{"id":"https://openalex.org/W2098830117","doi":"https://doi.org/10.1093/bioinformatics/bti396","title":"Determining functional specificity from protein sequences","display_name":"Determining functional specificity from protein sequences","publication_year":2005,"publication_date":"2005-03-29","ids":{"openalex":"https://openalex.org/W2098830117","doi":"https://doi.org/10.1093/bioinformatics/bti396","mag":"2098830117","pmid":"https://pubmed.ncbi.nlm.nih.gov/15797914"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/bti396","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/bti396","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/21/11/2629/48971407/bioinformatics_21_11_2629.pdf","source":{"id":"https://openalex.org/S4210188263","display_name":"Computer applications in the biosciences","issn_l":"0266-7061","issn":["0266-7061","1460-2059"],"is_oa":false,"is_in_doaj":false,"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","pubmed"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://academic.oup.com/bioinformatics/article-pdf/21/11/2629/48971407/bioinformatics_21_11_2629.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5081695483","display_name":"Jason E. Donald","orcid":null},"institutions":[{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"J. E. Donald","raw_affiliation_strings":["Department of Chemistry and Chemical Biology, Harvard University, 12 Oxford Street, Cambridge, MA 02138, USA","Department of Chemistry and Chemical Biology, Harvard University, 12 Oxford Street, Cambridge, MA, 02138, USA"],"affiliations":[{"raw_affiliation_string":"Department of Chemistry and Chemical Biology, Harvard University, 12 Oxford Street, Cambridge, MA 02138, USA","institution_ids":["https://openalex.org/I136199984"]},{"raw_affiliation_string":"Department of Chemistry and Chemical Biology, Harvard University, 12 Oxford Street, Cambridge, MA, 02138, USA","institution_ids":["https://openalex.org/I136199984"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082765817","display_name":"Eugene I. Shakhnovich","orcid":"https://orcid.org/0000-0002-4769-2265"},"institutions":[{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"E. I. Shakhnovich","raw_affiliation_strings":["Department of Chemistry and Chemical Biology, Harvard University  12 Oxford Street, Cambridge, MA 02138, USA","Department of Chemistry and Chemical Biology, Harvard University, 12 Oxford Street, Cambridge, MA, 02138, USA"],"affiliations":[{"raw_affiliation_string":"Department of Chemistry and Chemical Biology, Harvard University  12 Oxford Street, Cambridge, MA 02138, USA","institution_ids":["https://openalex.org/I136199984"]},{"raw_affiliation_string":"Department of Chemistry and Chemical Biology, Harvard University, 12 Oxford Street, Cambridge, MA, 02138, USA","institution_ids":["https://openalex.org/I136199984"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5081695483"],"corresponding_institution_ids":["https://openalex.org/I136199984"],"apc_list":null,"apc_paid":null,"fwci":1.0127,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.7437123,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":"21","issue":"11","first_page":"2629","last_page":"2635"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10044","display_name":"Protein Structure and Dynamics","score":0.9983999729156494,"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/T10044","display_name":"Protein Structure and Dynamics","score":0.9983999729156494,"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":0.9976999759674072,"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":0.9959999918937683,"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/granularity","display_name":"Granularity","score":0.8185341358184814},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.5293146967887878},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5222074389457703},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5196710824966431},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5162118077278137},{"id":"https://openalex.org/keywords/leucine-zipper","display_name":"Leucine zipper","score":0.5126975774765015},{"id":"https://openalex.org/keywords/protein-superfamily","display_name":"Protein superfamily","score":0.5110501050949097},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.49995923042297363},{"id":"https://openalex.org/keywords/protein-family","display_name":"Protein family","score":0.4666091799736023},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4366081953048706},{"id":"https://openalex.org/keywords/dna","display_name":"DNA","score":0.4146277904510498},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.4023427963256836},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.37086090445518494},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3465903401374817},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34635668992996216},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.332489013671875},{"id":"https://openalex.org/keywords/peptide-sequence","display_name":"Peptide sequence","score":0.3055601119995117},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.28936898708343506},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.1347789168357849}],"concepts":[{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.8185341358184814},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.5293146967887878},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5222074389457703},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5196710824966431},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5162118077278137},{"id":"https://openalex.org/C156860981","wikidata":"https://www.wikidata.org/wiki/Q2565229","display_name":"Leucine zipper","level":4,"score":0.5126975774765015},{"id":"https://openalex.org/C178180057","wikidata":"https://www.wikidata.org/wiki/Q7251477","display_name":"Protein superfamily","level":3,"score":0.5110501050949097},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.49995923042297363},{"id":"https://openalex.org/C171897839","wikidata":"https://www.wikidata.org/wiki/Q417841","display_name":"Protein family","level":3,"score":0.4666091799736023},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4366081953048706},{"id":"https://openalex.org/C552990157","wikidata":"https://www.wikidata.org/wiki/Q7430","display_name":"DNA","level":2,"score":0.4146277904510498},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.4023427963256836},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.37086090445518494},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3465903401374817},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34635668992996216},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.332489013671875},{"id":"https://openalex.org/C167625842","wikidata":"https://www.wikidata.org/wiki/Q899763","display_name":"Peptide sequence","level":3,"score":0.3055601119995117},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.28936898708343506},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.1347789168357849},{"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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"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":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":"D001665","descriptor_name":"Binding Sites","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001665","descriptor_name":"Binding Sites","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001665","descriptor_name":"Binding Sites","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D004247","descriptor_name":"DNA","qualifier_ui":"Q000032","qualifier_name":"analysis","is_major_topic":false},{"descriptor_ui":"D004247","descriptor_name":"DNA","qualifier_ui":"Q000032","qualifier_name":"analysis","is_major_topic":false},{"descriptor_ui":"D004247","descriptor_name":"DNA","qualifier_ui":"Q000032","qualifier_name":"analysis","is_major_topic":false},{"descriptor_ui":"D004247","descriptor_name":"DNA","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D004247","descriptor_name":"DNA","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D004247","descriptor_name":"DNA","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D004268","descriptor_name":"DNA-Binding Proteins","qualifier_ui":"Q000032","qualifier_name":"analysis","is_major_topic":false},{"descriptor_ui":"D004268","descriptor_name":"DNA-Binding Proteins","qualifier_ui":"Q000032","qualifier_name":"analysis","is_major_topic":false},{"descriptor_ui":"D004268","descriptor_name":"DNA-Binding Proteins","qualifier_ui":"Q000032","qualifier_name":"analysis","is_major_topic":false},{"descriptor_ui":"D004268","descriptor_name":"DNA-Binding Proteins","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":false},{"descriptor_ui":"D004268","descriptor_name":"DNA-Binding Proteins","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":false},{"descriptor_ui":"D004268","descriptor_name":"DNA-Binding Proteins","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":false},{"descriptor_ui":"D004268","descriptor_name":"DNA-Binding Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D004268","descriptor_name":"DNA-Binding Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D004268","descriptor_name":"DNA-Binding Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D011485","descriptor_name":"Protein Binding","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011485","descriptor_name":"Protein Binding","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011485","descriptor_name":"Protein Binding","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012689","descriptor_name":"Sequence Homology, Nucleic Acid","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012689","descriptor_name":"Sequence Homology, Nucleic Acid","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012689","descriptor_name":"Sequence Homology, Nucleic Acid","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013329","descriptor_name":"Structure-Activity Relationship","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013329","descriptor_name":"Structure-Activity Relationship","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013329","descriptor_name":"Structure-Activity Relationship","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D014584","descriptor_name":"User-Computer Interface","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D014584","descriptor_name":"User-Computer Interface","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D014584","descriptor_name":"User-Computer Interface","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":"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":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","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":"D025941","descriptor_name":"Protein Interaction Mapping","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D025941","descriptor_name":"Protein Interaction Mapping","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D025941","descriptor_name":"Protein Interaction Mapping","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false}],"locations_count":3,"locations":[{"id":"doi:10.1093/bioinformatics/bti396","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/bti396","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/21/11/2629/48971407/bioinformatics_21_11_2629.pdf","source":{"id":"https://openalex.org/S4210188263","display_name":"Computer applications in the biosciences","issn_l":"0266-7061","issn":["0266-7061","1460-2059"],"is_oa":false,"is_in_doaj":false,"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:15797914","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/15797914","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:CiteSeerX.psu:10.1.1.900.1693","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.900.1693","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://bioinformatics.oxfordjournals.org/content/early/2005/03/29/bioinformatics.bti396.full.pdf","raw_type":"text"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/bti396","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/bti396","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/21/11/2629/48971407/bioinformatics_21_11_2629.pdf","source":{"id":"https://openalex.org/S4210188263","display_name":"Computer applications in the biosciences","issn_l":"0266-7061","issn":["0266-7061","1460-2059"],"is_oa":false,"is_in_doaj":false,"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"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2098830117.pdf","grobid_xml":"https://content.openalex.org/works/W2098830117.grobid-xml"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W1990453950","https://openalex.org/W1990607929","https://openalex.org/W1994261741","https://openalex.org/W1997199912","https://openalex.org/W2001914359","https://openalex.org/W2008856488","https://openalex.org/W2015292449","https://openalex.org/W2018300877","https://openalex.org/W2041862730","https://openalex.org/W2055043387","https://openalex.org/W2055507015","https://openalex.org/W2093377893","https://openalex.org/W2095318832","https://openalex.org/W2100320834","https://openalex.org/W2106882534","https://openalex.org/W2121564430","https://openalex.org/W2124166542","https://openalex.org/W2126975650","https://openalex.org/W2129621613","https://openalex.org/W2133828198","https://openalex.org/W2141411672","https://openalex.org/W2146827656","https://openalex.org/W2154139219","https://openalex.org/W2159266221","https://openalex.org/W2169239268","https://openalex.org/W3199943451","https://openalex.org/W4236236547","https://openalex.org/W4238387639","https://openalex.org/W4241391257"],"related_works":["https://openalex.org/W2139240863","https://openalex.org/W2144482528","https://openalex.org/W2075451741","https://openalex.org/W2170171070","https://openalex.org/W2053803793","https://openalex.org/W1881473418","https://openalex.org/W2070693796","https://openalex.org/W2026016918","https://openalex.org/W2169356867","https://openalex.org/W2014927296"],"abstract_inverted_index":{"We":[0,21,116],"propose":[1],"a":[2,55,77],"consistent":[3],"way":[4],"of":[5,12,61,80,99,107],"choosing":[6],"the":[7,13,49,62,69,83,87,93,96,112],"granularity":[8,100],"that":[9,91,109,118],"is":[10,43,64],"independent":[11],"sequence":[14,17],"similarity":[15],"and":[16,33,104],"clustering":[18],"method":[19,42,79],"used.":[20],"study":[22],"three":[23,36],"large,":[24],"well-investigated":[25],"protein":[26,133],"families:":[27],"basic":[28],"leucine":[29],"zippers,":[30],"nuclear":[31],"receptors":[32],"proteins":[34,108],"with":[35],"consecutive":[37],"C2H2":[38],"zinc":[39],"fingers.":[40],"Our":[41],"tested":[44],"against":[45,76],"known":[46],"functional":[47],"information,":[48],"experimentally":[50],"determined":[51],"binding":[52,129],"specificities,":[53],"using":[54],"simple":[56],"scoring":[57],"method.":[58,85],"The":[59],"significance":[60],"groups":[63,106],"also":[65,131],"measured":[66],"by":[67],"randomizing":[68],"data.":[70],"Finally,":[71],"we":[72,89],"compare":[73],"our":[74],"algorithm":[75],"popular":[78],"grouping":[81],"proteins,":[82],"TRIBE-MCL":[84],"In":[86],"end,":[88],"determine":[90],"dividing":[92],"families":[94],"at":[95],"proposed":[97],"level":[98],"creates":[101],"very":[102],"significant":[103],"useful":[105,123],"correspond":[110],"to":[111],"different":[113],"DNA-binding":[114],"motifs.":[115],"expect":[117],"such":[119],"groupings":[120],"will":[121],"be":[122],"in":[124],"studying":[125],"not":[126],"only":[127],"DNA":[128],"but":[130],"other":[132],"interactions.":[134]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}