{"id":"https://openalex.org/W4412372943","doi":"https://doi.org/10.1186/s13015-025-00286-6","title":"Swiftly identifying strongly unique k-mers","display_name":"Swiftly identifying strongly unique k-mers","publication_year":2025,"publication_date":"2025-07-13","ids":{"openalex":"https://openalex.org/W4412372943","doi":"https://doi.org/10.1186/s13015-025-00286-6","pmid":"https://pubmed.ncbi.nlm.nih.gov/40653478"},"language":"en","primary_location":{"id":"doi:10.1186/s13015-025-00286-6","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13015-025-00286-6","pdf_url":"https://almob.biomedcentral.com/counter/pdf/10.1186/s13015-025-00286-6","source":{"id":"https://openalex.org/S205663195","display_name":"Algorithms for Molecular Biology","issn_l":"1748-7188","issn":["1748-7188"],"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":"Algorithms for Molecular Biology","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://almob.biomedcentral.com/counter/pdf/10.1186/s13015-025-00286-6","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5021804671","display_name":"Jens Zentgraf","orcid":"https://orcid.org/0000-0001-9444-2755"},"institutions":[{"id":"https://openalex.org/I91712215","display_name":"Saarland University","ror":"https://ror.org/01jdpyv68","country_code":"DE","type":"education","lineage":["https://openalex.org/I91712215"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jens Zentgraf","raw_affiliation_strings":["Algorithmic Bioinformatics, Department of Computer Science, Saarland University, Campus E2.1, Saarbr\u00fccken, 66123, Saarland, Germany","Center for Bioinformatics Saar, Saarland Informatics Campus, Campus E2.1, Saarbr\u00fccken, 66123, Saarland, Germany","Saarbr\u00fccken Graduate School of Computer Science, Saarland Informatics Campus, Campus E2.1, Saarbr\u00fccken, 66123, Saarland, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Algorithmic Bioinformatics, Department of Computer Science, Saarland University, Campus E2.1, Saarbr\u00fccken, 66123, Saarland, Germany","institution_ids":["https://openalex.org/I91712215"]},{"raw_affiliation_string":"Center for Bioinformatics Saar, Saarland Informatics Campus, Campus E2.1, Saarbr\u00fccken, 66123, Saarland, Germany","institution_ids":["https://openalex.org/I91712215"]},{"raw_affiliation_string":"Saarbr\u00fccken Graduate School of Computer Science, Saarland Informatics Campus, Campus E2.1, Saarbr\u00fccken, 66123, Saarland, Germany","institution_ids":["https://openalex.org/I91712215"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059606670","display_name":"Sven Rahmann","orcid":"https://orcid.org/0000-0002-8536-6065"},"institutions":[{"id":"https://openalex.org/I91712215","display_name":"Saarland University","ror":"https://ror.org/01jdpyv68","country_code":"DE","type":"education","lineage":["https://openalex.org/I91712215"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Sven Rahmann","raw_affiliation_strings":["Algorithmic Bioinformatics, Department of Computer Science, Saarland University, Campus E2.1, Saarbr\u00fccken, 66123, Saarland, Germany. sven.rahmann@uni-saarland.de","Center for Bioinformatics Saar, Saarland Informatics Campus, Campus E2.1, Saarbr\u00fccken, 66123, Saarland, Germany. sven.rahmann@uni-saarland.de"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Algorithmic Bioinformatics, Department of Computer Science, Saarland University, Campus E2.1, Saarbr\u00fccken, 66123, Saarland, Germany. sven.rahmann@uni-saarland.de","institution_ids":["https://openalex.org/I91712215"]},{"raw_affiliation_string":"Center for Bioinformatics Saar, Saarland Informatics Campus, Campus E2.1, Saarbr\u00fccken, 66123, Saarland, Germany. sven.rahmann@uni-saarland.de","institution_ids":["https://openalex.org/I91712215"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1490,"currency":"GBP","value_usd":1827},"apc_paid":{"value":1490,"currency":"GBP","value_usd":1827},"fwci":2.5692,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.89539407,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":"20","issue":"1","first_page":"13","last_page":"13"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13664","display_name":"Genome Rearrangement Algorithms","score":0.7569000124931335,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"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/T13664","display_name":"Genome Rearrangement Algorithms","score":0.7569000124931335,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"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":0.10989999771118164,"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"}},{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.08380000293254852,"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/hamming-distance","display_name":"Hamming distance","score":0.7539478540420532},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6581383943557739},{"id":"https://openalex.org/keywords/ambiguity","display_name":"Ambiguity","score":0.6440309882164001},{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.6405401229858398},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6316455602645874},{"id":"https://openalex.org/keywords/hamming-code","display_name":"Hamming code","score":0.5752674341201782},{"id":"https://openalex.org/keywords/k-mer","display_name":"k-mer","score":0.4866993725299835},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.44334763288497925},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.36388838291168213},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.35795363783836365},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.31147003173828125},{"id":"https://openalex.org/keywords/dna","display_name":"DNA","score":0.18408656120300293},{"id":"https://openalex.org/keywords/dna-sequencing","display_name":"DNA sequencing","score":0.15341722965240479},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.13876351714134216},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.10890153050422668},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.10463210940361023}],"concepts":[{"id":"https://openalex.org/C193319292","wikidata":"https://www.wikidata.org/wiki/Q272172","display_name":"Hamming distance","level":2,"score":0.7539478540420532},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6581383943557739},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.6440309882164001},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.6405401229858398},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6316455602645874},{"id":"https://openalex.org/C73150493","wikidata":"https://www.wikidata.org/wiki/Q853922","display_name":"Hamming code","level":4,"score":0.5752674341201782},{"id":"https://openalex.org/C2279292","wikidata":"https://www.wikidata.org/wiki/Q6322851","display_name":"k-mer","level":4,"score":0.4866993725299835},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.44334763288497925},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.36388838291168213},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.35795363783836365},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.31147003173828125},{"id":"https://openalex.org/C552990157","wikidata":"https://www.wikidata.org/wiki/Q7430","display_name":"DNA","level":2,"score":0.18408656120300293},{"id":"https://openalex.org/C51679486","wikidata":"https://www.wikidata.org/wiki/Q380546","display_name":"DNA sequencing","level":3,"score":0.15341722965240479},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.13876351714134216},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.10890153050422668},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.10463210940361023},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.0},{"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/C157125643","wikidata":"https://www.wikidata.org/wiki/Q884707","display_name":"Block code","level":3,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1186/s13015-025-00286-6","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13015-025-00286-6","pdf_url":"https://almob.biomedcentral.com/counter/pdf/10.1186/s13015-025-00286-6","source":{"id":"https://openalex.org/S205663195","display_name":"Algorithms for Molecular Biology","issn_l":"1748-7188","issn":["1748-7188"],"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":"Algorithms for Molecular Biology","raw_type":"journal-article"},{"id":"pmid:40653478","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40653478","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":"Algorithms for molecular biology : AMB","raw_type":null},{"id":"pmh:oai:doaj.org/article:13630b75b8cb442098ce9719dccab94e","is_oa":true,"landing_page_url":"https://doaj.org/article/13630b75b8cb442098ce9719dccab94e","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Algorithms for Molecular Biology, Vol 20, Iss 1, Pp 1-16 (2025)","raw_type":"article"},{"id":"pmh:oai:europepmc.org:11063085","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/12257829","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/s13015-025-00286-6","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13015-025-00286-6","pdf_url":"https://almob.biomedcentral.com/counter/pdf/10.1186/s13015-025-00286-6","source":{"id":"https://openalex.org/S205663195","display_name":"Algorithms for Molecular Biology","issn_l":"1748-7188","issn":["1748-7188"],"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":"Algorithms for Molecular Biology","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320323322","display_name":"Universit\u00e4t des Saarlandes","ror":"https://ror.org/01jdpyv68"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412372943.pdf","grobid_xml":"https://content.openalex.org/works/W4412372943.grobid-xml"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W2075013491","https://openalex.org/W2090983756","https://openalex.org/W2096128575","https://openalex.org/W2125266506","https://openalex.org/W2146292423","https://openalex.org/W2160265768","https://openalex.org/W2245493112","https://openalex.org/W2295828257","https://openalex.org/W2323326409","https://openalex.org/W2519890620","https://openalex.org/W2583363792","https://openalex.org/W2597444305","https://openalex.org/W2950964375","https://openalex.org/W2996751484","https://openalex.org/W3148116804","https://openalex.org/W4383186537","https://openalex.org/W4386113054","https://openalex.org/W4393989706","https://openalex.org/W4396966038","https://openalex.org/W6891645095","https://openalex.org/W6948004943","https://openalex.org/W6963485782"],"related_works":["https://openalex.org/W2943247777","https://openalex.org/W2740543340","https://openalex.org/W2371167013","https://openalex.org/W1493958394","https://openalex.org/W1582340598","https://openalex.org/W2794545997","https://openalex.org/W2584980534","https://openalex.org/W2182731056","https://openalex.org/W1600949677","https://openalex.org/W2779867339"],"abstract_inverted_index":{"MOTIVATION:":[0],"Short":[1],"DNA":[2,40],"sequences":[3],"of":[4,27,122,129,134,170,196,218,250,253,279],"length":[5],"k":[6],"that":[7,71,141,154,175],"appear":[8],"in":[9,19,73,120,149,180,245],"a":[10,15,20,24,64,68,94,127,146,167,177,191,209,264],"single":[11,16,21,59],"location":[12,45],"(e.g.,":[13],"at":[14,42,77,291],"genomic":[17],"position,":[18],"species":[22],"from":[23,152],"larger":[25],"set":[26,128,168],"species,":[28],"etc.)":[29],"are":[30,35,54,104],"called":[31],"unique":[32,65,106,109],"k-mers.":[33,254],"They":[34],"useful":[36],"for":[37,111,235],"placing":[38],"sequenced":[39],"fragments":[41],"the":[43,123,150,181,197,219,274,280],"correct":[44],"without":[46,50],"computing":[47],"alignments":[48],"and":[49,164,207,233,243],"ambiguity.":[51],"However,":[52],"they":[53],"not":[55],"necessarily":[56],"robust:":[57],"A":[58,100],"basepair":[60],"change":[61],"may":[62,72,84],"turn":[63],"k-mer":[66,98],"into":[67,231],"different":[69,81],"one":[70,78],"fact":[74],"be":[75,289],"present":[76,159],"or":[79,87],"more":[80,101],"locations,":[82],"which":[83,112],"give":[85],"confusing":[86],"contradictory":[88],"information":[89,118],"when":[90],"attempting":[91],"to":[92,136,162,247],"place":[93],"read":[95],"by":[96],"its":[97],"content.":[99],"robust":[102],"concept":[103],"strongly":[105],"k-mers,":[107,130],"i.e.,":[108],"k-mers":[110,144,172,226],"no":[113],"Hamming-distance-1":[114,147,178],"neighbor":[115,148,179],"with":[116,145,260],"conflicting":[117],"exists":[119],"all":[121,173],"considered":[124],"sequences.":[125],"Given":[126],"it":[131],"is":[132,186,203],"therefore":[133],"interest":[135],"have":[137,176,240],"an":[138],"efficient":[139,236],"method":[140],"can":[142,288],"distinguish":[143],"collection":[151],"those":[153],"do":[155],"not.":[156],"RESULTS:":[157],"We":[158],"engineered":[160],"algorithms":[161],"identify":[163],"mark":[165],"within":[166],"K":[169],"(canonical)":[171],"elements":[174],"same":[182],"set.":[183,199,221],"One":[184],"algorithm":[185,202],"based":[187,204],"on":[188,194,205,215,263,273],"recursively":[189],"running":[190,208,259],"4-way":[192],"comparison":[193],"sub-intervals":[195],"sorted":[198,220],"The":[200,238],"other":[201],"bucketing":[206],"pairwise":[210],"bit-parallel":[211],"Hamming":[212],"distance":[213],"test":[214],"small":[216],"buckets":[217],"Both":[222],"methods":[223,239],"consider":[224],"canonical":[225],"(i.e.,":[227],"taking":[228],"reverse":[229],"complements":[230],"account)":[232],"allow":[234],"parallelization.":[237],"been":[241],"implemented":[242],"applied":[244],"practice":[246],"sets":[248],"consisting":[249],"several":[251],"billions":[252],"An":[255,286],"optimized":[256],"combined":[257],"approach":[258],"16":[261],"threads":[262],"16-core":[265],"workstation":[266],"yields":[267],"wall":[268],"times":[269],"below":[270],"20":[271],"seconds":[272],"2.5":[275],"billion":[276],"distinct":[277],"31-mers":[278],"human":[281],"telomere-to-telomere":[282],"reference":[283],"genome.":[284],"AVAILABILITY:":[285],"implementation":[287],"found":[290],"https://gitlab.com/rahmannlab/strong-k-mers":[292],".":[293]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
