{"id":"https://openalex.org/W1995541084","doi":"https://doi.org/10.1186/1471-2105-8-s4-s10","title":"Clustering protein environments for function prediction: finding PROSITE motifs in 3D","display_name":"Clustering protein environments for function prediction: finding PROSITE motifs in 3D","publication_year":2007,"publication_date":"2007-05-01","ids":{"openalex":"https://openalex.org/W1995541084","doi":"https://doi.org/10.1186/1471-2105-8-s4-s10","mag":"1995541084","pmid":"https://pubmed.ncbi.nlm.nih.gov/17570144"},"language":"en","primary_location":{"id":"doi:10.1186/1471-2105-8-s4-s10","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-8-s4-s10","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-8-S4-S10","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/10.1186/1471-2105-8-S4-S10","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5086877012","display_name":"Sungroh Yoon","orcid":"https://orcid.org/0000-0002-2367-197X"},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]},{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sungroh Yoon","raw_affiliation_strings":["Computer Systems Laboratory, Stanford University, Stanford, CA 94305, USA. sungroh.yoon@intel.com","Computer Systems Laboratory, Stanford University, Stanford, USA","Intel Corporation, Santa Clara, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Systems Laboratory, Stanford University, Stanford, CA 94305, USA. sungroh.yoon@intel.com","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"Computer Systems Laboratory, Stanford University, Stanford, USA","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"Intel Corporation, Santa Clara, USA","institution_ids":["https://openalex.org/I1343180700"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073678594","display_name":"Jessica Ebert","orcid":null},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jessica C Ebert","raw_affiliation_strings":["Department of Genetics, Stanford University, Stanford, CA, 94305, USA","Dept. of Genetics, Stanford University, Stanford, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Genetics, Stanford University, Stanford, CA, 94305, USA","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"Dept. of Genetics, Stanford University, Stanford, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084016800","display_name":"Eui-Young Chung","orcid":"https://orcid.org/0000-0003-2013-8763"},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Eui-Young Chung","raw_affiliation_strings":["School of Electrical and Electronic Engineering, Yonsei University, Seoul, 120-749, Republic of Korea","School of Electrical & Electronic Engineering, Yonsei University, Seoul, Republic of Korea#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical and Electronic Engineering, Yonsei University, Seoul, 120-749, Republic of Korea","institution_ids":["https://openalex.org/I193775966"]},{"raw_affiliation_string":"School of Electrical & Electronic Engineering, Yonsei University, Seoul, Republic of Korea#TAB#","institution_ids":["https://openalex.org/I193775966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072927296","display_name":"Giovanni De Micheli","orcid":"https://orcid.org/0000-0002-7827-3215"},"institutions":[{"id":"https://openalex.org/I5124864","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I5124864"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Giovanni De Micheli","raw_affiliation_strings":["Integrated Systems Center, Swiss Federal Institute of Technology (EPFL), Lausanne, CH-1015, Switzerland","Integrated Systems Center, Swiss Federal Institute of Technology (EPFL), Lausanne, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Integrated Systems Center, Swiss Federal Institute of Technology (EPFL), Lausanne, CH-1015, Switzerland","institution_ids":["https://openalex.org/I5124864"]},{"raw_affiliation_string":"Integrated Systems Center, Swiss Federal Institute of Technology (EPFL), Lausanne, Switzerland","institution_ids":["https://openalex.org/I5124864"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084043782","display_name":"Russ B. Altman","orcid":"https://orcid.org/0000-0003-3859-2905"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Russ B Altman","raw_affiliation_strings":["Department of Genetics, Stanford University, Stanford, CA, 94305, USA","Dept. of Genetics, Stanford University, Stanford, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Genetics, Stanford University, Stanford, CA, 94305, USA","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"Dept. of Genetics, Stanford University, Stanford, USA","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5084043782"],"corresponding_institution_ids":["https://openalex.org/I97018004"],"apc_list":{"value":1690,"currency":"GBP","value_usd":2072},"apc_paid":{"value":1690,"currency":"GBP","value_usd":2072},"fwci":1.615,"has_fulltext":true,"cited_by_count":34,"citation_normalized_percentile":{"value":0.82015966,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"8","issue":"S4","first_page":"S10","last_page":"S10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10044","display_name":"Protein Structure and Dynamics","score":0.7537000179290771,"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":0.7537000179290771,"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":0.0997999981045723,"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":0.04749999940395355,"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":0.803247332572937},{"id":"https://openalex.org/keywords/structural-genomics","display_name":"Structural genomics","score":0.5773059129714966},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.5563341379165649},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5498318076133728},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5486524701118469},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.48023372888565063},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4761210083961487},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.44993850588798523},{"id":"https://openalex.org/keywords/structural-motif","display_name":"Structural motif","score":0.4454251825809479},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3814362585544586},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3492671847343445},{"id":"https://openalex.org/keywords/protein-structure","display_name":"Protein structure","score":0.33977392315864563},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.317257285118103},{"id":"https://openalex.org/keywords/evolutionary-biology","display_name":"Evolutionary biology","score":0.10440444946289062}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.803247332572937},{"id":"https://openalex.org/C192772702","wikidata":"https://www.wikidata.org/wiki/Q2583975","display_name":"Structural genomics","level":3,"score":0.5773059129714966},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.5563341379165649},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5498318076133728},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5486524701118469},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.48023372888565063},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4761210083961487},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.44993850588798523},{"id":"https://openalex.org/C132677234","wikidata":"https://www.wikidata.org/wiki/Q3273544","display_name":"Structural motif","level":2,"score":0.4454251825809479},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3814362585544586},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3492671847343445},{"id":"https://openalex.org/C47701112","wikidata":"https://www.wikidata.org/wiki/Q735188","display_name":"Protein structure","level":2,"score":0.33977392315864563},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.317257285118103},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.10440444946289062},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"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":"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":"D003198","descriptor_name":"Computer Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008024","descriptor_name":"Ligands","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008024","descriptor_name":"Ligands","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008024","descriptor_name":"Ligands","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":true},{"descriptor_ui":"D008956","descriptor_name":"Models, Chemical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008956","descriptor_name":"Models, Chemical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008958","descriptor_name":"Models, Molecular","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008958","descriptor_name":"Models, Molecular","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008958","descriptor_name":"Models, Molecular","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"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":"D011487","descriptor_name":"Protein Conformation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011487","descriptor_name":"Protein Conformation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011487","descriptor_name":"Protein Conformation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000648","qualifier_name":"ultrastructure","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000648","qualifier_name":"ultrastructure","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000648","qualifier_name":"ultrastructure","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":"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":"D020816","descriptor_name":"Amino Acid Motifs","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020816","descriptor_name":"Amino Acid Motifs","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020816","descriptor_name":"Amino Acid Motifs","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D021621","descriptor_name":"Imaging, Three-Dimensional","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D021621","descriptor_name":"Imaging, Three-Dimensional","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D021621","descriptor_name":"Imaging, Three-Dimensional","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false}],"locations_count":4,"locations":[{"id":"doi:10.1186/1471-2105-8-s4-s10","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-8-s4-s10","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-8-S4-S10","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:17570144","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/17570144","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:infoscience.epfl.ch:105065","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/105065","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"research article"},{"id":"pmh:oai:pubmedcentral.nih.gov:1892080","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/1892080","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:10.1186/1471-2105-8-s4-s10","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-8-s4-s10","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-8-S4-S10","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":[{"id":"https://openalex.org/G6411790401","display_name":null,"funder_award_id":"LM05652","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"}],"funders":[{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320333063","display_name":"Stanford Bio-X","ror":"https://ror.org/00f54p054"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1995541084.pdf","grobid_xml":"https://content.openalex.org/works/W1995541084.grobid-xml"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W18486434","https://openalex.org/W43803018","https://openalex.org/W255996521","https://openalex.org/W1480376833","https://openalex.org/W1493454437","https://openalex.org/W1619377810","https://openalex.org/W1972676371","https://openalex.org/W1982481323","https://openalex.org/W1992152661","https://openalex.org/W2004234681","https://openalex.org/W2009528611","https://openalex.org/W2045110975","https://openalex.org/W2047544230","https://openalex.org/W2050085817","https://openalex.org/W2050220764","https://openalex.org/W2063464166","https://openalex.org/W2069663555","https://openalex.org/W2081920176","https://openalex.org/W2083654996","https://openalex.org/W2096039340","https://openalex.org/W2102333330","https://openalex.org/W2114782816","https://openalex.org/W2119027485","https://openalex.org/W2130479394","https://openalex.org/W2132844390","https://openalex.org/W2147908920","https://openalex.org/W2171962405","https://openalex.org/W2171985093","https://openalex.org/W2999729612"],"related_works":["https://openalex.org/W2113714257","https://openalex.org/W2081920176","https://openalex.org/W2346580382","https://openalex.org/W2004234681","https://openalex.org/W2015390241","https://openalex.org/W2118652015","https://openalex.org/W2166261803","https://openalex.org/W1972763041","https://openalex.org/W2059333155","https://openalex.org/W1983686108"],"abstract_inverted_index":{"BACKGROUND:":[0],"Structural":[1],"genomics":[2],"initiatives":[3],"are":[4,66,75,135],"producing":[5],"increasing":[6],"numbers":[7],"of":[8,21,57,70,123,125,179,211],"three-dimensional":[9],"(3D)":[10],"structures":[11],"for":[12,34,55,93,103,120,183],"which":[13,138],"there":[14,65],"is":[15,24,50],"little":[16],"functional":[17,38,143,246],"information.":[18],"Structure-based":[19],"annotation":[20],"molecular":[22],"function":[23,78],"therefore":[25,140],"becoming":[26],"critical.":[27],"We":[28,62,114,147,176],"previously":[29,111],"presented":[30],"FEATURE,":[31],"a":[32,67,91,117,142,161,202],"method":[33,92,119],"describing":[35],"microenvironments":[36,96,126],"around":[37],"sites":[39,56,71,106],"in":[40,72,97,127],"proteins.":[41],"However,":[42],"FEATURE":[43],"uses":[44],"supervised":[45],"machine":[46],"learning":[47],"and":[48,60,137,156,205,221],"so":[49],"limited":[51],"to":[52,99,129,217,234],"building":[53],"models":[54],"known":[58,167,212],"importance":[59],"location.":[61],"hypothesized":[63],"that":[64,74,79,86,107,185,194,224,241],"large":[68],"number":[69],"proteins":[73],"associated":[76,170],"with":[77,171,238],"have":[80,89,108,115],"not":[81,109],"yet":[82],"been":[83,110],"recognized.":[84],"Toward":[85],"end,":[87],"we":[88,164,195],"developed":[90],"clustering":[94,122,207],"protein":[95,154,198],"order":[98,128],"evaluate":[100],"the":[101,219],"potential":[102],"discovering":[104],"novel":[105,243],"identified.":[112],"RESULTS:":[113],"prototyped":[116],"computational":[118],"rapid":[121],"millions":[124],"discover":[130],"residues":[131,184],"whose":[132],"surrounding":[133],"environments":[134,151,169,199],"similar":[136,239],"may":[139],"share":[141,186],"or":[144,245],"structural":[145,244],"role.":[146],"clustered":[148],"nearly":[149],"2,000,000":[150],"from":[152],"9,600":[153],"chains":[155],"defined":[157],"4,550":[158],"clusters.":[159,227],"As":[160],"preliminary":[162],"validation,":[163],"asked":[165],"whether":[166],"3D":[168,213],"PROSITE":[172,187],"motifs":[173,214],"were":[174],"\"rediscovered\".":[175],"found":[177],"examples":[178],"clusters":[180,237],"highly":[181],"enriched":[182],"sequence":[188],"motifs.":[189],"CONCLUSION:":[190],"Our":[191],"results":[192],"demonstrate":[193],"can":[196],"cluster":[197],"successfully":[200],"using":[201],"simplified":[203],"representation":[204],"K-means":[206],"algorithm.":[208],"The":[209],"rediscovery":[210],"allows":[215],"us":[216,233],"calibrate":[218],"size":[220],"intercluster":[222],"distances":[223],"characterize":[225],"useful":[226],"This":[228],"information":[229],"will":[230],"then":[231],"allow":[232],"find":[235],"new":[236],"characteristics":[240],"represent":[242],"sites.":[247]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2026-06-19T15:47:20.252518","created_date":"2025-10-10T00:00:00"}
