{"id":"https://openalex.org/W1772899683","doi":"https://doi.org/10.1186/1471-2105-6-242","title":"Clustering protein sequences with a novel metric transformed from sequence similarity scores and sequence alignments with neural networks","display_name":"Clustering protein sequences with a novel metric transformed from sequence similarity scores and sequence alignments with neural networks","publication_year":2005,"publication_date":"2005-10-03","ids":{"openalex":"https://openalex.org/W1772899683","doi":"https://doi.org/10.1186/1471-2105-6-242","mag":"1772899683","pmid":"https://pubmed.ncbi.nlm.nih.gov/16202129"},"language":"en","primary_location":{"id":"doi:10.1186/1471-2105-6-242","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-6-242","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-6-242","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/10.1186/1471-2105-6-242","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5113572495","display_name":"Qicheng Ma","orcid":null},"institutions":[{"id":"https://openalex.org/I4210117619","display_name":"Novartis (United States)","ror":"https://ror.org/028fhxy95","country_code":"US","type":"company","lineage":["https://openalex.org/I1283582996","https://openalex.org/I4210117619"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Qicheng Ma","raw_affiliation_strings":["Biomedical Computing, Genome and Proteome Sciences, Novartis Institutes for BioMedical Research, Inc., Cambridge, MA 02139, USA. Qicheng.Ma@novartis.com","Biomedical Computing, Genome and Proteome Sciences, Novartis Institutes for BioMedical Research, Inc., Cambridge, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Biomedical Computing, Genome and Proteome Sciences, Novartis Institutes for BioMedical Research, Inc., Cambridge, MA 02139, USA. Qicheng.Ma@novartis.com","institution_ids":["https://openalex.org/I4210117619"]},{"raw_affiliation_string":"Biomedical Computing, Genome and Proteome Sciences, Novartis Institutes for BioMedical Research, Inc., Cambridge, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110278574","display_name":"Gung\u2010Wei Chirn","orcid":null},"institutions":[{"id":"https://openalex.org/I1283582996","display_name":"Novartis (Switzerland)","ror":"https://ror.org/02f9zrr09","country_code":"CH","type":"company","lineage":["https://openalex.org/I1283582996"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Gung-Wei Chirn","raw_affiliation_strings":["Biomedical Computing, Genome and Proteome Sciences, Novartis Institutes for BioMedical Research, Inc., Cambridge, MA, 02139, USA","Biomedical Computing, Genome and Proteome Sciences, Novartis Institutes for BioMedical Research, Inc., Cambridge, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Biomedical Computing, Genome and Proteome Sciences, Novartis Institutes for BioMedical Research, Inc., Cambridge, MA, 02139, USA","institution_ids":["https://openalex.org/I1283582996"]},{"raw_affiliation_string":"Biomedical Computing, Genome and Proteome Sciences, Novartis Institutes for BioMedical Research, Inc., Cambridge, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066100108","display_name":"Richard Cai","orcid":null},"institutions":[{"id":"https://openalex.org/I1283582996","display_name":"Novartis (Switzerland)","ror":"https://ror.org/02f9zrr09","country_code":"CH","type":"company","lineage":["https://openalex.org/I1283582996"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Richard Cai","raw_affiliation_strings":["Biomedical Computing, Genome and Proteome Sciences, Novartis Institutes for BioMedical Research, Inc., Cambridge, MA, 02139, USA","Biomedical Computing, Genome and Proteome Sciences, Novartis Institutes for BioMedical Research, Inc., Cambridge, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Biomedical Computing, Genome and Proteome Sciences, Novartis Institutes for BioMedical Research, Inc., Cambridge, MA, 02139, USA","institution_ids":["https://openalex.org/I1283582996"]},{"raw_affiliation_string":"Biomedical Computing, Genome and Proteome Sciences, Novartis Institutes for BioMedical Research, Inc., Cambridge, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002355055","display_name":"Joseph D. Szustakowski","orcid":"https://orcid.org/0000-0001-7900-3973"},"institutions":[{"id":"https://openalex.org/I1283582996","display_name":"Novartis (Switzerland)","ror":"https://ror.org/02f9zrr09","country_code":"CH","type":"company","lineage":["https://openalex.org/I1283582996"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Joseph D Szustakowski","raw_affiliation_strings":["Biomedical Computing, Genome and Proteome Sciences, Novartis Institutes for BioMedical Research, Inc., Cambridge, MA, 02139, USA","Biomedical Computing, Genome and Proteome Sciences, Novartis Institutes for BioMedical Research, Inc., Cambridge, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Biomedical Computing, Genome and Proteome Sciences, Novartis Institutes for BioMedical Research, Inc., Cambridge, MA, 02139, USA","institution_ids":["https://openalex.org/I1283582996"]},{"raw_affiliation_string":"Biomedical Computing, Genome and Proteome Sciences, Novartis Institutes for BioMedical Research, Inc., Cambridge, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080176966","display_name":"Nanguneri Nirmala","orcid":"https://orcid.org/0000-0003-0267-9793"},"institutions":[{"id":"https://openalex.org/I1283582996","display_name":"Novartis (Switzerland)","ror":"https://ror.org/02f9zrr09","country_code":"CH","type":"company","lineage":["https://openalex.org/I1283582996"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"NR Nirmala","raw_affiliation_strings":["Biomedical Computing, Genome and Proteome Sciences, Novartis Institutes for BioMedical Research, Inc., Cambridge, MA, 02139, USA","Biomedical Computing, Genome and Proteome Sciences, Novartis Institutes for BioMedical Research, Inc., Cambridge, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Biomedical Computing, Genome and Proteome Sciences, Novartis Institutes for BioMedical Research, Inc., Cambridge, MA, 02139, USA","institution_ids":["https://openalex.org/I1283582996"]},{"raw_affiliation_string":"Biomedical Computing, Genome and Proteome Sciences, Novartis Institutes for BioMedical Research, Inc., Cambridge, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5113572495"],"corresponding_institution_ids":["https://openalex.org/I4210117619"],"apc_list":{"value":2790,"currency":"USD","value_usd":2790},"apc_paid":{"value":2790,"currency":"USD","value_usd":2790},"fwci":0.7119,"has_fulltext":true,"cited_by_count":17,"citation_normalized_percentile":{"value":0.65812035,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"6","issue":"1","first_page":"242","last_page":"242"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12946","display_name":"Fractal and DNA sequence analysis","score":0.3467000126838684,"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/T12946","display_name":"Fractal and DNA sequence analysis","score":0.3467000126838684,"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":0.23280000686645508,"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":0.14569999277591705,"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":0.7143237590789795},{"id":"https://openalex.org/keywords/genome","display_name":"Genome","score":0.5987906455993652},{"id":"https://openalex.org/keywords/hierarchical-clustering","display_name":"Hierarchical clustering","score":0.5586400032043457},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5038551688194275},{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.48628437519073486},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.4684230089187622},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.4540787637233734},{"id":"https://openalex.org/keywords/human-genome","display_name":"Human genome","score":0.4461199939250946},{"id":"https://openalex.org/keywords/sequence-alignment","display_name":"Sequence alignment","score":0.43742167949676514},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.4334191083908081},{"id":"https://openalex.org/keywords/distance-matrix","display_name":"Distance matrix","score":0.43182823061943054},{"id":"https://openalex.org/keywords/smith\u2013waterman-algorithm","display_name":"Smith\u2013Waterman algorithm","score":0.4299287796020508},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4225921332836151},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.35168153047561646},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35100555419921875},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.3342776298522949},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3275313377380371},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.2778046429157257},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.20399761199951172},{"id":"https://openalex.org/keywords/peptide-sequence","display_name":"Peptide sequence","score":0.1438019871711731}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7143237590789795},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.5987906455993652},{"id":"https://openalex.org/C92835128","wikidata":"https://www.wikidata.org/wiki/Q1277447","display_name":"Hierarchical clustering","level":3,"score":0.5586400032043457},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5038551688194275},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.48628437519073486},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.4684230089187622},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.4540787637233734},{"id":"https://openalex.org/C197077220","wikidata":"https://www.wikidata.org/wiki/Q720988","display_name":"Human genome","level":4,"score":0.4461199939250946},{"id":"https://openalex.org/C45484198","wikidata":"https://www.wikidata.org/wiki/Q827246","display_name":"Sequence alignment","level":4,"score":0.43742167949676514},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.4334191083908081},{"id":"https://openalex.org/C111208986","wikidata":"https://www.wikidata.org/wiki/Q901698","display_name":"Distance matrix","level":2,"score":0.43182823061943054},{"id":"https://openalex.org/C72802188","wikidata":"https://www.wikidata.org/wiki/Q1683352","display_name":"Smith\u2013Waterman algorithm","level":5,"score":0.4299287796020508},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4225921332836151},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.35168153047561646},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35100555419921875},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3342776298522949},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3275313377380371},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.2778046429157257},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.20399761199951172},{"id":"https://openalex.org/C167625842","wikidata":"https://www.wikidata.org/wiki/Q899763","display_name":"Peptide sequence","level":3,"score":0.1438019871711731},{"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/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012372","descriptor_name":"ROC Curve","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012372","descriptor_name":"ROC Curve","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012372","descriptor_name":"ROC Curve","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012986","descriptor_name":"Software Validation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012986","descriptor_name":"Software Validation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012986","descriptor_name":"Software Validation","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":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","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":"D019985","descriptor_name":"Benchmarking","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019985","descriptor_name":"Benchmarking","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019985","descriptor_name":"Benchmarking","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}],"locations_count":4,"locations":[{"id":"doi:10.1186/1471-2105-6-242","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-6-242","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-6-242","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:16202129","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/16202129","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC bioinformatics","raw_type":null},{"id":"pmh:oai:doaj.org/article:e1e478581b184cf9b6eec22ee71139b9","is_oa":true,"landing_page_url":"https://doaj.org/article/e1e478581b184cf9b6eec22ee71139b9","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":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Bioinformatics, Vol 6, Iss 1, p 242 (2005)","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:1261163","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/1261163","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Bioinformatics","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1186/1471-2105-6-242","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-6-242","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-6-242","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":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1772899683.pdf","grobid_xml":"https://content.openalex.org/works/W1772899683.grobid-xml"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W1480376833","https://openalex.org/W1480458797","https://openalex.org/W1554663460","https://openalex.org/W1990453950","https://openalex.org/W2022366078","https://openalex.org/W2041862730","https://openalex.org/W2055507015","https://openalex.org/W2057885377","https://openalex.org/W2058336694","https://openalex.org/W2060791849","https://openalex.org/W2080336769","https://openalex.org/W2097874946","https://openalex.org/W2101031524","https://openalex.org/W2102588875","https://openalex.org/W2107302432","https://openalex.org/W2110792853","https://openalex.org/W2121297744","https://openalex.org/W2123338063","https://openalex.org/W2124166542","https://openalex.org/W2135380784","https://openalex.org/W2135385301","https://openalex.org/W2146827656","https://openalex.org/W2148834305","https://openalex.org/W2148853951","https://openalex.org/W2158714788","https://openalex.org/W2176645417","https://openalex.org/W4252706339","https://openalex.org/W4388297464"],"related_works":["https://openalex.org/W2948014085","https://openalex.org/W2004215917","https://openalex.org/W2103737249","https://openalex.org/W1974956921","https://openalex.org/W2139695554","https://openalex.org/W1972247471","https://openalex.org/W2577956156","https://openalex.org/W1486249959","https://openalex.org/W2311297074","https://openalex.org/W2188796099"],"abstract_inverted_index":{"BACKGROUND:":[0],"The":[1,63,169,199,238],"sequencing":[2,65],"of":[3,15,27,52,66,76,86,97,124,148,178,182,191,214,251],"the":[4,28,84,87,98,157,163,173,183,189,207,221],"human":[5,34,88],"genome":[6],"has":[7,60,69,118],"enabled":[8],"us":[9,71],"to":[10,101,121,195,243],"access":[11],"a":[12,25,49,73,112,135,141,146,176],"comprehensive":[13],"list":[14],"genes":[16,36,53],"(both":[17],"experimental":[18],"and":[19,32,39,127,162,234,248],"predicted)":[20],"for":[21,56],"further":[22],"analysis.":[23],"While":[24],"majority":[26],"approximately":[29],"30,000":[30],"known":[31],"predicted":[33,128],"coding":[35],"are":[37,181],"characterized":[38],"have":[40],"been":[41,61,119],"assigned":[42],"at":[43],"least":[44],"one":[45,96],"function,":[46],"there":[47],"remains":[48],"fair":[50],"number":[51],"(about":[54],"12,000)":[55],"which":[57,80,139,187],"no":[58],"annotation":[59],"made.":[62],"recent":[64],"other":[67],"genomes":[68,133,247],"provided":[70],"with":[72,206,230],"huge":[74],"amount":[75],"auxiliary":[77],"sequence":[78,159],"data":[79],"could":[81],"help":[82],"in":[83,220],"characterization":[85],"genes.":[89],"Clustering":[90],"these":[91],"sequences":[92,123,180],"into":[93],"families":[94],"is":[95,140,154,172,204,241],"first":[99],"steps":[100],"perform":[102],"comparative":[103],"studies":[104,213],"across":[105],"several":[106,245,249],"genomes.":[107,253],"RESULTS:":[108],"Here":[109],"we":[110],"report":[111],"novel":[113,136],"clustering":[114,202,228,239],"algorithm":[115,216,226,240],"(CLUGEN)":[116],"that":[117,175,224],"used":[120],"cluster":[122,244],"experimentally":[125],"verified":[126],"proteins":[129],"from":[130],"all":[131],"sequenced":[132],"using":[134],"distance":[137,152,170,209],"metric":[138,153,171],"neural":[142],"network":[143],"score":[144,161],"between":[145,165],"pair":[147,177],"protein":[149,179],"sequences.":[150],"This":[151],"based":[155],"on":[156],"pairwise":[158],"similarity":[160,164],"their":[166],"domain":[167],"structures.":[168],"probability":[174],"same":[184],"Interpro":[185],"family/domain,":[186],"facilitates":[188],"modelling":[190],"transitive":[192],"homology":[193],"closure":[194],"detect":[196],"remote":[197],"homologues.":[198],"hierarchical":[200],"average":[201],"method":[203],"applied":[205,242],"new":[208],"metric.":[210],"CONCLUSION:":[211],"Benchmarking":[212],"our":[215,225],"versus":[217],"those":[218],"reported":[219],"literature":[222],"shows":[223],"provides":[227],"results":[229],"lower":[231],"false":[232,235],"positive":[233],"negative":[236],"rates.":[237],"eukaryotic":[246],"dozens":[250],"prokaryotic":[252]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}