{"id":"https://openalex.org/W2958637088","doi":"https://doi.org/10.1093/bioinformatics/btz551","title":"Look4TRs: a <i>de novo</i> tool for detecting simple tandem repeats using self-supervised hidden Markov models","display_name":"Look4TRs: a <i>de novo</i> tool for detecting simple tandem repeats using self-supervised hidden Markov models","publication_year":2019,"publication_date":"2019-07-08","ids":{"openalex":"https://openalex.org/W2958637088","doi":"https://doi.org/10.1093/bioinformatics/btz551","mag":"2958637088","pmid":"https://pubmed.ncbi.nlm.nih.gov/31287494"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btz551","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btz551","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/A5111164063","display_name":"Alfredo Velasco","orcid":null},"institutions":[{"id":"https://openalex.org/I87208437","display_name":"University of Tulsa","ror":"https://ror.org/04wn28048","country_code":"US","type":"education","lineage":["https://openalex.org/I87208437"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alfredo Velasco","raw_affiliation_strings":["Bioinformatics Toolsmith Laboratory, Tandy School of Computer Science, University of Tulsa The , Tulsa, OK 74104, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bioinformatics Toolsmith Laboratory, Tandy School of Computer Science, University of Tulsa The , Tulsa, OK 74104, USA","institution_ids":["https://openalex.org/I87208437"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063971635","display_name":"Benjamin T. James","orcid":"https://orcid.org/0000-0002-6228-055X"},"institutions":[{"id":"https://openalex.org/I87208437","display_name":"University of Tulsa","ror":"https://ror.org/04wn28048","country_code":"US","type":"education","lineage":["https://openalex.org/I87208437"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Benjamin T James","raw_affiliation_strings":["Bioinformatics Toolsmith Laboratory, Tandy School of Computer Science, University of Tulsa The , Tulsa, OK 74104, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bioinformatics Toolsmith Laboratory, Tandy School of Computer Science, University of Tulsa The , Tulsa, OK 74104, USA","institution_ids":["https://openalex.org/I87208437"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014111562","display_name":"V. Wells","orcid":null},"institutions":[{"id":"https://openalex.org/I87208437","display_name":"University of Tulsa","ror":"https://ror.org/04wn28048","country_code":"US","type":"education","lineage":["https://openalex.org/I87208437"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vincent D Wells","raw_affiliation_strings":["Bioinformatics Toolsmith Laboratory, Tandy School of Computer Science, University of Tulsa The , Tulsa, OK 74104, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bioinformatics Toolsmith Laboratory, Tandy School of Computer Science, University of Tulsa The , Tulsa, OK 74104, USA","institution_ids":["https://openalex.org/I87208437"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031037437","display_name":"Hani Z. Girgis","orcid":"https://orcid.org/0000-0002-6080-0320"},"institutions":[{"id":"https://openalex.org/I87208437","display_name":"University of Tulsa","ror":"https://ror.org/04wn28048","country_code":"US","type":"education","lineage":["https://openalex.org/I87208437"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Hani Z Girgis","raw_affiliation_strings":["Bioinformatics Toolsmith Laboratory, Tandy School of Computer Science, University of Tulsa The , Tulsa, OK 74104, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bioinformatics Toolsmith Laboratory, Tandy School of Computer Science, University of Tulsa The , Tulsa, OK 74104, USA","institution_ids":["https://openalex.org/I87208437"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5031037437"],"corresponding_institution_ids":["https://openalex.org/I87208437"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":null,"fwci":0.6072,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.65131462,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"36","issue":"2","first_page":"380","last_page":"387"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.5709999799728394,"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":0.5709999799728394,"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/T10012","display_name":"Genetic diversity and population structure","score":0.031599998474121094,"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"}},{"id":"https://openalex.org/T12946","display_name":"Fractal and DNA sequence analysis","score":0.01889999955892563,"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/hidden-markov-model","display_name":"Hidden Markov model","score":0.6611137390136719},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6499542593955994},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.6441463828086853},{"id":"https://openalex.org/keywords/tandem-repeat","display_name":"Tandem repeat","score":0.5619872808456421},{"id":"https://openalex.org/keywords/microsatellite","display_name":"Microsatellite","score":0.5335747599601746},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.5121650695800781},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.46423712372779846},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4321490526199341},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.4024639129638672},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3232421875},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.2729755640029907},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.23611778020858765},{"id":"https://openalex.org/keywords/genome","display_name":"Genome","score":0.14682281017303467},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.09052687883377075},{"id":"https://openalex.org/keywords/allele","display_name":"Allele","score":0.07181170582771301}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6611137390136719},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6499542593955994},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.6441463828086853},{"id":"https://openalex.org/C27149982","wikidata":"https://www.wikidata.org/wiki/Q3456514","display_name":"Tandem repeat","level":4,"score":0.5619872808456421},{"id":"https://openalex.org/C61320498","wikidata":"https://www.wikidata.org/wiki/Q265193","display_name":"Microsatellite","level":4,"score":0.5335747599601746},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.5121650695800781},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.46423712372779846},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4321490526199341},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.4024639129638672},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3232421875},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.2729755640029907},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.23611778020858765},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.14682281017303467},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.09052687883377075},{"id":"https://openalex.org/C180754005","wikidata":"https://www.wikidata.org/wiki/Q80726","display_name":"Allele","level":3,"score":0.07181170582771301},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[{"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":"D016680","descriptor_name":"Genome, Bacterial","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016680","descriptor_name":"Genome, Bacterial","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016680","descriptor_name":"Genome, Bacterial","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D018895","descriptor_name":"Microsatellite Repeats","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D018895","descriptor_name":"Microsatellite Repeats","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D018895","descriptor_name":"Microsatellite Repeats","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D056890","descriptor_name":"Eukaryota","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D056890","descriptor_name":"Eukaryota","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D056890","descriptor_name":"Eukaryota","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1093/bioinformatics/btz551","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btz551","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:31287494","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/31287494","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":[],"awards":[{"id":"https://openalex.org/G822455101","display_name":null,"funder_award_id":"PS17-015","funder_id":"https://openalex.org/F4320310627","funder_display_name":"Oklahoma Center for the Advancement of Science and Technology"}],"funders":[{"id":"https://openalex.org/F4320309552","display_name":"University of Tulsa","ror":"https://ror.org/04wn28048"},{"id":"https://openalex.org/F4320310627","display_name":"Oklahoma Center for the Advancement of Science and Technology","ror":"https://ror.org/02q578v20"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W1568479515","https://openalex.org/W1599106035","https://openalex.org/W1921457844","https://openalex.org/W1957444659","https://openalex.org/W1966585515","https://openalex.org/W1972924519","https://openalex.org/W1976049389","https://openalex.org/W1980073528","https://openalex.org/W1981779457","https://openalex.org/W1995819860","https://openalex.org/W2022077084","https://openalex.org/W2024054481","https://openalex.org/W2039752257","https://openalex.org/W2050712839","https://openalex.org/W2065853059","https://openalex.org/W2076490142","https://openalex.org/W2077114056","https://openalex.org/W2081561808","https://openalex.org/W2102007365","https://openalex.org/W2106263380","https://openalex.org/W2112814753","https://openalex.org/W2113130665","https://openalex.org/W2130396264","https://openalex.org/W2138000345","https://openalex.org/W2146683382","https://openalex.org/W2149459456","https://openalex.org/W2151831732","https://openalex.org/W2160382198","https://openalex.org/W2168475193","https://openalex.org/W2171777347","https://openalex.org/W2171787842","https://openalex.org/W2321404089","https://openalex.org/W2329659234","https://openalex.org/W2413005112","https://openalex.org/W2605276928","https://openalex.org/W2735337418","https://openalex.org/W2751152975","https://openalex.org/W2767665981","https://openalex.org/W2793054360","https://openalex.org/W2802282671","https://openalex.org/W4243117950","https://openalex.org/W6740608477"],"related_works":["https://openalex.org/W2121546023","https://openalex.org/W2058825091","https://openalex.org/W4223943358","https://openalex.org/W4236068647","https://openalex.org/W2385170838","https://openalex.org/W1510894296","https://openalex.org/W2134386692","https://openalex.org/W2084326697","https://openalex.org/W2194396582","https://openalex.org/W2027903142"],"abstract_inverted_index":{"MOTIVATION:":[0],"Simple":[1],"tandem":[2],"repeats,":[3],"microsatellites":[4,29],"in":[5,16,30],"particular,":[6],"have":[7],"regulatory":[8],"functions,":[9],"links":[10],"to":[11,64,70],"several":[12],"diseases":[13],"and":[14,77,99,106,113,119,125,129,139,146],"applications":[15],"biotechnology.":[17],"There":[18],"is":[19],"an":[20,24],"immediate":[21],"need":[22],"for":[23,27],"accurate":[25],"tool":[26],"detecting":[28],"newly":[31],"sequenced":[32],"genomes.":[33,91],"The":[34],"current":[35],"available":[36,157],"tools":[37,47,143],"are":[38,156],"either":[39],"sensitive":[40],"or":[41],"specific":[42],"but":[43],"not":[44],"both;":[45],"some":[46],"require":[48],"adjusting":[49],"parameters":[50],"manually.":[51],"RESULTS:":[52],"We":[53,85],"propose":[54],"Look4TRs,":[55],"the":[56,71,117,120,137,140],"first":[57],"application":[58],"of":[59],"self-supervised":[60],"hidden":[61],"Markov":[62],"models":[63],"discovering":[65],"microsatellites.":[66],"Look4TRs":[67,87,103,115,135],"adapts":[68],"itself":[69],"input":[72],"genomes,":[73,134],"balancing":[74],"high":[75],"sensitivity":[76,98],"low":[78],"false":[79,100],"positive":[80,101],"rate.":[81],"It":[82],"auto-calibrates":[83],"itself.":[84],"evaluated":[86],"on":[88,93],"26":[89],"eukaryotic":[90],"Based":[92],"F":[94],"measure,":[95],"which":[96],"combines":[97],"rate,":[102],"outperformed":[104,116,136],"TRF":[105],"MISA-the":[107],"most":[108],"widely":[109],"used":[110],"tools-by":[111],"78":[112],"84%.":[114],"second":[118,138],"third":[121,141],"best":[122,142],"tools,":[123],"MsDetector":[124],"Tantan,":[126],"by":[127,144],"17":[128],"34%.":[130],"On":[131],"eight":[132],"bacterial":[133],"27":[145],"137%.":[147],"AVAILABILITY":[148],"AND":[149],"IMPLEMENTATION:":[150],"https://github.com/TulsaBioinformaticsToolsmith/Look4TRs.":[151],"SUPPLEMENTARY":[152],"INFORMATION:":[153],"Supplementary":[154],"data":[155],"at":[158],"Bioinformatics":[159],"online.":[160]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1}],"updated_date":"2026-07-30T17:31:21.811387","created_date":"2019-07-23T00:00:00"}
