{"id":"https://openalex.org/W3132276725","doi":null,"title":"Suffix Tree, Minwise Hashing and Streaming Algorithms for Big Data Analysis in Bioinformatics","display_name":"Suffix Tree, Minwise Hashing and Streaming Algorithms for Big Data Analysis in Bioinformatics","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3132276725","mag":"3132276725"},"language":"en","primary_location":{"id":"pmh:oai:digitalcommons.unl.edu:computerscidiss-1227","doi":null,"is_oa":true,"landing_page_url":"https://digitalcommons.unl.edu/computerscidiss/201","pdf_url":"https://digitalcommons.unl.edu/cgi/viewcontent.cgi?article=1227&context=computerscidiss","source":{"id":"https://openalex.org/S4306400577","display_name":"Lincoln (University of Nebraska)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I114395901","host_organization_name":"University of Nebraska\u2013Lincoln","host_organization_lineage":["https://openalex.org/I114395901"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"School of Computing: Dissertations, Theses, and Student Research","raw_type":"text"},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://digitalcommons.unl.edu/cgi/viewcontent.cgi?article=1227&context=computerscidiss","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5011002061","display_name":"Sairam Behera","orcid":"https://orcid.org/0000-0002-9047-0203","observed_orcids":["https://orcid.org/0000-0002-9047-0203"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Sairam Behera","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-9047-0203","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5011002061"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":93},"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/T11269","display_name":"Algorithms and Data Compression","score":0.8817999958992004,"subfield":{"id":"https://openalex.org/subfields/2614","display_name":"Theoretical Computer Science"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.8817999958992004,"subfield":{"id":"https://openalex.org/subfields/2614","display_name":"Theoretical Computer Science"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.10930000245571136,"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/T12946","display_name":"Fractal and DNA sequence analysis","score":0.006200000178068876,"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/suffix-trees","display_name":"suffix trees","score":0.7730000019073486},{"id":"https://openalex.org/keywords/minhash","display_name":"MinHash","score":0.7300000190734863},{"id":"https://openalex.org/keywords/locality-sensitive-hashing","display_name":"locality-sensitive hashing","score":0.9919999837875366},{"id":"https://openalex.org/keywords/streaming-algorithms","display_name":"streaming algorithms","score":0.9470000267028809},{"id":"https://openalex.org/keywords/conserved-non-coding-sequences","display_name":"conserved non-coding elements","score":0.8619999885559082},{"id":"https://openalex.org/keywords/alternative-splicing","display_name":"alternative splicing","score":0.9210000038146973},{"id":"https://openalex.org/keywords/de-novo-transcriptome-assembly","display_name":"de novo transcriptome assembly","score":0.9649999737739563},{"id":"https://openalex.org/keywords/k-mer-indexing","display_name":"k-mer indexing","score":0.5649999976158142}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7023741602897644},{"id":"https://openalex.org/C2779804580","wikidata":"https://www.wikidata.org/wiki/Q102047","display_name":"Suffix","level":2,"score":0.6679724454879761},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.6181818246841431},{"id":"https://openalex.org/C2781166958","wikidata":"https://www.wikidata.org/wiki/Q1426863","display_name":"Suffix tree","level":3,"score":0.5849330425262451},{"id":"https://openalex.org/C118146561","wikidata":"https://www.wikidata.org/wiki/Q5532514","display_name":"Generalized suffix tree","level":4,"score":0.5030328631401062},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.4593297839164734},{"id":"https://openalex.org/C190290938","wikidata":"https://www.wikidata.org/wiki/Q387015","display_name":"Trie","level":3,"score":0.45477789640426636},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.44664886593818665},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.43727314472198486},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3986935615539551},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3902212083339691},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.29598116874694824},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19683855772018433},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.09423947334289551},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:digitalcommons.unl.edu:computerscidiss-1227","doi":null,"is_oa":true,"landing_page_url":"https://digitalcommons.unl.edu/computerscidiss/201","pdf_url":"https://digitalcommons.unl.edu/cgi/viewcontent.cgi?article=1227&context=computerscidiss","source":{"id":"https://openalex.org/S4306400577","display_name":"Lincoln (University of Nebraska)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I114395901","host_organization_name":"University of Nebraska\u2013Lincoln","host_organization_lineage":["https://openalex.org/I114395901"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"School of Computing: Dissertations, Theses, and Student Research","raw_type":"text"},{"id":"pmh:oai:digitalcommons.unl.edu:dissertations-16182","doi":null,"is_oa":false,"landing_page_url":"https://digitalcommons.unl.edu/dissertations/AAI28259457","pdf_url":null,"source":{"id":"https://openalex.org/S4306400577","display_name":"Lincoln (University of Nebraska)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I114395901","host_organization_name":"University of Nebraska\u2013Lincoln","host_organization_lineage":["https://openalex.org/I114395901"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ETD collection for University of Nebraska-Lincoln","raw_type":"text"},{"id":"mag:3132276725","doi":null,"is_oa":false,"landing_page_url":"https://digitalcommons.unl.edu/cgi/viewcontent.cgi?article=1227&context=computerscidiss","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:digitalcommons.unl.edu:computerscidiss-1227","doi":null,"is_oa":true,"landing_page_url":"https://digitalcommons.unl.edu/computerscidiss/201","pdf_url":"https://digitalcommons.unl.edu/cgi/viewcontent.cgi?article=1227&context=computerscidiss","source":{"id":"https://openalex.org/S4306400577","display_name":"Lincoln (University of Nebraska)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I114395901","host_organization_name":"University of Nebraska\u2013Lincoln","host_organization_lineage":["https://openalex.org/I114395901"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"School of Computing: Dissertations, Theses, and Student Research","raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320318803","display_name":"National Rice Research Institute, Indian Council of Agricultural Research","ror":null},{"id":"https://openalex.org/F4320332167","display_name":"Directorate for Biological Sciences","ror":"https://ror.org/001xhss06"},{"id":"https://openalex.org/F4320338283","display_name":"Office of Experimental Program to Stimulate Competitive Research","ror":"https://ror.org/04k9mqs78"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3132276725.pdf","grobid_xml":"https://content.openalex.org/works/W3132276725.grobid-xml"},"referenced_works_count":122,"referenced_works":["https://openalex.org/W1455310343","https://openalex.org/W1502916507","https://openalex.org/W1736726159","https://openalex.org/W1779017450","https://openalex.org/W1785933978","https://openalex.org/W1786896381","https://openalex.org/W1897931464","https://openalex.org/W1965972569","https://openalex.org/W1969435367","https://openalex.org/W1971899779","https://openalex.org/W1983426138","https://openalex.org/W1983924599","https://openalex.org/W1988832105","https://openalex.org/W1990061958","https://openalex.org/W1998117322","https://openalex.org/W2011565693","https://openalex.org/W2011657487","https://openalex.org/W2011920499","https://openalex.org/W2021809202","https://openalex.org/W2022986961","https://openalex.org/W2028384803","https://openalex.org/W2037444377","https://openalex.org/W2041391522","https://openalex.org/W2055043387","https://openalex.org/W2057253402","https://openalex.org/W2060842569","https://openalex.org/W2067786443","https://openalex.org/W2081193615","https://openalex.org/W2092178164","https://openalex.org/W2096128575","https://openalex.org/W2097160089","https://openalex.org/W2101250487","https://openalex.org/W2103126020","https://openalex.org/W2104005232","https://openalex.org/W2104677379","https://openalex.org/W2106184136","https://openalex.org/W2107038793","https://openalex.org/W2107555330","https://openalex.org/W2111307596","https://openalex.org/W2112132489","https://openalex.org/W2114049512","https://openalex.org/W2119312746","https://openalex.org/W2123845384","https://openalex.org/W2125266506","https://openalex.org/W2126419817","https://openalex.org/W2129933858","https://openalex.org/W2131726153","https://openalex.org/W2132799322","https://openalex.org/W2133557974","https://openalex.org/W2134112768","https://openalex.org/W2138615112","https://openalex.org/W2140729960","https://openalex.org/W2141458291","https://openalex.org/W2141978199","https://openalex.org/W2142827025","https://openalex.org/W2143228020","https://openalex.org/W2147717514","https://openalex.org/W2152556446","https://openalex.org/W2153936388","https://openalex.org/W2155628349","https://openalex.org/W2156125289","https://openalex.org/W2157550210","https://openalex.org/W2158714788","https://openalex.org/W2160969485","https://openalex.org/W2161546116","https://openalex.org/W2163584430","https://openalex.org/W2163830511","https://openalex.org/W2166558929","https://openalex.org/W2171003081","https://openalex.org/W2215130704","https://openalex.org/W2319666323","https://openalex.org/W2341599515","https://openalex.org/W2344026279","https://openalex.org/W2405567513","https://openalex.org/W2409002067","https://openalex.org/W2411730464","https://openalex.org/W2463091895","https://openalex.org/W2480204629","https://openalex.org/W2484133401","https://openalex.org/W2498287879","https://openalex.org/W2521310534","https://openalex.org/W2523684193","https://openalex.org/W2529108608","https://openalex.org/W2560164530","https://openalex.org/W2570372911","https://openalex.org/W2574633002","https://openalex.org/W2583363792","https://openalex.org/W2601620797","https://openalex.org/W2624089641","https://openalex.org/W2767310027","https://openalex.org/W2775774997","https://openalex.org/W2808736068","https://openalex.org/W2888692655","https://openalex.org/W2892014603","https://openalex.org/W2899600207","https://openalex.org/W2929062889","https://openalex.org/W2944627925","https://openalex.org/W2949074212","https://openalex.org/W2950150251","https://openalex.org/W2950287694","https://openalex.org/W2950744570","https://openalex.org/W2950954328","https://openalex.org/W2952596684","https://openalex.org/W2952932047","https://openalex.org/W2953174564","https://openalex.org/W2953498134","https://openalex.org/W2963367647","https://openalex.org/W2964849163","https://openalex.org/W2972131171","https://openalex.org/W2982563079","https://openalex.org/W2995527562","https://openalex.org/W3007722513","https://openalex.org/W3010772070","https://openalex.org/W3023137032","https://openalex.org/W3027249069","https://openalex.org/W3033216646","https://openalex.org/W3033999400","https://openalex.org/W3047897736","https://openalex.org/W3099485719","https://openalex.org/W3136290755","https://openalex.org/W3170515990","https://openalex.org/W7097764011"],"related_works":["https://openalex.org/W2888692655","https://openalex.org/W7100921678","https://openalex.org/W4226052879","https://openalex.org/W2756875566","https://openalex.org/W2570372911","https://openalex.org/W282286282","https://openalex.org/W4392272145","https://openalex.org/W7099730034","https://openalex.org/W2182215453","https://openalex.org/W7100522702"],"abstract_inverted_index":{"In":[0,162],"this":[1],"dissertation,":[2],"we":[3,253,271,286],"worked":[4],"on":[5,247,277],"several":[6],"algorithmic":[7],"problems":[8,39],"in":[9,84,160,228],"bioinformatics":[10,86],"using":[11,58,267,281,303],"mainly":[12],"three":[13],"approaches:":[14],"(a)":[15],"a":[16,41,64,75,102,111,273,288],"streaming":[17,32,60],"model,":[18],"(b)":[19],"suffix-tree":[20],"based":[21,246],"indexing,":[22],"and":[23,27,128,187,199,260,332],"(c)":[24],"minwise-hashing":[25],"(minhash)":[26],"locality-sensitive":[28],"hashing":[29],"(LSH).":[30],"The":[31],"models":[33],"are":[34,210],"useful":[35],"for":[36,106,110,150,204,243,293],"large":[37],"data":[38,104],"where":[40],"good":[42],"approximation":[43,55],"needs":[44],"to":[45,62,124,130,172,262,306,328],"be":[46],"achieved":[47],"with":[48,133],"limited":[49],"space":[50],"usage.":[51],"We":[52,93,118],"developed":[53,95,203,287],"an":[54,81,205],"algorithm":[56,193,240],"(KmerEstimate)":[57],"the":[59,68,167,174,213,221,264,294],"approach":[61,147,169,291],"obtain":[63],"better":[65],"estimation":[66],"of":[67,70,77,152],"frequency":[69],"k-mer":[71],"counts.":[72],"A":[73,145],"k-mer,":[74],"subsequence":[76],"length":[78],"k,":[79],"plays":[80],"important":[82],"role":[83],"many":[85],"analyses":[87],"such":[88],"as":[89,323,325],"genome":[90],"distance":[91],"estimation.":[92],"also":[94,178,196],"new":[96,164,192,289],"methods":[97,234],"that":[98,195,300],"use":[99],"suffix":[100],"tree,":[101],"trie":[103],"structure,":[105],"alignment-free,":[107],"non-pairwise":[108],"algorithms":[109,259],"conserved":[112],"non-coding":[113],"sequence":[114],"(CNS)":[115],"identification":[116,151],"problem.":[117,208],"provided":[119],"two":[120],"different":[121,146,229,278],"algorithms:":[122],"STAG-CNS":[123],"identify":[125,131,307],"exact-matched":[126],"CNSs":[127,132,138,154,188],"DiCE":[129],"mismatches.":[134],"Using":[135,177],"our":[136,163],"algorithms,":[137],"among":[139],"various":[140,312],"grass":[141],"species":[142],"were":[143,185,189],"identified.":[144,190],"was":[148,170,202],"employed":[149],"longer":[153],"(\u2265":[155],"100":[156],"bp,":[157],"mostly":[158],"found":[159],"animals).":[161],"method":[165],"(MinCNE),":[166],"minhash":[168,198,250,304],"used":[171],"estimate":[173],"Jaccard":[175],"similarity.":[176],"LSH,":[179],"k-mers":[180],"extracted":[181],"from":[182,212,311],"genomic":[183],"sequences":[184,223,245],"clustered":[186],"Another":[191],"(MinIsoClust)":[194],"uses":[197],"LSH":[200],"techniques":[201],"isoform":[206,222,244],"clustering":[207,233],"Isoforms":[209],"generated":[211],"same":[214],"gene":[215],"but":[216,227],"by":[217],"alternative":[218],"splicing.":[219],"As":[220],"share":[224],"some":[225],"exons":[226],"combinations,":[230],"regular":[231],"sequencing":[232],"do":[235],"not":[236],"work":[237],"well.":[238],"Our":[239],"generates":[241],"clusters":[242],"their":[248],"shared":[249],"signatures.":[251],"Finally,":[252],"discuss":[254],"de":[255,295,313,330],"novo":[256,296,314,331],"transcriptome":[257,279,297,315],"assembly":[258,265,298],"how":[261],"improve":[263],"accuracy":[266],"ensemble":[268,290,333],"approaches.":[269],"First,":[270],"did":[272],"comprehensive":[274],"performance":[275],"analysis":[276],"assemblers":[280],"simulated":[282],"benchmark":[283],"datasets.":[284],"Then,":[285],"(Minsemble)":[292],"problem":[299],"integrates":[301],"isoform-clustering":[302],"technique":[305],"potentially":[308],"correct":[309],"transcripts":[310,322],"assemblers.":[316],"Minsemble":[317],"identified":[318],"more":[319],"correctly":[320],"assembled":[321],"well":[324],"genes":[326],"compared":[327],"other":[329],"methods.":[334]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2021-03-01T00:00:00"}