{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,8,4]],"date-time":"2024-08-04T21:18:45Z","timestamp":1722806325762},"reference-count":15,"publisher":"Oxford University Press (OUP)","issue":"1","license":[{"start":{"date-parts":[[2016,9,10]],"date-time":"2016-09-10T00:00:00Z","timestamp":1473465600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/journals\/pages\/about_us\/legal\/notices"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017,1,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Summary<\/jats:title>\n                  <jats:p>Detecting homologous sequences in organisms is an essential step in protein structure and function prediction, gene annotation and phylogenetic tree construction. Heuristic methods are often employed for quality control of putative homology clusters. These heuristics, however, usually only apply to pairwise sequence comparison and do not examine clusters as a whole. We present the Orthology Group Cleaner (the OGCleaner), a tool designed for filtering putative orthology groups as homology or non-homology clusters by considering all sequences in a cluster. The OGCleaner relies on high-quality orthologous groups identified in OrthoDB to train machine learning algorithms that are able to distinguish between true-positive and false-positive homology groups. This package aims to improve the quality of phylogenetic tree construction especially in instances of lower-quality transcriptome assemblies.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Availability and Implementation<\/jats:title>\n                  <jats:p>https:\/\/github.com\/byucsl\/ogcleaner<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Supplementary information<\/jats:title>\n                  <jats:p>Supplementary data are available at Bioinformatics online.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btw571","type":"journal-article","created":{"date-parts":[[2016,9,11]],"date-time":"2016-09-11T00:28:40Z","timestamp":1473553720000},"page":"125-127","source":"Crossref","is-referenced-by-count":6,"title":["The OGCleaner: filtering false-positive homology clusters"],"prefix":"10.1093","volume":"33","author":[{"given":"M Stanley","family":"Fujimoto","sequence":"first","affiliation":[{"name":"Computer Science Department, Brigham Young University, Provo, UT, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anton","family":"Suvorov","sequence":"additional","affiliation":[{"name":"Department of Biology, Brigham Young University, Provo, UT, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nicholas O","family":"Jensen","sequence":"additional","affiliation":[{"name":"Department of Biology, Brigham Young University, Provo, UT, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mark J","family":"Clement","sequence":"additional","affiliation":[{"name":"Computer Science Department, Brigham Young University, Provo, UT, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Quinn","family":"Snell","sequence":"additional","affiliation":[{"name":"Computer Science Department, Brigham Young University, Provo, UT, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Seth M","family":"Bybee","sequence":"additional","affiliation":[{"name":"Department of Biology, Brigham Young University, Provo, UT, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"286","published-online":{"date-parts":[[2016,9,10]]},"reference":[{"key":"2023020204203639500_btw571-B1","doi-asserted-by":"crossref","first-page":"425","DOI":"10.1038\/nmeth.3830","article-title":"Standardized benchmarking in the quest for orthologs","volume":"13","author":"Altenhoff","year":"2016","journal-title":"Nat. Methods"},{"key":"2023020204203639500_btw571-B2","doi-asserted-by":"crossref","first-page":"D71","DOI":"10.1093\/nar\/gkr981","article-title":"Reorganizing the protein space at the universal protein resource (uniprot)","volume":"40","author":"Consortium","year":"2012","journal-title":"Nucleic Acids Res"},{"key":"2023020204203639500_btw571-B3","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s12859-016-0955-3","article-title":"Detecting false positive sequence homology: a machine learning approach","volume":"17","author":"Fujimoto","year":"2016","journal-title":"BMC Bioinf"},{"key":"2023020204203639500_btw571-B4","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/gb-2009-10-9-403","article-title":"Joining forces in the quest for orthologs","volume":"10","author":"Gabald\u00f3n","year":"2009","journal-title":"Genome Biol"},{"key":"2023020204203639500_btw571-B5","doi-asserted-by":"crossref","first-page":"90","DOI":"10.1109\/MCSE.2007.55","article-title":"Matplotlib: A 2d graphics environment","volume":"9","author":"Hunter","year":"2007","journal-title":"Comput. Sci. Eng"},{"key":"2023020204203639500_btw571-B6","doi-asserted-by":"crossref","first-page":"772","DOI":"10.1093\/molbev\/mst010","article-title":"Mafft multiple sequence alignment software version 7: improvements in performance and usability","volume":"30","author":"Katoh","year":"2013","journal-title":"Mol. Biol. Evol"},{"key":"2023020204203639500_btw571-B7","doi-asserted-by":"crossref","first-page":"D250","DOI":"10.1093\/nar\/gku1220","article-title":"Orthodb v8: update of the hierarchical catalog of orthologs and the underlying free software","volume":"43","author":"Kriventseva","year":"2015","journal-title":"Nucleic Acids Res"},{"key":"2023020204203639500_btw571-B8","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/1742-9994-7-10","article-title":"Parametric and non-parametric masking of randomness in sequence alignments can be improved and leads to better resolved trees","volume":"7","author":"K\u00fcck","year":"2010","journal-title":"Front. Zool"},{"key":"2023020204203639500_btw571-B9","doi-asserted-by":"crossref","first-page":"2178","DOI":"10.1101\/gr.1224503","article-title":"Orthomcl: identification of ortholog groups for eukaryotic genomes","volume":"13","author":"Li","year":"2003","journal-title":"Genome Res"},{"key":"2023020204203639500_btw571-B10","first-page":"51","volume-title":"Proceedings of the 9th Python in Science Conference","author":"McKinney","year":"2010"},{"key":"2023020204203639500_btw571-B11","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1093\/sysbio\/syp006","article-title":"A monte carlo approach successfully identifies randomness in multiple sequence alignments: a more objective means of data exclusion","volume":"58","author":"Misof","year":"2009","journal-title":"Syst. Biol"},{"key":"2023020204203639500_btw571-B12","first-page":"2825","article-title":"Scikit-learn: machine learning in Python","volume":"12","author":"Pedregosa","year":"2011","journal-title":"J. Mach. Learn. Res"},{"key":"2023020204203639500_btw571-B13","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1109\/MCSE.2007.53","article-title":"IPython: a system for interactive scientific computing","volume":"9","author":"P\u00e9rez","year":"2007","journal-title":"Comput. Sci. Eng"},{"key":"2023020204203639500_btw571-B14","first-page":"235","article-title":"Seq-gen: an application for the Monte Carlo simulation of DNA sequence evolution along phylogenetic trees","volume":"13","author":"Rambaut","year":"1997","journal-title":"Comput. Appl. Biosci. CABIOS"},{"key":"2023020204203639500_btw571-B15","first-page":"1586","article-title":"PAML 4: Phylogenetic Analysis by Maximum Likelihood","volume-title":"Mol. Biol. Evol","author":"Yang","year":"2007"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/33\/1\/125\/49037315\/bioinformatics_33_1_125.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/33\/1\/125\/49037315\/bioinformatics_33_1_125.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,2,2]],"date-time":"2023-02-02T04:21:12Z","timestamp":1675311672000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/33\/1\/125\/2525682"}},"subtitle":[],"editor":[{"given":"Alfonso","family":"Valencia","sequence":"additional","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2016,9,10]]},"references-count":15,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2017,1,1]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btw571","relation":{},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"value":"1367-4803","type":"print"},{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2017,1,1]]},"published":{"date-parts":[[2016,9,10]]}}}