{"id":"https://openalex.org/W2117456040","doi":"https://doi.org/10.1109/csb.2003.1227338","title":"Prokaryote phylogeny without sequence alignment: from avoidance signature to composition distance","display_name":"Prokaryote phylogeny without sequence alignment: from avoidance signature to composition distance","publication_year":2004,"publication_date":"2004-03-30","ids":{"openalex":"https://openalex.org/W2117456040","doi":"https://doi.org/10.1109/csb.2003.1227338","mag":"2117456040","pmid":"https://pubmed.ncbi.nlm.nih.gov/16452813"},"language":"en","primary_location":{"id":"doi:10.1109/csb.2003.1227338","is_oa":false,"landing_page_url":"https://doi.org/10.1109/csb.2003.1227338","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","pubmed"],"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/A5030152767","display_name":"Bailin Hao","orcid":null},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Bailin Hao","raw_affiliation_strings":["T-Life Research Center, Fudan University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"T-Life Research Center, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039579687","display_name":"Ji Qi","orcid":"https://orcid.org/0000-0001-7597-9725"},"institutions":[{"id":"https://openalex.org/I4210125404","display_name":"Institute of Theoretical Physics","ror":"https://ror.org/02xtbq882","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210125404"]},{"id":"https://openalex.org/I84653119","display_name":"Academia Sinica","ror":"https://ror.org/05bxb3784","country_code":"TW","type":"facility","lineage":["https://openalex.org/I84653119"]}],"countries":["CN","TW"],"is_corresponding":false,"raw_author_name":"Ji Qi","raw_affiliation_strings":["Institute of Theoretical Physics, Chinese Academy and Sciences, Beijing, China","Institute of Theoretical Physics, Academia Sinica, P.O. Box 2735, Beijing 100080, china"],"affiliations":[{"raw_affiliation_string":"Institute of Theoretical Physics, Chinese Academy and Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210125404"]},{"raw_affiliation_string":"Institute of Theoretical Physics, Academia Sinica, P.O. Box 2735, Beijing 100080, china","institution_ids":["https://openalex.org/I4210125404","https://openalex.org/I84653119"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5030152767"],"corresponding_institution_ids":["https://openalex.org/I24943067"],"apc_list":null,"apc_paid":null,"fwci":0.2339,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.53804506,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"9","issue":null,"first_page":"375","last_page":"384"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","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/T10015","display_name":"Genomics and Phylogenetic Studies","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":0.9667999744415283,"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/T10521","display_name":"RNA and protein synthesis mechanisms","score":0.9652000069618225,"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/prokaryote","display_name":"Prokaryote","score":0.8193904757499695},{"id":"https://openalex.org/keywords/phylogenetic-tree","display_name":"Phylogenetic tree","score":0.6494500637054443},{"id":"https://openalex.org/keywords/genome","display_name":"Genome","score":0.5629340410232544},{"id":"https://openalex.org/keywords/phylogenetics","display_name":"Phylogenetics","score":0.5470881462097168},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.5419330596923828},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5111804604530334},{"id":"https://openalex.org/keywords/evolutionary-biology","display_name":"Evolutionary biology","score":0.508705198764801},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.4838806390762329},{"id":"https://openalex.org/keywords/horizontal-gene-transfer","display_name":"Horizontal gene transfer","score":0.46767979860305786},{"id":"https://openalex.org/keywords/proteome","display_name":"Proteome","score":0.4601711630821228},{"id":"https://openalex.org/keywords/multiple-sequence-alignment","display_name":"Multiple sequence alignment","score":0.4172056317329407},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.3858581781387329},{"id":"https://openalex.org/keywords/biological-system","display_name":"Biological system","score":0.3644673824310303},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3632180094718933},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.30568867921829224},{"id":"https://openalex.org/keywords/sequence-alignment","display_name":"Sequence alignment","score":0.29455772042274475},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.2863720655441284},{"id":"https://openalex.org/keywords/peptide-sequence","display_name":"Peptide sequence","score":0.10326400399208069}],"concepts":[{"id":"https://openalex.org/C2780918051","wikidata":"https://www.wikidata.org/wiki/Q19081","display_name":"Prokaryote","level":3,"score":0.8193904757499695},{"id":"https://openalex.org/C193252679","wikidata":"https://www.wikidata.org/wiki/Q242125","display_name":"Phylogenetic tree","level":3,"score":0.6494500637054443},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.5629340410232544},{"id":"https://openalex.org/C90132467","wikidata":"https://www.wikidata.org/wiki/Q171184","display_name":"Phylogenetics","level":3,"score":0.5470881462097168},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.5419330596923828},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5111804604530334},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.508705198764801},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.4838806390762329},{"id":"https://openalex.org/C92938381","wikidata":"https://www.wikidata.org/wiki/Q83185","display_name":"Horizontal gene transfer","level":4,"score":0.46767979860305786},{"id":"https://openalex.org/C104397665","wikidata":"https://www.wikidata.org/wiki/Q860947","display_name":"Proteome","level":2,"score":0.4601711630821228},{"id":"https://openalex.org/C88031987","wikidata":"https://www.wikidata.org/wiki/Q1377767","display_name":"Multiple sequence alignment","level":5,"score":0.4172056317329407},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.3858581781387329},{"id":"https://openalex.org/C186060115","wikidata":"https://www.wikidata.org/wiki/Q30336093","display_name":"Biological system","level":1,"score":0.3644673824310303},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3632180094718933},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.30568867921829224},{"id":"https://openalex.org/C45484198","wikidata":"https://www.wikidata.org/wiki/Q827246","display_name":"Sequence alignment","level":4,"score":0.29455772042274475},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.2863720655441284},{"id":"https://openalex.org/C167625842","wikidata":"https://www.wikidata.org/wiki/Q899763","display_name":"Peptide sequence","level":3,"score":0.10326400399208069}],"mesh":[{"descriptor_ui":"D001482","descriptor_name":"Base Composition","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001482","descriptor_name":"Base Composition","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001482","descriptor_name":"Base Composition","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001483","descriptor_name":"Base Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001483","descriptor_name":"Base Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001483","descriptor_name":"Base Sequence","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":"D004252","descriptor_name":"DNA Mutational Analysis","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D004252","descriptor_name":"DNA Mutational Analysis","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D004252","descriptor_name":"DNA Mutational Analysis","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D004269","descriptor_name":"DNA, Bacterial","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D004269","descriptor_name":"DNA, Bacterial","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D004269","descriptor_name":"DNA, Bacterial","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":true},{"descriptor_ui":"D008957","descriptor_name":"Models, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008957","descriptor_name":"Models, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008969","descriptor_name":"Molecular Sequence Data","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008969","descriptor_name":"Molecular Sequence Data","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008969","descriptor_name":"Molecular Sequence Data","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":true},{"descriptor_ui":"D010802","descriptor_name":"Phylogeny","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D010802","descriptor_name":"Phylogeny","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D011995","descriptor_name":"Recombination, Genetic","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D011995","descriptor_name":"Recombination, Genetic","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D011995","descriptor_name":"Recombination, Genetic","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D015398","descriptor_name":"Signal Transduction","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D015398","descriptor_name":"Signal Transduction","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D015398","descriptor_name":"Signal Transduction","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","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}],"locations_count":2,"locations":[{"id":"doi:10.1109/csb.2003.1227338","is_oa":false,"landing_page_url":"https://doi.org/10.1109/csb.2003.1227338","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":"pmid:16452813","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/16452813","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":"Proceedings. IEEE Computer Society Bioinformatics Conference","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6399999856948853,"display_name":"Life in Land","id":"https://metadata.un.org/sdg/15"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321133","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1485044783","https://openalex.org/W1509766895","https://openalex.org/W1519987066","https://openalex.org/W1533591106","https://openalex.org/W1534406401","https://openalex.org/W1990738356","https://openalex.org/W1997327796","https://openalex.org/W2004099840","https://openalex.org/W2010808181","https://openalex.org/W2017754509","https://openalex.org/W2035407554","https://openalex.org/W2040461302","https://openalex.org/W2079115652","https://openalex.org/W2083119773","https://openalex.org/W2098386120","https://openalex.org/W2098558111","https://openalex.org/W2103065948","https://openalex.org/W2114049512","https://openalex.org/W2114293764","https://openalex.org/W2116988150","https://openalex.org/W2125598538","https://openalex.org/W2140211206","https://openalex.org/W2143276497","https://openalex.org/W2154565942","https://openalex.org/W2158350566","https://openalex.org/W2160614196","https://openalex.org/W2185695238","https://openalex.org/W3142275315","https://openalex.org/W4246395620","https://openalex.org/W6649710075"],"related_works":["https://openalex.org/W2061375526","https://openalex.org/W2793602347","https://openalex.org/W2357220603","https://openalex.org/W2086569686","https://openalex.org/W2133991766","https://openalex.org/W3038394335","https://openalex.org/W1999606269","https://openalex.org/W2131534116","https://openalex.org/W2140560927","https://openalex.org/W2106265368"],"abstract_inverted_index":{"A":[0,91],"new":[1],"and":[2,50,66],"essentially":[3],"simple":[4],"method":[5,46],"to":[6,36,63,68,117],"reconstruct":[7],"prokaryotic":[8],"phylogenetic":[9],"trees":[10],"from":[11,113],"their":[12,41],"complete":[13],"genome":[14],"data":[15],"without":[16,47],"using":[17,104],"sequence":[18],"alignment":[19],"is":[20,23,44,97],"proposed.":[21],"It":[22,54],"based":[24],"on":[25],"the":[26,57,72,78,83,114,119],"appearance":[27],"frequency":[28],"of":[29,31,52,59,82,86,99,108,122],"oligopeptides":[30],"a":[32,45,100,105],"fixed":[33],"length":[34],"(up":[35],"K":[37,110],"=":[38],"6)":[39],"in":[40,77,94],"proteomes.":[42],"This":[43],"fine":[48],"adjustment":[49],"choice":[51],"genes.":[53],"can":[55],"incorporate":[56],"effect":[58],"lateral":[60],"gene":[61],"transfer":[62],"some":[64],"extent":[65],"leads":[67],"results":[69],"comparable":[70],"with":[71],"bacteriologists'":[73],"systematics":[74],"as":[75],"reflected":[76],"latest":[79],"2001":[80],"edition":[81],"Bergey's":[84],"Manual":[85],"Systematic":[87],"Bacteriology":[88],"[1,":[89],"2].":[90],"key":[92],"point":[93],"our":[95],"approach":[96],"subtraction":[98],"random":[101],"background":[102],"by":[103],"Markovian":[106],"model":[107],"order":[109],"-":[111],"1":[112],"composition":[115],"vectors":[116],"highlight":[118],"shaping":[120],"role":[121],"natural":[123],"selection.":[124]},"counts_by_year":[{"year":2015,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
