{"id":"https://openalex.org/W2095598699","doi":"https://doi.org/10.1093/bioinformatics/btm048","title":"HomologMiner: looking for homologous genomic groups in whole genomes","display_name":"HomologMiner: looking for homologous genomic groups in whole genomes","publication_year":2007,"publication_date":"2007-02-18","ids":{"openalex":"https://openalex.org/W2095598699","doi":"https://doi.org/10.1093/bioinformatics/btm048","mag":"2095598699","pmid":"https://pubmed.ncbi.nlm.nih.gov/17308341"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btm048","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btm048","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/23/8/917/49822144/bioinformatics_23_8_917.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/23/8/917/49822144/bioinformatics_23_8_917.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5018863394","display_name":"Minmei Hou","orcid":null},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Minmei Hou","raw_affiliation_strings":["Department of Computer Science & Engineering, Penn State University, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science & Engineering, Penn State University, PA, USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023910624","display_name":"Piotr Berman","orcid":null},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Piotr Berman","raw_affiliation_strings":["Department of Computer Science & Engineering, Penn State University, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science & Engineering, Penn State University, PA, USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110360051","display_name":"Chih-Hao Hsu","orcid":null},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chih-Hao Hsu","raw_affiliation_strings":["Department of Computer Science & Engineering, Penn State University, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science & Engineering, Penn State University, PA, USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074817739","display_name":"Robert S. Harris","orcid":"https://orcid.org/0000-0001-5464-6892"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Robert S. Harris","raw_affiliation_strings":["Department of Computer Science & Engineering, Penn State University, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science & Engineering, Penn State University, PA, USA","institution_ids":["https://openalex.org/I130769515"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5018863394"],"corresponding_institution_ids":["https://openalex.org/I130769515"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":null,"fwci":1.1087,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.85888218,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"23","issue":"8","first_page":"917","last_page":"925"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.299699991941452,"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"}},"topics":[{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.299699991941452,"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/T12946","display_name":"Fractal and DNA sequence analysis","score":0.2750000059604645,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.267300009727478,"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/genome","display_name":"Genome","score":0.7436414957046509},{"id":"https://openalex.org/keywords/tandem-repeat","display_name":"Tandem repeat","score":0.6942269206047058},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.6626137495040894},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.584682285785675},{"id":"https://openalex.org/keywords/tandem-exon-duplication","display_name":"Tandem exon duplication","score":0.5179527997970581},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.5013606548309326},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.4794146716594696},{"id":"https://openalex.org/keywords/gene-duplication","display_name":"Gene duplication","score":0.44874024391174316},{"id":"https://openalex.org/keywords/direct-repeat","display_name":"Direct repeat","score":0.4358586072921753}],"concepts":[{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.7436414957046509},{"id":"https://openalex.org/C27149982","wikidata":"https://www.wikidata.org/wiki/Q3456514","display_name":"Tandem repeat","level":4,"score":0.6942269206047058},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.6626137495040894},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.584682285785675},{"id":"https://openalex.org/C156446351","wikidata":"https://www.wikidata.org/wiki/Q7682435","display_name":"Tandem exon duplication","level":4,"score":0.5179527997970581},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.5013606548309326},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.4794146716594696},{"id":"https://openalex.org/C7602840","wikidata":"https://www.wikidata.org/wiki/Q746284","display_name":"Gene duplication","level":3,"score":0.44874024391174316},{"id":"https://openalex.org/C29511175","wikidata":"https://www.wikidata.org/wiki/Q5280381","display_name":"Direct repeat","level":4,"score":0.4358586072921753}],"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":"D012091","descriptor_name":"Repetitive Sequences, Nucleic Acid","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D012091","descriptor_name":"Repetitive Sequences, Nucleic Acid","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D012091","descriptor_name":"Repetitive Sequences, Nucleic Acid","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D012689","descriptor_name":"Sequence Homology, Nucleic Acid","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012689","descriptor_name":"Sequence Homology, Nucleic Acid","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012689","descriptor_name":"Sequence Homology, Nucleic Acid","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","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":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false}],"locations_count":4,"locations":[{"id":"doi:10.1093/bioinformatics/btm048","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btm048","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/23/8/917/49822144/bioinformatics_23_8_917.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:17308341","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/17308341","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},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.108.607","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.108.607","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://bioinformatics.oxfordjournals.org/cgi/reprint/23/8/917.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.324.9488","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.324.9488","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://bioinformatics.oxfordjournals.org/content/23/8/917.full.pdf","raw_type":"text"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btm048","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btm048","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/23/8/917/49822144/bioinformatics_23_8_917.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":[{"id":"https://openalex.org/G4989899780","display_name":null,"funder_award_id":"HG 02238","funder_id":"https://openalex.org/F4320337348","funder_display_name":"National Human Genome Research Institute"}],"funders":[{"id":"https://openalex.org/F4320337348","display_name":"National Human Genome Research Institute","ror":"https://ror.org/00baak391"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2095598699.pdf"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W1537270317","https://openalex.org/W1576445761","https://openalex.org/W2019647140","https://openalex.org/W2057998009","https://openalex.org/W2060434878","https://openalex.org/W2099809434","https://openalex.org/W2109550992","https://openalex.org/W2112132489","https://openalex.org/W2122954888","https://openalex.org/W2124166542","https://openalex.org/W2128016314","https://openalex.org/W2133767259","https://openalex.org/W2138366649","https://openalex.org/W2144268209","https://openalex.org/W2147758638","https://openalex.org/W2151899848","https://openalex.org/W2155520400","https://openalex.org/W2158714788","https://openalex.org/W2159077471","https://openalex.org/W3111526966","https://openalex.org/W3145128584","https://openalex.org/W6632233322","https://openalex.org/W6634381264","https://openalex.org/W6683498667"],"related_works":["https://openalex.org/W1984349060","https://openalex.org/W3185201469","https://openalex.org/W2120250745","https://openalex.org/W1883409887","https://openalex.org/W2106870860","https://openalex.org/W3142592327","https://openalex.org/W1978469902","https://openalex.org/W1977690075","https://openalex.org/W1966020515","https://openalex.org/W2134993229"],"abstract_inverted_index":{"MOTIVATION:":[0],"Complex":[1],"genomes":[2,134,207],"contain":[3],"numerous":[4],"repeated":[5],"sequences,":[6],"and":[7,32,49,68,124,140,159,192,210,221,229],"genomic":[8],"duplication":[9],"is":[10],"believed":[11],"to":[12,18,47,108,113,131,186],"be":[13],"a":[14,86,90,94,98,104,175,183],"main":[15],"evolutionary":[16],"mechanism":[17],"obtain":[19],"new":[20,45,173,176,184,193],"functions.":[21],"Several":[22],"tools":[23],"are":[24,231],"available":[25],"for":[26,36,121],"de":[27],"novo":[28],"repeat":[29,224],"sequence":[30],"identification,":[31],"many":[33],"approaches":[34],"exist":[35],"clustering":[37],"homologous":[38,51,110,161],"protein":[39,99],"sequences.":[40],"We":[41,72,102,128,196],"present":[42],"an":[43],"efficient":[44],"approach":[46],"identify":[48,109],"cluster":[50],"DNA":[52],"sequences":[53,115],"with":[54],"high":[55],"accuracy":[56],"at":[57],"the":[58,75,132,202,205],"level":[59],"of":[60,77,135,179,201,217],"whole":[61,133],"genomes,":[62],"excluding":[63],"low-complexity":[64,122],"repeats,":[65,191],"tandem":[66,190,218],"repeats":[67,123,158],"annotated":[69,125],"interspersed":[70,126,157,223],"repeats.":[71,127],"also":[73,197],"determine":[74],"boundaries":[76,216],"each":[78],"group":[79],"member":[80],"so":[81],"that":[82,116,163],"it":[83,130],"closely":[84],"represents":[85],"biological":[87],"unit,":[88],"e.g.":[89],"complete":[91],"gene,":[92],"or":[93],"partial":[95],"gene":[96,146,151,219],"coding":[97],"domain.":[100],"RESULTS:":[101],"developed":[103],"program":[105,170],"called":[106],"HomologMiner":[107],"groups":[111,162],"applicable":[112],"genome":[114],"have":[117],"been":[118],"properly":[119],"marked":[120],"applied":[129],"human":[136],"(hg17),":[137],"macaque":[138],"(rheMac2)":[139],"mouse":[141],"(mm8).":[142],"Groups":[143],"obtained":[144],"include":[145],"families":[147],"(e.g.":[148],"olfactory":[149],"receptor":[150],"family,":[152],"zinc":[153],"finger":[154],"families),":[155],"unannotated":[156],"additional":[160],"resulted":[164],"from":[165,233],"recent":[166],"segmental":[167],"duplications.":[168],"Our":[169],"incorporates":[171],"several":[172,212],"methods:":[174],"abstract":[177],"definition":[178],"consistent":[180],"duplicate":[181],"units,":[182],"criterion":[185],"remove":[187],"moderately":[188],"frequent":[189],"algorithmic":[194],"techniques.":[195],"provide":[198],"preliminary":[199],"analysis":[200],"output":[203],"on":[204],"three":[206],"mentioned":[208],"above,":[209],"show":[211],"applications":[213],"including":[214],"identifying":[215],"clusters":[220],"novel":[222],"families.":[225],"AVAILABILITY:":[226],"All":[227],"programs":[228],"datasets":[230],"downloadable":[232],"www.bx.psu.edu/miller_lab.":[234]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2013,"cited_by_count":2}],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2025-10-10T00:00:00"}