{"id":"https://openalex.org/W2059523992","doi":"https://doi.org/10.1145/2382936.2382985","title":"Alignment seeding strategies using contiguous pyrimidine purine matches","display_name":"Alignment seeding strategies using contiguous pyrimidine purine matches","publication_year":2012,"publication_date":"2012-10-07","ids":{"openalex":"https://openalex.org/W2059523992","doi":"https://doi.org/10.1145/2382936.2382985","mag":"2059523992"},"language":"en","primary_location":{"id":"doi:10.1145/2382936.2382985","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2382936.2382985","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Conference on Bioinformatics, Computational Biology and Biomedicine","raw_type":"proceedings-article"},"type":"conference-paper","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/A5018863394","display_name":"Minmei Hou","orcid":null},"institutions":[{"id":"https://openalex.org/I102502594","display_name":"Northern Illinois University","ror":"https://ror.org/012wxa772","country_code":"US","type":"education","lineage":["https://openalex.org/I102502594"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Minmei Hou","raw_affiliation_strings":["Northern Illinois University, DeKalb, IL","[Northern Illinois University, DeKalb, IL]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northern Illinois University, DeKalb, IL","institution_ids":["https://openalex.org/I102502594"]},{"raw_affiliation_string":"[Northern Illinois University, DeKalb, IL]","institution_ids":["https://openalex.org/I102502594"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012300835","display_name":"Louxin Zhang","orcid":"https://orcid.org/0000-0003-0260-824X"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Louxin Zhang","raw_affiliation_strings":["National University of Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074817739","display_name":"Robert S. Harris","orcid":"https://orcid.org/0000-0001-5464-6892"},"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":"Robert S. Harris","raw_affiliation_strings":["Penn State University, PA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Penn State University, PA","institution_ids":["https://openalex.org/I130769515"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"384","last_page":"391"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9997000098228455,"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":0.9997000098228455,"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/T10434","display_name":"Chromosomal and Genetic Variations","score":0.9972000122070312,"subfield":{"id":"https://openalex.org/subfields/1110","display_name":"Plant Science"},"field":{"id":"https://openalex.org/fields/11","display_name":"Agricultural and Biological Sciences"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10222","display_name":"Genomics and Chromatin Dynamics","score":0.9889000058174133,"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/seeding","display_name":"Seeding","score":0.8180704116821289},{"id":"https://openalex.org/keywords/sensitivity","display_name":"Sensitivity (control systems)","score":0.7274007797241211},{"id":"https://openalex.org/keywords/transversion","display_name":"Transversion","score":0.6862996220588684},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5325020551681519},{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.5266449451446533},{"id":"https://openalex.org/keywords/base","display_name":"Base (topology)","score":0.42733487486839294},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.4259706139564514},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4062117636203766},{"id":"https://openalex.org/keywords/biological-system","display_name":"Biological system","score":0.4052446186542511},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40017077326774597},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3449639081954956},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.30978256464004517},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.30186665058135986},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.20130398869514465},{"id":"https://openalex.org/keywords/agronomy","display_name":"Agronomy","score":0.09734520316123962},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07409694790840149}],"concepts":[{"id":"https://openalex.org/C36248471","wikidata":"https://www.wikidata.org/wiki/Q7445669","display_name":"Seeding","level":2,"score":0.8180704116821289},{"id":"https://openalex.org/C21200559","wikidata":"https://www.wikidata.org/wiki/Q7451068","display_name":"Sensitivity (control systems)","level":2,"score":0.7274007797241211},{"id":"https://openalex.org/C64872895","wikidata":"https://www.wikidata.org/wiki/Q1361360","display_name":"Transversion","level":4,"score":0.6862996220588684},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5325020551681519},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.5266449451446533},{"id":"https://openalex.org/C42058472","wikidata":"https://www.wikidata.org/wiki/Q810214","display_name":"Base (topology)","level":2,"score":0.42733487486839294},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.4259706139564514},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4062117636203766},{"id":"https://openalex.org/C186060115","wikidata":"https://www.wikidata.org/wiki/Q30336093","display_name":"Biological system","level":1,"score":0.4052446186542511},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40017077326774597},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3449639081954956},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.30978256464004517},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.30186665058135986},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.20130398869514465},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.09734520316123962},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07409694790840149},{"id":"https://openalex.org/C24326235","wikidata":"https://www.wikidata.org/wiki/Q126095","display_name":"Electronic engineering","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C501734568","wikidata":"https://www.wikidata.org/wiki/Q42918","display_name":"Mutation","level":3,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2382936.2382985","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2382936.2382985","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Conference on Bioinformatics, Computational Biology and Biomedicine","raw_type":"proceedings-article"},{"id":"pmh:oai:scholarbank.nus.edu.sg:10635/104530","is_oa":false,"landing_page_url":"http://scholarbank.nus.edu.sg/handle/10635/104530","pdf_url":null,"source":{"id":"https://openalex.org/S7407052290","display_name":"National University of Singapore","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Scopus","raw_type":"Conference Paper"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Life in Land","score":0.6200000047683716,"id":"https://metadata.un.org/sdg/15"}],"awards":[{"id":"https://openalex.org/G5728075969","display_name":null,"funder_award_id":"R15 HG005913","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G935780728","display_name":null,"funder_award_id":"R-146-000-134-112","funder_id":"https://openalex.org/F4320320751","funder_display_name":"Ministry of Education - Singapore"}],"funders":[{"id":"https://openalex.org/F4320320751","display_name":"Ministry of Education - Singapore","ror":"https://ror.org/01kcva023"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1487781539","https://openalex.org/W1489596559","https://openalex.org/W1759861793","https://openalex.org/W1786896381","https://openalex.org/W1955121107","https://openalex.org/W1969250533","https://openalex.org/W1972051891","https://openalex.org/W1979713174","https://openalex.org/W1992209615","https://openalex.org/W2043615998","https://openalex.org/W2055043387","https://openalex.org/W2056176729","https://openalex.org/W2056923074","https://openalex.org/W2057998009","https://openalex.org/W2080901145","https://openalex.org/W2128016314","https://openalex.org/W2128591967","https://openalex.org/W2131010376","https://openalex.org/W2139371638","https://openalex.org/W2158714788","https://openalex.org/W3098719287"],"related_works":["https://openalex.org/W2409070081","https://openalex.org/W2052261230","https://openalex.org/W2352942191","https://openalex.org/W2421810400","https://openalex.org/W2390371481","https://openalex.org/W2128377962","https://openalex.org/W2373196487","https://openalex.org/W2013828213","https://openalex.org/W4242422371","https://openalex.org/W1987103269"],"abstract_inverted_index":{"Large-scale":[0],"genomic":[1,78],"pairwise":[2],"aligners":[3],"usually":[4],"start":[5],"with":[6,118],"a":[7,22,26,71,82,102,110,121,238],"seeding":[8,40,83,111,229,259],"procedure,":[9],"which":[10],"scans":[11],"two":[12],"sequences":[13],"to":[14,64,101,137,162,195],"obtain":[15],"base":[16,104,126,139],"matches":[17,117],"(called":[18,25],"hits)":[19],"that":[20,85,113,180],"follow":[21],"certain":[23,122],"pattern":[24,30],"seed).":[27],"The":[28],"seed":[29,152],"and":[31,36,42,48,97,133,177,212,214,224],"size":[32],"determine":[33],"the":[34,39,45,138,158,169,202,205,208,215,227,248],"sensitivity":[35,96,132,147,193],"specificity":[37,68,98,134,188],"of":[38,124,155,160,172,192,217,220,237,241,253],"procedure":[41],"greatly":[43],"affect":[44],"alignment":[46,235],"accuracy":[47],"computational":[49],"efficiency.":[50],"Much":[51],"effort":[52],"has":[53],"been":[54],"focused":[55],"on":[56,168,201],"obtaining":[57],"an":[58,149,196],"optimal":[59,150,197],"(set":[60],"of)":[61],"spaced":[62,151,198,255],"seed(s)":[63],"improve":[65,95],"sensitivity.":[66],"However,":[67],"also":[69,144,246],"becomes":[70],"big":[72],"concern":[73],"when":[74,157],"aligning":[75],"very":[76,186],"long":[77],"sequences.":[79],"We":[80,107],"present":[81,109],"strategy":[84,112],"identifies":[86,114],"contiguous":[87,103,115,125],"pyrimidine":[88],"purine":[89],"(py\u00b7pu)":[90],"matches.":[91,127],"This":[92,128,244],"model":[93,129,183],"may":[94],"simultaneously":[99,135],"compared":[100,136,194],"match":[105,140],"model.":[106,141],"further":[108],"py\u00b7pu":[116],"at":[119],"least":[120],"number":[123],"significantly":[130],"improves":[131],"It":[142],"can":[143,184],"achieve":[145],"better":[146],"than":[148],"without":[153,189],"loss":[154,191],"specificity,":[156],"ratio":[159,209],"transition":[161,211],"transversion":[163],"is":[164],"high.":[165],"Our":[166],"examination":[167],"CFTR":[170],"region":[171],"2M":[173],"bases":[174],"between":[175,210,222],"human":[176,223],"mouse":[178],"shows":[179],"this":[181],"new":[182,228],"have":[185],"high":[187],"much":[190],"seed.":[199],"Based":[200],"characteristics":[203],"(e.g.":[204],"sequence":[206],"similarity,":[207],"transversion,":[213],"lengths":[216],"gapless":[218],"alignments)":[219],"alignments":[221],"other":[225],"mammals,":[226],"strategies":[230],"are":[231],"promising":[232],"in":[233,257],"improving":[234],"quality":[236],"wide":[239],"selection":[240],"species":[242],"pairs.":[243],"paper":[245],"lays":[247],"groundwork":[249],"for":[250],"future":[251],"advancement":[252],"applying":[254],"patterns":[256],"these":[258],"strategies.":[260]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}