{"id":"https://openalex.org/W3163033414","doi":"https://doi.org/10.1186/s12859-021-04162-z","title":"Accel-Align: a fast sequence mapper and aligner based on the seed\u2013embed\u2013extend method","display_name":"Accel-Align: a fast sequence mapper and aligner based on the seed\u2013embed\u2013extend method","publication_year":2021,"publication_date":"2021-05-20","ids":{"openalex":"https://openalex.org/W3163033414","doi":"https://doi.org/10.1186/s12859-021-04162-z","mag":"3163033414","pmid":"https://pubmed.ncbi.nlm.nih.gov/34016035"},"language":"en","primary_location":{"id":"doi:10.1186/s12859-021-04162-z","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-021-04162-z","pdf_url":"https://bmcbioinformatics.biomedcentral.com/track/pdf/10.1186/s12859-021-04162-z","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"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":"BMC Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://bmcbioinformatics.biomedcentral.com/track/pdf/10.1186/s12859-021-04162-z","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102506791","display_name":"Yiqing Yan","orcid":"https://orcid.org/0000-0003-3062-0019"},"institutions":[{"id":"https://openalex.org/I1902872","display_name":"EURECOM","ror":"https://ror.org/00sse7z02","country_code":"FR","type":"education","lineage":["https://openalex.org/I1902872","https://openalex.org/I205703379"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Yiqing Yan","raw_affiliation_strings":["Data Science Department, EURECOM, 06410, Biot, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Data Science Department, EURECOM, 06410, Biot, France","institution_ids":["https://openalex.org/I1902872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012245890","display_name":"Nimisha Chaturvedi","orcid":"https://orcid.org/0000-0002-3065-0202"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nimisha Chaturvedi","raw_affiliation_strings":["ACCELOM, 06600, Antibes, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ACCELOM, 06600, Antibes, France","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019249875","display_name":"Raja Appuswamy","orcid":"https://orcid.org/0000-0001-5887-4091"},"institutions":[{"id":"https://openalex.org/I1902872","display_name":"EURECOM","ror":"https://ror.org/00sse7z02","country_code":"FR","type":"education","lineage":["https://openalex.org/I1902872","https://openalex.org/I205703379"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Raja Appuswamy","raw_affiliation_strings":["Data Science Department, EURECOM, 06410, Biot, France. raja.appuswamy@eurecom.fr","Data Science Department, EURECOM, 06410, Biot, France"],"raw_orcid":"https://orcid.org/0000-0001-5887-4091","affiliations":[{"raw_affiliation_string":"Data Science Department, EURECOM, 06410, Biot, France. raja.appuswamy@eurecom.fr","institution_ids":["https://openalex.org/I1902872"]},{"raw_affiliation_string":"Data Science Department, EURECOM, 06410, Biot, France","institution_ids":["https://openalex.org/I1902872"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5102506791"],"corresponding_institution_ids":["https://openalex.org/I1902872"],"apc_list":{"value":1690,"currency":"GBP","value_usd":2072},"apc_paid":{"value":1790,"currency":"EUR","value_usd":1930},"fwci":1.3029,"has_fulltext":true,"cited_by_count":21,"citation_normalized_percentile":{"value":0.79753437,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"22","issue":"1","first_page":"257","last_page":"257"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9221000075340271,"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":0.9221000075340271,"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/T13664","display_name":"Genome Rearrangement Algorithms","score":0.025800000876188278,"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/T12292","display_name":"Graph Theory and Algorithms","score":0.008999999612569809,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/computer-science","display_name":"Computer science","score":0.7790030241012573},{"id":"https://openalex.org/keywords/edit-distance","display_name":"Edit distance","score":0.7783952951431274},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.5754184126853943},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.4744911193847656},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4511718153953552},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.4460325837135315},{"id":"https://openalex.org/keywords/hamming-distance","display_name":"Hamming distance","score":0.4413597881793976},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.4228288233280182},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.41514450311660767},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.24267488718032837}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7790030241012573},{"id":"https://openalex.org/C44359876","wikidata":"https://www.wikidata.org/wiki/Q5338467","display_name":"Edit distance","level":2,"score":0.7783952951431274},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.5754184126853943},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.4744911193847656},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4511718153953552},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.4460325837135315},{"id":"https://openalex.org/C193319292","wikidata":"https://www.wikidata.org/wiki/Q272172","display_name":"Hamming distance","level":2,"score":0.4413597881793976},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.4228288233280182},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.41514450311660767},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.24267488718032837},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","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":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D059014","descriptor_name":"High-Throughput Nucleotide Sequencing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D059014","descriptor_name":"High-Throughput Nucleotide Sequencing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D059014","descriptor_name":"High-Throughput Nucleotide Sequencing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":4,"locations":[{"id":"doi:10.1186/s12859-021-04162-z","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-021-04162-z","pdf_url":"https://bmcbioinformatics.biomedcentral.com/track/pdf/10.1186/s12859-021-04162-z","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"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":"BMC Bioinformatics","raw_type":"journal-article"},{"id":"pmid:34016035","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/34016035","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":"BMC bioinformatics","raw_type":null},{"id":"pmh:oai:doaj.org/article:db6fb83f6d0344df8c0598c147a89165","is_oa":true,"landing_page_url":"https://doaj.org/article/db6fb83f6d0344df8c0598c147a89165","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":"BMC Bioinformatics, Vol 22, Iss 1, Pp 1-20 (2021)","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:8139006","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/8139006","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Bioinformatics","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1186/s12859-021-04162-z","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-021-04162-z","pdf_url":"https://bmcbioinformatics.biomedcentral.com/track/pdf/10.1186/s12859-021-04162-z","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"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":"BMC Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.5099999904632568,"display_name":"Industry, innovation and infrastructure"}],"awards":[{"id":"https://openalex.org/G235733448","display_name":"Oligoarchive - Intelligent DNA Storage for Archival","funder_award_id":"863320","funder_id":"https://openalex.org/F4320338336","funder_display_name":"H2020 Future and Emerging Technologies"},{"id":"https://openalex.org/G6541035449","display_name":"Oligoarchive - Intelligent DNA Storage for Archival","funder_award_id":"863320","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G7842005466","display_name":null,"funder_award_id":"Horizon 2020","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320338336","display_name":"H2020 Future and Emerging Technologies","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3163033414.pdf","grobid_xml":"https://content.openalex.org/works/W3163033414.grobid-xml"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W26356079","https://openalex.org/W794840634","https://openalex.org/W1828154403","https://openalex.org/W2055693471","https://openalex.org/W2095680943","https://openalex.org/W2110905563","https://openalex.org/W2121716038","https://openalex.org/W2128591967","https://openalex.org/W2143788241","https://openalex.org/W2144560237","https://openalex.org/W2162758337","https://openalex.org/W2168133698","https://openalex.org/W2170551349","https://openalex.org/W2416529140","https://openalex.org/W2526975281","https://openalex.org/W2585199909","https://openalex.org/W2766890412","https://openalex.org/W2784788330","https://openalex.org/W2788876413","https://openalex.org/W2789843538","https://openalex.org/W2887199083","https://openalex.org/W2923143097","https://openalex.org/W2949462305","https://openalex.org/W2950294163","https://openalex.org/W3003533349","https://openalex.org/W3086678357","https://openalex.org/W3103269557","https://openalex.org/W4254172385","https://openalex.org/W6600291067"],"related_works":["https://openalex.org/W1494289317","https://openalex.org/W1531307672","https://openalex.org/W2611868502","https://openalex.org/W2416529140","https://openalex.org/W2180288160","https://openalex.org/W2165259681","https://openalex.org/W162676011","https://openalex.org/W2612888708","https://openalex.org/W2888987343","https://openalex.org/W2140783370"],"abstract_inverted_index":{"BACKGROUND:":[0],"Improvements":[1],"in":[2,76,149,218],"sequencing":[3,8,183],"technology":[4],"continue":[5,185],"to":[6,18,27,53,120,139,186],"drive":[7],"cost":[9],"towards":[10],"$100":[11],"per":[12],"genome.":[13],"However,":[14,61],"mapping":[15],"sequenced":[16],"data":[17],"a":[19,23,83,128,222],"reference":[20,114],"genome":[21],"remains":[22],"computationally-intensive":[24],"task":[25],"due":[26],"the":[28,55,111,121,136,215],"dependence":[29],"on":[30,50,95,102,170],"edit":[31,58,117,212],"distance":[32,59,118,134],"for":[33,86,204,231],"dealing":[34],"with":[35],"INDELs":[36],"and":[37,48,90,113,131,159,193,240],"mismatches":[38],"introduced":[39],"by":[40,73,124,210],"sequencing.":[41],"All":[42],"modern":[43],"aligners":[44,169],"use":[45],"seed-filter-extend":[46],"methodology":[47,85],"rely":[49],"filtration":[51],"heuristics":[52],"reduce":[54],"overhead":[56],"of":[57],"computation.":[60],"filtering":[62],"has":[63],"inherent":[64],"performance-accuracy":[65],"trade-offs":[66],"that":[67,145,161,197,206],"limits":[68],"its":[69],"effectiveness.":[70],"RESULTS:":[71],"Motivated":[72],"algorithmic":[74],"advances":[75],"randomized":[77,129,198],"low-distortion":[78],"embedding,":[79],"we":[80,151,195],"introduce":[81],"SEE,":[82],"new":[84,202],"developing":[87],"sequence":[88,157,238,241],"mappers":[89],"aligners.":[91],"While":[92],"SFE":[93],"focuses":[94,100],"eliminating":[96],"sub-optimal":[97],"candidates,":[98],"SEE":[99,109,146],"instead":[101],"identifying":[103],"optimal":[104,141],"candidates.":[105,142],"To":[106,143],"do":[107],"so,":[108],"transforms":[110],"read":[112,188],"strings":[115],"from":[116],"regime":[119,123],"Hamming":[122,133],"embedding":[125],"them":[126],"using":[127,211],"algorithm,":[130],"uses":[132],"over":[135],"embedded":[137],"set":[138],"identify":[140],"show":[144],"performs":[147],"well":[148],"practice,":[150],"present":[152],"Accel-Align":[153],"an":[154],"SEE-based":[155],"short-read":[156],"mapper":[158],"aligner":[160],"is":[162],"3-12[Formula:":[163],"see":[164],"text]":[165],"faster":[166],"than":[167],"state-of-the-art":[168],"commodity":[171],"CPUs,":[172],"without":[173],"any":[174],"special-purpose":[175],"hardware,":[176],"while":[177,190],"providing":[178],"comparable":[179],"accuracy.":[180],"CONCLUSIONS:":[181],"As":[182],"technologies":[184],"increase":[187],"length":[189],"improving":[191],"throughput":[192],"accuracy,":[194],"believe":[196],"embeddings":[199],"open":[200],"up":[201],"avenues":[203],"optimization":[205],"cannot":[207],"be":[208,229],"achieved":[209],"distance.":[213],"Thus,":[214],"techniques":[216],"presented":[217],"this":[219],"paper":[220],"have":[221],"much":[223],"broader":[224],"scope":[225],"as":[226],"they":[227],"can":[228],"used":[230],"other":[232],"applications":[233],"like":[234],"graph":[235],"alignment,":[236,239],"multiple":[237],"assembly.":[242]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":2}],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2025-10-10T00:00:00"}