{"id":"https://openalex.org/W4401054544","doi":"https://doi.org/10.1142/s0219720024500197","title":"DNA sequences alignment method using sparse index on pan-genome graph","display_name":"DNA sequences alignment method using sparse index on pan-genome graph","publication_year":2024,"publication_date":"2024-07-27","ids":{"openalex":"https://openalex.org/W4401054544","doi":"https://doi.org/10.1142/s0219720024500197","pmid":"https://pubmed.ncbi.nlm.nih.gov/39215522"},"language":"en","primary_location":{"id":"doi:10.1142/s0219720024500197","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0219720024500197","pdf_url":null,"source":{"id":"https://openalex.org/S155349577","display_name":"Journal of Bioinformatics and Computational Biology","issn_l":"0219-7200","issn":["0219-7200","1757-6334"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311754","host_organization_name":"Imperial College Press","host_organization_lineage":["https://openalex.org/P4310311754"],"host_organization_lineage_names":["Imperial College Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Bioinformatics and Computational Biology","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":null,"display_name":"Jia Gao","orcid":"https://orcid.org/0009-0001-1678-9742"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jia Gao","raw_affiliation_strings":["Key Laboratory on High Performance Computing, Anhui Province, P.\u00a0R.\u00a0China","School of Computer Science, University of Science and Technology of China, Heifei, Anhui 230027, P.\u00a0R.\u00a0China"],"raw_orcid":"https://orcid.org/0009-0001-1678-9742","affiliations":[{"raw_affiliation_string":"Key Laboratory on High Performance Computing, Anhui Province, P.\u00a0R.\u00a0China","institution_ids":[]},{"raw_affiliation_string":"School of Computer Science, University of Science and Technology of China, Heifei, Anhui 230027, P.\u00a0R.\u00a0China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002484995","display_name":"Yun Xu","orcid":"https://orcid.org/0009-0003-4850-3299"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yun Xu","raw_affiliation_strings":["Key Laboratory on High Performance Computing, Anhui Province, P.\u00a0R.\u00a0China","School of Computer Science, University of Science and Technology of China, Heifei, Anhui 230027, P.\u00a0R.\u00a0China"],"raw_orcid":"https://orcid.org/0009-0003-4850-3299","affiliations":[{"raw_affiliation_string":"Key Laboratory on High Performance Computing, Anhui Province, P.\u00a0R.\u00a0China","institution_ids":[]},{"raw_affiliation_string":"School of Computer Science, University of Science and Technology of China, Heifei, Anhui 230027, P.\u00a0R.\u00a0China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.09448897,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"22","issue":"04","first_page":"2450019","last_page":"2450019"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9998000264167786,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9995999932289124,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9932000041007996,"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/genome","display_name":"Genome","score":0.575419545173645},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.509912371635437},{"id":"https://openalex.org/keywords/dna","display_name":"DNA","score":0.47895222902297974},{"id":"https://openalex.org/keywords/dna-sequencing","display_name":"DNA sequencing","score":0.4513992369174957},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.3998430073261261},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.3970588743686676},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.36376166343688965},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3323000371456146},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.278805673122406}],"concepts":[{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.575419545173645},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.509912371635437},{"id":"https://openalex.org/C552990157","wikidata":"https://www.wikidata.org/wiki/Q7430","display_name":"DNA","level":2,"score":0.47895222902297974},{"id":"https://openalex.org/C51679486","wikidata":"https://www.wikidata.org/wiki/Q380546","display_name":"DNA sequencing","level":3,"score":0.4513992369174957},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.3998430073261261},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.3970588743686676},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.36376166343688965},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3323000371456146},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.278805673122406}],"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":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","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":false},{"descriptor_ui":"D012984","descriptor_name":"Software","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":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015894","descriptor_name":"Genome, Human","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015894","descriptor_name":"Genome, Human","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015894","descriptor_name":"Genome, Human","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015894","descriptor_name":"Genome, Human","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":true},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":true},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":true},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":true},{"descriptor_ui":"D016678","descriptor_name":"Genome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016678","descriptor_name":"Genome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016678","descriptor_name":"Genome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016678","descriptor_name":"Genome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":true},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":true},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":true},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":true},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1142/s0219720024500197","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0219720024500197","pdf_url":null,"source":{"id":"https://openalex.org/S155349577","display_name":"Journal of Bioinformatics and Computational Biology","issn_l":"0219-7200","issn":["0219-7200","1757-6334"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311754","host_organization_name":"Imperial College Press","host_organization_lineage":["https://openalex.org/P4310311754"],"host_organization_lineage_names":["Imperial College Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Bioinformatics and Computational Biology","raw_type":"journal-article"},{"id":"pmid:39215522","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/39215522","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":"Journal of bioinformatics and computational biology","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2792051891","display_name":null,"funder_award_id":"61672480","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3308391300","display_name":null,"funder_award_id":"BP0719016","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W2011210839","https://openalex.org/W2074229180","https://openalex.org/W2104549677","https://openalex.org/W2129264270","https://openalex.org/W2137351413","https://openalex.org/W2141978199","https://openalex.org/W2144560237","https://openalex.org/W2158322625","https://openalex.org/W2158874082","https://openalex.org/W2344013120","https://openalex.org/W2789843538","https://openalex.org/W2888300707","https://openalex.org/W2964849163","https://openalex.org/W2966459122","https://openalex.org/W3042377559","https://openalex.org/W3043149968","https://openalex.org/W3085875665","https://openalex.org/W3088400220","https://openalex.org/W3092652421","https://openalex.org/W3100935868","https://openalex.org/W3193743296","https://openalex.org/W3202634790","https://openalex.org/W4200597270","https://openalex.org/W4249954951","https://openalex.org/W4255836900"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2086525401","https://openalex.org/W2006735166","https://openalex.org/W2079327011","https://openalex.org/W2053325634","https://openalex.org/W3178279768","https://openalex.org/W193851735","https://openalex.org/W2773861473","https://openalex.org/W1971903861","https://openalex.org/W3156986925"],"abstract_inverted_index":{"The":[0],"graph":[1,49,127],"of":[2,8,29,44,60,82,88,100,108,125,133,151,182],"sequences":[3],"represents":[4],"the":[5,25,40,47,53,80,86,98,113,119,134,139,143,149,171,185],"genetic":[6],"variations":[7],"pan-genome":[9,173],"concisely":[10],"and":[11,56,103,110,128,184],"space-efficiently":[12],"than":[13],"multiple":[14],"linear":[15],"reference":[16,31],"genome.":[17],"In":[18],"order":[19],"to":[20,24,35,51,74,147,168],"accelerate":[21],"aligning":[22,111],"reads":[23],"graph,":[26],"an":[27],"index":[28,54,122,162],"graph-based":[30],"genomes":[32],"is":[33],"used":[34],"obtain":[36],"candidate":[37],"locations.":[38],"However,":[39],"potential":[41],"combinatorial":[42],"explosion":[43],"nodes":[45,124],"on":[46,142],"sequence":[48,126],"leads":[50],"increasing":[52],"space":[55,93,164],"maximum":[57],"memory":[58,115,163],"usage":[59,94],"alignment":[61,89,104,183,187],"process":[62],"considerably,":[63],"especially":[64],"for":[65,170],"large-scale":[66],"datasets.":[67],"For":[68],"this,":[69],"existing":[70],"methods":[71],"typically":[72],"attempt":[73],"prune":[75],"complex":[76],"regions,":[77],"or":[78,179],"extend":[79],"length":[81],"seeds,":[83],"which":[84],"sacrifices":[85],"recall":[87],"algorithm":[90,105],"despite":[91],"reducing":[92],"slightly.":[95],"We":[96],"present":[97],"Sparse-index":[99],"Graph":[101],"(SIG)":[102],"SIG-Aligner,":[106],"capable":[107],"indexing":[109],"at":[112],"lower":[114],"cost.":[116],"SIG":[117,156],"builds":[118],"non-overlapping":[120],"minimizers":[121],"inside":[123],"SIG-Aligner":[129],"filters":[130],"out":[131],"most":[132],"false":[135],"positive":[136],"matches":[137],"by":[138],"method":[140],"based":[141],"pigeonhole":[144],"principle.":[145],"Compared":[146],"Giraffe,":[148],"results":[150],"computational":[152],"experiments":[153],"show":[154],"that":[155],"achieves":[157],"a":[158],"significant":[159],"reduction":[160],"in":[161],"ranging":[165],"from":[166],"50%":[167],"75%":[169],"human":[172],"graphs,":[174],"while":[175],"still":[176],"preserving":[177],"superior":[178],"comparable":[180],"accuracy":[181],"faster":[186],"time.":[188]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
