{"id":"https://openalex.org/W2098913407","doi":"https://doi.org/10.1186/1471-2105-6-216","title":"JACOP: A simple and robust method for the automated classification of protein sequences with modular architecture","display_name":"JACOP: A simple and robust method for the automated classification of protein sequences with modular architecture","publication_year":2005,"publication_date":"2005-08-31","ids":{"openalex":"https://openalex.org/W2098913407","doi":"https://doi.org/10.1186/1471-2105-6-216","mag":"2098913407","pmid":"https://pubmed.ncbi.nlm.nih.gov/16135248"},"language":"en","primary_location":{"id":"doi:10.1186/1471-2105-6-216","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-6-216","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-6-216","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/10.1186/1471-2105-6-216","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5041806695","display_name":"Peter Sperisen","orcid":null},"institutions":[{"id":"https://openalex.org/I12708293","display_name":"SIB Swiss Institute of Bioinformatics","ror":"https://ror.org/002n09z45","country_code":"CH","type":"nonprofit","lineage":["https://openalex.org/I12708293"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"Peter Sperisen","raw_affiliation_strings":["Swiss Institute of Bioinformatics, Computational Cancer Genomics Group-ISREC, Ch. des Boveresses 155, 1066 Epalinges, Switzerland. peter.sperisen@isb-sib.ch","Swiss Institute of Bioinformatics, Computational Cancer Genomics Group-ISREC, Ch. des Boveresses 155, 1066 Epalinges, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Swiss Institute of Bioinformatics, Computational Cancer Genomics Group-ISREC, Ch. des Boveresses 155, 1066 Epalinges, Switzerland. peter.sperisen@isb-sib.ch","institution_ids":["https://openalex.org/I12708293"]},{"raw_affiliation_string":"Swiss Institute of Bioinformatics, Computational Cancer Genomics Group-ISREC, Ch. des Boveresses 155, 1066 Epalinges, Switzerland","institution_ids":["https://openalex.org/I12708293"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006006798","display_name":"Marco Pagni","orcid":"https://orcid.org/0000-0001-9292-9463"},"institutions":[{"id":"https://openalex.org/I12708293","display_name":"SIB Swiss Institute of Bioinformatics","ror":"https://ror.org/002n09z45","country_code":"CH","type":"nonprofit","lineage":["https://openalex.org/I12708293"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Marco Pagni","raw_affiliation_strings":["Swiss Institute of Bioinformatics, Vital IT Group, BEP-UNIL, 1015, Lausanne, Switzerland","Swiss Institute of Bioinformatics, Vital IT Group, BEP-UNIL, Lausanne, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Swiss Institute of Bioinformatics, Vital IT Group, BEP-UNIL, 1015, Lausanne, Switzerland","institution_ids":["https://openalex.org/I12708293"]},{"raw_affiliation_string":"Swiss Institute of Bioinformatics, Vital IT Group, BEP-UNIL, Lausanne, Switzerland","institution_ids":["https://openalex.org/I12708293"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5041806695"],"corresponding_institution_ids":["https://openalex.org/I12708293"],"apc_list":{"value":2990,"currency":"USD","value_usd":2990},"apc_paid":{"value":2990,"currency":"USD","value_usd":2990},"fwci":0.4728,"has_fulltext":true,"cited_by_count":25,"citation_normalized_percentile":{"value":0.61670242,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"6","issue":"1","first_page":"216","last_page":"216"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.3741999864578247,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.3741999864578247,"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/T10044","display_name":"Protein Structure and Dynamics","score":0.16419999301433563,"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":0.09200000017881393,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6034670472145081},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.568168044090271},{"id":"https://openalex.org/keywords/modular-design","display_name":"Modular design","score":0.5186302065849304},{"id":"https://openalex.org/keywords/sequence-alignment","display_name":"Sequence alignment","score":0.4608653783798218},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4558592438697815},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.4483920633792877},{"id":"https://openalex.org/keywords/resampling","display_name":"Resampling","score":0.4445635974407196},{"id":"https://openalex.org/keywords/protein-domain","display_name":"Protein domain","score":0.425041139125824},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.42232710123062134},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4011092185974121},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.3963974118232727},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3611733019351959},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3055708408355713},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.2596919536590576},{"id":"https://openalex.org/keywords/peptide-sequence","display_name":"Peptide sequence","score":0.18052104115486145},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.10672131180763245}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6034670472145081},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.568168044090271},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.5186302065849304},{"id":"https://openalex.org/C45484198","wikidata":"https://www.wikidata.org/wiki/Q827246","display_name":"Sequence alignment","level":4,"score":0.4608653783798218},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4558592438697815},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4483920633792877},{"id":"https://openalex.org/C150921843","wikidata":"https://www.wikidata.org/wiki/Q1170431","display_name":"Resampling","level":2,"score":0.4445635974407196},{"id":"https://openalex.org/C144292202","wikidata":"https://www.wikidata.org/wiki/Q898273","display_name":"Protein domain","level":3,"score":0.425041139125824},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.42232710123062134},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4011092185974121},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.3963974118232727},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3611733019351959},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3055708408355713},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.2596919536590576},{"id":"https://openalex.org/C167625842","wikidata":"https://www.wikidata.org/wiki/Q899763","display_name":"Peptide sequence","level":3,"score":0.18052104115486145},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10672131180763245},{"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":"D008190","descriptor_name":"Lyases","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":false},{"descriptor_ui":"D008190","descriptor_name":"Lyases","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":false},{"descriptor_ui":"D008190","descriptor_name":"Lyases","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":false},{"descriptor_ui":"D008190","descriptor_name":"Lyases","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D008190","descriptor_name":"Lyases","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D008190","descriptor_name":"Lyases","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D011387","descriptor_name":"Prokaryotic Cells","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":false},{"descriptor_ui":"D011387","descriptor_name":"Prokaryotic Cells","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":false},{"descriptor_ui":"D011387","descriptor_name":"Prokaryotic Cells","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":false},{"descriptor_ui":"D011387","descriptor_name":"Prokaryotic Cells","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D011387","descriptor_name":"Prokaryotic Cells","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D011387","descriptor_name":"Prokaryotic Cells","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D015203","descriptor_name":"Reproducibility of Results","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015203","descriptor_name":"Reproducibility of Results","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015203","descriptor_name":"Reproducibility of Results","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015335","descriptor_name":"Molecular Probes","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015335","descriptor_name":"Molecular Probes","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015335","descriptor_name":"Molecular Probes","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":"D018909","descriptor_name":"src Homology Domains","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D018909","descriptor_name":"src Homology Domains","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D018909","descriptor_name":"src Homology Domains","qualifier_ui":"Q000235","qualifier_name":"genetics","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}],"locations_count":4,"locations":[{"id":"doi:10.1186/1471-2105-6-216","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-6-216","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-6-216","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:16135248","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/16135248","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":"Journal Article"},{"id":"pmh:oai:pubmedcentral.nih.gov:1208858","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/1208858","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"},{"id":"pmh:oai:doaj.org/article:3c90c4328d97458695a07b153c572e14","is_oa":false,"landing_page_url":"https://doaj.org/article/3c90c4328d97458695a07b153c572e14","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 6, Iss 1, p 216 (2005)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1186/1471-2105-6-216","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-6-216","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-6-216","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":0.46000000834465027,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320307773","display_name":"GlaxoSmithKline","ror":"https://ror.org/01xsqw823"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2098913407.pdf","grobid_xml":"https://content.openalex.org/works/W2098913407.grobid-xml"},"referenced_works_count":70,"referenced_works":["https://openalex.org/W1493454437","https://openalex.org/W1536270671","https://openalex.org/W1659313070","https://openalex.org/W1968697272","https://openalex.org/W1969051510","https://openalex.org/W1969761972","https://openalex.org/W1977701732","https://openalex.org/W1981871034","https://openalex.org/W1983698816","https://openalex.org/W1985057592","https://openalex.org/W1987971958","https://openalex.org/W1990264387","https://openalex.org/W1994154030","https://openalex.org/W1997199912","https://openalex.org/W1997268601","https://openalex.org/W2003087950","https://openalex.org/W2014719716","https://openalex.org/W2015292449","https://openalex.org/W2019032222","https://openalex.org/W2026257220","https://openalex.org/W2026808309","https://openalex.org/W2030966943","https://openalex.org/W2033406586","https://openalex.org/W2041976742","https://openalex.org/W2045067706","https://openalex.org/W2046310275","https://openalex.org/W2051916497","https://openalex.org/W2073186504","https://openalex.org/W2076540369","https://openalex.org/W2087064593","https://openalex.org/W2089431713","https://openalex.org/W2094519647","https://openalex.org/W2096039184","https://openalex.org/W2097874946","https://openalex.org/W2098567615","https://openalex.org/W2102122585","https://openalex.org/W2124166542","https://openalex.org/W2124181495","https://openalex.org/W2124563802","https://openalex.org/W2125489655","https://openalex.org/W2125806930","https://openalex.org/W2126975650","https://openalex.org/W2131724426","https://openalex.org/W2136563879","https://openalex.org/W2140455347","https://openalex.org/W2141885858","https://openalex.org/W2143210482","https://openalex.org/W2144362290","https://openalex.org/W2145445013","https://openalex.org/W2147285856","https://openalex.org/W2152376949","https://openalex.org/W2155606054","https://openalex.org/W2158714788","https://openalex.org/W2162097287","https://openalex.org/W2165979580","https://openalex.org/W2171963266","https://openalex.org/W2312194337","https://openalex.org/W2343849816","https://openalex.org/W2479395228","https://openalex.org/W2613359208","https://openalex.org/W2999729612","https://openalex.org/W3026721701","https://openalex.org/W3138771162","https://openalex.org/W3199943451","https://openalex.org/W4210400672","https://openalex.org/W4234937118","https://openalex.org/W4235169531","https://openalex.org/W4236154753","https://openalex.org/W4246726420","https://openalex.org/W4254275792"],"related_works":["https://openalex.org/W2514476306","https://openalex.org/W2088164904","https://openalex.org/W2028741573","https://openalex.org/W2135912076","https://openalex.org/W2926533301","https://openalex.org/W4220937102","https://openalex.org/W2161339256","https://openalex.org/W2236962729","https://openalex.org/W2121560377","https://openalex.org/W2134646385"],"abstract_inverted_index":{"BACKGROUND:":[0],"Whole-genome":[1],"sequencing":[2],"projects":[3],"are":[4,96,108,207],"rapidly":[5],"producing":[6],"an":[7],"enormous":[8],"number":[9],"of":[10,17,22,44,84,88,91,118,129,134,149,190],"new":[11],"sequences.":[12,93],"Consequently":[13],"almost":[14],"every":[15],"family":[16],"proteins":[18,166,183],"now":[19],"contains":[20,146,164],"hundreds":[21],"members.":[23],"It":[24],"has":[25],"thus":[26],"become":[27],"necessary":[28],"to":[29,50,98,110],"develop":[30],"tools,":[31],"which":[32,54,78],"classify":[33],"protein":[34,55],"sequences":[35,56,114,148],"automatically":[36],"and":[37,40,66,201,222],"also":[38],"quickly":[39],"reliably.":[41],"The":[42,94,132,143,161,188,205],"difficulty":[43],"this":[45,122,135],"task":[46],"is":[47,79,137,193],"intimately":[48],"linked":[49],"the":[51,99,106,112,130,147,211],"mechanism":[52],"by":[53,59,139],"diverge,":[57],"i.e.":[58],"simultaneous":[60],"residue":[61],"substitutions,":[62],"insertions":[63],"and/or":[64],"deletions":[65],"whole":[67],"domain":[68],"reorganisations":[69],"(duplications/swapping/fusion).":[70],"RESULTS:":[71],"Here":[72],"we":[73],"present":[74],"a":[75,89,103,157],"novel":[76],"approach,":[77],"based":[80],"on":[81,126,217],"random":[82],"sampling":[83],"sub-sequences":[85],"(probes)":[86],"out":[87],"set":[90],"input":[92,100,113],"probes":[95],"compared":[97],"sequences,":[101],"after":[102],"normalisation":[104],"step;":[105],"results":[107,206],"used":[109],"partition":[111],"into":[115],"homogeneous":[116],"groups":[117],"proteins.":[119,131],"In":[120],"addition,":[121],"method":[123,136,192,214],"provides":[124],"information":[125],"diagnostic":[127],"parts":[128],"performance":[133],"challenged":[138],"two":[140],"data":[141],"sets.":[142],"first":[144],"one":[145,163,174],"prokaryotic":[150],"lyases":[151],"that":[152],"could":[153],"be":[154],"arranged":[155],"as":[156,197],"multiple":[158],"sequence":[159],"alignment.":[160],"second":[162],"all":[165],"from":[167],"Swiss-Prot":[168],"Release":[169],"36":[170],"with":[171,184,210],"at":[172],"least":[173],"Src":[175],"homology":[176],"2":[177],"(SH2)":[178],"domain--a":[179],"classical":[180],"example":[181],"for":[182],"modular":[185],"architecture.":[186],"CONCLUSION:":[187],"outcome":[189],"our":[191],"robust,":[194],"highly":[195],"reproducible":[196],"shown":[198],"using":[199],"bootstrap":[200],"resampling":[202],"validation":[203],"procedures.":[204],"essentially":[208],"coherent":[209],"biology.":[212],"This":[213],"depends":[215],"solely":[216],"well-established":[218],"publicly":[219],"available":[220],"software":[221],"algorithms.":[223]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"year":2012,"cited_by_count":3}],"updated_date":"2026-08-24T07:32:12.397491","created_date":"2025-10-10T00:00:00"}