{"id":"https://openalex.org/W2129867368","doi":"https://doi.org/10.1109/csb.2003.1227381","title":"Automatic recognition of regions of intrinsically poor multiple alignment using machine learning","display_name":"Automatic recognition of regions of intrinsically poor multiple alignment using machine learning","publication_year":2004,"publication_date":"2004-03-30","ids":{"openalex":"https://openalex.org/W2129867368","doi":"https://doi.org/10.1109/csb.2003.1227381","mag":"2129867368"},"language":"en","primary_location":{"id":"doi:10.1109/csb.2003.1227381","is_oa":false,"landing_page_url":"https://doi.org/10.1109/csb.2003.1227381","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Systems Bioinformatics. CSB2003. Proceedings of the 2003 IEEE Bioinformatics Conference. CSB2003","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/A5088475144","display_name":"Ying Shan","orcid":"https://orcid.org/0000-0003-3253-3197"},"institutions":[{"id":"https://openalex.org/I129902397","display_name":"Dalhousie University","ror":"https://ror.org/01e6qks80","country_code":"CA","type":"education","lineage":["https://openalex.org/I129902397"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Y. Shan","raw_affiliation_strings":["Faculty of Computer Science, Dalhousie University, Halifax, NS, Canada"],"affiliations":[{"raw_affiliation_string":"Faculty of Computer Science, Dalhousie University, Halifax, NS, Canada","institution_ids":["https://openalex.org/I129902397"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013989913","display_name":"Evangelos Milios","orcid":"https://orcid.org/0000-0001-5549-4675"},"institutions":[{"id":"https://openalex.org/I129902397","display_name":"Dalhousie University","ror":"https://ror.org/01e6qks80","country_code":"CA","type":"education","lineage":["https://openalex.org/I129902397"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"E.E. Milios","raw_affiliation_strings":["Faculty of Computer Science, Dalhousie University, Halifax, NS, Canada"],"affiliations":[{"raw_affiliation_string":"Faculty of Computer Science, Dalhousie University, Halifax, NS, Canada","institution_ids":["https://openalex.org/I129902397"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053095410","display_name":"Andrew J. Roger","orcid":"https://orcid.org/0000-0003-1370-9820"},"institutions":[{"id":"https://openalex.org/I2802864159","display_name":"Genome Canada","ror":"https://ror.org/029s29983","country_code":"CA","type":"nonprofit","lineage":["https://openalex.org/I2802864159"]},{"id":"https://openalex.org/I129902397","display_name":"Dalhousie University","ror":"https://ror.org/01e6qks80","country_code":"CA","type":"education","lineage":["https://openalex.org/I129902397"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"A.J. Roger","raw_affiliation_strings":["Department of Biochemistry and Molecular Biology, Genome Atlantic, Genome Canada Dalhousie University, Halifax, NS, Canada"],"affiliations":[{"raw_affiliation_string":"Department of Biochemistry and Molecular Biology, Genome Atlantic, Genome Canada Dalhousie University, Halifax, NS, Canada","institution_ids":["https://openalex.org/I2802864159","https://openalex.org/I129902397"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054585121","display_name":"Christian Blouin","orcid":"https://orcid.org/0000-0002-4434-4142"},"institutions":[{"id":"https://openalex.org/I2802864159","display_name":"Genome Canada","ror":"https://ror.org/029s29983","country_code":"CA","type":"nonprofit","lineage":["https://openalex.org/I2802864159"]},{"id":"https://openalex.org/I129902397","display_name":"Dalhousie University","ror":"https://ror.org/01e6qks80","country_code":"CA","type":"education","lineage":["https://openalex.org/I129902397"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"C. Blouin","raw_affiliation_strings":["Department of Biochemistry and Molecular Biology, Genome Atlantic, Genome Canada Dalhousie University, Halifax, NS, Canada"],"affiliations":[{"raw_affiliation_string":"Department of Biochemistry and Molecular Biology, Genome Atlantic, Genome Canada Dalhousie University, Halifax, NS, Canada","institution_ids":["https://openalex.org/I2802864159","https://openalex.org/I129902397"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021576212","display_name":"Edward Susko","orcid":"https://orcid.org/0000-0003-1122-8740"},"institutions":[{"id":"https://openalex.org/I129902397","display_name":"Dalhousie University","ror":"https://ror.org/01e6qks80","country_code":"CA","type":"education","lineage":["https://openalex.org/I129902397"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"E. Susko","raw_affiliation_strings":["Department of Mathematics and Statistics, Dalhousie University, Halifax, NS, Canada"],"affiliations":[{"raw_affiliation_string":"Department of Mathematics and Statistics, Dalhousie University, Halifax, NS, Canada","institution_ids":["https://openalex.org/I129902397"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5088475144"],"corresponding_institution_ids":["https://openalex.org/I129902397"],"apc_list":null,"apc_paid":null,"fwci":0.2412,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.55313678,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"482","last_page":"483"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9958999752998352,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9919999837875366,"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/support-vector-machine","display_name":"Support vector machine","score":0.7179513573646545},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.687829852104187},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6877608299255371},{"id":"https://openalex.org/keywords/phylogenetic-tree","display_name":"Phylogenetic tree","score":0.6864611506462097},{"id":"https://openalex.org/keywords/naive-bayes-classifier","display_name":"Naive Bayes classifier","score":0.6589603424072266},{"id":"https://openalex.org/keywords/decision-tree","display_name":"Decision tree","score":0.6319836378097534},{"id":"https://openalex.org/keywords/multiple-sequence-alignment","display_name":"Multiple sequence alignment","score":0.5290024876594543},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5206234455108643},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5164496898651123},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.5020241737365723},{"id":"https://openalex.org/keywords/bayes-theorem","display_name":"Bayes' theorem","score":0.49495190382003784},{"id":"https://openalex.org/keywords/sequence-alignment","display_name":"Sequence alignment","score":0.3185758590698242},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.2113872766494751},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.206182599067688},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.1351667046546936},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11566877365112305}],"concepts":[{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.7179513573646545},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.687829852104187},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6877608299255371},{"id":"https://openalex.org/C193252679","wikidata":"https://www.wikidata.org/wiki/Q242125","display_name":"Phylogenetic tree","level":3,"score":0.6864611506462097},{"id":"https://openalex.org/C52001869","wikidata":"https://www.wikidata.org/wiki/Q812530","display_name":"Naive Bayes classifier","level":3,"score":0.6589603424072266},{"id":"https://openalex.org/C84525736","wikidata":"https://www.wikidata.org/wiki/Q831366","display_name":"Decision tree","level":2,"score":0.6319836378097534},{"id":"https://openalex.org/C88031987","wikidata":"https://www.wikidata.org/wiki/Q1377767","display_name":"Multiple sequence alignment","level":5,"score":0.5290024876594543},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5206234455108643},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5164496898651123},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.5020241737365723},{"id":"https://openalex.org/C207201462","wikidata":"https://www.wikidata.org/wiki/Q182505","display_name":"Bayes' theorem","level":3,"score":0.49495190382003784},{"id":"https://openalex.org/C45484198","wikidata":"https://www.wikidata.org/wiki/Q827246","display_name":"Sequence alignment","level":4,"score":0.3185758590698242},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.2113872766494751},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.206182599067688},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.1351667046546936},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11566877365112305},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C167625842","wikidata":"https://www.wikidata.org/wiki/Q899763","display_name":"Peptide sequence","level":3,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/csb.2003.1227381","is_oa":false,"landing_page_url":"https://doi.org/10.1109/csb.2003.1227381","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Systems Bioinformatics. CSB2003. Proceedings of the 2003 IEEE Bioinformatics Conference. CSB2003","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.136.6734","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.136.6734","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://csdl.computer.org/comp/proceedings/csb/2003/2000/00/20000482.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7400000095367432,"id":"https://metadata.un.org/sdg/1","display_name":"No poverty"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320310787","display_name":"Genome Canada","ror":"https://ror.org/029s29983"},{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W2123504579","https://openalex.org/W2466512847","https://openalex.org/W2938524560","https://openalex.org/W6761450353","https://openalex.org/W7055702063"],"related_works":["https://openalex.org/W4389954502","https://openalex.org/W2771255398","https://openalex.org/W2930428186","https://openalex.org/W3200027047","https://openalex.org/W4385770464","https://openalex.org/W2537862391","https://openalex.org/W2417174640","https://openalex.org/W4224262160","https://openalex.org/W3120363735","https://openalex.org/W4214820172"],"abstract_inverted_index":{"Phylogenetic":[0],"analysis":[1],"requires":[2],"alignment":[3,29,36,61],"of":[4,11,33,51,59],"gene":[5],"or":[6],"protein":[7],"sequences.":[8],"Some":[9],"regions":[10,32,58],"genes":[12],"evolve":[13],"fast":[14],"and":[15,19,22,40,76],"suffer":[16],"numerous":[17],"insertion":[18],"deletion":[20],"events":[21],"cannot":[23],"be":[24],"aligned":[25],"reliably":[26],"with":[27],"automatic":[28],"algorithms.":[30],"Such":[31],"intrinsically":[34],"uncertain":[35],"are":[37],"currently":[38],"detected":[39],"deleted":[41],"manually":[42],"before":[43],"performing":[44],"phylogenetic":[45],"analysis.":[46],"We":[47,63],"present":[48],"the":[49,65],"results":[50,66],"a":[52],"machine":[53,79],"learning":[54],"approach":[55],"to":[56],"detect":[57],"poor":[60],"automatically.":[62],"compare":[64],"obtained":[67],"from":[68],"Naive":[69],"Bayes":[70],"(NB),":[71],"C4.5":[72],"decision":[73],"tree":[74],"(C4.5)":[75],"support":[77],"vector":[78],"(SVM)":[80],"approaches.":[81]},"counts_by_year":[{"year":2014,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
