{"id":"https://openalex.org/W2760969120","doi":"https://doi.org/10.1109/cibcb.2017.8058529","title":"Infinite string block matching features for DNA classification","display_name":"Infinite string block matching features for DNA classification","publication_year":2017,"publication_date":"2017-08-01","ids":{"openalex":"https://openalex.org/W2760969120","doi":"https://doi.org/10.1109/cibcb.2017.8058529","mag":"2760969120"},"language":"en","primary_location":{"id":"doi:10.1109/cibcb.2017.8058529","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cibcb.2017.8058529","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology (CIBCB)","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/A5080870632","display_name":"Daniel Ashlock","orcid":"https://orcid.org/0000-0003-2209-7504"},"institutions":[{"id":"https://openalex.org/I79817857","display_name":"University of Guelph","ror":"https://ror.org/01r7awg59","country_code":"CA","type":"education","lineage":["https://openalex.org/I79817857"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Daniel Ashlock","raw_affiliation_strings":["Department of Mathematics and Statistics, University of Guelph, Guelph, Ontario, Canada"],"affiliations":[{"raw_affiliation_string":"Department of Mathematics and Statistics, University of Guelph, Guelph, Ontario, Canada","institution_ids":["https://openalex.org/I79817857"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072141714","display_name":"Sierra Gillis","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sierra Gillis","raw_affiliation_strings":["41 Lambert Cr., McGuinness Consulting, Inc., Guelph, Ontario, Canada"],"affiliations":[{"raw_affiliation_string":"41 Lambert Cr., McGuinness Consulting, Inc., Guelph, Ontario, Canada","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066757355","display_name":"Wendy Ashlock","orcid":null},"institutions":[{"id":"https://openalex.org/I79817857","display_name":"University of Guelph","ror":"https://ror.org/01r7awg59","country_code":"CA","type":"education","lineage":["https://openalex.org/I79817857"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Wendy Ashlock","raw_affiliation_strings":["Department of Mathematics and Statistics, University of Guelph, Guelph, Ontario, Canada"],"affiliations":[{"raw_affiliation_string":"Department of Mathematics and Statistics, University of Guelph, Guelph, Ontario, Canada","institution_ids":["https://openalex.org/I79817857"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5080870632"],"corresponding_institution_ids":["https://openalex.org/I79817857"],"apc_list":null,"apc_paid":null,"fwci":0.4253,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.619891,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"3","issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9990000128746033,"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":0.9990000128746033,"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":0.9986000061035156,"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":0.9973000288009644,"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/string-searching-algorithm","display_name":"String searching algorithm","score":0.6543498635292053},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.610078752040863},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5476736426353455},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.5345605611801147},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.515912652015686},{"id":"https://openalex.org/keywords/string-metric","display_name":"String metric","score":0.4520740509033203},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41670021414756775},{"id":"https://openalex.org/keywords/pattern-matching","display_name":"Pattern matching","score":0.35076355934143066},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3219224214553833},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.13199806213378906}],"concepts":[{"id":"https://openalex.org/C7757238","wikidata":"https://www.wikidata.org/wiki/Q374040","display_name":"String searching algorithm","level":3,"score":0.6543498635292053},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.610078752040863},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5476736426353455},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.5345605611801147},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.515912652015686},{"id":"https://openalex.org/C22820288","wikidata":"https://www.wikidata.org/wiki/Q9050568","display_name":"String metric","level":4,"score":0.4520740509033203},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41670021414756775},{"id":"https://openalex.org/C68859911","wikidata":"https://www.wikidata.org/wiki/Q1503724","display_name":"Pattern matching","level":2,"score":0.35076355934143066},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3219224214553833},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.13199806213378906},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cibcb.2017.8058529","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cibcb.2017.8058529","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology (CIBCB)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1526653623","https://openalex.org/W1944340687","https://openalex.org/W1974524840","https://openalex.org/W2020816856","https://openalex.org/W2031754607","https://openalex.org/W2063478894","https://openalex.org/W2076871417","https://openalex.org/W2085380703","https://openalex.org/W2097892623","https://openalex.org/W2163881232","https://openalex.org/W2559212254","https://openalex.org/W6655478935"],"related_works":["https://openalex.org/W2257399947","https://openalex.org/W2371263218","https://openalex.org/W2366300241","https://openalex.org/W2386746909","https://openalex.org/W2245915510","https://openalex.org/W2141423589","https://openalex.org/W2037600093","https://openalex.org/W3145288231","https://openalex.org/W1521505584","https://openalex.org/W2399644331"],"abstract_inverted_index":{"Automatic":[0],"classification":[1],"of":[2,10,15,52,98],"DNA":[3,28,65,126],"can":[4],"be":[5],"performed":[6],"in":[7,59,72,105],"a":[8,13,20,32,49,56,95,130],"number":[9],"ways":[11],"using":[12,129],"variety":[14],"features.":[16],"This":[17],"study":[18],"introduces":[19],"novel":[21],"technique":[22],"for":[23,27,114],"generating":[24],"global":[25,64,99],"features":[26,150],"classification.":[29],"Based":[30],"on":[31,89,137,151],"new":[33],"technique,":[34],"the":[35,60,81,111],"\u201cdo":[36],"what's":[37],"possible\u201d":[38],"representation,":[39],"infinite":[40,116,145],"string":[41,74,85,117,146],"generators":[42,118,147],"are":[43],"evolved":[44,115,144],"to":[45,121],"produce":[46],"strings":[47],"with":[48],"maximized":[50],"collection":[51],"matching":[53,86],"blocks":[54],"above":[55],"critical":[57],"length":[58],"target":[61,82],"DNA.":[62,83],"Most":[63],"features,":[66],"such":[67],"as":[68,154],"GC-content":[69],"or":[70],"those":[71],"spectrum":[73],"kernels,":[75],"capture":[76],"diffuse":[77],"statistical":[78],"information":[79],"about":[80],"Infinite":[84],"is":[87,108,119],"based":[88],"multiple":[90],"loci,":[91],"and":[92],"thus":[93],"finds":[94],"different":[96],"type":[97],"feature":[100,132],"than":[101],"most":[102],"techniques":[103],"now":[104],"use.":[106],"It":[107],"discovered":[109],"that":[110,143],"block-matching":[112],"score":[113],"able":[120],"cleanly":[122],"separate":[123],"high-entropy":[124],"synthetic":[125],"data":[127,153],"sets":[128],"single":[131],"threshold":[133],"classifier.":[134],"Preliminary":[135],"evaluation":[136],"human":[138],"endogenous":[139],"retrovirus":[140],"sequences":[141],"shows":[142],"locate":[148],"promising":[149],"biological":[152],"well.":[155]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}