{"id":"https://openalex.org/W4294670644","doi":"https://doi.org/10.1093/bioinformatics/btac604","title":"A closed formula relevant to \u2018Theory of local k-mer selection with applications to long-read alignment\u2019 by Jim Shaw and Yun William Yu","display_name":"A closed formula relevant to \u2018Theory of local k-mer selection with applications to long-read alignment\u2019 by Jim Shaw and Yun William Yu","publication_year":2022,"publication_date":"2022-09-01","ids":{"openalex":"https://openalex.org/W4294670644","doi":"https://doi.org/10.1093/bioinformatics/btac604","pmid":"https://pubmed.ncbi.nlm.nih.gov/36063041"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btac604","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btac604","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/38/20/4848/48449144/btac604.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"type":"letter","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://academic.oup.com/bioinformatics/article-pdf/38/20/4848/48449144/btac604.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5039386346","display_name":"John L. Spouge","orcid":"https://orcid.org/0000-0001-6207-1419"},"institutions":[{"id":"https://openalex.org/I2800548410","display_name":"United States National Library of Medicine","ror":"https://ror.org/0060t0j89","country_code":"US","type":"archive","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238","https://openalex.org/I2800548410"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"John L Spouge","raw_affiliation_strings":["Intramural Research Program, National Library of Medicine , Bethesda, MD 20894, USA"],"affiliations":[{"raw_affiliation_string":"Intramural Research Program, National Library of Medicine , Bethesda, MD 20894, USA","institution_ids":["https://openalex.org/I2800548410"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5039386346"],"corresponding_institution_ids":["https://openalex.org/I2800548410"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":{"value":3618,"currency":"USD","value_usd":3618},"fwci":0.24613832,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.48016117,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"38","issue":"20","first_page":"4848","last_page":"4849"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","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"}},"topics":[{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","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/T10207","display_name":"Advanced biosensing and bioanalysis techniques","score":0.9973999857902527,"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/T10521","display_name":"RNA and protein synthesis mechanisms","score":0.9958999752998352,"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/recursion","display_name":"Recursion (computer science)","score":0.8532202243804932},{"id":"https://openalex.org/keywords/sketch","display_name":"Sketch","score":0.8203789591789246},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.7354854345321655},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.6116882562637329},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.5878486037254333},{"id":"https://openalex.org/keywords/base","display_name":"Base (topology)","score":0.4975147545337677},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4771813154220581},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.4684595763683319},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.4335692226886749},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.42565861344337463},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.39880239963531494},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.3549545407295227},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.11734387278556824},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.09193724393844604},{"id":"https://openalex.org/keywords/mathematical-analysis","display_name":"Mathematical analysis","score":0.07158088684082031}],"concepts":[{"id":"https://openalex.org/C168773036","wikidata":"https://www.wikidata.org/wiki/Q264164","display_name":"Recursion (computer science)","level":2,"score":0.8532202243804932},{"id":"https://openalex.org/C2779231336","wikidata":"https://www.wikidata.org/wiki/Q7534724","display_name":"Sketch","level":2,"score":0.8203789591789246},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.7354854345321655},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.6116882562637329},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.5878486037254333},{"id":"https://openalex.org/C42058472","wikidata":"https://www.wikidata.org/wiki/Q810214","display_name":"Base (topology)","level":2,"score":0.4975147545337677},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4771813154220581},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.4684595763683319},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4335692226886749},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.42565861344337463},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.39880239963531494},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.3549545407295227},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.11734387278556824},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.09193724393844604},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.07158088684082031},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":3,"locations":[{"id":"doi:10.1093/bioinformatics/btac604","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btac604","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/38/20/4848/48449144/btac604.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:36063041","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/36063041","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":"Bioinformatics (Oxford, England)","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:9801975","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/9801975","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Bioinformatics","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btac604","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btac604","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/38/20/4848/48449144/btac604.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.6499999761581421,"display_name":"Life in Land","id":"https://metadata.un.org/sdg/15"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4294670644.pdf","grobid_xml":"https://content.openalex.org/works/W4294670644.grobid-xml"},"referenced_works_count":6,"referenced_works":["https://openalex.org/W2144560237","https://openalex.org/W3114310315","https://openalex.org/W3128964673","https://openalex.org/W4226289813","https://openalex.org/W4243450674","https://openalex.org/W4307475426"],"related_works":["https://openalex.org/W2378994405","https://openalex.org/W2385974820","https://openalex.org/W2373478030","https://openalex.org/W2378679551","https://openalex.org/W3149739944","https://openalex.org/W2392363776","https://openalex.org/W2063051341","https://openalex.org/W1494563618","https://openalex.org/W2963684594","https://openalex.org/W3212463983"],"abstract_inverted_index":{"To":[0],"handle":[1],"the":[2,36,40,49,69,88,106,109,130],"volume":[3],"from":[4],"next-generation":[5],"sequencing":[6],"data,":[7],"modern":[8],"sequence":[9,15,73,140],"comparison":[10],"often":[11],"relies":[12],"on":[13],"summary":[14],"sketches":[16,141],"such":[17],"as":[18],"minimizers,":[19,105],"syncmers,":[20],"and":[21,58,80,98,117],"minimally":[22],"overlapping":[23],"words.":[24],"Let":[25],"us":[26],"call":[27],"an":[28],"oligonucleotide":[29],"of":[30,38,43,56,65,71,108,129],"length":[31],"k":[32],"a":[33,44,52,61,66,72,83,90,123],"k-mer.":[34],"With":[35],"aim":[37],"anticipating":[39],"practical":[41],"performance":[42],"rule":[45],"f":[46],"that":[47,92,115],"selects":[48],"k-mers":[50],"in":[51,68],"sketch,":[53],"Theorem":[54],"2":[55],"Shaw":[57,79,116],"Yu":[59,81],"gives":[60],"formula":[62,132],"quantifying":[63],"conservation":[64],"sketch":[67],"presence":[70],"mutation":[74],"probability":[75],"\u03b8":[76],"per":[77],"base.":[78],"give":[82],"four-variable":[84],"recursion":[85,119],"for":[86,101],"computing":[87],"formula,":[89],"computation":[91],"is":[93,120],"complicated,":[94],"difficult":[95],"to":[96,122,138],"implement,":[97],"computationally":[99],"expensive":[100],"large":[102],"parameter":[103],"values.For":[104],"earliest":[107],"k-mer":[110],"sketches,":[111],"this":[112],"letter":[113],"shows":[114],"Yu's":[118],"equivalent":[121],"simple":[124],"explicit":[125,131],"formula.":[126],"The":[127],"proof":[128],"can":[133],"be":[134],"generalized,":[135],"with":[136],"applications":[137],"other":[139],"likely.":[142]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}