{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T01:58:53Z","timestamp":1775613533234,"version":"3.50.1"},"reference-count":15,"publisher":"Oxford University Press (OUP)","issue":"10","license":[{"start":{"date-parts":[[2020,2,25]],"date-time":"2020-02-25T00:00:00Z","timestamp":1582588800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/journals\/pages\/open_access\/funder_policies\/chorus\/standard_publication_model"}],"funder":[{"name":"H2020-MSCA-RISE project REFRACT","award":["823886"],"award-info":[{"award-number":["823886"]}]},{"DOI":"10.13039\/100000060","name":"National Institute of Allergy and Infectious Diseases","doi-asserted-by":"publisher","award":["1R01AI12123701"],"award-info":[{"award-number":["1R01AI12123701"]}],"id":[{"id":"10.13039\/100000060","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004564","name":"Ministry of Education, Science and Technological Development of the Republic of Serbia","doi-asserted-by":"publisher","award":["173001"],"award-info":[{"award-number":["173001"]}],"id":[{"id":"10.13039\/501100004564","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020,5,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Motivation<\/jats:title>\n                  <jats:p>Proteins containing tandem repeats (TRs) are abundant, frequently fold in elongated non-globular structures and perform vital functions. A number of computational tools have been developed to detect TRs in protein sequences. A blurred boundary between imperfect TR motifs and non-repetitive sequences gave rise to necessity to validate the detected TRs.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>Tally-2.0 is a scoring tool based on a machine learning (ML) approach, which allows to validate the results of TR detection. It was upgraded by using improved training datasets and additional ML features. Tally-2.0 performs at a level of 93% sensitivity, 83% specificity and an area under the receiver operating characteristic curve of 95%.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Availability and implementation<\/jats:title>\n                  <jats:p>Tally-2.0 is available, as a web tool and as a standalone application published under Apache License 2.0, on the URL https:\/\/bioinfo.crbm.cnrs.fr\/index.php? route=tools&amp;tool=27. It is supported on Linux. Source code is available upon request.<\/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\/btaa121","type":"journal-article","created":{"date-parts":[[2020,2,18]],"date-time":"2020-02-18T20:13:28Z","timestamp":1582056808000},"page":"3260-3262","source":"Crossref","is-referenced-by-count":5,"title":["Tally-2.0: upgraded validator of tandem repeat detection in protein sequences"],"prefix":"10.1093","volume":"36","author":[{"given":"Vladimir","family":"Perovic","sequence":"first","affiliation":[{"name":"Laboratory for Bioinformatics and Computational Chemistry , Institute of Nuclear Sciences VINCA, University of Belgrade, Belgrade 11001, Serbia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jeremy Y","family":"Leclercq","sequence":"additional","affiliation":[{"name":"Centre de Recherche en Biologie cellulaire de Montpellier , UMR 5237 CNRS, Universit\u00e9 de Montpellier, Montpellier 34293, France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Neven","family":"Sumonja","sequence":"additional","affiliation":[{"name":"Laboratory for Bioinformatics and Computational Chemistry , Institute of Nuclear Sciences VINCA, University of Belgrade, Belgrade 11001, Serbia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Francois D","family":"Richard","sequence":"additional","affiliation":[{"name":"Centre de Recherche en Biologie cellulaire de Montpellier , UMR 5237 CNRS, Universit\u00e9 de Montpellier, Montpellier 34293, France"},{"name":"Laboratory for Translational Breast Cancer Research , Department of Oncology, KU Leuven, Leuven 3000, Belgium"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nevena","family":"Veljkovic","sequence":"additional","affiliation":[{"name":"Laboratory for Bioinformatics and Computational Chemistry , Institute of Nuclear Sciences VINCA, University of Belgrade, Belgrade 11001, Serbia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andrey V","family":"Kajava","sequence":"additional","affiliation":[{"name":"Centre de Recherche en Biologie cellulaire de Montpellier , UMR 5237 CNRS, Universit\u00e9 de Montpellier, Montpellier 34293, France"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"286","published-online":{"date-parts":[[2020,2,25]]},"reference":[{"key":"2023013112030631300_btaa121-B1","doi-asserted-by":"crossref","first-page":"115","DOI":"10.1038\/ng1095-115","article-title":"HEAT repeats in the Huntington\u2019s disease protein","volume":"11","author":"Andrade","year":"1995","journal-title":"Nat. Genet"},{"key":"2023013112030631300_btaa121-B2","doi-asserted-by":"crossref","first-page":"807","DOI":"10.1093\/bioinformatics\/btn039","article-title":"De novo identification of highly diverged protein repeats by probabilistic consistency","volume":"24","author":"Biegert","year":"2008","journal-title":"Bioinformatics"},{"key":"2023013112030631300_btaa121-B3","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random forest","volume":"45","author":"Breiman","year":"2001","journal-title":"Machine Learn"},{"key":"2023013112030631300_btaa121-B4","volume-title":"Conformation in Fibrous Proteins and Related Synthetic Polypeptides","author":"Fraser","year":"1973"},{"key":"2023013112030631300_btaa121-B5","doi-asserted-by":"crossref","first-page":"2632","DOI":"10.1093\/bioinformatics\/btp482","article-title":"T-REKS: identification of Tandem REpeats in sequences with a K-meanS based algorithm","volume":"25","author":"Jorda","year":"2009","journal-title":"Bioinformatics"},{"key":"2023013112030631300_btaa121-B6","doi-asserted-by":"crossref","first-page":"279","DOI":"10.1016\/j.jsb.2011.08.009","article-title":"Tandem repeats in proteins: from sequence to structure","volume":"179","author":"Kajava","year":"2012","journal-title":"J. Struct. Biol"},{"key":"2023013112030631300_btaa121-B7","doi-asserted-by":"crossref","first-page":"725","DOI":"10.1016\/S0959-440X(01)00266-4","article-title":"The leucine-rich repeat as a protein recognition motif","volume":"11","author":"Kobe","year":"2001","journal-title":"Curr. Opin. Struct. Biol"},{"key":"2023013112030631300_btaa121-B8","doi-asserted-by":"crossref","first-page":"151","DOI":"10.1006\/jmbi.1999.3136","article-title":"A census of protein repeats","volume":"293","author":"Marcotte","year":"1999","journal-title":"J. Mol. Biol"},{"key":"2023013112030631300_btaa121-B9","doi-asserted-by":"crossref","first-page":"93","DOI":"10.1093\/protein\/2.2.93","article-title":"Cluster analysis of amino acid indices for prediction of protein structure and function","volume":"2","author":"Nakai","year":"1988","journal-title":"Prot. Eng"},{"key":"2023013112030631300_btaa121-B10","doi-asserted-by":"crossref","first-page":"143","DOI":"10.3389\/fbioe.2015.00143","article-title":"Tandem repeats in proteins: prediction algorithms and biological role","volume":"3","author":"Pellegrini","year":"2015","journal-title":"Front. Bioeng. Biotechnol"},{"key":"2023013112030631300_btaa121-B11","doi-asserted-by":"crossref","first-page":"1952","DOI":"10.1093\/bioinformatics\/btw118","article-title":"Tally: a scoring tool for boundary determination between repetitive and non-repetitive protein sequences","volume":"32","author":"Richard","year":"2016","journal-title":"Bioinformatics"},{"key":"2023013112030631300_btaa121-B12","doi-asserted-by":"crossref","first-page":"807","DOI":"10.1042\/BST20150073","article-title":"In search of the boundary between repetitive and non-repetitive protein sequences","volume":"43","author":"Richard","year":"2015","journal-title":"Biochem. Soc. Trans"},{"key":"2023013112030631300_btaa121-B13","doi-asserted-by":"crossref","first-page":"2507","DOI":"10.1093\/bioinformatics\/btm344","article-title":"A review of feature selection techniques in bioinformatics","volume":"23","author":"Saeys","year":"2007","journal-title":"Bioinformatics"},{"key":"2023013112030631300_btaa121-B14","doi-asserted-by":"crossref","first-page":"i311","DOI":"10.1093\/bioinformatics\/bth911","article-title":"Tracking repeats using significance and transitivity","volume":"20 (Suppl. 1","author":"Szklarczyk","year":"2004","journal-title":"Bioinformatics"},{"key":"2023013112030631300_btaa121-B15","doi-asserted-by":"crossref","first-page":"441","DOI":"10.2174\/092986707779941014","article-title":"Application of the EIIP\/ISM bioinformatics concept in development of new drugs","volume":"14","author":"Veljkovic","year":"2007","journal-title":"Curr. Med. Chem"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btaa121\/32923771\/btaa121.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/36\/10\/3260\/48990958\/bioinformatics_36_10_3260.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/36\/10\/3260\/48990958\/bioinformatics_36_10_3260.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,31]],"date-time":"2023-01-31T21:13:39Z","timestamp":1675199619000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/36\/10\/3260\/5756200"}},"subtitle":[],"editor":[{"given":"Jinbo","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2020,2,25]]},"references-count":15,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2020,5,1]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btaa121","relation":{},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"value":"1367-4803","type":"print"},{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2020,5,15]]},"published":{"date-parts":[[2020,2,25]]}}}