{"id":"https://openalex.org/W44752627","doi":null,"title":"Utilization of Probabilistic Models in Short Read Assembly from Second-Generation Sequencing","display_name":"Utilization of Probabilistic Models in Short Read Assembly from Second-Generation Sequencing","publication_year":2012,"publication_date":"2012-01-01","ids":{"openalex":"https://openalex.org/W44752627","mag":"44752627"},"language":"en","primary_location":{"id":"pmh:oai:digitalcommons.bucknell.edu:honors_theses-1105","doi":null,"is_oa":true,"landing_page_url":"https://digitalcommons.bucknell.edu/honors_theses/97","pdf_url":"https://digitalcommons.bucknell.edu/honors_theses/97","source":{"id":"https://openalex.org/S4377196650","display_name":"Bucknell Digital Commons (Bucknell University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I131221577","host_organization_name":"Bucknell University","host_organization_lineage":["https://openalex.org/I131221577"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Honors Theses","raw_type":"text"},"volume":null,"type":"dissertation","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://digitalcommons.bucknell.edu/honors_theses/97","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5007166261","display_name":"Matthew W. Segar","orcid":"https://orcid.org/0000-0001-6100-0897","observed_orcids":["https://orcid.org/0000-0001-6100-0897"]},"institutions":[{"id":"https://openalex.org/I131221577","display_name":"Bucknell University","ror":"https://ror.org/00fc1qt65","country_code":"US","type":"education","lineage":["https://openalex.org/I131221577"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Matthew W. Segar","raw_affiliation_strings":["(Bucknell University"],"raw_orcid":"https://orcid.org/0000-0001-6100-0897","affiliations":[{"raw_affiliation_string":"(Bucknell University","institution_ids":["https://openalex.org/I131221577"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5007166261"],"corresponding_institution_ids":["https://openalex.org/I131221577"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9945999979972839,"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":0.9945999979972839,"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":0.002899999963119626,"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/T12946","display_name":"Fractal and DNA sequence analysis","score":0.0005000000237487257,"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-assembly","display_name":"genome assembly","score":0.9089999794960022},{"id":"https://openalex.org/keywords/short-read-sequencing","display_name":"short-read sequencing","score":0.7020000219345093},{"id":"https://openalex.org/keywords/next-generation-sequencing","display_name":"next-generation sequencing","score":0.7820000052452087},{"id":"https://openalex.org/keywords/n-gram-indexing","display_name":"n-gram indexing","score":0.8199999928474426},{"id":"https://openalex.org/keywords/simulated-genomes","display_name":"simulated genomes","score":0.6010000109672546},{"id":"https://openalex.org/keywords/genome-reconstruction","display_name":"genome reconstruction","score":0.4180000126361847}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7136107683181763},{"id":"https://openalex.org/C18949551","wikidata":"https://www.wikidata.org/wiki/Q740578","display_name":"Sequence assembly","level":5,"score":0.6731775999069214},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.6356607675552368},{"id":"https://openalex.org/C2778692605","wikidata":"https://www.wikidata.org/wiki/Q4041866","display_name":"Joins","level":2,"score":0.6235002279281616},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.587178111076355},{"id":"https://openalex.org/C2279292","wikidata":"https://www.wikidata.org/wiki/Q6322851","display_name":"k-mer","level":4,"score":0.5744430422782898},{"id":"https://openalex.org/C113425843","wikidata":"https://www.wikidata.org/wiki/Q5953213","display_name":"Hybrid genome assembly","level":5,"score":0.5579485893249512},{"id":"https://openalex.org/C70712619","wikidata":"https://www.wikidata.org/wiki/Q908889","display_name":"DNA sequencer","level":4,"score":0.4678198993206024},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.4566788077354431},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.4533965587615967},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.44997438788414},{"id":"https://openalex.org/C42058472","wikidata":"https://www.wikidata.org/wiki/Q810214","display_name":"Base (topology)","level":2,"score":0.44995951652526855},{"id":"https://openalex.org/C51679486","wikidata":"https://www.wikidata.org/wiki/Q380546","display_name":"DNA sequencing","level":3,"score":0.4402520954608917},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4167461097240448},{"id":"https://openalex.org/C101985253","wikidata":"https://www.wikidata.org/wiki/Q1073526","display_name":"Shotgun sequencing","level":4,"score":0.3882342576980591},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.3491003215312958},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.34307581186294556},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.19345924258232117},{"id":"https://openalex.org/C552990157","wikidata":"https://www.wikidata.org/wiki/Q7430","display_name":"DNA","level":2,"score":0.1783166527748108},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.17504480481147766},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.15602698922157288},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13488170504570007},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09668320417404175},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.08789166808128357},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08468851447105408},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"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/C150194340","wikidata":"https://www.wikidata.org/wiki/Q26972","display_name":"Gene expression","level":3,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C162317418","wikidata":"https://www.wikidata.org/wiki/Q252857","display_name":"Transcriptome","level":4,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:digitalcommons.bucknell.edu:honors_theses-1105","doi":null,"is_oa":true,"landing_page_url":"https://digitalcommons.bucknell.edu/honors_theses/97","pdf_url":"https://digitalcommons.bucknell.edu/honors_theses/97","source":{"id":"https://openalex.org/S4377196650","display_name":"Bucknell Digital Commons (Bucknell University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I131221577","host_organization_name":"Bucknell University","host_organization_lineage":["https://openalex.org/I131221577"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Honors Theses","raw_type":"text"},{"id":"mag:44752627","doi":null,"is_oa":false,"landing_page_url":"https://eg.bucknell.edu/~brk009/research/papers/2012%20Thesis%20-%20Segar.pdf","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.bucknell.edu:honors_theses-1105","doi":null,"is_oa":true,"landing_page_url":"https://digitalcommons.bucknell.edu/honors_theses/97","pdf_url":"https://digitalcommons.bucknell.edu/honors_theses/97","source":{"id":"https://openalex.org/S4377196650","display_name":"Bucknell Digital Commons (Bucknell University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I131221577","host_organization_name":"Bucknell University","host_organization_lineage":["https://openalex.org/I131221577"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Honors Theses","raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W44752627.pdf","grobid_xml":"https://content.openalex.org/works/W44752627.grobid-xml"},"referenced_works_count":27,"referenced_works":["https://openalex.org/W1585731293","https://openalex.org/W1589943916","https://openalex.org/W1595661905","https://openalex.org/W1961147827","https://openalex.org/W1966822396","https://openalex.org/W1970939265","https://openalex.org/W1972924519","https://openalex.org/W1981194976","https://openalex.org/W2000730583","https://openalex.org/W2016974511","https://openalex.org/W2033083661","https://openalex.org/W2103903744","https://openalex.org/W2108075537","https://openalex.org/W2114133992","https://openalex.org/W2117608012","https://openalex.org/W2136651963","https://openalex.org/W2150575159","https://openalex.org/W2152073175","https://openalex.org/W2159497035","https://openalex.org/W2160969485","https://openalex.org/W2161546116","https://openalex.org/W2161668137","https://openalex.org/W2166265186","https://openalex.org/W3130383601","https://openalex.org/W3145128584","https://openalex.org/W7098838276","https://openalex.org/W7099585975"],"related_works":["https://openalex.org/W2796252340","https://openalex.org/W2152073175","https://openalex.org/W2377861083","https://openalex.org/W1498892184","https://openalex.org/W1539571741","https://openalex.org/W2182176375","https://openalex.org/W2138846808","https://openalex.org/W280975","https://openalex.org/W2157107905","https://openalex.org/W2342125198"],"abstract_inverted_index":{"With":[0],"the":[1,29,64,89,110,126,140],"advent":[2],"of":[3,16,22,48,74,112,134,142],"cheaper":[4],"and":[5,37,62],"faster":[6],"DNA":[7,72],"sequencing":[8],"technologies,":[9],"assembly":[10,111],"methods":[11],"have":[12],"greatly":[13],"changed.":[14],"Instead":[15],"outputting":[17],"reads":[18,49,65,129,146],"that":[19,138],"are":[20,69,79],"thousands":[21],"base":[23,39],"pairs":[24],"long,":[25],"new":[26,136],"sequencers":[27],"parallelize":[28],"task":[30],"by":[31,60],"producing":[32],"read":[33,85,99,156],"lengths":[34,165],"between":[35],"35":[36],"400":[38],"pairs.":[40,100],"Reconstructing":[41],"an":[42,93],"organism\u2019s":[43],"genome":[44],"from":[45,114,166],"these":[46],"millions":[47],"is":[50],"a":[51,105,118,135],"computationally":[52],"expensive":[53],"task.":[54],"Our":[55,101],"algorithm":[56],"solves":[57],"this":[58],"problem":[59],"organizing":[61],"indexing":[63],"using":[66,153],"n-grams,":[67],"which":[68],"short,":[70],"fixed-length":[71],"sequences":[73],"length":[75],"n.":[76],"These":[77],"n-grams":[78],"used":[80],"to":[81,91,124,130,168,173,179,185],"efficiently":[82],"locate":[83],"putative":[84],"joins,":[86],"thereby":[87],"eliminating":[88],"need":[90],"perform":[92],"exhaustive":[94],"search":[95],"over":[96],"all":[97],"possible":[98],"goal":[102],"was":[103,122],"develop":[104],"novel":[106],"n-gram":[107],"method":[108],"for":[109],"genomes":[113,162,183],"next-generation":[115],"sequencers.":[116],"Specifically,":[117],"probabilistic,":[119],"iterative":[120],"approach":[121],"utilized":[123],"determine":[125],"most":[127],"likely":[128],"join":[131],"through":[132],"development":[133],"metric":[137],"models":[139],"probability":[141],"any":[143],"two":[144],"arbitrary":[145],"being":[147],"joined":[148],"together.":[149],"Tests":[150],"were":[151,177],"run":[152],"simulated":[154],"short":[155],"data":[157],"based":[158],"on":[159],"randomly":[160],"created":[161],"ranging":[163],"in":[164,188],"10,000":[167],"100,000":[169,186],"nucleotides":[170,187],"with":[171],"16":[172],"20x":[174],"coverage.":[175],"We":[176],"able":[178],"successfully":[180],"re-assemble":[181],"entire":[182],"up":[184],"length.":[189]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2016-06-24T00:00:00"}