{"id":"https://openalex.org/W2104677379","doi":"https://doi.org/10.1093/bioinformatics/btt310","title":"Informed and automated <i>k</i>-mer size selection for genome assembly","display_name":"Informed and automated <i>k</i>-mer size selection for genome assembly","publication_year":2013,"publication_date":"2013-06-03","ids":{"openalex":"https://openalex.org/W2104677379","doi":"https://doi.org/10.1093/bioinformatics/btt310","mag":"2104677379","pmid":"https://pubmed.ncbi.nlm.nih.gov/23732276"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btt310","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btt310","pdf_url":null,"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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5058310668","display_name":"Rayan Chikhi","orcid":"https://orcid.org/0000-0003-1099-8735"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rayan Chikhi","raw_affiliation_strings":["1 Department of Computer Science and Engineering and 2Department of Biochemistry and Molecular Biology, The Pennsylvania State University, University Park, PA 16802, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"1 Department of Computer Science and Engineering and 2Department of Biochemistry and Molecular Biology, The Pennsylvania State University, University Park, PA 16802, USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066909672","display_name":"Paul Medvedev","orcid":"https://orcid.org/0000-0003-3143-594X"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Paul Medvedev","raw_affiliation_strings":["1 Department of Computer Science and Engineering and 2Department of Biochemistry and Molecular Biology, The Pennsylvania State University, University Park, PA 16802, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"1 Department of Computer Science and Engineering and 2Department of Biochemistry and Molecular Biology, The Pennsylvania State University, University Park, PA 16802, USA","institution_ids":["https://openalex.org/I130769515"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5066909672"],"corresponding_institution_ids":["https://openalex.org/I130769515"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":null,"fwci":25.9394,"has_fulltext":false,"cited_by_count":794,"citation_normalized_percentile":{"value":0.99734347,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"30","issue":"1","first_page":"31","last_page":"37"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13664","display_name":"Genome Rearrangement Algorithms","score":0.63919997215271,"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":0.63919997215271,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.3334999978542328,"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/T11287","display_name":"Cancer Genomics and Diagnostics","score":0.00279999990016222,"subfield":{"id":"https://openalex.org/subfields/1306","display_name":"Cancer Research"},"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/computer-science","display_name":"Computer science","score":0.6706609129905701},{"id":"https://openalex.org/keywords/sequence-assembly","display_name":"Sequence assembly","score":0.6263639330863953},{"id":"https://openalex.org/keywords/histogram","display_name":"Histogram","score":0.6190723776817322},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.5499047636985779},{"id":"https://openalex.org/keywords/de-bruijn-graph","display_name":"De Bruijn graph","score":0.4766966998577118},{"id":"https://openalex.org/keywords/k-mer","display_name":"k-mer","score":0.4597395360469818},{"id":"https://openalex.org/keywords/de-bruijn-sequence","display_name":"De Bruijn sequence","score":0.4565929174423218},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4532904624938965},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.42621666193008423},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.41956597566604614},{"id":"https://openalex.org/keywords/genome","display_name":"Genome","score":0.38254278898239136},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.29848378896713257},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.22592341899871826},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.18249592185020447},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17241215705871582},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.09491580724716187},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.08604928851127625},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.0856526792049408}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6706609129905701},{"id":"https://openalex.org/C18949551","wikidata":"https://www.wikidata.org/wiki/Q740578","display_name":"Sequence assembly","level":5,"score":0.6263639330863953},{"id":"https://openalex.org/C53533937","wikidata":"https://www.wikidata.org/wiki/Q185020","display_name":"Histogram","level":3,"score":0.6190723776817322},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.5499047636985779},{"id":"https://openalex.org/C20218877","wikidata":"https://www.wikidata.org/wiki/Q3066095","display_name":"De Bruijn graph","level":3,"score":0.4766966998577118},{"id":"https://openalex.org/C2279292","wikidata":"https://www.wikidata.org/wiki/Q6322851","display_name":"k-mer","level":4,"score":0.4597395360469818},{"id":"https://openalex.org/C170320093","wikidata":"https://www.wikidata.org/wiki/Q1953457","display_name":"De Bruijn sequence","level":2,"score":0.4565929174423218},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4532904624938965},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.42621666193008423},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.41956597566604614},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.38254278898239136},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.29848378896713257},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.22592341899871826},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.18249592185020447},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17241215705871582},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.09491580724716187},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.08604928851127625},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0856526792049408},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0},{"id":"https://openalex.org/C162317418","wikidata":"https://www.wikidata.org/wiki/Q252857","display_name":"Transcriptome","level":4,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C150194340","wikidata":"https://www.wikidata.org/wiki/Q26972","display_name":"Gene expression","level":3,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"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":"D000818","descriptor_name":"Animals","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000818","descriptor_name":"Animals","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000818","descriptor_name":"Animals","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001331","descriptor_name":"Automation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001331","descriptor_name":"Automation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001331","descriptor_name":"Automation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007313","descriptor_name":"Insecta","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007313","descriptor_name":"Insecta","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007313","descriptor_name":"Insecta","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013211","descriptor_name":"Staphylococcus aureus","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013211","descriptor_name":"Staphylococcus aureus","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013211","descriptor_name":"Staphylococcus aureus","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016678","descriptor_name":"Genome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016678","descriptor_name":"Genome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016678","descriptor_name":"Genome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"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":"D059014","descriptor_name":"High-Throughput Nucleotide Sequencing","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D059014","descriptor_name":"High-Throughput Nucleotide Sequencing","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D059014","descriptor_name":"High-Throughput Nucleotide Sequencing","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false}],"locations_count":3,"locations":[{"id":"doi:10.1093/bioinformatics/btt310","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btt310","pdf_url":null,"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:23732276","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/23732276","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:HAL:hal-01477511v1","is_oa":false,"landing_page_url":"https://hal.science/hal-01477511","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":"Bioinformatics, 2013, 30 (1), pp.31 - 37. &#x27E8;10.1093/bioinformatics/btt310&#x27E9;","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":63,"referenced_works":["https://openalex.org/W131256579","https://openalex.org/W1244212151","https://openalex.org/W1506364108","https://openalex.org/W1519039476","https://openalex.org/W1521233004","https://openalex.org/W1546639740","https://openalex.org/W1665727945","https://openalex.org/W1675664170","https://openalex.org/W1738124305","https://openalex.org/W1935763178","https://openalex.org/W1970097261","https://openalex.org/W1987048516","https://openalex.org/W1988123382","https://openalex.org/W1989348205","https://openalex.org/W1999649480","https://openalex.org/W2002115597","https://openalex.org/W2006840986","https://openalex.org/W2009309457","https://openalex.org/W2012912756","https://openalex.org/W2021032815","https://openalex.org/W2022601349","https://openalex.org/W2022634824","https://openalex.org/W2024350113","https://openalex.org/W2034252391","https://openalex.org/W2038028366","https://openalex.org/W2053031122","https://openalex.org/W2057253402","https://openalex.org/W2061338306","https://openalex.org/W2095199125","https://openalex.org/W2096128575","https://openalex.org/W2097382368","https://openalex.org/W2102139220","https://openalex.org/W2102532874","https://openalex.org/W2107772251","https://openalex.org/W2112613953","https://openalex.org/W2113287691","https://openalex.org/W2115501618","https://openalex.org/W2118267499","https://openalex.org/W2120902911","https://openalex.org/W2121876311","https://openalex.org/W2123127913","https://openalex.org/W2127768708","https://openalex.org/W2129933858","https://openalex.org/W2131726153","https://openalex.org/W2132422681","https://openalex.org/W2133956160","https://openalex.org/W2135361281","https://openalex.org/W2136651963","https://openalex.org/W2136845009","https://openalex.org/W2141920662","https://openalex.org/W2144837992","https://openalex.org/W2148698435","https://openalex.org/W2151017710","https://openalex.org/W2151526017","https://openalex.org/W2152075687","https://openalex.org/W2155818894","https://openalex.org/W2156952892","https://openalex.org/W2160770624","https://openalex.org/W2160969485","https://openalex.org/W2166187656","https://openalex.org/W2168531624","https://openalex.org/W2179933869","https://openalex.org/W6679951598"],"related_works":["https://openalex.org/W2120956621","https://openalex.org/W2915362964","https://openalex.org/W3215786367","https://openalex.org/W2991626973","https://openalex.org/W3205360317","https://openalex.org/W4318940746","https://openalex.org/W2562683361","https://openalex.org/W4214573178","https://openalex.org/W4387083702","https://openalex.org/W2133531097"],"abstract_inverted_index":{"MOTIVATION:":[0],"Genome":[1],"assembly":[2],"tools":[3,35],"based":[4],"on":[5,12],"the":[6,40,55,94,104,112,132],"de":[7],"Bruijn":[8],"graph":[9],"framework":[10],"rely":[11],"a":[13,18,32,65,89],"parameter":[14],"k,":[15],"which":[16],"represents":[17],"trade-off":[19],"between":[20],"several":[21,77],"competing":[22],"effects":[23],"that":[24,36,52,71,92,123],"are":[25],"difficult":[26],"to":[27,43,57,102,129],"quantify.":[28],"There":[29],"is":[30,139],"currently":[31],"lack":[33],"of":[34,49,79,108,114,126,131],"would":[37,53],"automatically":[38],"estimate":[39,103],"best":[41,105,133],"k":[42,100,127],"use":[44],"and/or":[45],"quickly":[46],"generate":[47],"histograms":[48,75,97],"k-mer":[50],"abundances":[51],"allow":[54],"user":[56],"make":[58],"an":[59],"informed":[60],"decision.":[61],"RESULTS:":[62],"We":[63,86,110],"develop":[64],"fast":[66,90],"and":[67,121],"accurate":[68],"sampling":[69],"method":[70],"constructs":[72],"approximate":[73],"abundance":[74,96],"with":[76],"orders":[78],"magnitude":[80],"performance":[81],"improvement":[82],"over":[83],"traditional":[84],"methods.":[85],"then":[87],"present":[88],"heuristic":[91],"uses":[93],"generated":[95],"for":[98],"putative":[99],"values":[101],"possible":[106],"value":[107],"k.":[109],"test":[111],"effectiveness":[113],"our":[115],"tool":[116,137],"using":[117],"diverse":[118],"sequencing":[119],"datasets":[120],"find":[122],"its":[124],"choice":[125],"leads":[128],"some":[130],"assemblies.":[134],"AVAILABILITY:":[135],"Our":[136],"KmerGenie":[138],"freely":[140],"available":[141],"at:":[142],"http://kmergenie.bx.psu.edu/.":[143]},"counts_by_year":[{"year":2026,"cited_by_count":24},{"year":2025,"cited_by_count":56},{"year":2024,"cited_by_count":85},{"year":2023,"cited_by_count":64},{"year":2022,"cited_by_count":62},{"year":2021,"cited_by_count":88},{"year":2020,"cited_by_count":65},{"year":2019,"cited_by_count":85},{"year":2018,"cited_by_count":68},{"year":2017,"cited_by_count":74},{"year":2016,"cited_by_count":58},{"year":2015,"cited_by_count":37},{"year":2014,"cited_by_count":25},{"year":2013,"cited_by_count":3}],"updated_date":"2026-07-25T09:21:30.201066","created_date":"2016-06-24T00:00:00"}