{"id":"https://openalex.org/W2093302730","doi":"https://doi.org/10.1109/iccabs.2014.6863919","title":"In search of perfect reads","display_name":"In search of perfect reads","publication_year":2014,"publication_date":"2014-06-01","ids":{"openalex":"https://openalex.org/W2093302730","doi":"https://doi.org/10.1109/iccabs.2014.6863919","mag":"2093302730"},"language":"en","primary_location":{"id":"doi:10.1109/iccabs.2014.6863919","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccabs.2014.6863919","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE 4th International Conference on Computational Advances in Bio and Medical Sciences (ICCABS)","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/A5086885083","display_name":"Soumitra Pal","orcid":"https://orcid.org/0000-0003-4840-3944"},"institutions":[{"id":"https://openalex.org/I162827531","display_name":"Indian Institute of Technology Bombay","ror":"https://ror.org/02qyf5152","country_code":"IN","type":"education","lineage":["https://openalex.org/I162827531"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Soumitra Pal","raw_affiliation_strings":["Department of Computer Science and Engineering, Indian Institute of Technology Bombay, Powai, Mumbai, India"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Indian Institute of Technology Bombay, Powai, Mumbai, India","institution_ids":["https://openalex.org/I162827531"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074347913","display_name":"Srinivas Aluru","orcid":"https://orcid.org/0000-0003-4279-469X"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]},{"id":"https://openalex.org/I162827531","display_name":"Indian Institute of Technology Bombay","ror":"https://ror.org/02qyf5152","country_code":"IN","type":"education","lineage":["https://openalex.org/I162827531"]}],"countries":["IN","US"],"is_corresponding":false,"raw_author_name":"Srinivas Aluru","raw_affiliation_strings":["Department of Computer Science and Engineering, Indian Institute of Technology Bombay, Powai, Mumbai, India","School of Computational Science and Engineering College of Computing, Georgia Institute of Technology 266 Ferst Drive, Atlanta, GA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Indian Institute of Technology Bombay, Powai, Mumbai, India","institution_ids":["https://openalex.org/I162827531"]},{"raw_affiliation_string":"School of Computational Science and Engineering College of Computing, Georgia Institute of Technology 266 Ferst Drive, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5086885083"],"corresponding_institution_ids":["https://openalex.org/I162827531"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.10346941,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"3","issue":null,"first_page":"1","last_page":"2"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9983999729156494,"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":0.9983999729156494,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9901000261306763,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T11269","display_name":"Algorithms and Data Compression","score":0.9886000156402588,"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/computer-science","display_name":"Computer science","score":0.7073158621788025},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5317721962928772},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5287120938301086},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.5243368744850159},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.516295850276947},{"id":"https://openalex.org/keywords/k-mer","display_name":"k-mer","score":0.5048721432685852},{"id":"https://openalex.org/keywords/hybrid-genome-assembly","display_name":"Hybrid genome assembly","score":0.4953409731388092},{"id":"https://openalex.org/keywords/error-detection-and-correction","display_name":"Error detection and correction","score":0.47744065523147583},{"id":"https://openalex.org/keywords/dna-sequencing","display_name":"DNA sequencing","score":0.37964338064193726},{"id":"https://openalex.org/keywords/reference-genome","display_name":"Reference genome","score":0.30628687143325806},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.1561458706855774},{"id":"https://openalex.org/keywords/dna","display_name":"DNA","score":0.13155853748321533},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.13144704699516296},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.0938778817653656},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08693042397499084},{"id":"https://openalex.org/keywords/wireless","display_name":"Wireless","score":0.08374756574630737}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7073158621788025},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5317721962928772},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5287120938301086},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.5243368744850159},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.516295850276947},{"id":"https://openalex.org/C2279292","wikidata":"https://www.wikidata.org/wiki/Q6322851","display_name":"k-mer","level":4,"score":0.5048721432685852},{"id":"https://openalex.org/C113425843","wikidata":"https://www.wikidata.org/wiki/Q5953213","display_name":"Hybrid genome assembly","level":5,"score":0.4953409731388092},{"id":"https://openalex.org/C103088060","wikidata":"https://www.wikidata.org/wiki/Q1062839","display_name":"Error detection and correction","level":2,"score":0.47744065523147583},{"id":"https://openalex.org/C51679486","wikidata":"https://www.wikidata.org/wiki/Q380546","display_name":"DNA sequencing","level":3,"score":0.37964338064193726},{"id":"https://openalex.org/C192953774","wikidata":"https://www.wikidata.org/wiki/Q7307127","display_name":"Reference genome","level":4,"score":0.30628687143325806},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.1561458706855774},{"id":"https://openalex.org/C552990157","wikidata":"https://www.wikidata.org/wiki/Q7430","display_name":"DNA","level":2,"score":0.13155853748321533},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.13144704699516296},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0938778817653656},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08693042397499084},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.08374756574630737},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iccabs.2014.6863919","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccabs.2014.6863919","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE 4th International Conference on Computational Advances in Bio and Medical Sciences (ICCABS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320320719","display_name":"Department of Science and Technology, Ministry of Science and Technology, India","ror":"https://ror.org/0101xrq71"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W142724965","https://openalex.org/W1980032728","https://openalex.org/W1980667059","https://openalex.org/W2014099509","https://openalex.org/W2096128575","https://openalex.org/W2101250487","https://openalex.org/W2103441770","https://openalex.org/W2119745866","https://openalex.org/W2120076861","https://openalex.org/W2122812051","https://openalex.org/W2142702487","https://openalex.org/W2152246890","https://openalex.org/W2160265768","https://openalex.org/W2160665949","https://openalex.org/W6605867779"],"related_works":["https://openalex.org/W1820394219","https://openalex.org/W220770808","https://openalex.org/W2127768708","https://openalex.org/W2008090296","https://openalex.org/W3013890241","https://openalex.org/W2767590279","https://openalex.org/W3090794301","https://openalex.org/W2887611835","https://openalex.org/W2169178436","https://openalex.org/W4387216472"],"abstract_inverted_index":{"Continued":[0],"advances":[1],"in":[2,35,89],"next":[3],"generation":[4],"short-read":[5],"sequencing":[6],"technologies":[7],"are":[8,31,44,92],"increasing":[9],"throughput":[10],"and":[11,38,69],"read":[12],"lengths,":[13],"while":[14],"driving":[15],"down":[16],"the":[17,29,87,119,146],"error":[18],"rates,":[19],"for":[20,24],"example":[21],"within":[22],"1%":[23],"Illumina":[25],"HiSeq":[26],"reads.":[27,78],"Moreover,":[28],"errors":[30],"not":[32],"uniformly":[33],"distributed":[34],"all":[36],"reads,":[37],"a":[39,67,90],"large":[40],"percentage":[41],"of":[42,60,86,100,142],"reads":[43,52,88,111],"indeed":[45],"error-free.":[46],"Ability":[47],"to":[48,75],"predict":[49],"such":[50],"perfect":[51],"can":[53,136],"have":[54],"significant":[55],"impact":[56],"on":[57,124],"run-time":[58],"complexity":[59],"applications.":[61],"In":[62],"this":[63],"paper,":[64],"we":[65],"present":[66],"simple":[68],"fast":[70],"k-spectrum":[71],"analysis":[72],"based":[73],"method":[74,96,117],"identify":[76],"error-free":[77],"Our":[79],"experiments":[80],"show":[81],"that":[82],"if":[83],"around":[84],"80%":[85],"dataset":[91],"perfect,":[93],"then":[94],"our":[95,116],"retains":[97],"almost":[98],"99.9%":[99],"them":[101],"with":[102],"more":[103],"than":[104],"90%":[105],"precision":[106],"rate.":[107],"Though":[108],"filtering":[109],"out":[110],"identified":[112],"as":[113],"erroneous":[114],"by":[115,121],"reduces":[118],"coverage":[120,127],"about":[122],"7%":[123],"an":[125],"average,":[126],"pattern":[128],"across":[129],"genome":[130],"remains":[131],"similar.":[132],"The":[133],"filtration":[134],"process":[135],"be":[137],"customized":[138],"at":[139],"several":[140],"levels":[141],"stringency":[143],"depending":[144],"upon":[145],"downstream":[147],"application":[148],"need.":[149]},"counts_by_year":[{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
