{"id":"https://openalex.org/W3213765778","doi":"https://doi.org/10.1109/tcbb.2021.3127879","title":"DiagAF: A More Accurate and Efficient Pre-Alignment Filter for Sequence Alignment","display_name":"DiagAF: A More Accurate and Efficient Pre-Alignment Filter for Sequence Alignment","publication_year":2021,"publication_date":"2021-11-15","ids":{"openalex":"https://openalex.org/W3213765778","doi":"https://doi.org/10.1109/tcbb.2021.3127879","mag":"3213765778","pmid":"https://pubmed.ncbi.nlm.nih.gov/34780330"},"language":"en","primary_location":{"id":"doi:10.1109/tcbb.2021.3127879","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcbb.2021.3127879","pdf_url":null,"source":{"id":"https://openalex.org/S36029991","display_name":"IEEE/ACM Transactions on Computational Biology and Bioinformatics","issn_l":"1545-5963","issn":["1545-5963","1557-9964","2374-0043"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Computational Biology and Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","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/A5102845995","display_name":"Changyong Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Changyong Yu","raw_affiliation_strings":["College of Computer Science and Engineering, Northeastern University, Shenyang, Liaoning, China"],"raw_orcid":"https://orcid.org/0000-0002-2803-4291","affiliations":[{"raw_affiliation_string":"College of Computer Science and Engineering, Northeastern University, Shenyang, Liaoning, China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101620559","display_name":"Yuhai Zhao","orcid":"https://orcid.org/0000-0002-1080-0859"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuhai Zhao","raw_affiliation_strings":["College of Computer Science and Engineering, Northeastern University, Shenyang, Liaoning, China"],"raw_orcid":"https://orcid.org/0000-0002-1080-0859","affiliations":[{"raw_affiliation_string":"College of Computer Science and Engineering, Northeastern University, Shenyang, Liaoning, China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100940341","display_name":"Zhao Chu","orcid":null},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chu Zhao","raw_affiliation_strings":["College of Computer Science and Engineering, Northeastern University, Shenyang, Liaoning, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Engineering, Northeastern University, Shenyang, Liaoning, China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100663827","display_name":"Haitao Ma","orcid":"https://orcid.org/0000-0002-9644-0435"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haitao Ma","raw_affiliation_strings":["College of Computer Science and Engineering, Northeastern University, Shenyang, Liaoning, China"],"raw_orcid":"https://orcid.org/0000-0002-9644-0435","affiliations":[{"raw_affiliation_string":"College of Computer Science and Engineering, Northeastern University, Shenyang, Liaoning, China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054991337","display_name":"Guoren Wang","orcid":"https://orcid.org/0000-0002-0181-8379"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guoren Wang","raw_affiliation_strings":["School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3172,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.56068161,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"19","issue":"6","first_page":"3404","last_page":"3415"},"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/T11269","display_name":"Algorithms and Data Compression","score":0.9976999759674072,"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":0.9926999807357788,"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/sequence","display_name":"Sequence (biology)","score":0.7150065898895264},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6971163749694824},{"id":"https://openalex.org/keywords/hamming-distance","display_name":"Hamming distance","score":0.6922920346260071},{"id":"https://openalex.org/keywords/edit-distance","display_name":"Edit distance","score":0.6290625333786011},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.5695748925209045},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5588372349739075},{"id":"https://openalex.org/keywords/multiple-sequence-alignment","display_name":"Multiple sequence alignment","score":0.5481454133987427},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5281087160110474},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.4789039194583893},{"id":"https://openalex.org/keywords/smith\u2013waterman-algorithm","display_name":"Smith\u2013Waterman algorithm","score":0.4592582583427429},{"id":"https://openalex.org/keywords/sequence-alignment","display_name":"Sequence alignment","score":0.4568851590156555},{"id":"https://openalex.org/keywords/hamming-code","display_name":"Hamming code","score":0.4531753659248352},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4436192512512207},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.11125746369361877},{"id":"https://openalex.org/keywords/block-code","display_name":"Block code","score":0.070392906665802}],"concepts":[{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.7150065898895264},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6971163749694824},{"id":"https://openalex.org/C193319292","wikidata":"https://www.wikidata.org/wiki/Q272172","display_name":"Hamming distance","level":2,"score":0.6922920346260071},{"id":"https://openalex.org/C44359876","wikidata":"https://www.wikidata.org/wiki/Q5338467","display_name":"Edit distance","level":2,"score":0.6290625333786011},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.5695748925209045},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5588372349739075},{"id":"https://openalex.org/C88031987","wikidata":"https://www.wikidata.org/wiki/Q1377767","display_name":"Multiple sequence alignment","level":5,"score":0.5481454133987427},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5281087160110474},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.4789039194583893},{"id":"https://openalex.org/C72802188","wikidata":"https://www.wikidata.org/wiki/Q1683352","display_name":"Smith\u2013Waterman algorithm","level":5,"score":0.4592582583427429},{"id":"https://openalex.org/C45484198","wikidata":"https://www.wikidata.org/wiki/Q827246","display_name":"Sequence alignment","level":4,"score":0.4568851590156555},{"id":"https://openalex.org/C73150493","wikidata":"https://www.wikidata.org/wiki/Q853922","display_name":"Hamming code","level":4,"score":0.4531753659248352},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4436192512512207},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.11125746369361877},{"id":"https://openalex.org/C157125643","wikidata":"https://www.wikidata.org/wiki/Q884707","display_name":"Block code","level":3,"score":0.070392906665802},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C167625842","wikidata":"https://www.wikidata.org/wiki/Q899763","display_name":"Peptide sequence","level":3,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","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":"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":"D023281","descriptor_name":"Genomics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1109/tcbb.2021.3127879","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcbb.2021.3127879","pdf_url":null,"source":{"id":"https://openalex.org/S36029991","display_name":"IEEE/ACM Transactions on Computational Biology and Bioinformatics","issn_l":"1545-5963","issn":["1545-5963","1557-9964","2374-0043"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Computational Biology and Bioinformatics","raw_type":"journal-article"},{"id":"pmid:34780330","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/34780330","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":"IEEE/ACM transactions on computational biology and bioinformatics","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8079908881","display_name":"\u57fa\u4e8e\u9ad8\u9636SNP\u4e92\u4f5c\u6316\u6398\u4e0e\u5206\u6790\u7684\u590d\u6742\u75be\u75c5\u5168\u57fa\u56e0\u7ec4\u5173\u8054\u7814\u7a76","funder_award_id":"61772124","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W14085413","https://openalex.org/W794840634","https://openalex.org/W1498160656","https://openalex.org/W1534435001","https://openalex.org/W1828154403","https://openalex.org/W2005271647","https://openalex.org/W2011652244","https://openalex.org/W2016219933","https://openalex.org/W2025648894","https://openalex.org/W2052601433","https://openalex.org/W2074231493","https://openalex.org/W2075996757","https://openalex.org/W2087064593","https://openalex.org/W2119305840","https://openalex.org/W2121716038","https://openalex.org/W2133687564","https://openalex.org/W2139747296","https://openalex.org/W2146379626","https://openalex.org/W2150356570","https://openalex.org/W2158322625","https://openalex.org/W2166081493","https://openalex.org/W2168544607","https://openalex.org/W2170551349","https://openalex.org/W2560228154","https://openalex.org/W2605348885","https://openalex.org/W2728531063","https://openalex.org/W2793465614","https://openalex.org/W2923143097"],"related_works":["https://openalex.org/W3183986862","https://openalex.org/W2348501199","https://openalex.org/W3000366369","https://openalex.org/W3142260990","https://openalex.org/W88386512","https://openalex.org/W2350395044","https://openalex.org/W2190962063","https://openalex.org/W1975373989","https://openalex.org/W1975635212","https://openalex.org/W3213765778"],"abstract_inverted_index":{"Sequence":[0],"alignment":[1,166],"is":[2],"an":[3],"essential":[4],"step":[5],"in":[6],"computational":[7],"genomics.":[8],"More":[9],"accurate":[10,36],"and":[11,37,79],"efficient":[12,38],"sequence":[13,42,103,165],"pre-alignment":[14,39],"methods":[15,112],"that":[16,155],"run":[17],"before":[18],"conducting":[19],"expensive":[20],"computation":[21],"for":[22,41,114,125],"final":[23],"verification":[24],"are":[25],"still":[26],"urgently":[27],"needed.":[28],"In":[29,128],"this":[30],"article,":[31],"we":[32,131],"propose":[33],"a":[34,49,140],"more":[35],"algorithm":[40,157],"alignment,":[43],"called":[44],"DiagAF.":[45],"Firstly,":[46],"DiagAF":[47,97,118,133,137,156,172],"uses":[48],"new":[50,62],"lower":[51,63],"bound":[52,64],"of":[53,67,87,102,163,171],"edit":[54,88],"distance":[55,89],"based":[56],"on":[57,92],"shift":[58,69,93],"hamming":[59,70,94],"masks.":[60,95],"The":[61,168],"makes":[65],"use":[66,148],"fewer":[68],"masks":[71],"comparing":[72],"with":[73,100,105,122,134],"state-of-the-art":[74,111,135,164],"algorithms":[75],"such":[76],"as":[77],"SHD":[78],"MAGNET.":[80],"Moreover,":[81],"it":[82],"takes":[83],"account":[84],"the":[85,129,161],"information":[86],"path":[90],"exchanging":[91],"Secondly,":[96],"can":[98,119,138,158,173],"deal":[99],"alignments":[101],"pairs":[104],"not":[106],"equal":[107,115],"length,":[108],"rather":[109],"than":[110,145,151],"just":[113],"length.":[116],"Thirdly,":[117],"align":[120],"sequences":[121],"early":[123],"termination":[124],"true":[126],"alignments.":[127],"experiment,":[130],"compared":[132],"methods.":[136],"achieve":[139],"much":[141],"smaller":[142],"error":[143],"rate":[144],"them,":[146],"meanwhile":[147],"less":[149],"time":[150],"them.":[152],"We":[153],"believe":[154],"further":[159],"improve":[160],"performance":[162],"softwares.":[167],"source":[169],"codes":[170],"be":[174],"downloaded":[175],"from":[176],"web":[177],"site":[178],"https://github.com/BioLab-cz/DiagAF.":[179]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
