{"id":"https://openalex.org/W2158384625","doi":"https://doi.org/10.1093/bioinformatics/bti658","title":"Optimal word sizes for dissimilarity measures and estimation of the degree of dissimilarity between DNA sequences","display_name":"Optimal word sizes for dissimilarity measures and estimation of the degree of dissimilarity between DNA sequences","publication_year":2005,"publication_date":"2005-09-06","ids":{"openalex":"https://openalex.org/W2158384625","doi":"https://doi.org/10.1093/bioinformatics/bti658","mag":"2158384625","pmid":"https://pubmed.ncbi.nlm.nih.gov/16144805"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/bti658","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/bti658","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/21/22/4125/16841012/bti658.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://academic.oup.com/bioinformatics/article-pdf/21/22/4125/16841012/bti658.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5108450109","display_name":"Tiee\u2010Jian Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I91807558","display_name":"National Cheng Kung University","ror":"https://ror.org/01b8kcc49","country_code":"TW","type":"education","lineage":["https://openalex.org/I91807558"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Tiee-Jian Wu","raw_affiliation_strings":["Department of Statistics, National Cheng-Kung University 1 \u00a0 1 \u00a0 \u00a0 Tainan, Taiwan 70101"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Statistics, National Cheng-Kung University 1 \u00a0 1 \u00a0 \u00a0 Tainan, Taiwan 70101","institution_ids":["https://openalex.org/I91807558"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073633996","display_name":"Ying-Hsueh Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]},{"id":"https://openalex.org/I4210141710","display_name":"Institute of Statistical Science, Academia Sinica","ror":"https://ror.org/044gv5910","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210141710","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Ying-Hsueh Huang","raw_affiliation_strings":["Institute of Bioinformatics, National Yang-Ming University 3 \u00a0 3 \u00a0 \u00a0 Taipei, Taiwan 11221","Institute of Statistical Science, Academia Sinica 2 \u00a0 2 \u00a0 \u00a0 Taipei, Taiwan 11529"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Bioinformatics, National Yang-Ming University 3 \u00a0 3 \u00a0 \u00a0 Taipei, Taiwan 11221","institution_ids":["https://openalex.org/I148366613"]},{"raw_affiliation_string":"Institute of Statistical Science, Academia Sinica 2 \u00a0 2 \u00a0 \u00a0 Taipei, Taiwan 11529","institution_ids":["https://openalex.org/I4210141710"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023440880","display_name":"Lung\u2010An Li","orcid":null},"institutions":[{"id":"https://openalex.org/I4210141710","display_name":"Institute of Statistical Science, Academia Sinica","ror":"https://ror.org/044gv5910","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210141710","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Lung-An Li","raw_affiliation_strings":["Institute of Statistical Science, Academia Sinica 2 \u00a0 2 \u00a0 \u00a0 Taipei, Taiwan 11529"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Statistical Science, Academia Sinica 2 \u00a0 2 \u00a0 \u00a0 Taipei, Taiwan 11529","institution_ids":["https://openalex.org/I4210141710"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5108450109"],"corresponding_institution_ids":["https://openalex.org/I91807558"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":null,"fwci":1.0108,"has_fulltext":false,"cited_by_count":58,"citation_normalized_percentile":{"value":0.74774565,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"21","issue":"22","first_page":"4125","last_page":"4132"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12946","display_name":"Fractal and DNA sequence analysis","score":0.7626000046730042,"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/T12946","display_name":"Fractal and DNA sequence analysis","score":0.7626000046730042,"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/T10222","display_name":"Genomics and Chromatin Dynamics","score":0.11219999939203262,"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/T10885","display_name":"Gene expression and cancer classification","score":0.04899999871850014,"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/word","display_name":"Word (group theory)","score":0.7703588604927063},{"id":"https://openalex.org/keywords/degree","display_name":"Degree (music)","score":0.7618864178657532},{"id":"https://openalex.org/keywords/estimation","display_name":"Estimation","score":0.6274981498718262},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5515048503875732},{"id":"https://openalex.org/keywords/word-length","display_name":"Word length","score":0.4618164300918579},{"id":"https://openalex.org/keywords/dna","display_name":"DNA","score":0.44279202818870544},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.42624813318252563},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4262348413467407},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41346073150634766},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3754110336303711},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3715086579322815},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.2185087502002716},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.19556811451911926}],"concepts":[{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.7703588604927063},{"id":"https://openalex.org/C2775997480","wikidata":"https://www.wikidata.org/wiki/Q586277","display_name":"Degree (music)","level":2,"score":0.7618864178657532},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.6274981498718262},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5515048503875732},{"id":"https://openalex.org/C3019641298","wikidata":"https://www.wikidata.org/wiki/Q625642","display_name":"Word length","level":2,"score":0.4618164300918579},{"id":"https://openalex.org/C552990157","wikidata":"https://www.wikidata.org/wiki/Q7430","display_name":"DNA","level":2,"score":0.44279202818870544},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.42624813318252563},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4262348413467407},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41346073150634766},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3754110336303711},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3715086579322815},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.2185087502002716},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.19556811451911926},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003201","descriptor_name":"Computers","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003201","descriptor_name":"Computers","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003201","descriptor_name":"Computers","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D004247","descriptor_name":"DNA","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D004247","descriptor_name":"DNA","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D004247","descriptor_name":"DNA","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D004926","descriptor_name":"Escherichia coli","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D004926","descriptor_name":"Escherichia coli","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D004926","descriptor_name":"Escherichia coli","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D005798","descriptor_name":"Genes, Bacterial","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005798","descriptor_name":"Genes, Bacterial","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005798","descriptor_name":"Genes, Bacterial","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008071","descriptor_name":"Lipoprotein Lipase","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D008071","descriptor_name":"Lipoprotein Lipase","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D008071","descriptor_name":"Lipoprotein Lipase","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D008957","descriptor_name":"Models, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008957","descriptor_name":"Models, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008957","descriptor_name":"Models, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010363","descriptor_name":"Pattern Recognition, Automated","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010363","descriptor_name":"Pattern Recognition, Automated","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010363","descriptor_name":"Pattern Recognition, Automated","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010802","descriptor_name":"Phylogeny","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010802","descriptor_name":"Phylogeny","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010802","descriptor_name":"Phylogeny","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012763","descriptor_name":"Shigella flexneri","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D012763","descriptor_name":"Shigella flexneri","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D012763","descriptor_name":"Shigella flexneri","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013045","descriptor_name":"Species Specificity","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013045","descriptor_name":"Species Specificity","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013045","descriptor_name":"Species Specificity","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015233","descriptor_name":"Models, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015233","descriptor_name":"Models, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015233","descriptor_name":"Models, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015345","descriptor_name":"Oligonucleotide Probes","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D015345","descriptor_name":"Oligonucleotide Probes","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D015345","descriptor_name":"Oligonucleotide Probes","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D016366","descriptor_name":"Open Reading Frames","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016366","descriptor_name":"Open Reading Frames","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016366","descriptor_name":"Open Reading Frames","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016678","descriptor_name":"Genome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016678","descriptor_name":"Genome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016678","descriptor_name":"Genome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020411","descriptor_name":"Oligonucleotide Array Sequence Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020411","descriptor_name":"Oligonucleotide Array Sequence Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020411","descriptor_name":"Oligonucleotide Array Sequence Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030541","descriptor_name":"Databases, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030541","descriptor_name":"Databases, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030541","descriptor_name":"Databases, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D045473","descriptor_name":"Severe acute respiratory syndrome-related coronavirus","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D045473","descriptor_name":"Severe acute respiratory syndrome-related coronavirus","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D045473","descriptor_name":"Severe acute respiratory syndrome-related coronavirus","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1093/bioinformatics/bti658","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/bti658","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/21/22/4125/16841012/bti658.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:16144805","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/16144805","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics (Oxford, England)","raw_type":null}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/bti658","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/bti658","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/21/22/4125/16841012/bti658.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W297918892","https://openalex.org/W1502936039","https://openalex.org/W1516900628","https://openalex.org/W1558365920","https://openalex.org/W1968467471","https://openalex.org/W1969234006","https://openalex.org/W1973243276","https://openalex.org/W1983087557","https://openalex.org/W1987680287","https://openalex.org/W1997455636","https://openalex.org/W1998690237","https://openalex.org/W2015292449","https://openalex.org/W2016017944","https://openalex.org/W2019346516","https://openalex.org/W2025584660","https://openalex.org/W2036306946","https://openalex.org/W2055043387","https://openalex.org/W2075486601","https://openalex.org/W2097383747","https://openalex.org/W2098475202","https://openalex.org/W2105837518","https://openalex.org/W2124464500","https://openalex.org/W2141224484","https://openalex.org/W2149240185","https://openalex.org/W2158714788","https://openalex.org/W2163097179","https://openalex.org/W2166162901","https://openalex.org/W2171963266","https://openalex.org/W2334744046","https://openalex.org/W4251919163","https://openalex.org/W6649700783","https://openalex.org/W6656634277","https://openalex.org/W6659397386","https://openalex.org/W6683971125","https://openalex.org/W6783806376"],"related_works":["https://openalex.org/W2068578356","https://openalex.org/W237537940","https://openalex.org/W1898422521","https://openalex.org/W2133478886","https://openalex.org/W2033995689","https://openalex.org/W4235762796","https://openalex.org/W1995096030","https://openalex.org/W4250812604","https://openalex.org/W1792229902","https://openalex.org/W4233398620"],"abstract_inverted_index":{"MOTIVATION:":[0],"Several":[1],"measures":[2,48],"of":[3,12,22,66,81,87,156,171],"DNA":[4,88],"sequence":[5,97],"dissimilarity":[6,82],"have":[7],"been":[8],"developed.":[9],"The":[10,215],"purpose":[11],"this":[13],"paper":[14],"is":[15,139,143,185],"3-fold.":[16],"Firstly,":[17],"we":[18,29,54],"compare":[19],"the":[20,36,41,64,79,100,125,135,153],"performance":[21,142],"several":[23,46],"word-based":[24,47],"or":[25],"alignment-based":[26,176],"methods.":[27],"Secondly,":[28],"give":[30],"a":[31,56,168],"general":[32],"guideline":[33],"for":[34,45,95,122,179,212],"choosing":[35],"window":[37,51,101,131],"size":[38,102,128,138],"and":[39,148,174,182,220,228],"determining":[40],"optimal":[42,126,136],"word":[43,127,137],"sizes":[44],"at":[49,231],"different":[50],"sizes.":[52],"Thirdly,":[53],"use":[55],"large-scale":[57],"simulation":[58,147,221],"method":[59],"to":[60,77,164],"simulate":[61],"data":[62,73,150],"from":[63],"distribution":[65],"SK-LD":[67,141,160],"(symmetric":[68],"Kullback-Leibler":[69],"discrepancy).":[70],"These":[71],"simulated":[72],"can":[74,161,196],"be":[75,105,162],"used":[76,163],"estimate":[78,154,218],"degree":[80],"beta":[83,155,157,184,219],"between":[84],"any":[85],"pair":[86],"sequences.":[89],"RESULTS:":[90],"Our":[91],"study":[92],"shows":[93],"(1)":[94],"whole":[96],"similiarity/dissimilarity":[98],"identification":[99],"taken":[103],"should":[104],"as":[106,108,114],"large":[107,169],"possible,":[109],"but":[110],"probably":[111],"not":[112],">3000,":[113],"restricted":[115],"by":[116],"CPU":[117],"time":[118],"in":[119,145,188,198,209,225],"practice,":[120],"(2)":[121],"each":[123],"measure":[124],"increases":[129],"with":[130,202],"size,":[132],"(3)":[133],"when":[134],"used,":[140],"superior":[144],"both":[146],"real":[149],"analysis,":[151],"(4)":[152],"based":[158],"on":[159],"filter":[165],"out":[166],"quickly":[167],"number":[170],"dissimilar":[172],"sequences":[173,181],"speed":[175],"database":[177],"search":[178],"similar":[180],"(5)":[183],"also":[186],"applicable":[187],"local":[189],"similarity":[190],"comparison":[191],"situations.":[192],"For":[193],"example,":[194],"it":[195],"help":[197],"selecting":[199],"oligo":[200],"probes":[201],"high":[203],"specificity":[204],"and,":[205],"therefore,":[206],"has":[207],"potential":[208],"probe":[210],"design":[211],"microarrays.":[213],"AVAILABILITY:":[214],"algorithm":[216],"SK-LD,":[217],"software":[222],"are":[223,229],"implemented":[224],"MATLAB":[226],"code,":[227],"available":[230],"http://www.stat.ncku.edu.tw/tjwu":[232]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":3}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
