{"id":"https://openalex.org/W2024112220","doi":"https://doi.org/10.1109/gensips.2011.6169487","title":"Minimum description length based selection of reference sequences for comparative assemblers","display_name":"Minimum description length based selection of reference sequences for comparative assemblers","publication_year":2011,"publication_date":"2011-12-01","ids":{"openalex":"https://openalex.org/W2024112220","doi":"https://doi.org/10.1109/gensips.2011.6169487","mag":"2024112220"},"language":"en","primary_location":{"id":"doi:10.1109/gensips.2011.6169487","is_oa":false,"landing_page_url":"https://doi.org/10.1109/gensips.2011.6169487","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Workshop on Genomic Signal Processing and Statistics (GENSIPS)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5051600305","display_name":"Bilal Wajid","orcid":"https://orcid.org/0000-0003-0220-7788"},"institutions":[{"id":"https://openalex.org/I142732210","display_name":"University of Engineering and Technology Lahore","ror":"https://ror.org/0051w2v06","country_code":"PK","type":"education","lineage":["https://openalex.org/I142732210"]}],"countries":["PK"],"is_corresponding":false,"raw_author_name":"Bilal Wajid","raw_affiliation_strings":["University of Engineering and Technology Lahore, Lahore, Pakistan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Engineering and Technology Lahore, Lahore, Pakistan","institution_ids":["https://openalex.org/I142732210"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034213361","display_name":"Erchin Serpedin","orcid":"https://orcid.org/0000-0001-9069-770X"},"institutions":[{"id":"https://openalex.org/I91045830","display_name":"Texas A&M University","ror":"https://ror.org/01f5ytq51","country_code":"US","type":"education","lineage":["https://openalex.org/I91045830"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Erchin Serpedin","raw_affiliation_strings":["Texas A&M University, College Station, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Texas A&M University, College Station, United States","institution_ids":["https://openalex.org/I91045830"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.9765,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.92854259,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"230","last_page":"233"},"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":0.9987999796867371,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9968000054359436,"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/minimum-description-length","display_name":"Minimum description length","score":0.8273370265960693},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.6711978316307068},{"id":"https://openalex.org/keywords/reference-genome","display_name":"Reference genome","score":0.6472688317298889},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6098434925079346},{"id":"https://openalex.org/keywords/genome","display_name":"Genome","score":0.5597953796386719},{"id":"https://openalex.org/keywords/regret","display_name":"Regret","score":0.5044432878494263},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.49962854385375977},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.47412872314453125},{"id":"https://openalex.org/keywords/joins","display_name":"Joins","score":0.4457828104496002},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3630622625350952},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.34205883741378784},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.29755324125289917},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.23800581693649292},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.15129172801971436},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.12910130620002747},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.07685503363609314}],"concepts":[{"id":"https://openalex.org/C87465248","wikidata":"https://www.wikidata.org/wiki/Q1417790","display_name":"Minimum description length","level":2,"score":0.8273370265960693},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.6711978316307068},{"id":"https://openalex.org/C192953774","wikidata":"https://www.wikidata.org/wiki/Q7307127","display_name":"Reference genome","level":4,"score":0.6472688317298889},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6098434925079346},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.5597953796386719},{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.5044432878494263},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.49962854385375977},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.47412872314453125},{"id":"https://openalex.org/C2778692605","wikidata":"https://www.wikidata.org/wiki/Q4041866","display_name":"Joins","level":2,"score":0.4457828104496002},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3630622625350952},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.34205883741378784},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.29755324125289917},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.23800581693649292},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.15129172801971436},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.12910130620002747},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.07685503363609314},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/gensips.2011.6169487","is_oa":false,"landing_page_url":"https://doi.org/10.1109/gensips.2011.6169487","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Workshop on Genomic Signal Processing and Statistics (GENSIPS)","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"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1559448277","https://openalex.org/W2000689241","https://openalex.org/W2019732294","https://openalex.org/W2040575507","https://openalex.org/W2049797130","https://openalex.org/W2054658115","https://openalex.org/W2090667881","https://openalex.org/W2101460669","https://openalex.org/W2137509018","https://openalex.org/W2141823231","https://openalex.org/W2991116385","https://openalex.org/W3123545922","https://openalex.org/W6770729006"],"related_works":["https://openalex.org/W2971351794","https://openalex.org/W4376155396","https://openalex.org/W1947085858","https://openalex.org/W2174986909","https://openalex.org/W2527791220","https://openalex.org/W2101991911","https://openalex.org/W2155070487","https://openalex.org/W2131823082","https://openalex.org/W1995839104","https://openalex.org/W2024112220"],"abstract_inverted_index":{"Genome":[0,16,23,44],"sequences":[1],"are":[2,37],"the":[3,19,22,28,63,72,77,81,95,109,142,145,160,169,176],"most":[4,7],"basic,":[5],"yet":[6],"essential":[8],"pieces":[9],"of":[10,34,65,80,102,144,175],"data":[11,161],"in":[12,42,159],"all":[13,100,165],"biological":[14],"analysis.":[15],"sequence":[17,30,112,179],"is":[18,47,52,152],"solution":[20],"to":[21,71,75,85,93,107,141,172],"Assembly":[24,45],"problem":[25,46,146],"which":[26,36],"remakes":[27],"entire":[29],"from":[31],"a":[32,66],"set":[33],"reads":[35,82],"unordered":[38],"and":[39,51,57,88,124,127,155],"very":[40],"small":[41],"size.":[43],"therefore,":[48],"quite":[49],"complex":[50],"broadly":[53],"divided":[54],"into":[55],"denovo":[56],"comparative":[58,114,166],"assembly.":[59,115],"Comparative":[60],"assembly":[61,170],"takes":[62],"aid":[64],"reference":[67,111,178],"sequence,":[68],"closely":[69],"related":[70],"unassembled":[73],"genome,":[74],"determine":[76],"relative":[78],"order":[79],"with":[83],"respect":[84],"one":[86],"another,":[87],"then":[89],"joins":[90],"them":[91],"together":[92],"form":[94],"sequence.":[96],"This":[97],"paper":[98,117],"explores":[99],"variants":[101],"Minimum":[103],"Description":[104],"Length":[105],"(MDL)":[106],"find":[108],"best":[110,177],"for":[113,164],"The":[116,149],"looked":[118],"at":[119],"two-part":[120,135],"MDL,":[121,136],"Sophisticated":[122,130],"MDL":[123,131],"MiniMax":[125,138],"Regret":[126],"found":[128],"that":[129],"performs":[132],"better":[133],"than":[134],"however,":[137],"regret":[139],"owing":[140],"nature":[143],"was":[147],"unsuitable.":[148],"proposed":[150],"scheme":[151],"prior":[153],"free":[154],"can":[156],"be":[157],"incorporated":[158],"preprocessing":[162],"stage":[163],"assemblers":[167],"allowing":[168],"process":[171],"make":[173],"use":[174],"available.":[180]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}