{"id":"https://openalex.org/W2124626190","doi":"https://doi.org/10.1093/nar/gku398","title":"Spaced words and kmacs: fast alignment-free sequence comparison based on inexact word matches","display_name":"Spaced words and kmacs: fast alignment-free sequence comparison based on inexact word matches","publication_year":2014,"publication_date":"2014-05-14","ids":{"openalex":"https://openalex.org/W2124626190","doi":"https://doi.org/10.1093/nar/gku398","mag":"2124626190","pmid":"https://pubmed.ncbi.nlm.nih.gov/24829447"},"language":"en","primary_location":{"id":"doi:10.1093/nar/gku398","is_oa":true,"landing_page_url":"https://doi.org/10.1093/nar/gku398","pdf_url":null,"source":{"id":"https://openalex.org/S134668137","display_name":"Nucleic Acids Research","issn_l":"0305-1048","issn":["0305-1048","1362-4954","1362-4962"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Nucleic Acids Research","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1093/nar/gku398","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5091074959","display_name":"Sebastian Horwege","orcid":null},"institutions":[{"id":"https://openalex.org/I74656192","display_name":"University of G\u00f6ttingen","ror":"https://ror.org/01y9bpm73","country_code":"DE","type":"education","lineage":["https://openalex.org/I74656192"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Sebastian Horwege","raw_affiliation_strings":["University of G\u00f6ttingen, Institute of Microbiology and Genetics, Department of Bioinformatics, Goldschmidtstra\u00dfe 1, 37073 G\u00f6ttingen, Germany Sebastian.Horwege@stud.uni-goettingen.de","Georg-August-University = Georg-August-Universit\u00e4t G\u00f6ttingen"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of G\u00f6ttingen, Institute of Microbiology and Genetics, Department of Bioinformatics, Goldschmidtstra\u00dfe 1, 37073 G\u00f6ttingen, Germany Sebastian.Horwege@stud.uni-goettingen.de","institution_ids":["https://openalex.org/I74656192"]},{"raw_affiliation_string":"Georg-August-University = Georg-August-Universit\u00e4t G\u00f6ttingen","institution_ids":["https://openalex.org/I74656192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058503347","display_name":"Sebastian Lindner","orcid":"https://orcid.org/0000-0002-5694-9675"},"institutions":[{"id":"https://openalex.org/I74656192","display_name":"University of G\u00f6ttingen","ror":"https://ror.org/01y9bpm73","country_code":"DE","type":"education","lineage":["https://openalex.org/I74656192"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Sebastian Lindner","raw_affiliation_strings":["University of G\u00f6ttingen, Institute of Microbiology and Genetics, Department of Bioinformatics, Goldschmidtstra\u00dfe 1, 37073 G\u00f6ttingen, Germany","Georg-August-University = Georg-August-Universit\u00e4t G\u00f6ttingen"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of G\u00f6ttingen, Institute of Microbiology and Genetics, Department of Bioinformatics, Goldschmidtstra\u00dfe 1, 37073 G\u00f6ttingen, Germany","institution_ids":["https://openalex.org/I74656192"]},{"raw_affiliation_string":"Georg-August-University = Georg-August-Universit\u00e4t G\u00f6ttingen","institution_ids":["https://openalex.org/I74656192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068522592","display_name":"Marcus Boden","orcid":null},"institutions":[{"id":"https://openalex.org/I74656192","display_name":"University of G\u00f6ttingen","ror":"https://ror.org/01y9bpm73","country_code":"DE","type":"education","lineage":["https://openalex.org/I74656192"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Marcus Boden","raw_affiliation_strings":["University of G\u00f6ttingen, Institute of Microbiology and Genetics, Department of Bioinformatics, Goldschmidtstra\u00dfe 1, 37073 G\u00f6ttingen, Germany","Georg-August-University = Georg-August-Universit\u00e4t G\u00f6ttingen"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of G\u00f6ttingen, Institute of Microbiology and Genetics, Department of Bioinformatics, Goldschmidtstra\u00dfe 1, 37073 G\u00f6ttingen, Germany","institution_ids":["https://openalex.org/I74656192"]},{"raw_affiliation_string":"Georg-August-University = Georg-August-Universit\u00e4t G\u00f6ttingen","institution_ids":["https://openalex.org/I74656192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062772449","display_name":"Klas Hatje","orcid":"https://orcid.org/0000-0001-5425-8195"},"institutions":[{"id":"https://openalex.org/I149899117","display_name":"Max Planck Society","ror":"https://ror.org/01hhn8329","country_code":"DE","type":"nonprofit","lineage":["https://openalex.org/I149899117"]},{"id":"https://openalex.org/I4210131661","display_name":"Max Planck Institute for Biophysical Chemistry","ror":"https://ror.org/03e76ya46","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210131661"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Klas Hatje","raw_affiliation_strings":["Max-Planck-Institute for Biophysical Chemistry, Department of NMR-based Structural Biology, Group Systems Biology of Motor Proteins, Am Fassberg 11, 37077 G\u00f6ttingen, Germany","Max Planck Institute for Biophysical Chemistry"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Max-Planck-Institute for Biophysical Chemistry, Department of NMR-based Structural Biology, Group Systems Biology of Motor Proteins, Am Fassberg 11, 37077 G\u00f6ttingen, Germany","institution_ids":["https://openalex.org/I149899117"]},{"raw_affiliation_string":"Max Planck Institute for Biophysical Chemistry","institution_ids":["https://openalex.org/I4210131661"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057644887","display_name":"Martin Kollmar","orcid":"https://orcid.org/0000-0002-9768-1855"},"institutions":[{"id":"https://openalex.org/I149899117","display_name":"Max Planck Society","ror":"https://ror.org/01hhn8329","country_code":"DE","type":"nonprofit","lineage":["https://openalex.org/I149899117"]},{"id":"https://openalex.org/I4210131661","display_name":"Max Planck Institute for Biophysical Chemistry","ror":"https://ror.org/03e76ya46","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210131661"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Martin Kollmar","raw_affiliation_strings":["Max-Planck-Institute for Biophysical Chemistry, Department of NMR-based Structural Biology, Group Systems Biology of Motor Proteins, Am Fassberg 11, 37077 G\u00f6ttingen, Germany","Max Planck Institute for Biophysical Chemistry"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Max-Planck-Institute for Biophysical Chemistry, Department of NMR-based Structural Biology, Group Systems Biology of Motor Proteins, Am Fassberg 11, 37077 G\u00f6ttingen, Germany","institution_ids":["https://openalex.org/I149899117"]},{"raw_affiliation_string":"Max Planck Institute for Biophysical Chemistry","institution_ids":["https://openalex.org/I4210131661"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038295086","display_name":"Chris-Andr\u00e9 Leimeister","orcid":"https://orcid.org/0000-0002-5742-2744"},"institutions":[{"id":"https://openalex.org/I74656192","display_name":"University of G\u00f6ttingen","ror":"https://ror.org/01y9bpm73","country_code":"DE","type":"education","lineage":["https://openalex.org/I74656192"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Chris-Andr\u00e9 Leimeister","raw_affiliation_strings":["University of G\u00f6ttingen, Institute of Microbiology and Genetics, Department of Bioinformatics, Goldschmidtstra\u00dfe 1, 37073 G\u00f6ttingen, Germany","Georg-August-University = Georg-August-Universit\u00e4t G\u00f6ttingen"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of G\u00f6ttingen, Institute of Microbiology and Genetics, Department of Bioinformatics, Goldschmidtstra\u00dfe 1, 37073 G\u00f6ttingen, Germany","institution_ids":["https://openalex.org/I74656192"]},{"raw_affiliation_string":"Georg-August-University = Georg-August-Universit\u00e4t G\u00f6ttingen","institution_ids":["https://openalex.org/I74656192"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024220352","display_name":"Burkhard Morgenstern","orcid":"https://orcid.org/0000-0002-7431-2862"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210116548","display_name":"Laboratoire de Statistique Th\u00e9orique et Appliqu\u00e9e","ror":"https://ror.org/01vnn4t89","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I39804081","https://openalex.org/I4210116548","https://openalex.org/I4210141950"]},{"id":"https://openalex.org/I74656192","display_name":"University of G\u00f6ttingen","ror":"https://ror.org/01y9bpm73","country_code":"DE","type":"education","lineage":["https://openalex.org/I74656192"]},{"id":"https://openalex.org/I88467170","display_name":"Universit\u00e9 d'\u00c9vry Val-d'Essonne","ror":"https://ror.org/00e96v939","country_code":"FR","type":"education","lineage":["https://openalex.org/I277688954","https://openalex.org/I88467170"]}],"countries":["DE","FR"],"is_corresponding":false,"raw_author_name":"Burkhard Morgenstern","raw_affiliation_strings":["University of G\u00f6ttingen, Institute of Microbiology and Genetics, Department of Bioinformatics, Goldschmidtstra\u00dfe 1, 37073 G\u00f6ttingen, Germany Universit\u00e9 d'\u00c9vry Val d'Essonne, Laboratoire Statistique et G\u00e9nome, UMR CNRS 8071, USC INRA, 23 Boulevard de France, 91037 \u00c9vry, France","Georg-August-University = Georg-August-Universit\u00e4t G\u00f6ttingen","Laboratoire Statistique et G\u00e9nome"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of G\u00f6ttingen, Institute of Microbiology and Genetics, Department of Bioinformatics, Goldschmidtstra\u00dfe 1, 37073 G\u00f6ttingen, Germany Universit\u00e9 d'\u00c9vry Val d'Essonne, Laboratoire Statistique et G\u00e9nome, UMR CNRS 8071, USC INRA, 23 Boulevard de France, 91037 \u00c9vry, France","institution_ids":["https://openalex.org/I88467170","https://openalex.org/I1294671590"]},{"raw_affiliation_string":"Georg-August-University = Georg-August-Universit\u00e4t G\u00f6ttingen","institution_ids":["https://openalex.org/I74656192"]},{"raw_affiliation_string":"Laboratoire Statistique et G\u00e9nome","institution_ids":["https://openalex.org/I4210116548"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":3630,"currency":"USD","value_usd":3630},"apc_paid":{"value":1267,"currency":"EUR","value_usd":1366},"fwci":5.9777,"has_fulltext":true,"cited_by_count":89,"citation_normalized_percentile":{"value":0.9715397,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"42","issue":"W1","first_page":"W7","last_page":"W11"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9994999766349792,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9994999766349792,"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/T12946","display_name":"Fractal and DNA sequence analysis","score":0.9991999864578247,"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/T11269","display_name":"Algorithms and Data Compression","score":0.998199999332428,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.7981456518173218},{"id":"https://openalex.org/keywords/substring","display_name":"Substring","score":0.7518565654754639},{"id":"https://openalex.org/keywords/multiple-sequence-alignment","display_name":"Multiple sequence alignment","score":0.6834904551506042},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6788902282714844},{"id":"https://openalex.org/keywords/distance-matrix","display_name":"Distance matrix","score":0.6517969369888306},{"id":"https://openalex.org/keywords/edit-distance","display_name":"Edit distance","score":0.6295344233512878},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.6216514706611633},{"id":"https://openalex.org/keywords/distance-matrices-in-phylogeny","display_name":"Distance matrices in phylogeny","score":0.5859264731407166},{"id":"https://openalex.org/keywords/sequence-alignment","display_name":"Sequence alignment","score":0.5364528298377991},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5091533064842224},{"id":"https://openalex.org/keywords/position","display_name":"Position (finance)","score":0.44543176889419556},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.44193288683891296},{"id":"https://openalex.org/keywords/alignment-free-sequence-analysis","display_name":"Alignment-free sequence analysis","score":0.4362875521183014},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.4357336163520813},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4350232779979706},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.4183501899242401},{"id":"https://openalex.org/keywords/interface","display_name":"Interface (matter)","score":0.4162744879722595},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4109504222869873},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.31595975160598755},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.23544538021087646},{"id":"https://openalex.org/keywords/bioinformatics","display_name":"Bioinformatics","score":0.19419166445732117},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.168533056974411},{"id":"https://openalex.org/keywords/peptide-sequence","display_name":"Peptide sequence","score":0.09467130899429321}],"concepts":[{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.7981456518173218},{"id":"https://openalex.org/C182407805","wikidata":"https://www.wikidata.org/wiki/Q2626534","display_name":"Substring","level":3,"score":0.7518565654754639},{"id":"https://openalex.org/C88031987","wikidata":"https://www.wikidata.org/wiki/Q1377767","display_name":"Multiple sequence alignment","level":5,"score":0.6834904551506042},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6788902282714844},{"id":"https://openalex.org/C111208986","wikidata":"https://www.wikidata.org/wiki/Q901698","display_name":"Distance matrix","level":2,"score":0.6517969369888306},{"id":"https://openalex.org/C44359876","wikidata":"https://www.wikidata.org/wiki/Q5338467","display_name":"Edit distance","level":2,"score":0.6295344233512878},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.6216514706611633},{"id":"https://openalex.org/C5349765","wikidata":"https://www.wikidata.org/wiki/Q5282866","display_name":"Distance matrices in phylogeny","level":2,"score":0.5859264731407166},{"id":"https://openalex.org/C45484198","wikidata":"https://www.wikidata.org/wiki/Q827246","display_name":"Sequence alignment","level":4,"score":0.5364528298377991},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5091533064842224},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.44543176889419556},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.44193288683891296},{"id":"https://openalex.org/C180384323","wikidata":"https://www.wikidata.org/wiki/Q16335137","display_name":"Alignment-free sequence analysis","level":5,"score":0.4362875521183014},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.4357336163520813},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4350232779979706},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.4183501899242401},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.4162744879722595},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4109504222869873},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31595975160598755},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.23544538021087646},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.19419166445732117},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.168533056974411},{"id":"https://openalex.org/C167625842","wikidata":"https://www.wikidata.org/wiki/Q899763","display_name":"Peptide sequence","level":3,"score":0.09467130899429321},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C55352822","wikidata":"https://www.wikidata.org/wiki/Q5558978","display_name":"Gibbs isotherm","level":3,"score":0.0},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C58226133","wikidata":"https://www.wikidata.org/wiki/Q1324199","display_name":"Pulmonary surfactant","level":2,"score":0.0},{"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":"D010802","descriptor_name":"Phylogeny","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D010802","descriptor_name":"Phylogeny","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D010802","descriptor_name":"Phylogeny","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":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D014584","descriptor_name":"User-Computer Interface","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D014584","descriptor_name":"User-Computer Interface","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D014584","descriptor_name":"User-Computer Interface","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":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","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":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":"D020407","descriptor_name":"Internet","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020407","descriptor_name":"Internet","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020407","descriptor_name":"Internet","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":8,"locations":[{"id":"doi:10.1093/nar/gku398","is_oa":true,"landing_page_url":"https://doi.org/10.1093/nar/gku398","pdf_url":null,"source":{"id":"https://openalex.org/S134668137","display_name":"Nucleic Acids Research","issn_l":"0305-1048","issn":["0305-1048","1362-4954","1362-4962"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Nucleic Acids Research","raw_type":"journal-article"},{"id":"pmid:24829447","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/24829447","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":"Nucleic acids research","raw_type":null},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.790.6645","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.790.6645","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ftp://ftp.ncbi.nlm.nih.gov/pub/pmc/63/6d/gku398.PMC4086093.pdf","raw_type":"text"},{"id":"pmh:oai:HAL:hal-02636898v1","is_oa":false,"landing_page_url":"https://hal.inrae.fr/hal-02636898","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://nar.oxfordjournals.org/","raw_type":"Journal articles"},{"id":"pmh:oai:escidoc.org:escidoc:2053244","is_oa":true,"landing_page_url":"http://hdl.handle.net/11858/00-001M-0000-0023-C6E4-C","pdf_url":null,"source":{"id":"https://openalex.org/S7407052962","display_name":"Max Planck Digital Library","issn_l":null,"issn":[],"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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:europepmc.org:3176823","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/4086093","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"},{"id":"pmh:oai:goescholar:1/10456","is_oa":true,"landing_page_url":"http://resolver.sub.uni-goettingen.de/purl?gs-1/10456","pdf_url":null,"source":{"id":"https://openalex.org/S4306401634","display_name":"GoeScholar  The Publication Server of the Georg-August-Universit\u00e4t G\u00f6ttingen (Georg-August-Universit\u00e4t G\u00f6ttingen)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210122495","host_organization_name":"Asklepios Klinik St. Georg","host_organization_lineage":["https://openalex.org/I4210122495"],"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":"","raw_type":"journalArticle"},{"id":"pmh:oai:publications.goettingen-research-online.de:2/32985","is_oa":true,"landing_page_url":"https://resolver.sub.uni-goettingen.de/purl?gro-2/32985","pdf_url":null,"source":{"id":"https://openalex.org/S4306401634","display_name":"GoeScholar  The Publication Server of the Georg-August-Universit\u00e4t G\u00f6ttingen (Georg-August-Universit\u00e4t G\u00f6ttingen)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210122495","host_organization_name":"Asklepios Klinik St. Georg","host_organization_lineage":["https://openalex.org/I4210122495"],"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":"","raw_type":"journal_article"}],"best_oa_location":{"id":"doi:10.1093/nar/gku398","is_oa":true,"landing_page_url":"https://doi.org/10.1093/nar/gku398","pdf_url":null,"source":{"id":"https://openalex.org/S134668137","display_name":"Nucleic Acids Research","issn_l":"0305-1048","issn":["0305-1048","1362-4954","1362-4962"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Nucleic Acids Research","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W938539187","https://openalex.org/W1504417041","https://openalex.org/W1583827615","https://openalex.org/W1614203862","https://openalex.org/W1873119440","https://openalex.org/W1971239653","https://openalex.org/W1975775747","https://openalex.org/W1990061958","https://openalex.org/W1992056504","https://openalex.org/W2017519756","https://openalex.org/W2031611770","https://openalex.org/W2039491180","https://openalex.org/W2091338378","https://openalex.org/W2095724872","https://openalex.org/W2097160089","https://openalex.org/W2109692166","https://openalex.org/W2111588838","https://openalex.org/W2120771433","https://openalex.org/W2128591967","https://openalex.org/W2138486754","https://openalex.org/W2146950091","https://openalex.org/W2150680311","https://openalex.org/W2150774511","https://openalex.org/W2171963266","https://openalex.org/W2264160242","https://openalex.org/W2591373418","https://openalex.org/W2953211673","https://openalex.org/W2970344678","https://openalex.org/W3199943451","https://openalex.org/W4390808053","https://openalex.org/W6628896446","https://openalex.org/W6634774584","https://openalex.org/W6654563908","https://openalex.org/W6693282682","https://openalex.org/W6800717233"],"related_works":["https://openalex.org/W2136519138","https://openalex.org/W1989944203","https://openalex.org/W1998479724","https://openalex.org/W2546839375","https://openalex.org/W2358678896","https://openalex.org/W2180288160","https://openalex.org/W2149286566","https://openalex.org/W2188796099","https://openalex.org/W2387028079","https://openalex.org/W2167896124"],"abstract_inverted_index":{"In":[0],"this":[1,116],"article,":[2],"we":[3,15],"present":[4],"a":[5,133,146,157,174],"user-friendly":[6],"web":[7,175],"interface":[8,176],"for":[9,102,160],"two":[10,98,168],"alignment-free":[11,19,169],"sequence-comparison":[12],"methods":[13,20],"that":[14,118,152],"recently":[16],"developed.":[17],"Most":[18],"rely":[21],"on":[22,43,83,86],"exact":[23],"word":[24,45],"matches":[25],"to":[26,127],"estimate":[27],"pairwise":[28,149],"similarities":[29],"or":[30,69,139,163],"distances":[31],"between":[32,97],"the":[33,53,61,95,106,109,112,122,186],"input":[34,62,143],"sequences.":[35],"By":[36],"contrast,":[37],"our":[38],"new":[39],"algorithms":[40,162],"are":[41,171],"based":[42,85],"inexact":[44],"matches.":[46],"The":[47,167],"first":[48,107],"of":[49,56,111,135,148],"these":[50],"approaches":[51,131],"uses":[52],"relative":[54],"frequencies":[55],"so-called":[57],"spaced":[58],"words":[59,65],"in":[60,105,121],"sequences,":[63],"i.e.":[64],"containing":[66],"'don't":[67],"care'":[68],"'wildcard'":[70],"symbols":[71],"at":[72,115,177],"certain":[73],"pre-defined":[74],"positions.":[75],"Various":[76],"distance":[77,96,150],"measures":[78],"can":[79,153,189],"then":[80],"be":[81,154,190],"defined":[82],"sequences":[84,99,141],"their":[87],"different":[88],"spaced-word":[89],"composition.":[90],"Our":[91],"second":[92,123],"approach":[93],"defines":[94],"by":[100],"estimating":[101],"each":[103],"position":[104,117],"sequence":[108,124],"length":[110],"longest":[113],"substring":[114],"also":[119],"occurs":[120],"with":[125],"up":[126],"k":[128],"mismatches.":[129],"Both":[130],"take":[132],"set":[134],"deoxyribonucleic":[136],"acid":[137],"(DNA)":[138],"protein":[140],"as":[142,156],"and":[144,185],"return":[145],"matrix":[147],"values":[151],"used":[155],"starting":[158],"point":[159],"clustering":[161],"distance-based":[164],"phylogeny":[165],"reconstruction.":[166],"programmes":[170],"accessible":[172],"through":[173],"'G\u00f6ttingen":[178],"Bioinformatics":[179],"Compute":[180],"Server":[181],"(GOBICS)':":[182],"http://spaced.gobics.de":[183],"http://kmacs.gobics.de":[184],"source":[187],"codes":[188],"downloaded.":[191]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":13},{"year":2018,"cited_by_count":14},{"year":2017,"cited_by_count":12},{"year":2016,"cited_by_count":15},{"year":2015,"cited_by_count":10},{"year":2014,"cited_by_count":5}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
