{"id":"https://openalex.org/W2144560237","doi":"https://doi.org/10.1093/bioinformatics/bth408","title":"Reducing storage requirements for biological sequence comparison","display_name":"Reducing storage requirements for biological sequence comparison","publication_year":2004,"publication_date":"2004-07-15","ids":{"openalex":"https://openalex.org/W2144560237","doi":"https://doi.org/10.1093/bioinformatics/bth408","mag":"2144560237","pmid":"https://pubmed.ncbi.nlm.nih.gov/15256412"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/bth408","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/bth408","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/20/18/3363/48906547/bioinformatics_20_18_3363.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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://academic.oup.com/bioinformatics/article-pdf/20/18/3363/48906547/bioinformatics_20_18_3363.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5000564935","display_name":"Michael Roberts","orcid":"https://orcid.org/0000-0002-1441-7363"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Michael Roberts","raw_affiliation_strings":["Institute for Physical Science and Technology, University of Maryland, College Park, MD 20742-2431, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Physical Science and Technology, University of Maryland, College Park, MD 20742-2431, USA","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028882289","display_name":"Wayne B. Hayes","orcid":"https://orcid.org/0000-0002-3310-6042"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wayne Hayes","raw_affiliation_strings":["Institute for Physical Science and Technology, University of Maryland, College Park, MD 20742-2431, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Physical Science and Technology, University of Maryland, College Park, MD 20742-2431, USA","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019387364","display_name":"Brian R. Hunt","orcid":"https://orcid.org/0000-0003-0779-9866"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Brian R. Hunt","raw_affiliation_strings":["Institute for Physical Science and Technology, University of Maryland, College Park, MD 20742-2431, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Physical Science and Technology, University of Maryland, College Park, MD 20742-2431, USA","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040594310","display_name":"Stephen M. Mount","orcid":"https://orcid.org/0000-0003-2748-8205"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Stephen M. Mount","raw_affiliation_strings":["Institute for Physical Science and Technology, University of Maryland, College Park, MD 20742-2431, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Physical Science and Technology, University of Maryland, College Park, MD 20742-2431, USA","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022360238","display_name":"James A. Yorke","orcid":"https://orcid.org/0000-0002-9599-0136"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"James A. Yorke","raw_affiliation_strings":["Institute for Physical Science and Technology, University of Maryland, College Park, MD 20742-2431, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Physical Science and Technology, University of Maryland, College Park, MD 20742-2431, USA","institution_ids":["https://openalex.org/I66946132"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5000564935"],"corresponding_institution_ids":["https://openalex.org/I66946132"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":null,"fwci":0.4534,"has_fulltext":true,"cited_by_count":592,"citation_normalized_percentile":{"value":0.60772626,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"20","issue":"18","first_page":"3363","last_page":"3369"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.6604999899864197,"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":0.6604999899864197,"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/T13937","display_name":"Genetics, Bioinformatics, and Biomedical Research","score":0.0414000004529953,"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":0.04129999876022339,"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/substring","display_name":"Substring","score":0.943501889705658},{"id":"https://openalex.org/keywords/string","display_name":"String (physics)","score":0.7276164293289185},{"id":"https://openalex.org/keywords/string-searching-algorithm","display_name":"String searching algorithm","score":0.638222873210907},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.624378502368927},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.6196533441543579},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5926946997642517},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5799738764762878},{"id":"https://openalex.org/keywords/fraction","display_name":"Fraction (chemistry)","score":0.5073031783103943},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5014636516571045},{"id":"https://openalex.org/keywords/approximate-string-matching","display_name":"Approximate string matching","score":0.46154075860977173},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.43389901518821716},{"id":"https://openalex.org/keywords/pattern-matching","display_name":"Pattern matching","score":0.43302592635154724},{"id":"https://openalex.org/keywords/genome","display_name":"Genome","score":0.41891977190971375},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3596779704093933},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3569653034210205},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3520148992538452},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.3265951871871948},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.26890432834625244},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.21025514602661133},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.16562747955322266},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.12572407722473145},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.1013246476650238},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.08687391877174377},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08156022429466248},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.08040937781333923}],"concepts":[{"id":"https://openalex.org/C182407805","wikidata":"https://www.wikidata.org/wiki/Q2626534","display_name":"Substring","level":3,"score":0.943501889705658},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.7276164293289185},{"id":"https://openalex.org/C7757238","wikidata":"https://www.wikidata.org/wiki/Q374040","display_name":"String searching algorithm","level":3,"score":0.638222873210907},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.624378502368927},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.6196533441543579},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5926946997642517},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5799738764762878},{"id":"https://openalex.org/C149629883","wikidata":"https://www.wikidata.org/wiki/Q660926","display_name":"Fraction (chemistry)","level":2,"score":0.5073031783103943},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5014636516571045},{"id":"https://openalex.org/C32610155","wikidata":"https://www.wikidata.org/wiki/Q1798621","display_name":"Approximate string matching","level":3,"score":0.46154075860977173},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.43389901518821716},{"id":"https://openalex.org/C68859911","wikidata":"https://www.wikidata.org/wiki/Q1503724","display_name":"Pattern matching","level":2,"score":0.43302592635154724},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.41891977190971375},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3596779704093933},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3569653034210205},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3520148992538452},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.3265951871871948},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.26890432834625244},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.21025514602661133},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.16562747955322266},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.12572407722473145},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.1013246476650238},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.08687391877174377},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08156022429466248},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.08040937781333923},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","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},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009716","descriptor_name":"Numerical Analysis, Computer-Assisted","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009716","descriptor_name":"Numerical Analysis, Computer-Assisted","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009716","descriptor_name":"Numerical Analysis, Computer-Assisted","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D017421","descriptor_name":"Sequence Analysis","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D017421","descriptor_name":"Sequence Analysis","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D017421","descriptor_name":"Sequence Analysis","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":true},{"descriptor_ui":"D030541","descriptor_name":"Databases, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D030541","descriptor_name":"Databases, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":5,"locations":[{"id":"doi:10.1093/bioinformatics/bth408","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/bth408","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/20/18/3363/48906547/bioinformatics_20_18_3363.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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:15256412","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/15256412","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:CiteSeerX.psu:10.1.1.1013.7523","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.1013.7523","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://bioinformatics.oxfordjournals.org/content/20/18/3363.full.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.1023.4323","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.1023.4323","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://bioinformatics.oxfordjournals.org/content/early/2004/07/15/bioinformatics.bth408.full.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.72.9748","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.72.9748","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.csri.utoronto.ca/~wayne/research/papers/minimizers.pdf","raw_type":"text"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/bth408","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/bth408","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/20/18/3363/48906547/bioinformatics_20_18_3363.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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3345364255","display_name":"Improving overlap-finding techniques for whole genome shotgun data","funder_award_id":"0312360","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6708711055","display_name":"Applications of Nonlinear Dynamics","funder_award_id":"0104087","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7335511789","display_name":"Arabidopsis 2010:  Pre-mRNA Splicing Signals in Arabidopsis","funder_award_id":"0114792","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8124727942","display_name":null,"funder_award_id":"1R01HG0294501","funder_id":"https://openalex.org/F4320337348","funder_display_name":"National Human Genome Research Institute"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337348","display_name":"National Human Genome Research Institute","ror":"https://ror.org/00baak391"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2144560237.pdf","grobid_xml":"https://content.openalex.org/works/W2144560237.grobid-xml"},"referenced_works_count":13,"referenced_works":["https://openalex.org/W1635391495","https://openalex.org/W2010454899","https://openalex.org/W2015292449","https://openalex.org/W2029195137","https://openalex.org/W2055043387","https://openalex.org/W2055666215","https://openalex.org/W2127230663","https://openalex.org/W2128591967","https://openalex.org/W2142619120","https://openalex.org/W2144662851","https://openalex.org/W2153889777","https://openalex.org/W2158714788","https://openalex.org/W4236236547"],"related_works":["https://openalex.org/W52396946","https://openalex.org/W2298204719","https://openalex.org/W1564013439","https://openalex.org/W2395807140","https://openalex.org/W4230921427","https://openalex.org/W2902482624","https://openalex.org/W3112977702","https://openalex.org/W2376315482","https://openalex.org/W2366227422","https://openalex.org/W2218650848"],"abstract_inverted_index":{"MOTIVATION:":[0],"Comparison":[1],"of":[2,12,18,29,46,80,103,134,159],"nucleic":[3],"acid":[4],"and":[5,89,125],"protein":[6,91],"sequences":[7],"is":[8,22,52],"a":[9,43,111,123,131,150,156],"fundamental":[10],"tool":[11],"modern":[13],"bioinformatics.":[14],"A":[15],"dominant":[16],"method":[17,127],"such":[19,49,84,95],"string":[20],"matching":[21,118],"the":[23,61,66,78,100,117,160],"'seed-and-extend'":[24],"approach,":[25],"in":[26,42,77,108,128],"which":[27,129],"occurrences":[28],"short":[30],"subsequences":[31],"called":[32,136],"'seeds'":[33],"are":[34],"used":[35],"to":[36,55,70,139],"search":[37,81],"for":[38],"potentially":[39],"longer":[40],"matches":[41,161],"large":[44,96,151],"database":[45,79],"sequences.":[47],"Each":[48],"potential":[50],"match":[51],"then":[53],"checked":[54],"see":[56],"if":[57],"it":[58],"extends":[59],"beyond":[60],"seed.":[62],"To":[63],"be":[64,106,140],"effective,":[65],"seed-and-extend":[67],"approach":[68],"needs":[69,138],"catalogue":[71],"seeds":[72,104],"from":[73],"virtually":[74],"every":[75],"substring":[76],"strings.":[82],"Projects":[83],"as":[85],"mammalian":[86],"genome":[87],"assemblies":[88],"large-scale":[90],"matching,":[92],"however,":[93],"have":[94],"sequence":[97],"databases":[98],"that":[99],"resulting":[101],"list":[102],"cannot":[105],"stored":[107],"RAM":[109],"on":[110],"single":[112],"computer.":[113],"This":[114],"significantly":[115],"slows":[116],"process.":[119],"RESULTS:":[120],"We":[121],"present":[122],"simple":[124],"elegant":[126],"only":[130,155],"small":[132,157],"fraction":[133,158],"seeds,":[135],"'minimizers',":[137],"stored.":[141],"Using":[142],"minimizers":[143],"can":[144],"speed":[145],"up":[146],"string-matching":[147],"computations":[148],"by":[149],"factor":[152],"while":[153],"missing":[154],"found":[162],"using":[163],"all":[164],"seeds.":[165]},"counts_by_year":[{"year":2026,"cited_by_count":20},{"year":2025,"cited_by_count":61},{"year":2024,"cited_by_count":88},{"year":2023,"cited_by_count":110},{"year":2022,"cited_by_count":62},{"year":2021,"cited_by_count":59},{"year":2020,"cited_by_count":60},{"year":2019,"cited_by_count":38},{"year":2018,"cited_by_count":31},{"year":2017,"cited_by_count":21},{"year":2016,"cited_by_count":8},{"year":2015,"cited_by_count":12},{"year":2014,"cited_by_count":9},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":3}],"updated_date":"2026-07-17T09:13:05.818461","created_date":"2025-10-10T00:00:00"}
