutoff":[209],"determine":[211],"true-negatives.":[212],"Moreover,":[213],"sifting":[214],"through":[215],"some":[221],"them":[223],"have":[224],"been":[225],"substantiated":[226],"annotations":[229],"2009.":[232,251],"Finally":[233],"extract,":[235],"production":[237],"purposes,":[238],"trained":[243],"enzymes":[247,308],"This":[252],"new":[253,262],"increases":[255],"considerably":[256],"recall":[258],"DME.":[260],"The":[261,288],"being":[266],"applied":[267],"three":[269],"metagenomes:":[270],"Sargasso":[271],"Sea":[272],"over":[274,280],"1,000,000":[275],"producing":[277],"220,000":[281],"human":[285],"gut":[286],"metagenomes.":[287],"outcome":[289],"these":[291],"analyses":[292],"be":[294],"characterized":[295],"enzymatic":[298,319],"profile":[299],"metagenomes,":[302],"describing":[303],"relative":[305],"numbers":[306],"observed":[309],"categories.":[313],"CONCLUSIONS:":[314],"Employing":[315],"predicting":[318],"activity":[320],"works":[323],"well":[324],"once":[325],"one":[326],"utilizes":[327],"criteria.":[329],"In":[330],"analysis,":[332],"L":[333],">or=":[334],"7":[335],"led":[337],"highly":[339],"accurate":[340],"results.":[341]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":2}],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2025-10-10T00:00:00"}