{"id":"https://openalex.org/W2147368249","doi":"https://doi.org/10.1093/bioinformatics/btg1017","title":"Sensitive pattern discovery with \u2018fuzzy\u2019 alignments of distantlyrelated proteins","display_name":"Sensitive pattern discovery with \u2018fuzzy\u2019 alignments of distantlyrelated proteins","publication_year":2003,"publication_date":"2003-07-03","ids":{"openalex":"https://openalex.org/W2147368249","doi":"https://doi.org/10.1093/bioinformatics/btg1017","mag":"2147368249","pmid":"https://pubmed.ncbi.nlm.nih.gov/12855449"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btg1017","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btg1017","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/19/suppl_1/i130/614457/btg1017.pdf","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":true,"oa_status":"bronze","oa_url":"https://academic.oup.com/bioinformatics/article-pdf/19/suppl_1/i130/614457/btg1017.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5021930729","display_name":"Andreas Heger","orcid":"https://orcid.org/0000-0001-7720-0447"},"institutions":[{"id":"https://openalex.org/I133731052","display_name":"University of Helsinki","ror":"https://ror.org/040af2s02","country_code":"FI","type":"education","lineage":["https://openalex.org/I133731052"]},{"id":"https://openalex.org/I2800229700","display_name":"Helsinki Institute of Physics","ror":"https://ror.org/01x2x1522","country_code":"FI","type":"facility","lineage":["https://openalex.org/I133731052","https://openalex.org/I2800229700","https://openalex.org/I63548447","https://openalex.org/I94722563","https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Andreas Heger","raw_affiliation_strings":["Institute of Biotechnology, P.O. Box 56, 00014 University of Helsinki Finland","Institute of Biotechnology, P.O. Box 56, 00014 University of Helsinki, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Biotechnology, P.O. Box 56, 00014 University of Helsinki Finland","institution_ids":["https://openalex.org/I2800229700"]},{"raw_affiliation_string":"Institute of Biotechnology, P.O. Box 56, 00014 University of Helsinki, Finland","institution_ids":["https://openalex.org/I133731052","https://openalex.org/I2800229700"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064498279","display_name":"Liisa Holm","orcid":"https://orcid.org/0000-0002-7807-2966"},"institutions":[{"id":"https://openalex.org/I133731052","display_name":"University of Helsinki","ror":"https://ror.org/040af2s02","country_code":"FI","type":"education","lineage":["https://openalex.org/I133731052"]},{"id":"https://openalex.org/I2800229700","display_name":"Helsinki Institute of Physics","ror":"https://ror.org/01x2x1522","country_code":"FI","type":"facility","lineage":["https://openalex.org/I133731052","https://openalex.org/I2800229700","https://openalex.org/I63548447","https://openalex.org/I94722563","https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Liisa Holm","raw_affiliation_strings":["Institute of Biotechnology, P.O. Box 56, 00014 University of Helsinki Finland","Institute of Biotechnology, P.O. Box 56, 00014 University of Helsinki, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Biotechnology, P.O. Box 56, 00014 University of Helsinki Finland","institution_ids":["https://openalex.org/I2800229700"]},{"raw_affiliation_string":"Institute of Biotechnology, P.O. Box 56, 00014 University of Helsinki, Finland","institution_ids":["https://openalex.org/I133731052","https://openalex.org/I2800229700"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":null,"fwci":1.5173,"has_fulltext":false,"cited_by_count":50,"citation_normalized_percentile":{"value":0.81760574,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"19","issue":"suppl_1","first_page":"i130","last_page":"i137"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10044","display_name":"Protein Structure and Dynamics","score":0.3366999924182892,"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":0.3366999924182892,"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":0.1979999989271164,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.11339999735355377,"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":0.5727341771125793},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5455202460289001},{"id":"https://openalex.org/keywords/fuzzy-logic","display_name":"Fuzzy logic","score":0.5196653604507446},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41030001640319824},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4100390672683716},{"id":"https://openalex.org/keywords/bioinformatics","display_name":"Bioinformatics","score":0.3640362620353699},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.3506826162338257},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33232247829437256}],"concepts":[{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.5727341771125793},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5455202460289001},{"id":"https://openalex.org/C58166","wikidata":"https://www.wikidata.org/wiki/Q224821","display_name":"Fuzzy logic","level":2,"score":0.5196653604507446},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41030001640319824},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4100390672683716},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.3640362620353699},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.3506826162338257},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33232247829437256}],"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":"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":"D008956","descriptor_name":"Models, Chemical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008956","descriptor_name":"Models, Chemical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008956","descriptor_name":"Models, Chemical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008969","descriptor_name":"Molecular Sequence Data","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008969","descriptor_name":"Molecular Sequence Data","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008969","descriptor_name":"Molecular Sequence Data","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010363","descriptor_name":"Pattern Recognition, Automated","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010363","descriptor_name":"Pattern Recognition, Automated","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010363","descriptor_name":"Pattern Recognition, Automated","qualifier_ui":null,"qualifier_name":null,"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":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","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":"D014510","descriptor_name":"Urease","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":false},{"descriptor_ui":"D014510","descriptor_name":"Urease","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":false},{"descriptor_ui":"D014510","descriptor_name":"Urease","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":false},{"descriptor_ui":"D014510","descriptor_name":"Urease","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D014510","descriptor_name":"Urease","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D014510","descriptor_name":"Urease","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D014510","descriptor_name":"Urease","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D014510","descriptor_name":"Urease","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D014510","descriptor_name":"Urease","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D015233","descriptor_name":"Models, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015233","descriptor_name":"Models, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015233","descriptor_name":"Models, Statistical","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":"D017143","descriptor_name":"Fuzzy Logic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D017143","descriptor_name":"Fuzzy Logic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D017143","descriptor_name":"Fuzzy Logic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D017386","descriptor_name":"Sequence Homology, Amino Acid","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017386","descriptor_name":"Sequence Homology, Amino Acid","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017386","descriptor_name":"Sequence Homology, Amino Acid","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019143","descriptor_name":"Evolution, Molecular","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019143","descriptor_name":"Evolution, Molecular","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019143","descriptor_name":"Evolution, Molecular","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":"D020869","descriptor_name":"Gene Expression Profiling","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020869","descriptor_name":"Gene Expression Profiling","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020869","descriptor_name":"Gene Expression Profiling","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1093/bioinformatics/btg1017","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btg1017","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/19/suppl_1/i130/614457/btg1017.pdf","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:12855449","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/12855449","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}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btg1017","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btg1017","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/19/suppl_1/i130/614457/btg1017.pdf","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"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1902027874","https://openalex.org/W1973578915","https://openalex.org/W1985444263","https://openalex.org/W1995924392","https://openalex.org/W2009566340","https://openalex.org/W2027036222","https://openalex.org/W2028903194","https://openalex.org/W2041255394","https://openalex.org/W2067913741","https://openalex.org/W2100750044","https://openalex.org/W2133312664","https://openalex.org/W2152350018","https://openalex.org/W2160216877","https://openalex.org/W2299279932"],"related_works":["https://openalex.org/W1921169094","https://openalex.org/W366410996","https://openalex.org/W4239902399","https://openalex.org/W2002243093","https://openalex.org/W2146076056","https://openalex.org/W2971191913","https://openalex.org/W2144092555","https://openalex.org/W2731939565","https://openalex.org/W1528058524","https://openalex.org/W2800590509"],"abstract_inverted_index":{"MOTIVATION:":[0],"Evolutionary":[1],"comparison":[2],"leads":[3,41],"to":[4,15,20,42,83,96,148],"efficient":[5],"functional":[6,22],"characterisation":[7],"of":[8,36,45,61,88,104,138],"hypothetical":[9],"proteins.":[10,90],"Here,":[11],"our":[12],"goal":[13],"is":[14,107,115],"map":[16],"specific":[17],"sequence":[18,62,67],"patterns":[19,141],"putative":[21],"classes.":[23],"The":[24,48,102,113],"evolutionary":[25],"signal":[26],"stands":[27],"out":[28],"most":[29],"clearly":[30],"in":[31,142],"a":[32,43,75],"maximally":[33],"diverse":[34,145],"set":[35],"homologues.":[37],"This":[38],"diversity,":[39],"however,":[40],"number":[44],"technical":[46],"difficulties.":[47],"targeted":[49],"patterns-as":[50],"gleaned":[51],"from":[52],"structure":[53],"comparisons-are":[54],"too":[55],"sparse":[56],"for":[57],"statistically":[58],"significant":[59],"signals":[60],"similarity":[63],"and":[64,119],"accurate":[65],"multiple":[66,129],"alignment.":[68],"RESULTS:":[69],"We":[70,91,134],"address":[71],"this":[72],"problem":[73],"by":[74],"fuzzy":[76],"alignment":[77],"model,":[78],"which":[79],"probabilistically":[80],"assigns":[81],"residues":[82],"structurally":[84],"equivalent":[85],"positions":[86],"(attributes)":[87],"the":[89,97,105,136],"then":[92],"apply":[93],"multivariate":[94],"analysis":[95],"'attributes":[98],"x":[99],"proteins'":[100],"matrix.":[101],"dimensionality":[103],"space":[106],"reduced":[108],"using":[109],"non-negative":[110],"matrix":[111],"factorization.":[112],"method":[114],"general,":[116],"fully":[117],"automatic":[118],"works":[120],"without":[121],"assumptions":[122],"about":[123],"pattern":[124],"density,":[125],"minimum":[126],"support,":[127],"explicit":[128],"alignments,":[130],"phylogenetic":[131],"trees,":[132],"etc.":[133],"demonstrate":[135],"discovery":[137],"biologically":[139],"meaningful":[140],"an":[143],"extremely":[144],"superfamily":[146],"related":[147],"urease.":[149]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":6}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}