{"id":"https://openalex.org/W2053578062","doi":"https://doi.org/10.1142/s0219720011005677","title":"SEQUENCE-BASED ENZYME CATALYTIC DOMAIN PREDICTION USING CLUSTERING AND AGGREGATED MUTUAL INFORMATION CONTENT","display_name":"SEQUENCE-BASED ENZYME CATALYTIC DOMAIN PREDICTION USING CLUSTERING AND AGGREGATED MUTUAL INFORMATION CONTENT","publication_year":2011,"publication_date":"2011-08-11","ids":{"openalex":"https://openalex.org/W2053578062","doi":"https://doi.org/10.1142/s0219720011005677","mag":"2053578062","pmid":"https://pubmed.ncbi.nlm.nih.gov/21976378"},"language":"en","primary_location":{"id":"doi:10.1142/s0219720011005677","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0219720011005677","pdf_url":null,"source":{"id":"https://openalex.org/S155349577","display_name":"Journal of Bioinformatics and Computational Biology","issn_l":"0219-7200","issn":["0219-7200","1757-6334"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311754","host_organization_name":"Imperial College Press","host_organization_lineage":["https://openalex.org/P4310311754"],"host_organization_lineage_names":["Imperial College Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Bioinformatics and Computational Biology","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","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/A5024894867","display_name":"Kwangmin Choi","orcid":"https://orcid.org/0000-0003-4671-962X"},"institutions":[{"id":"https://openalex.org/I1285204247","display_name":"Cincinnati Children's Hospital Medical Center","ror":"https://ror.org/01hcyya48","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1285204247"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"KWANGMIN CHOI","raw_affiliation_strings":["Division of Experimental Hematology and Cancer Biology, Cincinnati Children's Hospital Medical Center, 3333 Burnet Avenue, Cincinnati, Ohio 45229, USA"],"affiliations":[{"raw_affiliation_string":"Division of Experimental Hematology and Cancer Biology, Cincinnati Children's Hospital Medical Center, 3333 Burnet Avenue, Cincinnati, Ohio 45229, USA","institution_ids":["https://openalex.org/I1285204247"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100460439","display_name":"\ufeffSun Kim","orcid":"https://orcid.org/0000-0001-5385-9546"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"SUN KIM","raw_affiliation_strings":["School of Computer Science and Engineering and Interdisciplinary Program in Bioinformatics, Seoul National University, Gwanak-1, Gwanak-ro, Gwanak-gu, Seoul 151-744, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering and Interdisciplinary Program in Bioinformatics, Seoul National University, Gwanak-1, Gwanak-ro, Gwanak-gu, Seoul 151-744, Republic of Korea","institution_ids":["https://openalex.org/I139264467"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5024894867"],"corresponding_institution_ids":["https://openalex.org/I1285204247"],"apc_list":null,"apc_paid":null,"fwci":0.6026,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.6747909,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"09","issue":"05","first_page":"597","last_page":"611"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9994000196456909,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9994000196456909,"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/T10521","display_name":"RNA and protein synthesis mechanisms","score":0.9993000030517578,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9993000030517578,"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/cluster-analysis","display_name":"Cluster analysis","score":0.7710484862327576},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5344483256340027},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.516305148601532},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.49430131912231445},{"id":"https://openalex.org/keywords/sequence-alignment","display_name":"Sequence alignment","score":0.46380212903022766},{"id":"https://openalex.org/keywords/multiple-sequence-alignment","display_name":"Multiple sequence alignment","score":0.4632861018180847},{"id":"https://openalex.org/keywords/hierarchical-clustering","display_name":"Hierarchical clustering","score":0.4479309618473053},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.441896915435791},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.42521733045578003},{"id":"https://openalex.org/keywords/in-silico","display_name":"In silico","score":0.4246165454387665},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35377198457717896},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.3488255739212036},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32513290643692017},{"id":"https://openalex.org/keywords/peptide-sequence","display_name":"Peptide sequence","score":0.23105698823928833},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.2269766628742218},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.17443197965621948},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.121192067861557}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7710484862327576},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5344483256340027},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.516305148601532},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.49430131912231445},{"id":"https://openalex.org/C45484198","wikidata":"https://www.wikidata.org/wiki/Q827246","display_name":"Sequence alignment","level":4,"score":0.46380212903022766},{"id":"https://openalex.org/C88031987","wikidata":"https://www.wikidata.org/wiki/Q1377767","display_name":"Multiple sequence alignment","level":5,"score":0.4632861018180847},{"id":"https://openalex.org/C92835128","wikidata":"https://www.wikidata.org/wiki/Q1277447","display_name":"Hierarchical clustering","level":3,"score":0.4479309618473053},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.441896915435791},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.42521733045578003},{"id":"https://openalex.org/C2775905019","wikidata":"https://www.wikidata.org/wiki/Q192572","display_name":"In silico","level":3,"score":0.4246165454387665},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35377198457717896},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.3488255739212036},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32513290643692017},{"id":"https://openalex.org/C167625842","wikidata":"https://www.wikidata.org/wiki/Q899763","display_name":"Peptide sequence","level":3,"score":0.23105698823928833},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.2269766628742218},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.17443197965621948},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.121192067861557},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D004798","descriptor_name":"Enzymes","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":false},{"descriptor_ui":"D004798","descriptor_name":"Enzymes","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":false},{"descriptor_ui":"D004798","descriptor_name":"Enzymes","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":false},{"descriptor_ui":"D004798","descriptor_name":"Enzymes","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D004798","descriptor_name":"Enzymes","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D004798","descriptor_name":"Enzymes","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D004798","descriptor_name":"Enzymes","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D004798","descriptor_name":"Enzymes","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D004798","descriptor_name":"Enzymes","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D004798","descriptor_name":"Enzymes","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D004798","descriptor_name":"Enzymes","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D004798","descriptor_name":"Enzymes","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D008958","descriptor_name":"Models, Molecular","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008958","descriptor_name":"Models, Molecular","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008958","descriptor_name":"Models, Molecular","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false},{"descriptor_ui":"D017124","descriptor_name":"Conserved Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017124","descriptor_name":"Conserved Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017124","descriptor_name":"Conserved Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020134","descriptor_name":"Catalytic Domain","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D020134","descriptor_name":"Catalytic Domain","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D020134","descriptor_name":"Catalytic Domain","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false},{"descriptor_ui":"D029968","descriptor_name":"Escherichia coli Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D029968","descriptor_name":"Escherichia coli Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D029968","descriptor_name":"Escherichia coli Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D029968","descriptor_name":"Escherichia coli Proteins","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D029968","descriptor_name":"Escherichia coli Proteins","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D029968","descriptor_name":"Escherichia coli Proteins","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D029968","descriptor_name":"Escherichia coli Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D029968","descriptor_name":"Escherichia coli Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D029968","descriptor_name":"Escherichia coli Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D048168","descriptor_name":"Escherichia coli K12","qualifier_ui":"Q000201","qualifier_name":"enzymology","is_major_topic":false},{"descriptor_ui":"D048168","descriptor_name":"Escherichia coli K12","qualifier_ui":"Q000201","qualifier_name":"enzymology","is_major_topic":false},{"descriptor_ui":"D048168","descriptor_name":"Escherichia coli K12","qualifier_ui":"Q000201","qualifier_name":"enzymology","is_major_topic":false},{"descriptor_ui":"D048168","descriptor_name":"Escherichia coli K12","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D048168","descriptor_name":"Escherichia coli K12","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D048168","descriptor_name":"Escherichia coli K12","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1142/s0219720011005677","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0219720011005677","pdf_url":null,"source":{"id":"https://openalex.org/S155349577","display_name":"Journal of Bioinformatics and Computational Biology","issn_l":"0219-7200","issn":["0219-7200","1757-6334"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311754","host_organization_name":"Imperial College Press","host_organization_lineage":["https://openalex.org/P4310311754"],"host_organization_lineage_names":["Imperial College Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Bioinformatics and Computational Biology","raw_type":"journal-article"},{"id":"pmid:21976378","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/21976378","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":"Journal of bioinformatics and computational biology","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5699999928474426,"id":"https://metadata.un.org/sdg/8","display_name":"Decent work and economic growth"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320307758","display_name":"Eli Lilly and Company","ror":"https://ror.org/01qat3289"},{"id":"https://openalex.org/F4320337397","display_name":"Division of Molecular and Cellular Biosciences","ror":"https://ror.org/002jdaq33"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1519266993","https://openalex.org/W1604281503","https://openalex.org/W1967293793","https://openalex.org/W1969738839","https://openalex.org/W2002600840","https://openalex.org/W2015292449","https://openalex.org/W2024722087","https://openalex.org/W2041877620","https://openalex.org/W2043904638","https://openalex.org/W2055043387","https://openalex.org/W2077737382","https://openalex.org/W2079048673","https://openalex.org/W2104514367","https://openalex.org/W2132886170","https://openalex.org/W2138366649","https://openalex.org/W2140000393","https://openalex.org/W2142237411","https://openalex.org/W2154333184","https://openalex.org/W2158020463","https://openalex.org/W2158266834","https://openalex.org/W2158783389","https://openalex.org/W2164176644","https://openalex.org/W4210623056"],"related_works":["https://openalex.org/W2051969447","https://openalex.org/W2111937814","https://openalex.org/W2162923930","https://openalex.org/W1482324242","https://openalex.org/W2133116680","https://openalex.org/W2091678889","https://openalex.org/W2029514038","https://openalex.org/W2149492307","https://openalex.org/W1985408726","https://openalex.org/W2141411672"],"abstract_inverted_index":{"Characterizing":[0],"enzyme":[1,44,81,110,122,156,189,260,313],"sequences":[2,29,82,123,130,261,314],"and":[3,20,30,43,66,124,138,146,169,216,289],"identifying":[4,40,309],"their":[5],"active":[6,186,206,256,310],"sites":[7,187,207,229,257,311],"is":[8,73,97,181,197,246],"a":[9,55,63,116,127,132],"very":[10],"important":[11],"task.":[12],"The":[13,70,94,112,191,209],"current":[14],"experimental":[15],"methods":[16,38,222],"are":[17,47,121,126,167],"too":[18],"expensive":[19],"labor":[21],"intensive":[22],"to":[23,74,99,149,154,183,199,202,248,280],"handle":[24,100],"the":[25,76,84,90,101,155,163,214,217,239,259,267,281,286,302],"rapidly":[26],"accumulating":[27],"protein":[28],"structure":[31],"data.":[32],"Thus":[33],"accurate,":[34],"high-throughput":[35],"in":[36,109,162,188,225,230,236,253,258,278,285],"silico":[37],"for":[39,308],"catalytic":[41,58,228],"residues":[42,204],"function":[45],"prediction":[46,60],"much":[48,297],"needed.":[49],"In":[50],"this":[51],"paper,":[52],"we":[53],"propose":[54],"novel":[56],"sequence-based":[57],"domain":[59],"method":[61,211,245,304],"using":[62],"sequence":[64,77,106,117,136,151,287],"clustering":[65,78,95,113,215,268],"an":[67,171],"information-theoretic":[68],"approaches.":[69],"first":[71],"step":[72],"perform":[75],"analysis":[79,96,114],"of":[80,103,129,135,205,212,232,238,283,291,312],"from":[83,315],"same":[85,91],"functional":[86],"category":[87],"(those":[88],"with":[89,131],"EC":[92],"label).":[93],"used":[98],"problem":[102],"widely":[104],"varying":[105],"similarity":[107],"levels":[108],"sequences.":[111,157,190],"constructs":[115],"graph":[118,140,272,288],"where":[119],"nodes":[120],"edges":[125,284],"pair":[128],"certain":[133],"degree":[134],"similarity,":[137],"uses":[139],"properties,":[141],"such":[142],"as":[143],"biconnected":[144],"components":[145],"articulation":[147],"points,":[148],"generate":[150],"segments":[152],"common":[153,164],"Then":[158],"amino":[159],"acid":[160],"subsequences":[161],"shared":[165],"regions":[166],"aligned":[168],"then":[170],"information":[172,193,219,293],"theoretic":[173],"approach":[174,269],"called":[175],"aggregated":[176,192,218],"column":[177],"related":[178],"scoring":[179,195,221],"scheme":[180,196],"performed":[182],"highlight":[184,203],"potential":[185,255],"content":[194,220],"shown":[198,247],"be":[200,249,276,306],"effective":[201],"effectively.":[208],"proposed":[210,303],"combining":[213],"was":[223],"successful":[224],"highlighting":[226],"known":[227],"enzymes":[231],"Escherichia":[233],"coli":[234],"K12":[235],"terms":[237],"Catalytic":[240],"Site":[241],"Atlas":[242],"database.":[243],"Our":[244],"not":[250,295],"only":[251],"accurate":[252],"predicting":[254],"but":[262],"also":[263],"computationally":[264],"efficient":[265],"since":[266],"utilizes":[270],"two":[271],"properties":[273],"that":[274,301],"can":[275,305],"computed":[277],"linear":[279],"number":[282],"computation":[290],"mutual":[292],"does":[294],"require":[296],"time.":[298],"We":[299],"believe":[300],"useful":[307],"many":[316],"genome":[317],"projects.":[318]},"counts_by_year":[{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}