{"id":"https://openalex.org/W2164661812","doi":"https://doi.org/10.1145/2506583.2506644","title":"Suffix-Tree Based Error Correction of NGS Reads Using Multiple Manifestations of an Error","display_name":"Suffix-Tree Based Error Correction of NGS Reads Using Multiple Manifestations of an Error","publication_year":2013,"publication_date":"2013-09-22","ids":{"openalex":"https://openalex.org/W2164661812","doi":"https://doi.org/10.1145/2506583.2506644","mag":"2164661812"},"language":"en","primary_location":{"id":"doi:10.1145/2506583.2506644","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2506583.2506644","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=2506644&type=pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference on Bioinformatics, Computational Biology and Biomedical Informatics","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"http://dl.acm.org/ft_gateway.cfm?id=2506644&type=pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5062011950","display_name":"Daniel Savel","orcid":"https://orcid.org/0000-0002-5051-7177"},"institutions":[{"id":"https://openalex.org/I58956616","display_name":"Case Western Reserve University","ror":"https://ror.org/051fd9666","country_code":"US","type":"education","lineage":["https://openalex.org/I58956616"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel M. Savel","raw_affiliation_strings":["Electrical Engineering and Computer Science, Case Western Reserve University Cleveland, OH"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electrical Engineering and Computer Science, Case Western Reserve University Cleveland, OH","institution_ids":["https://openalex.org/I58956616"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043924588","display_name":"Thomas LaFramboise","orcid":"https://orcid.org/0000-0003-1793-4777"},"institutions":[{"id":"https://openalex.org/I58956616","display_name":"Case Western Reserve University","ror":"https://ror.org/051fd9666","country_code":"US","type":"education","lineage":["https://openalex.org/I58956616"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Thomas LaFramboise","raw_affiliation_strings":["Genetics and Genome Sciences and Center for Proteomics and Bioinformatics, Case Western Reserve University Cleveland, OH"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Genetics and Genome Sciences and Center for Proteomics and Bioinformatics, Case Western Reserve University Cleveland, OH","institution_ids":["https://openalex.org/I58956616"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019202832","display_name":"Ananth Grama","orcid":"https://orcid.org/0000-0002-9378-9244"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ananth Grama","raw_affiliation_strings":["Dept. of Computer Science, Purdue University, West Lafayette, IN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Computer Science, Purdue University, West Lafayette, IN","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035558591","display_name":"Mehmet Koyut\u00fcrk","orcid":"https://orcid.org/0000-0002-3434-5512"},"institutions":[{"id":"https://openalex.org/I58956616","display_name":"Case Western Reserve University","ror":"https://ror.org/051fd9666","country_code":"US","type":"education","lineage":["https://openalex.org/I58956616"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mehmet Koyut\u00fcrk","raw_affiliation_strings":["Electrical Engineering and Computer Science and Center for Proteomics and Bioinformatics, Case Western Reserve University Cleveland, OH"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electrical Engineering and Computer Science and Center for Proteomics and Bioinformatics, Case Western Reserve University Cleveland, OH","institution_ids":["https://openalex.org/I58956616"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4488,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.66877719,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"351","last_page":"358"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9937000274658203,"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":0.989799976348877,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/substring","display_name":"Substring","score":0.9017906188964844},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.733749508857727},{"id":"https://openalex.org/keywords/suffix-tree","display_name":"Suffix tree","score":0.7126932740211487},{"id":"https://openalex.org/keywords/error-detection-and-correction","display_name":"Error detection and correction","score":0.6509224772453308},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.5507930517196655},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.49431300163269043},{"id":"https://openalex.org/keywords/k-mer","display_name":"k-mer","score":0.4827677309513092},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.4509243667125702},{"id":"https://openalex.org/keywords/trie","display_name":"Trie","score":0.43823856115341187},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.431215763092041},{"id":"https://openalex.org/keywords/generalized-suffix-tree","display_name":"Generalized suffix tree","score":0.420565664768219},{"id":"https://openalex.org/keywords/dna-sequencing","display_name":"DNA sequencing","score":0.2756854295730591},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.23159673810005188},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.228681743144989},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.19780176877975464}],"concepts":[{"id":"https://openalex.org/C182407805","wikidata":"https://www.wikidata.org/wiki/Q2626534","display_name":"Substring","level":3,"score":0.9017906188964844},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.733749508857727},{"id":"https://openalex.org/C2781166958","wikidata":"https://www.wikidata.org/wiki/Q1426863","display_name":"Suffix tree","level":3,"score":0.7126932740211487},{"id":"https://openalex.org/C103088060","wikidata":"https://www.wikidata.org/wiki/Q1062839","display_name":"Error detection and correction","level":2,"score":0.6509224772453308},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.5507930517196655},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.49431300163269043},{"id":"https://openalex.org/C2279292","wikidata":"https://www.wikidata.org/wiki/Q6322851","display_name":"k-mer","level":4,"score":0.4827677309513092},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4509243667125702},{"id":"https://openalex.org/C190290938","wikidata":"https://www.wikidata.org/wiki/Q387015","display_name":"Trie","level":3,"score":0.43823856115341187},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.431215763092041},{"id":"https://openalex.org/C118146561","wikidata":"https://www.wikidata.org/wiki/Q5532514","display_name":"Generalized suffix tree","level":4,"score":0.420565664768219},{"id":"https://openalex.org/C51679486","wikidata":"https://www.wikidata.org/wiki/Q380546","display_name":"DNA sequencing","level":3,"score":0.2756854295730591},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.23159673810005188},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.228681743144989},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19780176877975464},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C552990157","wikidata":"https://www.wikidata.org/wiki/Q7430","display_name":"DNA","level":2,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2506583.2506644","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2506583.2506644","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=2506644&type=pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference on Bioinformatics, Computational Biology and Biomedical Informatics","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/2506583.2506644","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2506583.2506644","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=2506644&type=pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference on Bioinformatics, Computational Biology and Biomedical Informatics","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.5899999737739563,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G4398992664","display_name":null,"funder_award_id":"IIS-0916102","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G555309615","display_name":"III: Small: Computational Infrastructure for the Identification of Copy Number Variations from SNP Microarrays","funder_award_id":"0916102","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G945671693","display_name":"Collaborative Research:   CDI-Type II: Probing Complex Dynamics of Small Interfering RNA (siRNA) Transfection by Petascale Simulations and Network Analysis","funder_award_id":"1124962","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306095","display_name":"American Cancer Society","ror":"https://ror.org/02e463172"},{"id":"https://openalex.org/F4320309036","display_name":"Purdue University","ror":"https://ror.org/02dqehb95"},{"id":"https://openalex.org/F4320310281","display_name":"Case Western Reserve University","ror":"https://ror.org/051fd9666"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2164661812.pdf","grobid_xml":"https://content.openalex.org/works/W2164661812.grobid-xml"},"referenced_works_count":11,"referenced_works":["https://openalex.org/W2061680337","https://openalex.org/W2102532874","https://openalex.org/W2119745866","https://openalex.org/W2122812051","https://openalex.org/W2133956160","https://openalex.org/W2136651963","https://openalex.org/W2142702487","https://openalex.org/W2152246890","https://openalex.org/W2153805608","https://openalex.org/W2157539385","https://openalex.org/W2160969485"],"related_works":["https://openalex.org/W2102450363","https://openalex.org/W2070949798","https://openalex.org/W2032737507","https://openalex.org/W2939624094","https://openalex.org/W2053292606","https://openalex.org/W3119013032","https://openalex.org/W2067956663","https://openalex.org/W2355763156","https://openalex.org/W2411730464","https://openalex.org/W3157818565"],"abstract_inverted_index":{"Next":[0],"Generation":[1],"Sequencing":[2],"(NGS)":[3],"technologies":[4],"produce":[5],"large":[6],"quantities":[7],"of":[8,56,62,64,86,88,133,167,178,199,205],"short":[9],"length":[10],"reads":[11,17,34,114],"with":[12,215],"higher":[13],"error":[14,123,169,187,200],"rates.":[15],"Erroneous":[16],"that":[18,140,211],"cannot":[19],"be":[20,30,78],"aligned,":[21],"are":[22,69],"either":[23],"ignored":[24],"during":[25],"de-novo":[26],"sequencing,":[27],"or":[28,232],"must":[29],"suitably":[31],"corrected.":[32],"Such":[33],"pose":[35],"problems":[36],"for":[37,52,72],"mapping":[38],"as":[39],"well,":[40],"since":[41,75],"it":[42],"is":[43,146,230,234,237],"difficult":[44],"to":[45,80,112,115,148,222],"distinguish":[46],"errors":[47,57,96,184,214],"from":[48],"true":[49],"variants.":[50],"Methods":[51],"detection":[53],"and":[54,82,103,182,218],"correction":[55,118,188,201],"typically":[58],"rely":[59],"on":[60,142,152,202],"frequencies":[61,85],"substrings":[63,87],"the":[65,84,113,117,176,197,203,220,228],"reads.":[66],"Suffix":[67],"trees":[68],"often":[70],"utilized":[71],"this":[73,153],"purpose,":[74],"they":[76,107],"can":[77],"used":[79],"index":[81],"count":[83],"all":[89],"lengths.":[90],"Existing":[91],"suffix-tree":[92],"based":[93],"methods":[94],"detect":[95],"by":[97,164],"identifying":[98],"statistically":[99],"under-represented":[100],"branches":[101],"(suffixes)":[102],"fix":[104],"them.":[105],"However,":[106],"do":[108],"not":[109],"refer":[110],"back":[111],"put":[116],"in":[119,124,180],"context.":[120],"Since":[121],"an":[122,157,168],"a":[125,134,137,171],"single":[126],"read":[127],"manifests":[128],"itself":[129],"at":[130,240],"multiple":[131,144,165],"nodes":[132],"suffix":[135],"tree,":[136],"read-driven":[138],"approach":[139],"relies":[141],"its":[143],"manifestations":[145,166],"expected":[147],"perform":[149],"better.":[150],"Based":[151],"observation,":[154],"we":[155],"develop":[156],"algorithm,":[158],"PLURIBUS,":[159],"which":[160],"reconciles":[161],"corrections":[162],"suggested":[163],"using":[170,190],"voting":[172],"scheme.":[173],"We":[174,194],"compare":[175],"accuracy":[177],"PLURIBUS":[179,212,236],"detecting":[181],"correcting":[183],"against":[185],"existing":[186],"techniques":[189],"simulated":[191],"sequencing":[192],"data.":[193],"also":[195],"assess":[196],"impact":[198],"performance":[204],"sequence":[206],"assembly.":[207],"Our":[208],"results":[209],"show":[210],"corrects":[213],"improved":[216],"precision":[217],"enables":[219],"assembler":[221],"generate":[223],"longer":[224],"contigs,":[225],"particularly":[226],"when":[227],"genome":[229],"longer,":[231],"coverage":[233],"lower.":[235],"freely":[238],"available":[239],"http://compbio.case.edu/pluribus/.":[241]},"counts_by_year":[{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
