{"id":"https://openalex.org/W2150356570","doi":"https://doi.org/10.1093/bioinformatics/btq648","title":"Anatomy of a hash-based long read sequence mapping algorithm for next generation DNA sequencing","display_name":"Anatomy of a hash-based long read sequence mapping algorithm for next generation DNA sequencing","publication_year":2010,"publication_date":"2010-11-18","ids":{"openalex":"https://openalex.org/W2150356570","doi":"https://doi.org/10.1093/bioinformatics/btq648","mag":"2150356570"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btq648","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btq648","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/27/2/189/48866960/bioinformatics_27_2_189.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"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://academic.oup.com/bioinformatics/article-pdf/27/2/189/48866960/bioinformatics_27_2_189.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5085992504","display_name":"Sanchit Misra","orcid":"https://orcid.org/0000-0001-7863-858X"},"institutions":[{"id":"https://openalex.org/I111979921","display_name":"Northwestern University","ror":"https://ror.org/000e0be47","country_code":"US","type":"education","lineage":["https://openalex.org/I111979921"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Sanchit Misra","raw_affiliation_strings":["Department of Electrical Engineering and Computer Science, Northwestern University, 2145 Sheridan Road, Evanston, IL 60208, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, Northwestern University, 2145 Sheridan Road, Evanston, IL 60208, USA","institution_ids":["https://openalex.org/I111979921"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004659592","display_name":"Ankit Agrawal","orcid":"https://orcid.org/0000-0002-5519-0302"},"institutions":[{"id":"https://openalex.org/I111979921","display_name":"Northwestern University","ror":"https://ror.org/000e0be47","country_code":"US","type":"education","lineage":["https://openalex.org/I111979921"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ankit Agrawal","raw_affiliation_strings":["Department of Electrical Engineering and Computer Science, Northwestern University, 2145 Sheridan Road, Evanston, IL 60208, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, Northwestern University, 2145 Sheridan Road, Evanston, IL 60208, USA","institution_ids":["https://openalex.org/I111979921"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047602285","display_name":"Wei\u2010keng Liao","orcid":"https://orcid.org/0009-0008-9411-2543"},"institutions":[{"id":"https://openalex.org/I111979921","display_name":"Northwestern University","ror":"https://ror.org/000e0be47","country_code":"US","type":"education","lineage":["https://openalex.org/I111979921"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wei-keng Liao","raw_affiliation_strings":["Department of Electrical Engineering and Computer Science, Northwestern University, 2145 Sheridan Road, Evanston, IL 60208, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, Northwestern University, 2145 Sheridan Road, Evanston, IL 60208, USA","institution_ids":["https://openalex.org/I111979921"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074976770","display_name":"Alok Choudhary","orcid":"https://orcid.org/0000-0001-8152-6319"},"institutions":[{"id":"https://openalex.org/I111979921","display_name":"Northwestern University","ror":"https://ror.org/000e0be47","country_code":"US","type":"education","lineage":["https://openalex.org/I111979921"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alok Choudhary","raw_affiliation_strings":["Department of Electrical Engineering and Computer Science, Northwestern University, 2145 Sheridan Road, Evanston, IL 60208, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, Northwestern University, 2145 Sheridan Road, Evanston, IL 60208, USA","institution_ids":["https://openalex.org/I111979921"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5085992504"],"corresponding_institution_ids":["https://openalex.org/I111979921"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":null,"fwci":1.3554,"has_fulltext":false,"cited_by_count":31,"citation_normalized_percentile":{"value":0.80265219,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"27","issue":"2","first_page":"189","last_page":"195"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9980999827384949,"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":0.9958000183105469,"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/dna-sequencing","display_name":"DNA sequencing","score":0.7013643980026245},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6389191150665283},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.6161525845527649},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.5253120064735413},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5146887898445129},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.4364240765571594},{"id":"https://openalex.org/keywords/dna","display_name":"DNA","score":0.38127899169921875},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.2948760390281677},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.22519969940185547},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.0895136296749115}],"concepts":[{"id":"https://openalex.org/C51679486","wikidata":"https://www.wikidata.org/wiki/Q380546","display_name":"DNA sequencing","level":3,"score":0.7013643980026245},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6389191150665283},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.6161525845527649},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.5253120064735413},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5146887898445129},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.4364240765571594},{"id":"https://openalex.org/C552990157","wikidata":"https://www.wikidata.org/wiki/Q7430","display_name":"DNA","level":2,"score":0.38127899169921875},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.2948760390281677},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.22519969940185547},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0895136296749115}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1093/bioinformatics/btq648","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btq648","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/27/2/189/48866960/bioinformatics_27_2_189.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":"pmh:oai:CiteSeerX.psu:10.1.1.369.8278","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.369.8278","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://users.eecs.northwestern.edu/~choudhar/Publications/AnatomyHashbasedLongReadSeqAlgorithmNextGenDNA.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.591.6097","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.591.6097","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ece.northwestern.edu/~choudhar/Publications/MisAgr10.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.650.9243","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.650.9243","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://cucis.ece.northwestern.edu/publications/pdf/MisAgr11.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.893.8101","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.893.8101","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/27/2/189.full.pdf","raw_type":"text"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btq648","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btq648","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/27/2/189/48866960/bioinformatics_27_2_189.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":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2150356570.pdf","grobid_xml":"https://content.openalex.org/works/W2150356570.grobid-xml"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W1986262731","https://openalex.org/W1998048394","https://openalex.org/W2015292449","https://openalex.org/W2052890777","https://openalex.org/W2055043387","https://openalex.org/W2067474031","https://openalex.org/W2072193858","https://openalex.org/W2074231493","https://openalex.org/W2087064593","https://openalex.org/W2096760403","https://openalex.org/W2103441770","https://openalex.org/W2112113834","https://openalex.org/W2118246164","https://openalex.org/W2124985265","https://openalex.org/W2136145671","https://openalex.org/W2139760555","https://openalex.org/W2142619120","https://openalex.org/W2153527981","https://openalex.org/W2168142506","https://openalex.org/W2230252988","https://openalex.org/W4247053599","https://openalex.org/W4293196852","https://openalex.org/W6689741660","https://openalex.org/W6842402754"],"related_works":["https://openalex.org/W2159024673","https://openalex.org/W3001987467","https://openalex.org/W4252190074","https://openalex.org/W2968165261","https://openalex.org/W1603161560","https://openalex.org/W2154676777","https://openalex.org/W2950663250","https://openalex.org/W2133252868","https://openalex.org/W2151748484","https://openalex.org/W2404914496"],"abstract_inverted_index":{"Abstract":[0],"Motivation:":[1],"Recently,":[2],"a":[3,15,98,114,136],"number":[4],"of":[5,19,148],"programs":[6],"have":[7],"been":[8],"proposed":[9],"for":[10,24,32,43,122,191],"mapping":[11,26,120,150],"short":[12],"reads":[13,44,56,96,125],"to":[14,61,91,97,101,144,166,198],"reference":[16,99],"genome.":[17],"Many":[18],"them":[20,38],"are":[21,29,52,59,69,77,216],"heavily":[22],"optimized":[23],"short-read":[25],"and":[27,57,75,84,135,164,168,176,188,200,206],"hence":[28],"very":[30],"efficient":[31],"shorter":[33],"queries,":[34],"but":[35],"that":[36,126,157],"makes":[37],"inefficient":[39],"or":[40,104],"not":[41],"applicable":[42],"longer":[45,55,123],"than":[46,162,185,204],"200":[47],"bp.":[48],"However,":[49,82],"many":[50],"sequencers":[51],"already":[53],"generating":[54],"more":[58,160],"expected":[60],"follow.":[62],"For":[63,170],"long":[64,94],"read":[65,177],"sequence":[66,119],"mapping,":[67],"there":[68],"limited":[70],"options;":[71],"BLAT,":[72,163,186],"SSAHA2,":[73],"FANGS":[74],"BWA-SW":[76,167,199],"among":[78,141],"the":[79,149,192],"popular":[80],"ones.":[81],"resequencing":[83],"personalized":[85],"medicine":[86],"need":[87],"much":[88],"faster":[89,184,203],"software":[90],"map":[92],"these":[93],"sequencing":[95],"genome":[100],"identify":[102],"SNPs":[103],"rare":[105],"transcripts.":[106],"Results:":[107],"We":[108],"present":[109],"AGILE":[110,158,181,195],"(AliGnIng":[111],"Long":[112],"rEads),":[113],"hash":[115],"table":[116],"based":[117],"high-throughput":[118],"algorithm":[121],"454":[124],"uses":[127],"diagonal":[128],"multiple":[129],"seed-match":[130],"criteria,":[131],"customized":[132],"q-gram":[133],"filtering":[134],"dynamic":[137],"incremental":[138],"search":[139],"approach":[140],"other":[142,193],"heuristics":[143],"optimize":[145],"every":[146],"step":[147],"process.":[151],"In":[152],"our":[153],"experiments,":[154],"we":[155],"observe":[156],"is":[159,182,196],"accurate":[161],"comparable":[165,197],"SSAHA2.":[169,207],"practical":[171],"error":[172],"rates":[173],"(<":[174],"5%)":[175],"lengths":[178],"(200\u20131000":[179],"bp),":[180],"significantly":[183],"SSAHA2":[187],"BWA-SW.":[189],"Even":[190],"cases,":[194],"several":[201],"times":[202],"BLAT":[205],"Availability:":[208],"http://www.ece.northwestern.edu/~smi539/agile.html.":[209],"Contact:":[210],"smi539@eecs.northwestern.edu":[211],"Supplementary":[212,214],"information:":[213],"data":[215],"available":[217],"at":[218],"Bioinformatics":[219],"online.":[220]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":6},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}