{"id":"https://openalex.org/W2122804925","doi":"https://doi.org/10.1093/bioinformatics/btm405","title":"Identification of compositionally distinct regions in genomes using the centroid method","display_name":"Identification of compositionally distinct regions in genomes using the centroid method","publication_year":2007,"publication_date":"2007-08-27","ids":{"openalex":"https://openalex.org/W2122804925","doi":"https://doi.org/10.1093/bioinformatics/btm405","mag":"2122804925","pmid":"https://pubmed.ncbi.nlm.nih.gov/17724060"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btm405","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btm405","pdf_url":null,"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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5089669269","display_name":"Issaac Rajan","orcid":null},"institutions":[{"id":"https://openalex.org/I55215948","display_name":"Tata Consultancy Services (India)","ror":"https://ror.org/01b9n8m42","country_code":"IN","type":"company","lineage":["https://openalex.org/I4210086519","https://openalex.org/I55215948"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Issaac Rajan","raw_affiliation_strings":["1 Life Sciences Research and 2e-Security R&D, Advanced Technology Centre, Tata Consultancy Services, Hyderabad 500 081, Andhra Pradesh, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"1 Life Sciences Research and 2e-Security R&D, Advanced Technology Centre, Tata Consultancy Services, Hyderabad 500 081, Andhra Pradesh, India","institution_ids":["https://openalex.org/I55215948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071818365","display_name":"Sarang Aravamuthan","orcid":null},"institutions":[{"id":"https://openalex.org/I55215948","display_name":"Tata Consultancy Services (India)","ror":"https://ror.org/01b9n8m42","country_code":"IN","type":"company","lineage":["https://openalex.org/I4210086519","https://openalex.org/I55215948"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sarang Aravamuthan","raw_affiliation_strings":["1 Life Sciences Research and 2e-Security R&D, Advanced Technology Centre, Tata Consultancy Services, Hyderabad 500 081, Andhra Pradesh, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"1 Life Sciences Research and 2e-Security R&D, Advanced Technology Centre, Tata Consultancy Services, Hyderabad 500 081, Andhra Pradesh, India","institution_ids":["https://openalex.org/I55215948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053125644","display_name":"Sharmila S. Mande","orcid":"https://orcid.org/0000-0002-2614-1982"},"institutions":[{"id":"https://openalex.org/I55215948","display_name":"Tata Consultancy Services (India)","ror":"https://ror.org/01b9n8m42","country_code":"IN","type":"company","lineage":["https://openalex.org/I4210086519","https://openalex.org/I55215948"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sharmila S. Mande","raw_affiliation_strings":["1 Life Sciences Research and 2e-Security R&D, Advanced Technology Centre, Tata Consultancy Services, Hyderabad 500 081, Andhra Pradesh, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"1 Life Sciences Research and 2e-Security R&D, Advanced Technology Centre, Tata Consultancy Services, Hyderabad 500 081, Andhra Pradesh, India","institution_ids":["https://openalex.org/I55215948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I55215948"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":null,"fwci":1.3324,"has_fulltext":false,"cited_by_count":59,"citation_normalized_percentile":{"value":0.7969873,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"23","issue":"20","first_page":"2672","last_page":"2677"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.42239999771118164,"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":0.42239999771118164,"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/T12946","display_name":"Fractal and DNA sequence analysis","score":0.19140000641345978,"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/T13664","display_name":"Genome Rearrangement Algorithms","score":0.06109999865293503,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"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/genome","display_name":"Genome","score":0.7982787489891052},{"id":"https://openalex.org/keywords/centroid","display_name":"Centroid","score":0.7979133129119873},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.724424421787262},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.579625129699707},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.5502434372901917},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4640914797782898},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.4437708556652069},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.43236345052719116},{"id":"https://openalex.org/keywords/strain","display_name":"Strain (injury)","score":0.41801023483276367},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.3705540895462036},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.3328961730003357},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.20181533694267273},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08014199137687683}],"concepts":[{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.7982787489891052},{"id":"https://openalex.org/C146599234","wikidata":"https://www.wikidata.org/wiki/Q511093","display_name":"Centroid","level":2,"score":0.7979133129119873},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.724424421787262},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.579625129699707},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.5502434372901917},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4640914797782898},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.4437708556652069},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.43236345052719116},{"id":"https://openalex.org/C2778022156","wikidata":"https://www.wikidata.org/wiki/Q576145","display_name":"Strain (injury)","level":2,"score":0.41801023483276367},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.3705540895462036},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3328961730003357},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.20181533694267273},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08014199137687683},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C105702510","wikidata":"https://www.wikidata.org/wiki/Q514","display_name":"Anatomy","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"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":"D002874","descriptor_name":"Chromosome Mapping","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D002874","descriptor_name":"Chromosome Mapping","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D002874","descriptor_name":"Chromosome Mapping","qualifier_ui":"Q000379","qualifier_name":"methods","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":"D008969","descriptor_name":"Molecular Sequence Data","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016680","descriptor_name":"Genome, Bacterial","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D016680","descriptor_name":"Genome, Bacterial","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D016680","descriptor_name":"Genome, Bacterial","qualifier_ui":"Q000235","qualifier_name":"genetics","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":"D037521","descriptor_name":"Virulence Factors","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D037521","descriptor_name":"Virulence Factors","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D037521","descriptor_name":"Virulence Factors","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D044404","descriptor_name":"Genomic Islands","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D044404","descriptor_name":"Genomic Islands","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D044404","descriptor_name":"Genomic Islands","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1093/bioinformatics/btm405","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btm405","pdf_url":null,"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:17724060","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/17724060","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":null,"sustainable_development_goals":[{"display_name":"Life below water","score":0.8600000143051147,"id":"https://metadata.un.org/sdg/14"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320313903","display_name":"Tata Consultancy Services","ror":"https://ror.org/01b9n8m42"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1906780201","https://openalex.org/W1944107535","https://openalex.org/W1966336245","https://openalex.org/W1971192547","https://openalex.org/W2018983884","https://openalex.org/W2040745248","https://openalex.org/W2043627486","https://openalex.org/W2047531378","https://openalex.org/W2052178620","https://openalex.org/W2054275184","https://openalex.org/W2063699100","https://openalex.org/W2099599852","https://openalex.org/W2105801693","https://openalex.org/W2115095549","https://openalex.org/W2116183012","https://openalex.org/W2125872703","https://openalex.org/W2128584436","https://openalex.org/W2132682438","https://openalex.org/W2132732087","https://openalex.org/W2140320695","https://openalex.org/W2142392294","https://openalex.org/W2158023121","https://openalex.org/W2165533158","https://openalex.org/W2167417066","https://openalex.org/W2170959083","https://openalex.org/W6679166915","https://openalex.org/W6684430665"],"related_works":["https://openalex.org/W2002128513","https://openalex.org/W2092874662","https://openalex.org/W2171277769","https://openalex.org/W2389073067","https://openalex.org/W2360025963","https://openalex.org/W1991523530","https://openalex.org/W3037260512","https://openalex.org/W2187207551","https://openalex.org/W2069184423","https://openalex.org/W1603543036"],"abstract_inverted_index":{"MOTIVATION:":[0],"It":[1],"is":[2,138],"known":[3],"that":[4,40],"most":[5],"genomic":[6,15,64],"regions":[7,62,103],"of":[8,24,47,88,101,133],"special":[9],"interest,":[10],"e.g.":[11],"horizontally":[12],"acquired":[13],"sequences,":[14],"islands,":[16],"etc.":[17],"have":[18],"distinct":[19,61,107],"word":[20,50,69],"(m-mer)":[21],"compositions.":[22,35],"Most":[23],"the":[25,55,98,102,143],"earlier":[26],"work":[27],"along":[28],"this":[29],"direction,":[30],"addressed":[31],"di-":[32],"and":[33,80,121],"tri-nucleotide":[34],"We":[36,72,95],"present":[37],"an":[38],"approach":[39],"can":[41,58],"be":[42,131],"applied":[43,73],"to":[44,76,84,130],"analyze":[45],"compositions":[46],"any":[48,67],"given":[49,68],"size.":[51,70],"The":[52],"method,":[53,110],"called":[54],"centroid":[56],"approach,":[57],"reveal":[59],"compositionally":[60,106],"in":[63],"sequences":[65,87],"for":[66,111],"RESULTS:":[71],"our":[74,109,115],"method":[75],"50":[77],"bacterial":[78],"genomes":[79],"demonstrated":[81],"its":[82],"ability":[83],"identify":[85],"embedded":[86],"varying":[89],"lengths":[90],"from":[91,114,142],"distantly":[92],"related":[93],"organisms.":[94],"also":[96],"investigated":[97],"genetic":[99],"makeup":[100],"identified":[104],"as":[105],"by":[108],"four":[112],"organisms":[113],"dataset.":[116],"Pathogenicity":[117],"island":[118],"(PAI)":[119],"components":[120],"genes":[122],"encoding":[123],"strain-specific":[124],"proteins":[125],"are":[126,149],"all":[127],"frequently":[128],"seen":[129],"constituents":[132],"these":[134],"regions.":[135],"AVAILABILITY:":[136],"Program":[137],"available":[139,150],"on":[140],"request":[141],"authors.":[144],"SUPPLEMENTARY":[145],"INFORMATION:":[146],"Supplementary":[147],"data":[148],"at":[151],"Bioinformatics":[152],"online.":[153]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":7},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":7},{"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"}
