{"id":"https://openalex.org/W2136552830","doi":"https://doi.org/10.1145/1739041.1739074","title":"Anchoring millions of distinct reads on the human genome within seconds","display_name":"Anchoring millions of distinct reads on the human genome within seconds","publication_year":2010,"publication_date":"2010-03-16","ids":{"openalex":"https://openalex.org/W2136552830","doi":"https://doi.org/10.1145/1739041.1739074","mag":"2136552830"},"language":"en","primary_location":{"id":"doi:10.1145/1739041.1739074","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1739041.1739074","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 13th International Conference on Extending Database Technology","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"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/A5111979997","display_name":"Toan Huynh","orcid":"https://orcid.org/0000-0002-6455-3056"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Tien Huynh","raw_affiliation_strings":["IBM T.J. Watson Research Center","IBM T.J. Watson research Center"],"affiliations":[{"raw_affiliation_string":"IBM T.J. Watson Research Center","institution_ids":[]},{"raw_affiliation_string":"IBM T.J. Watson research Center","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091785745","display_name":"Michail Vlachos","orcid":"https://orcid.org/0000-0003-1008-5290"},"institutions":[{"id":"https://openalex.org/I4210126328","display_name":"IBM Research - Zurich","ror":"https://ror.org/02js37d36","country_code":"CH","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210126328"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Michail Vlachos","raw_affiliation_strings":["IBM Z\u00fcrich Research Laboratory"],"affiliations":[{"raw_affiliation_string":"IBM Z\u00fcrich Research Laboratory","institution_ids":["https://openalex.org/I4210126328"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054046136","display_name":"Isidore Rigoutsos","orcid":"https://orcid.org/0000-0003-1529-8631"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Isidore Rigoutsos","raw_affiliation_strings":["IBM T.J. Watson Research Center","IBM T.J. Watson research Center"],"affiliations":[{"raw_affiliation_string":"IBM T.J. Watson Research Center","institution_ids":[]},{"raw_affiliation_string":"IBM T.J. Watson research Center","institution_ids":["https://openalex.org/I1341412227"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5111979997"],"corresponding_institution_ids":["https://openalex.org/I1341412227"],"apc_list":null,"apc_paid":null,"fwci":0.1355,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.55124666,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"252","last_page":"262"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9998000264167786,"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":0.9998000264167786,"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":0.995199978351593,"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"}},{"id":"https://openalex.org/T10521","display_name":"RNA and protein synthesis mechanisms","score":0.9918000102043152,"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/computer-science","display_name":"Computer science","score":0.7602656483650208},{"id":"https://openalex.org/keywords/genome","display_name":"Genome","score":0.5706769227981567},{"id":"https://openalex.org/keywords/simd","display_name":"SIMD","score":0.5574249029159546},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.5047093629837036},{"id":"https://openalex.org/keywords/hybrid-genome-assembly","display_name":"Hybrid genome assembly","score":0.41987884044647217},{"id":"https://openalex.org/keywords/reference-genome","display_name":"Reference genome","score":0.4015381336212158},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.3763166666030884},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.37227964401245117},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.22702506184577942},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.18167883157730103},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.11399635672569275}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7602656483650208},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.5706769227981567},{"id":"https://openalex.org/C150552126","wikidata":"https://www.wikidata.org/wiki/Q339387","display_name":"SIMD","level":2,"score":0.5574249029159546},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5047093629837036},{"id":"https://openalex.org/C113425843","wikidata":"https://www.wikidata.org/wiki/Q5953213","display_name":"Hybrid genome assembly","level":5,"score":0.41987884044647217},{"id":"https://openalex.org/C192953774","wikidata":"https://www.wikidata.org/wiki/Q7307127","display_name":"Reference genome","level":4,"score":0.4015381336212158},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.3763166666030884},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.37227964401245117},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.22702506184577942},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.18167883157730103},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.11399635672569275},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1739041.1739074","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1739041.1739074","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 13th International Conference on Extending Database Technology","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.158.9938","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.158.9938","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.ucr.edu/~mvlachos/pubs/edbt2010.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1510641627","https://openalex.org/W1611419331","https://openalex.org/W1974956214","https://openalex.org/W1981509058","https://openalex.org/W1986849101","https://openalex.org/W1995078504","https://openalex.org/W2014829665","https://openalex.org/W2044684763","https://openalex.org/W2051298118","https://openalex.org/W2059099579","https://openalex.org/W2062490063","https://openalex.org/W2067082782","https://openalex.org/W2095674416","https://openalex.org/W2103441770","https://openalex.org/W2105776281","https://openalex.org/W2112113834","https://openalex.org/W2124985265","https://openalex.org/W2127651281","https://openalex.org/W2131106071","https://openalex.org/W2136145671","https://openalex.org/W2139216037","https://openalex.org/W2139760555","https://openalex.org/W2148788068","https://openalex.org/W2150677022","https://openalex.org/W2153010521","https://openalex.org/W2154186552","https://openalex.org/W2160969485","https://openalex.org/W2161315819","https://openalex.org/W2413526056","https://openalex.org/W4248144637","https://openalex.org/W6645515742","https://openalex.org/W6663171665","https://openalex.org/W6842402754"],"related_works":["https://openalex.org/W2291920536","https://openalex.org/W2022397046","https://openalex.org/W2162726111","https://openalex.org/W1603583590","https://openalex.org/W338671845","https://openalex.org/W2063770303","https://openalex.org/W2018511057","https://openalex.org/W2286348849","https://openalex.org/W1587248296","https://openalex.org/W2001175489"],"abstract_inverted_index":{"With":[0],"the":[1,14,25,35,57],"advent":[2],"of":[3,16,27,37,62,75,79,118,125],"next-generation":[4],"DNA":[5,30],"sequencing":[6],"machines,":[7],"there":[8],"is":[9,90],"an":[10],"increasing":[11],"need":[12],"for":[13,51],"development":[15],"computational":[17,87],"tools":[18],"that":[19,113],"can":[20,97,115],"anchor":[21,116],"accurately":[22],"and":[23,48,60,77,86,89],"expediently":[24],"millions":[26,117],"generated":[28],"short":[29,120],"sequences":[31],"(or":[32],"reads)":[33],"onto":[34],"genomes":[36],"target":[38],"organisms.":[39],"In":[40],"this":[41,53],"work,":[42],"we":[43],"describe":[44],"'Q-Pick',":[45],"a":[46,126,132],"new":[47],"efficient":[49],"method":[50],"solving":[52],"problem.":[54],"Q-Pick":[55,81,114],"allows":[56],"rapid":[58],"identification":[59],"anchoring":[61],"such":[63],"reads":[64,121],"with":[65],"possible":[66],"wildcards":[67],"in":[68,129],"large":[69],"genomic":[70],"databases,":[71],"while":[72],"guaranteeing":[73],"completeness":[74],"results":[76],"efficiency":[78],"operation.":[80],"requires":[82],"very":[83],"spartan":[84],"memory":[85],"resources,":[88],"trivially":[91],"amenable":[92],"to":[93,102],"SIMD":[94],"implementation;":[95],"it":[96],"also":[98],"be":[99],"easily":[100],"extended":[101],"handle":[103],"longer":[104],"reads,":[105],"e.g.":[106],"75-mers":[107],"or":[108],"longer.":[109],"Our":[110],"experiments":[111],"indicate":[112],"distinct":[119],"against":[122],"both":[123],"strands":[124],"mammalian":[127],"genome":[128],"seconds,":[130],"using":[131],"single-core":[133],"computer":[134],"processor.":[135]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
