{"id":"https://openalex.org/W1967349811","doi":"https://doi.org/10.1186/s12859-015-0450-2","title":"Alignment-free clustering of transcription factor binding motifs using a genetic-k-medoids approach","display_name":"Alignment-free clustering of transcription factor binding motifs using a genetic-k-medoids approach","publication_year":2015,"publication_date":"2015-01-27","ids":{"openalex":"https://openalex.org/W1967349811","doi":"https://doi.org/10.1186/s12859-015-0450-2","mag":"1967349811","pmid":"https://pubmed.ncbi.nlm.nih.gov/25627106"},"language":"en","primary_location":{"id":"doi:10.1186/s12859-015-0450-2","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-015-0450-2","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/s12859-015-0450-2","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/s12859-015-0450-2","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5065444619","display_name":"Pilib \u00d3 Broin","orcid":"https://orcid.org/0000-0002-6702-8564"},"institutions":[{"id":"https://openalex.org/I129975664","display_name":"Albert Einstein College of Medicine","ror":"https://ror.org/05cf8a891","country_code":"US","type":"education","lineage":["https://openalex.org/I129975664","https://openalex.org/I4210112371"]},{"id":"https://openalex.org/I181231927","display_name":"National University of Ireland","ror":"https://ror.org/00shsf120","country_code":"IE","type":"education","lineage":["https://openalex.org/I181231927"]},{"id":"https://openalex.org/I188760350","display_name":"Ollscoil na Gaillimhe \u2013 University of Galway","ror":"https://ror.org/03bea9k73","country_code":"IE","type":"education","lineage":["https://openalex.org/I188760350"]}],"countries":["IE","US"],"is_corresponding":false,"raw_author_name":"Pilib \u00d3 Broin","raw_affiliation_strings":["Department of Genetics, Albert Einstein College of Medicine, 1301 Morris Park Avenue, Bronx, New York, 10461, USA. pilib.obroin@einstein.yu.edu","National Centre for Biomedical Engineering Science, National University of Ireland, University Road, Galway, Ireland. pilib.obroin@einstein.yu.edu","Department of Genetics, Albert Einstein College of Medicine, New York, USA","National Centre for Biomedical Engineering Science, National University of Ireland, Galway, Ireland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Genetics, Albert Einstein College of Medicine, 1301 Morris Park Avenue, Bronx, New York, 10461, USA. pilib.obroin@einstein.yu.edu","institution_ids":["https://openalex.org/I129975664"]},{"raw_affiliation_string":"National Centre for Biomedical Engineering Science, National University of Ireland, University Road, Galway, Ireland. pilib.obroin@einstein.yu.edu","institution_ids":["https://openalex.org/I188760350","https://openalex.org/I181231927"]},{"raw_affiliation_string":"Department of Genetics, Albert Einstein College of Medicine, New York, USA","institution_ids":["https://openalex.org/I129975664"]},{"raw_affiliation_string":"National Centre for Biomedical Engineering Science, National University of Ireland, Galway, Ireland","institution_ids":["https://openalex.org/I188760350"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101903427","display_name":"Terry Smith","orcid":"https://orcid.org/0000-0002-4956-3299"},"institutions":[{"id":"https://openalex.org/I129975664","display_name":"Albert Einstein College of Medicine","ror":"https://ror.org/05cf8a891","country_code":"US","type":"education","lineage":["https://openalex.org/I129975664","https://openalex.org/I4210112371"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Terry J Smith","raw_affiliation_strings":["Department of Genetics, Albert Einstein College of Medicine, 1301 Morris Park Avenue, Bronx, New York, 10461, USA. terry.smith@nuigalway.ie","Department of Genetics, Albert Einstein College of Medicine, New York, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Genetics, Albert Einstein College of Medicine, 1301 Morris Park Avenue, Bronx, New York, 10461, USA. terry.smith@nuigalway.ie","institution_ids":["https://openalex.org/I129975664"]},{"raw_affiliation_string":"Department of Genetics, Albert Einstein College of Medicine, New York, USA","institution_ids":["https://openalex.org/I129975664"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035389230","display_name":"Aaron Golden","orcid":"https://orcid.org/0000-0001-8208-4292"},"institutions":[{"id":"https://openalex.org/I129975664","display_name":"Albert Einstein College of Medicine","ror":"https://ror.org/05cf8a891","country_code":"US","type":"education","lineage":["https://openalex.org/I129975664","https://openalex.org/I4210112371"]},{"id":"https://openalex.org/I19772626","display_name":"Yeshiva University","ror":"https://ror.org/045x93337","country_code":"US","type":"education","lineage":["https://openalex.org/I19772626"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Aaron AJ Golden","raw_affiliation_strings":["Department of Genetics, Albert Einstein College of Medicine, 1301 Morris Park Avenue, Bronx, New York, 10461, USA. aaron.golden@einstein.yu.edu","Department of Mathematical Sciences, Yeshiva University, New York, 10033, NY, USA. aaron.golden@einstein.yu.edu","Department of Mathematical Sciences, Yeshiva University, New York, USA","Department of Genetics, Albert Einstein College of Medicine, New York, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Genetics, Albert Einstein College of Medicine, 1301 Morris Park Avenue, Bronx, New York, 10461, USA. aaron.golden@einstein.yu.edu","institution_ids":["https://openalex.org/I129975664"]},{"raw_affiliation_string":"Department of Mathematical Sciences, Yeshiva University, New York, 10033, NY, USA. aaron.golden@einstein.yu.edu","institution_ids":["https://openalex.org/I19772626"]},{"raw_affiliation_string":"Department of Mathematical Sciences, Yeshiva University, New York, USA","institution_ids":["https://openalex.org/I19772626"]},{"raw_affiliation_string":"Department of Genetics, Albert Einstein College of Medicine, New York, USA","institution_ids":["https://openalex.org/I129975664"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5035389230"],"corresponding_institution_ids":["https://openalex.org/I129975664","https://openalex.org/I19772626"],"apc_list":{"value":1690,"currency":"GBP","value_usd":2072},"apc_paid":{"value":1690,"currency":"GBP","value_usd":2072},"fwci":1.6257,"has_fulltext":true,"cited_by_count":23,"citation_normalized_percentile":{"value":0.83156899,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"16","issue":"1","first_page":"22","last_page":"22"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10222","display_name":"Genomics and Chromatin Dynamics","score":0.9409999847412109,"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/T10222","display_name":"Genomics and Chromatin Dynamics","score":0.9409999847412109,"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/T10885","display_name":"Gene expression and cancer classification","score":0.024800000712275505,"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":0.014800000004470348,"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":0.6717694401741028},{"id":"https://openalex.org/keywords/motif","display_name":"Motif (music)","score":0.6133131980895996},{"id":"https://openalex.org/keywords/dna-binding-site","display_name":"DNA binding site","score":0.5960614681243896},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5599591732025146},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5105167627334595},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.44596824049949646},{"id":"https://openalex.org/keywords/sequence-motif","display_name":"Sequence motif","score":0.4127280116081238},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39262858033180237},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.37787288427352905},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.3401295840740204},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.272540807723999},{"id":"https://openalex.org/keywords/dna","display_name":"DNA","score":0.19781950116157532},{"id":"https://openalex.org/keywords/promoter","display_name":"Promoter","score":0.1685899794101715},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.13002058863639832}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6717694401741028},{"id":"https://openalex.org/C32276052","wikidata":"https://www.wikidata.org/wiki/Q908349","display_name":"Motif (music)","level":2,"score":0.6133131980895996},{"id":"https://openalex.org/C3662595","wikidata":"https://www.wikidata.org/wiki/Q5205743","display_name":"DNA binding site","level":5,"score":0.5960614681243896},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5599591732025146},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5105167627334595},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.44596824049949646},{"id":"https://openalex.org/C117745874","wikidata":"https://www.wikidata.org/wiki/Q901612","display_name":"Sequence motif","level":3,"score":0.4127280116081238},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39262858033180237},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.37787288427352905},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.3401295840740204},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.272540807723999},{"id":"https://openalex.org/C552990157","wikidata":"https://www.wikidata.org/wiki/Q7430","display_name":"DNA","level":2,"score":0.19781950116157532},{"id":"https://openalex.org/C101762097","wikidata":"https://www.wikidata.org/wiki/Q224093","display_name":"Promoter","level":4,"score":0.1685899794101715},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.13002058863639832},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0},{"id":"https://openalex.org/C150194340","wikidata":"https://www.wikidata.org/wiki/Q26972","display_name":"Gene expression","level":3,"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":"D004247","descriptor_name":"DNA","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D004247","descriptor_name":"DNA","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D004247","descriptor_name":"DNA","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D004247","descriptor_name":"DNA","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D004247","descriptor_name":"DNA","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D004247","descriptor_name":"DNA","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D004268","descriptor_name":"DNA-Binding Proteins","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D004268","descriptor_name":"DNA-Binding Proteins","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D004268","descriptor_name":"DNA-Binding Proteins","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","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":"D011485","descriptor_name":"Protein Binding","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D014157","descriptor_name":"Transcription Factors","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D014157","descriptor_name":"Transcription Factors","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D014157","descriptor_name":"Transcription Factors","qualifier_ui":"Q000378","qualifier_name":"metabolism","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":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D030541","descriptor_name":"Databases, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030541","descriptor_name":"Databases, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030541","descriptor_name":"Databases, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D059372","descriptor_name":"Nucleotide Motifs","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D059372","descriptor_name":"Nucleotide Motifs","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D059372","descriptor_name":"Nucleotide Motifs","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":5,"locations":[{"id":"doi:10.1186/s12859-015-0450-2","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-015-0450-2","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/s12859-015-0450-2","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:25627106","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/25627106","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:aran.library.nuigalway.ie/:10379/5923","is_oa":false,"landing_page_url":"http://hdl.handle.net/10379/5923","pdf_url":null,"source":{"id":"https://openalex.org/S4377196322","display_name":"ARAN (University of Galway Research Repository) (Ollscoil na Gaillimhe \u2013 University of Galway)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I188760350","host_organization_name":"Ollscoil na Gaillimhe \u2013 University of Galway","host_organization_lineage":["https://openalex.org/I188760350"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"Article"},{"id":"pmh:http://www.rian.ie/162283/","is_oa":false,"landing_page_url":"http://hdl.handle.net/10379/10548","pdf_url":null,"source":{"id":"https://openalex.org/S4306400033","display_name":"Arrow@dit (Dublin Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I115570527","host_organization_name":"Dublin Institute of Technology","host_organization_lineage":["https://openalex.org/I115570527"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Journal article"},{"id":"pmh:oai:europepmc.org:3349862","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/4384390","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"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":null,"raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1186/s12859-015-0450-2","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-015-0450-2","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/s12859-015-0450-2","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/G6762943121","display_name":"Decoding cis-regulatory Modules in Human DNA Using Artificial Intelligence Techniques","funder_award_id":"05/RFP/CMS0001","funder_id":"https://openalex.org/F4320320847","funder_display_name":"Science Foundation Ireland"}],"funders":[{"id":"https://openalex.org/F4320320847","display_name":"Science Foundation Ireland","ror":"https://ror.org/0271asj38"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1967349811.pdf","grobid_xml":"https://content.openalex.org/works/W1967349811.grobid-xml"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W1493454437","https://openalex.org/W1497256448","https://openalex.org/W1527979595","https://openalex.org/W1987971958","https://openalex.org/W1996261696","https://openalex.org/W2018567038","https://openalex.org/W2027662098","https://openalex.org/W2065635150","https://openalex.org/W2071949631","https://openalex.org/W2074231493","https://openalex.org/W2084620487","https://openalex.org/W2085487226","https://openalex.org/W2087064593","https://openalex.org/W2102941368","https://openalex.org/W2103325210","https://openalex.org/W2109383935","https://openalex.org/W2110403456","https://openalex.org/W2111359483","https://openalex.org/W2119804413","https://openalex.org/W2120900302","https://openalex.org/W2123223165","https://openalex.org/W2125077974","https://openalex.org/W2149769193","https://openalex.org/W2150593711","https://openalex.org/W2151638714","https://openalex.org/W2154846630","https://openalex.org/W2162829784","https://openalex.org/W2166898290","https://openalex.org/W2182836616","https://openalex.org/W2229908198","https://openalex.org/W2463089998","https://openalex.org/W2999729612","https://openalex.org/W3023540311","https://openalex.org/W4250434996"],"related_works":["https://openalex.org/W2073661767","https://openalex.org/W2380185347","https://openalex.org/W2370034659","https://openalex.org/W2159636084","https://openalex.org/W2117168988","https://openalex.org/W2103777723","https://openalex.org/W2610941444","https://openalex.org/W2162836426","https://openalex.org/W2734802753","https://openalex.org/W2149312834"],"abstract_inverted_index":{"BACKGROUND:":[0],"Familial":[1],"binding":[2,8,57],"profiles":[3,22],"(FBPs)":[4],"represent":[5],"the":[6,24,54,86,93,126,132,159,165,187,214,225,270],"average":[7],"specificity":[9],"for":[10,95,216],"a":[11,99,111,181,203,217],"group":[12],"of":[13,20,26,56,134,183,206,220,227,237,244,272],"structurally":[14,207],"related":[15],"DNA-binding":[16],"proteins.":[17],"The":[18,150],"construction":[19],"such":[21],"allows":[23,115],"classification":[25],"novel":[27],"motifs":[28,79,116,185,239],"based":[29],"on":[30,67,84,138,232,284],"similarity":[31],"to":[32,37,62,104,117,230,253],"known":[33,238],"families,":[34],"can":[35,49,72,201,259,275],"help":[36],"reduce":[38],"redundancy":[39],"in":[40,85,90,125,171,192],"motif":[41,64,141,175,194],"databases":[42],"and":[43,48,71,162,197,263],"de":[44],"novo":[45],"prediction":[46],"algorithms,":[47],"provide":[50,276],"valuable":[51],"insights":[52],"into":[53],"evolution":[55],"sites.":[58],"Many":[59],"current":[60,147],"approaches":[61],"automated":[63],"clustering":[65,127,195],"rely":[66],"progressive":[68],"tree-based":[69],"techniques,":[70],"suffer":[73],"from":[74,158,186],"so-called":[75],"frozen":[76,273],"sub-alignments,":[77,274],"where":[78],"which":[80,114],"are":[81],"clustered":[82],"early":[83],"process":[87],"remain":[88],"'locked'":[89],"place":[91],"despite":[92],"potential":[94],"better":[96],"placement":[97],"at":[98,122],"later":[100],"stage.":[101],"In":[102],"order":[103],"avoid":[105],"this":[106],"scenario,":[107],"we":[108,223],"have":[109],"developed":[110],"genetic-k-medoids":[112],"approach":[113,169],"move":[118],"freely":[119],"between":[120],"clusters":[121,209],"any":[123,254],"point":[124],"process.":[128],"RESULTS:":[129],"We":[130,178],"demonstrate":[131,198],"performance":[133],"our":[135,228],"algorithm,":[136],"GMACS,":[137],"multiple":[139,233],"benchmark":[140,285],"datasets,":[142],"comparing":[143],"results":[144,278],"obtained":[145],"with":[146,241,281],"leading":[148],"approaches.":[149],"first":[151],"dataset":[152],"includes":[153],"355":[154],"position":[155],"weight":[156],"matrices":[157],"TRANSFAC":[160],"database":[161,189],"indicates":[163],"that":[164,199],"k-mer":[166],"frequency":[167],"vector":[168],"used":[170,191],"GMACS":[172,200],"outperforms":[173],"other":[174,211],"comparison":[176],"techniques.":[177],"then":[179],"cluster":[180],"set":[182],"79":[184],"JASPAR":[188],"previously":[190],"several":[193],"studies":[196],"produce":[202,260],"higher":[204],"number":[205,219],"homogeneous":[208],"than":[210],"methods":[212],"without":[213],"need":[215],"large":[218],"singletons.":[221],"Finally,":[222],"show":[224],"robustness":[226],"algorithm":[229,249],"noise":[231],"synthetic":[234],"datasets":[235],"consisting":[236],"convolved":[240],"varying":[242],"degrees":[243],"noise.":[245],"CONCLUSIONS:":[246],"Our":[247],"proposed":[248],"is":[250],"generally":[251],"applicable":[252],"DNA":[255],"or":[256],"protein":[257],"motifs,":[258],"highly":[261],"stable":[262],"biologically":[264],"meaningful":[265],"clusters,":[266],"and,":[267],"by":[268],"avoiding":[269],"problem":[271],"improved":[277],"when":[279],"compared":[280],"existing":[282],"techniques":[283],"datasets.":[286]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":2}],"updated_date":"2026-07-02T09:51:11.867554","created_date":"2025-10-10T00:00:00"}
