{"id":"https://openalex.org/W2950645354","doi":"https://doi.org/10.17615/e5ft-5y97","title":"Mining emerging massive scientific sequence data using block-wise decomposition methods","display_name":"Mining emerging massive scientific sequence data using block-wise decomposition methods","publication_year":2019,"publication_date":"2019-08-13","ids":{"openalex":"https://openalex.org/W2950645354","doi":"https://doi.org/10.17615/e5ft-5y97","mag":"2950645354"},"language":"en","primary_location":{"id":"pmh:oai:cdr.lib.unc.edu:uuid:c5c13eda-230e-4cae-826e-e21af96ae55a","is_oa":true,"landing_page_url":"https://cdr.lib.unc.edu/record/uuid:c5c13eda-230e-4cae-826e-e21af96ae55a","pdf_url":"https://cdr.lib.unc.edu/record/uuid:c5c13eda-230e-4cae-826e-e21af96ae55a","source":{"id":"https://openalex.org/S4306401075","display_name":"Carolina Digital Repository (University of North Carolina at Chapel Hill)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I114027177","host_organization_name":"University of North Carolina at Chapel Hill","host_organization_lineage":["https://openalex.org/I114027177"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},"type":"article","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://cdr.lib.unc.edu/record/uuid:c5c13eda-230e-4cae-826e-e21af96ae55a","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100665641","display_name":"Qi Zhang","orcid":"https://orcid.org/0000-0003-2942-7430"},"institutions":[{"id":"https://openalex.org/I114027177","display_name":"University of North Carolina at Chapel Hill","ror":"https://ror.org/0130frc33","country_code":"US","type":"education","lineage":["https://openalex.org/I114027177"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Zhang, Qi","raw_affiliation_strings":["University of North Carolina at Chapel Hill"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of North Carolina at Chapel Hill","institution_ids":["https://openalex.org/I114027177"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5100665641"],"corresponding_institution_ids":["https://openalex.org/I114027177"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.04374096,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10885","display_name":"Gene expression and cancer classification","score":0.732699990272522,"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/T10885","display_name":"Gene expression and cancer classification","score":0.732699990272522,"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/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.6891000270843506,"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/T14280","display_name":"Big Data Technologies and Applications","score":0.680400013923645,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5658107399940491},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.530551016330719},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.4763343930244446},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4594685733318329},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.22636768221855164},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.12226206064224243},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.10724246501922607}],"concepts":[{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5658107399940491},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.530551016330719},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.4763343930244446},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4594685733318329},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.22636768221855164},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.12226206064224243},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.10724246501922607},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:cdr.lib.unc.edu:uuid:c5c13eda-230e-4cae-826e-e21af96ae55a","is_oa":true,"landing_page_url":"https://cdr.lib.unc.edu/record/uuid:c5c13eda-230e-4cae-826e-e21af96ae55a","pdf_url":"https://cdr.lib.unc.edu/record/uuid:c5c13eda-230e-4cae-826e-e21af96ae55a","source":{"id":"https://openalex.org/S4306401075","display_name":"Carolina Digital Repository (University of North Carolina at Chapel Hill)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I114027177","host_organization_name":"University of North Carolina at Chapel Hill","host_organization_lineage":["https://openalex.org/I114027177"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},{"id":"mag:2950645354","is_oa":false,"landing_page_url":"https://cdr.lib.unc.edu/concern/dissertations/02870w76n","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":null},{"id":"doi:10.17615/e5ft-5y97","is_oa":true,"landing_page_url":"https://doi.org/10.17615/e5ft-5y97","pdf_url":null,"source":{"id":"https://openalex.org/S7407051488","display_name":"UNC Libraries","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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"thesis"}],"best_oa_location":{"id":"pmh:oai:cdr.lib.unc.edu:uuid:c5c13eda-230e-4cae-826e-e21af96ae55a","is_oa":true,"landing_page_url":"https://cdr.lib.unc.edu/record/uuid:c5c13eda-230e-4cae-826e-e21af96ae55a","pdf_url":"https://cdr.lib.unc.edu/record/uuid:c5c13eda-230e-4cae-826e-e21af96ae55a","source":{"id":"https://openalex.org/S4306401075","display_name":"Carolina Digital Repository (University of North Carolina at Chapel Hill)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I114027177","host_organization_name":"University of North Carolina at Chapel Hill","host_organization_lineage":["https://openalex.org/I114027177"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},"sustainable_development_goals":[{"score":0.4300000071525574,"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2950645354.pdf","grobid_xml":"https://content.openalex.org/works/W2950645354.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W633040745","https://openalex.org/W1669021284","https://openalex.org/W1977906644","https://openalex.org/W2752545538","https://openalex.org/W595549847","https://openalex.org/W2106974772","https://openalex.org/W2291955788","https://openalex.org/W1603029321"],"abstract_inverted_index":{"I":[0,105,174,199,279,300],"present":[1,106,280],"efficient":[2,281,302],"data":[3,21,34,61,176,290,311,318],"mining":[4,109,177,284],"algorithms":[5,99,110,180,262,282,303],"for":[6,27,42,65,111,138,252,283,291,314,336],"knowledge":[7,66],"discovery":[8,67],"on":[9,101,229,264,275],"two":[10],"types":[11],"of":[12,49,58,78,90,130,146,152,192,211,232],"emerging":[13],"large-scale":[14,277],"sequence-based":[15],"scientific":[16],"datasets:":[17],"1)":[18],"static":[19],"sequence":[20,33,317],"generated":[22],"from":[23,187,196],"SNP":[24,51,80,124,190],"diversity":[25],"arrays":[26,52,81,125],"genomic":[28],"studies,":[29],"and":[30,38,53,72,82,108,133,140,167,179,237,260,273,287,297,324,330,341],"2)":[31],"dynamic":[32,258,316],"collected":[35,319],"in":[36,117,149,158,245,320],"streaming":[37,83,286,325],"sensor":[39,59,84,288,322],"network":[40,60,289,323],"systems":[41,326],"environmental":[43,298],"studies.":[44,142,170,299],"The":[45],"massive,":[46],"noisy":[47],"nature":[48,57],"the":[50,54,75,79,113,144,188,201,208,219,226,240,253,310,315,321],"distributive,":[55],"online":[56,313],"pose":[62],"challenging":[63],"issues":[64],"such":[68,163,294],"as":[69,88,135,164,216,218,295],"scalability,":[70],"robustness,":[71],"efficiency.":[73],"Despite":[74],"different":[76],"characteristics":[77],"data,":[85],"when":[86],"viewed":[87],"sequences":[89,194],"ordered":[91],"observations,":[92],"both":[93],"can":[94,270],"be":[95],"efficiently":[96,182],"mined":[97],"using":[98,304],"based":[100,263],"block-wise":[102,265,305],"decomposition":[103,266],"methods.":[104],"models":[107,178],"inferring":[112],"genetic":[114,139,147,184],"variation":[115,132,148,185],"structure":[116,186,210,228],"genome-wide":[118,276],"Single-Nucleotide":[119],"Polymorphism":[120],"(SNP)":[121],"arrays.":[122],"Genome-wide":[123],"provide":[126],"a":[127,150,212,230],"comprehensive":[128],"view":[129],"genome":[131],"serve":[134],"powerful":[136],"resources":[137],"biomedical":[141],"Understanding":[143],"patterns":[145,243],"population":[151],"individuals":[153],"plays":[154],"an":[155],"important":[156,250],"role":[157],"solving":[159],"many":[160],"genetics":[161],"problems":[162],"genealogy":[165],"reconstruction":[166],"gene":[168],"association":[169,255],"In":[171],"this":[172],"thesis,":[173],"propose":[175],"to":[181,206,224,308],"infer":[183,207,225],"massive":[189,285],"panels":[191],"recombinant":[193,214,233,246],"resulting":[195],"meiotic":[197],"recombination.":[198],"introduced":[200],"Minimum":[202,220],"Segmentation":[203],"Problem":[204,222],"(MSP)":[205],"segmentation":[209],"single":[213],"strain,":[215],"well":[217],"Mosaic":[221],"(MMP)":[223],"mosaic":[227],"panel":[231],"strains.":[234],"Both":[235],"MSP":[236,272],"MMP":[238,274],"estimate":[239],"ancestral":[241],"polymorphism":[242],"exhibited":[244],"strains":[247],"which":[248,269,333],"provides":[249],"inputs":[251],"subsequent":[254],"analysis.":[256,345],"Efficient":[257],"programming":[259],"graph":[261],"are":[267],"proposed":[268,301],"solve":[271],"panels.":[278],"observational":[292],"sciences":[293],"ecology":[296],"synopsis":[306],"construction":[307],"capture":[309],"distribution":[312],"including":[327],"clustering":[328],"analysis":[329],"order-statistics":[331],"computation,":[332],"is":[334],"critical":[335],"real-time":[337],"monitoring,":[338],"anomaly":[339],"detection,":[340],"other":[342],"domain":[343],"specific":[344]},"counts_by_year":[],"updated_date":"2026-08-04T08:18:43.703281","created_date":"2025-10-10T00:00:00"}