{"id":"https://openalex.org/W1965687515","doi":"https://doi.org/10.1109/bibmw.2012.6470222","title":"A meta-genome sequencing and assembly preprocessing algorithm inspired by restriction site base composition","display_name":"A meta-genome sequencing and assembly preprocessing algorithm inspired by restriction site base composition","publication_year":2012,"publication_date":"2012-10-01","ids":{"openalex":"https://openalex.org/W1965687515","doi":"https://doi.org/10.1109/bibmw.2012.6470222","mag":"1965687515"},"language":"en","primary_location":{"id":"doi:10.1109/bibmw.2012.6470222","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibmw.2012.6470222","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE International Conference on Bioinformatics and Biomedicine Workshops","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"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/A5028954340","display_name":"Oliver Bonham-Carter","orcid":"https://orcid.org/0000-0001-9032-0398"},"institutions":[{"id":"https://openalex.org/I2802450327","display_name":"University of Nebraska System","ror":"https://ror.org/0238rvs44","country_code":"US","type":"education","lineage":["https://openalex.org/I2802450327"]},{"id":"https://openalex.org/I122266389","display_name":"University of Nebraska at Omaha","ror":"https://ror.org/04yrkc140","country_code":"US","type":"education","lineage":["https://openalex.org/I122266389"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Oliver Bonham-Carter","raw_affiliation_strings":["University of Nebraska System, Lincoln, NE, US","College of Information Science & Technology, School of Interdisciplinary Informatics, Peter Kiewit Institute, University of Nebraska, Omaha, NE USA#TAB#"],"affiliations":[{"raw_affiliation_string":"University of Nebraska System, Lincoln, NE, US","institution_ids":["https://openalex.org/I2802450327"]},{"raw_affiliation_string":"College of Information Science & Technology, School of Interdisciplinary Informatics, Peter Kiewit Institute, University of Nebraska, Omaha, NE USA#TAB#","institution_ids":["https://openalex.org/I122266389"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047703641","display_name":"Hesham Ali","orcid":"https://orcid.org/0000-0001-6675-7987"},"institutions":[{"id":"https://openalex.org/I122266389","display_name":"University of Nebraska at Omaha","ror":"https://ror.org/04yrkc140","country_code":"US","type":"education","lineage":["https://openalex.org/I122266389"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hesham Ali","raw_affiliation_strings":["College of Information Science & Technology, University of Nebraska, Omaha, NE, USA","College of Information Science & Technology, School of Interdisciplinary Informatics, Peter Kiewit Institute, University of Nebraska, Omaha, NE USA#TAB#"],"affiliations":[{"raw_affiliation_string":"College of Information Science & Technology, University of Nebraska, Omaha, NE, USA","institution_ids":["https://openalex.org/I122266389"]},{"raw_affiliation_string":"College of Information Science & Technology, School of Interdisciplinary Informatics, Peter Kiewit Institute, University of Nebraska, Omaha, NE USA#TAB#","institution_ids":["https://openalex.org/I122266389"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036016911","display_name":"Dhundy Bastola","orcid":"https://orcid.org/0000-0003-1128-4451"},"institutions":[{"id":"https://openalex.org/I122266389","display_name":"University of Nebraska at Omaha","ror":"https://ror.org/04yrkc140","country_code":"US","type":"education","lineage":["https://openalex.org/I122266389"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dhundy Bastola","raw_affiliation_strings":["College of Information Science & Technology, University of Nebraska, Omaha, NE, USA","College of Information Science & Technology, School of Interdisciplinary Informatics, Peter Kiewit Institute, University of Nebraska, Omaha, NE USA#TAB#"],"affiliations":[{"raw_affiliation_string":"College of Information Science & Technology, University of Nebraska, Omaha, NE, USA","institution_ids":["https://openalex.org/I122266389"]},{"raw_affiliation_string":"College of Information Science & Technology, School of Interdisciplinary Informatics, Peter Kiewit Institute, University of Nebraska, Omaha, NE USA#TAB#","institution_ids":["https://openalex.org/I122266389"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5028954340"],"corresponding_institution_ids":["https://openalex.org/I122266389","https://openalex.org/I2802450327"],"apc_list":null,"apc_paid":null,"fwci":0.6567,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.665613,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"25","issue":null,"first_page":"696","last_page":"703"},"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/T13326","display_name":"Biochemical and Structural Characterization","score":0.9934999942779541,"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/T10521","display_name":"RNA and protein synthesis mechanisms","score":0.9919000267982483,"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/contig","display_name":"Contig","score":0.9146387577056885},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.671367883682251},{"id":"https://openalex.org/keywords/genome","display_name":"Genome","score":0.6032773852348328},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5479850172996521},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.4682508707046509},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.46064454317092896},{"id":"https://openalex.org/keywords/dna-sequencing","display_name":"DNA sequencing","score":0.424153208732605},{"id":"https://openalex.org/keywords/sequence-assembly","display_name":"Sequence assembly","score":0.41841191053390503},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.34653377532958984},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.28304582834243774},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.22339856624603271},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.09758168458938599}],"concepts":[{"id":"https://openalex.org/C59582021","wikidata":"https://www.wikidata.org/wiki/Q1128751","display_name":"Contig","level":4,"score":0.9146387577056885},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.671367883682251},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.6032773852348328},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5479850172996521},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.4682508707046509},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.46064454317092896},{"id":"https://openalex.org/C51679486","wikidata":"https://www.wikidata.org/wiki/Q380546","display_name":"DNA sequencing","level":3,"score":0.424153208732605},{"id":"https://openalex.org/C18949551","wikidata":"https://www.wikidata.org/wiki/Q740578","display_name":"Sequence assembly","level":5,"score":0.41841191053390503},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.34653377532958984},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.28304582834243774},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.22339856624603271},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.09758168458938599},{"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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":1,"locations":[{"id":"doi:10.1109/bibmw.2012.6470222","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibmw.2012.6470222","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE International Conference on Bioinformatics and Biomedicine Workshops","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320337354","display_name":"National Institute of General Medical Sciences","ror":"https://ror.org/04q48ey07"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1968613135","https://openalex.org/W1982827785","https://openalex.org/W2005129098","https://openalex.org/W2048818637","https://openalex.org/W2052903982","https://openalex.org/W2075970797","https://openalex.org/W2092277118","https://openalex.org/W2096717068","https://openalex.org/W2097766704","https://openalex.org/W2099533874","https://openalex.org/W2114907886","https://openalex.org/W2115622704","https://openalex.org/W2127230663","https://openalex.org/W2143063533","https://openalex.org/W2160525528","https://openalex.org/W2161546116","https://openalex.org/W2165460636","https://openalex.org/W2167719367","https://openalex.org/W6674999361"],"related_works":["https://openalex.org/W2089480001","https://openalex.org/W2885619582","https://openalex.org/W3167837387","https://openalex.org/W54719527","https://openalex.org/W4250462852","https://openalex.org/W2060480089","https://openalex.org/W2993223466","https://openalex.org/W2944010518","https://openalex.org/W4381279187","https://openalex.org/W2013063066"],"abstract_inverted_index":{"Motivation:":[0],"In":[1,137,177],"meta-genome":[2,109,242],"sequencing":[3,110,243],"and":[4,30,84,111,122,233,244],"assembly":[5,112,245],"projects,":[6],"where":[7],"there":[8],"are":[9,144],"different":[10,25,97,146,169,172],"types":[11],"of":[12,22,54,59,66,128,154,184,201,215,228],"contigs":[13,40,76,95,130,218],"mixed":[14],"together":[15],"in":[16,93,241],"a":[17,28,52,108,185,226,231,238],"single":[18],"pool,":[19],"the":[20,39,56,75,126,129,155,182,196,205],"task":[21],"assembling":[23],"its":[24],"organisms":[26,121],"is":[27,34,117,189,208],"complex":[29],"challenging":[31],"problem.":[32],"It":[33],"therefore":[35],"desirable":[36],"to":[37,48,63,70,87,119,123,174,191,219],"sort":[38],"by":[41,147],"origins":[42],"into":[43],"separate":[44],"bins":[45],"from":[46,77,96,134],"which":[47,68,131,160,188],"work.":[49],"We":[50,80,99],"propose":[51],"framework":[53,103],"using":[55],"base":[57],"compositions":[58],"bacterial":[60],"restriction":[61,164],"sites":[62],"generate":[64],"sets":[65,83,170],"motifs":[67],"work":[69],"differentiate":[71,120],"organismal":[72],"groups,":[73],"including":[74],"those":[78],"groups.":[79],"introduce":[81],"spectrum":[82,158,186],"show":[85,140,167,180],"how":[86],"strategically":[88],"select":[89],"them":[90],"for":[91,230,237],"use":[92],"binning":[94],"organisms.":[98],"suggest":[100],"that":[101,141,168,181],"this":[102],"can":[104],"save":[105],"time":[106],"during":[107],"project.":[113],"Results:":[114],"Our":[115],"method":[116,236],"able":[118],"successfully":[124],"determine":[125],"association":[127],"were":[132],"derived":[133],"an":[135],"organism.":[136],"particular,":[138],"we":[139,166,179],"two":[142],"genera":[143],"fundamentally":[145],"analyzing":[148],"their":[149],"motif":[150],"proportions.":[151],"Using":[152,212],"one":[153,192],"four":[156],"total":[157],"sets,":[159],"encompass":[161],"all":[162],"known":[163],"sites,":[165],"have":[171],"abilities":[173],"distinguish":[175],"sequences.":[176],"addition,":[178],"selection":[183],"set":[187],"relevant":[190],"organism,":[193],"but":[194],"not":[195],"other,":[197],"greatly":[198],"improves":[199],"performance":[200],"differentiation,":[202],"even":[203],"when":[204],"contig":[206],"size":[207],"short":[209],"(1000bps).":[210],"Conclusions:":[211],"ten":[213],"trials":[214],"newly":[216],"selected":[217],"confirm":[220],"our":[221,223],"premise,":[222],"study":[224],"provides":[225],"proof":[227],"concept":[229],"novel":[232],"computationally":[234],"effective":[235],"preprocessing":[239],"step":[240],"tasks.":[246]},"counts_by_year":[{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
