{"id":"https://openalex.org/W2018274021","doi":"https://doi.org/10.1109/cibcb.2012.6217236","title":"An efficient machine learning approach to low-complexity filtering in biological sequences","display_name":"An efficient machine learning approach to low-complexity filtering in biological sequences","publication_year":2012,"publication_date":"2012-05-01","ids":{"openalex":"https://openalex.org/W2018274021","doi":"https://doi.org/10.1109/cibcb.2012.6217236","mag":"2018274021"},"language":"en","primary_location":{"id":"doi:10.1109/cibcb.2012.6217236","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cibcb.2012.6217236","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE Symposium 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/A5042720964","display_name":"Christopher Barber","orcid":null},"institutions":[{"id":"https://openalex.org/I142606810","display_name":"Pacific Northwest National Laboratory","ror":"https://ror.org/05h992307","country_code":"US","type":"facility","lineage":["https://openalex.org/I1325736334","https://openalex.org/I1330989302","https://openalex.org/I142606810","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"C. A. Barber","raw_affiliation_strings":["Pacific Northwest National Laboratory, Richland, WA, USA","Pacific Northwest National Laboratory, Richland, Washington 99352, USA"],"affiliations":[{"raw_affiliation_string":"Pacific Northwest National Laboratory, Richland, WA, USA","institution_ids":["https://openalex.org/I142606810"]},{"raw_affiliation_string":"Pacific Northwest National Laboratory, Richland, Washington 99352, USA","institution_ids":["https://openalex.org/I142606810"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013287908","display_name":"Christopher Oehmen","orcid":"https://orcid.org/0009-0004-5246-930X"},"institutions":[{"id":"https://openalex.org/I142606810","display_name":"Pacific Northwest National Laboratory","ror":"https://ror.org/05h992307","country_code":"US","type":"facility","lineage":["https://openalex.org/I1325736334","https://openalex.org/I1330989302","https://openalex.org/I142606810","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"C. S. Oehmen","raw_affiliation_strings":["Pacific Northwest National Laboratory, Richland, WA, USA","Pacific Northwest National Laboratory, Richland, Washington 99352, USA"],"affiliations":[{"raw_affiliation_string":"Pacific Northwest National Laboratory, Richland, WA, USA","institution_ids":["https://openalex.org/I142606810"]},{"raw_affiliation_string":"Pacific Northwest National Laboratory, Richland, Washington 99352, USA","institution_ids":["https://openalex.org/I142606810"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5042720964"],"corresponding_institution_ids":["https://openalex.org/I142606810"],"apc_list":null,"apc_paid":null,"fwci":0.1313,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.50619897,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"237","last_page":"243"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9995999932289124,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9995999932289124,"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":0.9990000128746033,"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"}},{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9973999857902527,"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/computer-science","display_name":"Computer science","score":0.7575511932373047},{"id":"https://openalex.org/keywords/suite","display_name":"Suite","score":0.5966838002204895},{"id":"https://openalex.org/keywords/computational-complexity-theory","display_name":"Computational complexity theory","score":0.581188440322876},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5659857392311096},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.5423834919929504},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5177866220474243},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.47590622305870056},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.45317983627319336},{"id":"https://openalex.org/keywords/biological-data","display_name":"Biological data","score":0.4519221782684326},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3524427115917206},{"id":"https://openalex.org/keywords/bioinformatics","display_name":"Bioinformatics","score":0.089989572763443}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7575511932373047},{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.5966838002204895},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.581188440322876},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5659857392311096},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.5423834919929504},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5177866220474243},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.47590622305870056},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.45317983627319336},{"id":"https://openalex.org/C201797286","wikidata":"https://www.wikidata.org/wiki/Q4914986","display_name":"Biological data","level":2,"score":0.4519221782684326},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3524427115917206},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.089989572763443},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cibcb.2012.6217236","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cibcb.2012.6217236","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE Symposium on Computational Intelligence in Bioinformatics and Computational Biology (CIBCB)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320306250","display_name":"Battelle","ror":"https://ror.org/01h5tnr73"},{"id":"https://openalex.org/F4320337547","display_name":"Laboratory Directed Research and Development","ror":"https://ror.org/01e41cf67"},{"id":"https://openalex.org/F4320338354","display_name":"Pacific Northwest National Laboratory","ror":"https://ror.org/05h992307"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W1542075762","https://openalex.org/W1973862547","https://openalex.org/W2051916497","https://openalex.org/W2059513841","https://openalex.org/W2158714788"],"related_works":["https://openalex.org/W4231704780","https://openalex.org/W2083794993","https://openalex.org/W352609212","https://openalex.org/W4200340037","https://openalex.org/W1511772879","https://openalex.org/W4379115841","https://openalex.org/W608917066","https://openalex.org/W4283652261","https://openalex.org/W585424826","https://openalex.org/W564602992"],"abstract_inverted_index":{"Biological":[0],"sequences":[1,83],"contain":[2],"low-complexity":[3,31],"regions":[4,26],"(LCRs)":[5],"which":[6,39,56,96],"produce":[7],"superfluous":[8],"matches":[9],"in":[10,42],"homology":[11],"searches,":[12],"and":[13,37,91],"lead":[14],"to":[15,89],"slow":[16],"execution":[17],"of":[18,51,64],"database":[19],"search":[20],"algorithms":[21,33,47],"such":[22,34],"as":[23,35,71,73],"BLAST.":[24],"These":[25,46],"are":[27,40,66,87],"efficiently":[28],"identified":[29],"by":[30],"filtering":[32,76,101],"SDUST":[36],"SEG,":[38],"included":[41],"the":[43,99],"BLAST":[44],"tool-suite.":[45],"target":[48],"differing":[49],"notions":[50],"complexity,":[52],"so":[53],"an":[54,93],"algorithm":[55,77],"combines":[57],"their":[58],"sensitivities":[59],"is":[60],"pursued.":[61],"A":[62],"variety":[63],"features":[65],"derived":[67],"from":[68],"these":[69],"algorithms,":[70],"well":[72],"a":[74],"new":[75],"based":[78],"on":[79],"Lempel-Ziv":[80],"complexity.":[81],"Artificial":[82],"with":[84],"known":[85],"LCRs":[86],"used":[88],"train":[90],"evaluate":[92],"SVM":[94],"classifier,":[95],"significantly":[97],"outperforms":[98],"standalone":[100],"algorithms.":[102]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}