{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,8]],"date-time":"2026-01-08T03:02:58Z","timestamp":1767841378280,"version":"3.49.0"},"reference-count":54,"publisher":"Oxford University Press (OUP)","issue":"6","license":[{"start":{"date-parts":[[2021,8,5]],"date-time":"2021-08-05T00:00:00Z","timestamp":1628121600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/journals\/pages\/open_access\/funder_policies\/chorus\/standard_publication_model"}],"funder":[{"DOI":"10.13039\/100009647","name":"Ministry of Health","doi-asserted-by":"publisher","award":["Ricerca Corrente 2018-2020"],"award-info":[{"award-number":["Ricerca Corrente 2018-2020"]}],"id":[{"id":"10.13039\/100009647","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,11,5]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Hundreds of human proteins were found to establish transient interactions with rather degenerated consensus DNA sequences or motifs. Identifying these motifs and the genomic sites where interactions occur represent one of the most challenging research goals in modern molecular biology and bioinformatics. The last twenty years witnessed an explosion of computational tools designed to perform this task, whose performance has been last compared fifteen years ago. Here, we survey sixteen of them, benchmark their ability to identify known motifs nested in twenty-nine simulated sequence datasets, and finally report their strengths, weaknesses, and complementarity.<\/jats:p>","DOI":"10.1093\/bib\/bbab303","type":"journal-article","created":{"date-parts":[[2021,7,16]],"date-time":"2021-07-16T11:13:48Z","timestamp":1626434028000},"source":"Crossref","is-referenced-by-count":10,"title":["A comparative benchmark of classic DNA motif discovery tools on synthetic data"],"prefix":"10.1093","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8688-9530","authenticated-orcid":false,"given":"Stefano","family":"Castellana","sequence":"first","affiliation":[{"name":"Bioinformatics Unit, IRCCS Casa Sollievo della Sofferenza, S. Giovanni Rotondo 71013, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tommaso","family":"Biagini","sequence":"additional","affiliation":[{"name":"Bioinformatics Unit, IRCCS Casa Sollievo della Sofferenza, S. Giovanni Rotondo 71013, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Luca","family":"Parca","sequence":"additional","affiliation":[{"name":"Bioinformatics Unit, IRCCS Casa Sollievo della Sofferenza, S. Giovanni Rotondo 71013, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Francesco","family":"Petrizzelli","sequence":"additional","affiliation":[{"name":"Bioinformatics Unit, IRCCS Casa Sollievo della Sofferenza, S. Giovanni Rotondo 71013, Italy"},{"name":"Department of Experimental Medicine, Sapienza University of Rome, Rome 00161, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Salvatore Daniele","family":"Bianco","sequence":"additional","affiliation":[{"name":"Bioinformatics Unit, IRCCS Casa Sollievo della Sofferenza, S. Giovanni Rotondo 71013, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Angelo Luigi","family":"Vescovi","sequence":"additional","affiliation":[{"name":"ISBReMIT Institute for Stem Cell Biology, Regenerative Medicine and Innovative Therapies, IRCSS Casa Sollievo della Sofferenza, San Giovanni Rotondo (FG), 71013, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Massimo","family":"Carella","sequence":"additional","affiliation":[{"name":"Medical Genetics Unit, IRCCS Casa Sollievo della Sofferenza, S. Giovanni Rotondo 71013, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0434-8533","authenticated-orcid":false,"given":"Tommaso","family":"Mazza","sequence":"additional","affiliation":[{"name":"Bioinformatics Unit, IRCCS Casa Sollievo della Sofferenza, S. Giovanni Rotondo 71013, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"286","published-online":{"date-parts":[[2021,8,5]]},"reference":[{"key":"2021110815090432200_ref1","doi-asserted-by":"crossref","first-page":"306","DOI":"10.1016\/j.molcel.2019.08.010","article-title":"Mechanisms of interplay between transcription factors and the 3D genome","volume":"76","author":"Kim","year":"2019","journal-title":"Mol Cell"},{"key":"2021110815090432200_ref2","doi-asserted-by":"crossref","first-page":"225","DOI":"10.1093\/bib\/bbs016","article-title":"Motif discovery and transcription factor binding sites before and after the next-generation sequencing era","volume":"14","author":"Zambelli","year":"2013","journal-title":"Brief Bioinform"},{"key":"2021110815090432200_ref3","doi-asserted-by":"crossref","first-page":"973","DOI":"10.1534\/genetics.112.143370","article-title":"Why transcription factor binding sites are ten nucleotides long","volume":"192","author":"Stewart","year":"2012","journal-title":"Genetics"},{"key":"2021110815090432200_ref4","first-page":"D87","article-title":"JASPAR 2020: update of the open-access database of transcription factor binding profiles","volume":"48","author":"Fornes","year":"2020","journal-title":"Nucleic Acids Res"},{"key":"2021110815090432200_ref5","doi-asserted-by":"crossref","first-page":"2.15.1","DOI":"10.1002\/0471250953.bi0215s51","article-title":"DNA motif databases and their uses","volume":"51","author":"Stormo","year":"2015","journal-title":"Curr Protoc Bioinformatics"},{"key":"2021110815090432200_ref6","doi-asserted-by":"crossref","first-page":"636","DOI":"10.1126\/science.1105136","article-title":"The ENCODE (ENCyclopedia of DNA elements) project","volume":"306","author":"ENCODE Project Consortium","year":"2004","journal-title":"Science"},{"key":"2021110815090432200_ref7","doi-asserted-by":"crossref","first-page":"D252","DOI":"10.1093\/nar\/gkx1106","article-title":"HOCOMOCO: towards a complete collection of transcription factor binding models for human and mouse via large-scale ChIP-Seq analysis","volume":"46","author":"Kulakovskiy","year":"2018","journal-title":"Nucleic Acids Res"},{"key":"2021110815090432200_ref8","doi-asserted-by":"crossref","first-page":"2622","DOI":"10.1093\/bioinformatics\/btq488","article-title":"Deep and wide digging for binding motifs in ChIP-Seq data","volume":"26","author":"Kulakovskiy","year":"2010","journal-title":"Bioinformatics"},{"key":"2021110815090432200_ref9","doi-asserted-by":"crossref","first-page":"D100","DOI":"10.1093\/nar\/gky1128","article-title":"GTRD: a database on gene transcription regulation-2019 update","volume":"47","author":"Yevshin","year":"2019","journal-title":"Nucleic Acids Res"},{"key":"2021110815090432200_ref10","doi-asserted-by":"crossref","first-page":"D212","DOI":"10.1093\/nar\/gky1077","article-title":"RegulonDB v 10.5: tackling challenges to unify classic and high throughput knowledge of gene regulation inE. coliK-12","volume":"47","author":"Santos-Zavaleta","year":"2019","journal-title":"Nucleic Acids Res"},{"key":"2021110815090432200_ref11","doi-asserted-by":"crossref","first-page":"238","DOI":"10.1093\/nar\/24.1.238","article-title":"TRANSFAC: a database on transcription factors and their DNA binding sites","volume":"24","author":"Wingender","year":"1996","journal-title":"Nucleic Acids Res"},{"key":"2021110815090432200_ref12","doi-asserted-by":"crossref","first-page":"D1284","DOI":"10.1093\/nar\/gkx1188","article-title":"JASPAR 2018: update of the open-access database of transcription factor binding profiles and its web framework","volume":"46","author":"Khan","year":"2018","journal-title":"Nucleic Acids Res"},{"key":"2021110815090432200_ref13","doi-asserted-by":"crossref","first-page":"4899","DOI":"10.1093\/nar\/gki791","article-title":"Limitations and potentials of current motif discovery algorithms","volume":"33","author":"Hu","year":"2005","journal-title":"Nucleic Acids Res"},{"key":"2021110815090432200_ref14","doi-asserted-by":"crossref","first-page":"939","DOI":"10.1038\/nbt1098-939","article-title":"Finding DNA regulatory motifs within unaligned noncoding sequences clustered by whole-genome mRNA quantitation","volume":"16","author":"Roth","year":"1998","journal-title":"Nat Biotechnol"},{"key":"2021110815090432200_ref15","doi-asserted-by":"crossref","first-page":"W202","DOI":"10.1093\/nar\/gkp335","article-title":"MEME SUITE: tools for motif discovery and searching","volume":"37","author":"Bailey","year":"2009","journal-title":"Nucleic Acids Res"},{"key":"2021110815090432200_ref16","doi-asserted-by":"crossref","first-page":"835","DOI":"10.1038\/nbt717","article-title":"An algorithm for finding protein-DNA binding sites with applications to chromatin-immunoprecipitation microarray experiments","volume":"20","author":"Liu","year":"2002","journal-title":"Nat Biotechnol"},{"key":"2021110815090432200_ref17","doi-asserted-by":"crossref","first-page":"1113","DOI":"10.1093\/bioinformatics\/17.12.1113","article-title":"A higher-order background model improves the detection of promoter regulatory elements by Gibbs sampling","volume":"17","author":"Thijs","year":"2001","journal-title":"Bioinformatics"},{"key":"2021110815090432200_ref18","doi-asserted-by":"crossref","first-page":"193","DOI":"10.1186\/1471-2105-8-193","article-title":"Improved benchmarks for computational motif discovery","volume":"8","author":"Sandve","year":"2007","journal-title":"BMC Bioinformatics"},{"key":"2021110815090432200_ref19","doi-asserted-by":"crossref","first-page":"547","DOI":"10.1186\/s12859-016-1298-9","article-title":"Evaluating tools for transcription factor binding site prediction","volume":"17","author":"Jayaram","year":"2016","journal-title":"BMC Bioinformatics"},{"key":"2021110815090432200_ref20","doi-asserted-by":"crossref","first-page":"137","DOI":"10.1038\/nbt1053","article-title":"Assessing computational tools for the discovery of transcription factor binding sites","volume":"23","author":"Tompa","year":"2005","journal-title":"Nat Biotechnol"},{"key":"2021110815090432200_ref21","doi-asserted-by":"crossref","first-page":"W566","DOI":"10.1093\/nar\/gkl285","article-title":"MoD tools: regulatory motif discovery in nucleotide sequences from co-regulated or homologous genes","volume":"34","author":"Pavesi","year":"2006","journal-title":"Nucleic Acids Res"},{"issue":"Suppl 9","key":"2021110815090432200_ref22","doi-asserted-by":"crossref","first-page":"S6","DOI":"10.1186\/1471-2105-9-S9-S6","article-title":"MTAP: the motif tool assessment platform","volume":"9","author":"Quest","year":"2008","journal-title":"BMC Bioinformatics"},{"key":"2021110815090432200_ref23","doi-asserted-by":"crossref","first-page":"i356","DOI":"10.1093\/bioinformatics\/btp188","article-title":"Efficient exact motif discovery","volume":"25","author":"Marschall","year":"2009","journal-title":"Bioinformatics"},{"key":"2021110815090432200_ref24","doi-asserted-by":"crossref","first-page":"135","DOI":"10.1016\/B978-0-12-411637-5.00005-6","article-title":"DNA sequence motif: a jack of all trades for ChIP-Seq data","volume":"91","author":"Kulakovskiy","year":"2013","journal-title":"Adv Protein Chem Struct Biol"},{"key":"2021110815090432200_ref25","doi-asserted-by":"crossref","first-page":"1428","DOI":"10.1038\/nprot.2014.083","article-title":"Motif-based analysis of large nucleotide data sets using MEME-ChIP","volume":"9","author":"Ma","year":"2014","journal-title":"Nat Protoc"},{"key":"2021110815090432200_ref26","doi-asserted-by":"crossref","first-page":"4","DOI":"10.1186\/1745-6150-9-4","article-title":"A survey of motif finding web tools for detecting binding site motifs in ChIP-Seq data","volume":"9","author":"Tran","year":"2014","journal-title":"Biol Direct"},{"key":"2021110815090432200_ref27","doi-asserted-by":"crossref","first-page":"1740012","DOI":"10.1142\/S0219720017400121","article-title":"Argo_CUDA: exhaustive GPU based approach for motif discovery in large DNA datasets","volume":"16","author":"Vishnevsky","year":"2018","journal-title":"J Bioinform Comput Biol"},{"key":"2021110815090432200_ref28","first-page":"218068","article-title":"A fast cluster motif finding algorithm for ChIP-Seq data sets","volume":"2015","author":"Zhang","year":"2015","journal-title":"Biomed Res Int"},{"key":"2021110815090432200_ref29","doi-asserted-by":"crossref","first-page":"1069","DOI":"10.1093\/bib\/bbx026","article-title":"An algorithmic perspective of de novo cis-regulatory motif finding based on ChIP-seq data","volume":"19","author":"Liu","year":"2018","journal-title":"Brief Bioinform"},{"key":"2021110815090432200_ref30","doi-asserted-by":"crossref","first-page":"964","DOI":"10.1093\/bib\/bbv022","article-title":"A review of ensemble methods for de novo motif discovery in ChIP-Seq data","volume":"16","author":"Lihu","year":"2015","journal-title":"Brief Bioinform"},{"key":"2021110815090432200_ref31","doi-asserted-by":"crossref","first-page":"25","DOI":"10.1016\/j.ins.2018.07.004","article-title":"A comprehensive survey on genetic algorithms for DNA motif prediction","volume":"466","author":"Lee","year":"2018","journal-title":"Inform Sci"},{"key":"2021110815090432200_ref32","doi-asserted-by":"crossref","first-page":"1577","DOI":"10.1093\/bioinformatics\/btl147","article-title":"GAME: detecting cis-regulatory elements using a genetic algorithm","volume":"22","author":"Wei","year":"2006","journal-title":"Bioinformatics"},{"key":"2021110815090432200_ref33","doi-asserted-by":"crossref","first-page":"831","DOI":"10.1038\/nbt.3300","article-title":"Predicting the sequence specificities of DNA- and RNA-binding proteins by deep learning","volume":"33","author":"Alipanahi","year":"2015","journal-title":"Nat Biotechnol"},{"key":"2021110815090432200_ref34","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1093\/bib\/bbaa229","article-title":"A survey on deep learning in DNA\/RNA motif mining","volume":"22","author":"He","year":"2021","journal-title":"Brief Bioinform"},{"key":"2021110815090432200_ref35","doi-asserted-by":"crossref","first-page":"i269","DOI":"10.1093\/bioinformatics\/btz339","article-title":"Comprehensive evaluation of deep learning architectures for prediction of DNA\/RNA sequence binding specificities","volume":"35","author":"Trabelsi","year":"2019","journal-title":"Bioinformatics"},{"key":"2021110815090432200_ref36","doi-asserted-by":"crossref","first-page":"131","DOI":"10.1016\/S1672-0229(07)60023-0","article-title":"Comparative analysis of regulatory motif discovery tools for transcription factor binding sites","volume":"5","author":"Wei","year":"2007","journal-title":"Genomics Proteomics Bioinformatics"},{"issue":"Suppl 7","key":"2021110815090432200_ref37","doi-asserted-by":"crossref","first-page":"S21","DOI":"10.1186\/1471-2105-8-S7-S21","article-title":"A survey of DNA motif finding algorithms","volume":"8","author":"Das","year":"2007","journal-title":"BMC Bioinformatics"},{"key":"2021110815090432200_ref38","doi-asserted-by":"crossref","first-page":"W215","DOI":"10.1093\/nar\/gky431","article-title":"The BaMM web server for de-novo motif discovery and regulatory sequence analysis","volume":"46","author":"Kiesel","year":"2018","journal-title":"Nucleic Acids Res"},{"key":"2021110815090432200_ref39","doi-asserted-by":"crossref","first-page":"270","DOI":"10.1093\/bioinformatics\/btq636","article-title":"GimmeMotifs: a de novo motif prediction pipeline for ChIP-sequencing experiments","volume":"27","author":"Heeringen","year":"2011","journal-title":"Bioinformatics"},{"key":"2021110815090432200_ref40","doi-asserted-by":"crossref","first-page":"1743","DOI":"10.1126\/science.1102216","article-title":"Environmentally induced foregut remodeling by PHA-4\/FoxA and DAF-12\/NHR","volume":"305","author":"Ao","year":"2004","journal-title":"Science"},{"key":"2021110815090432200_ref41","doi-asserted-by":"crossref","first-page":"W86","DOI":"10.1093\/nar\/gkr377","article-title":"RSAT 2011: regulatory sequence analysis tools","volume":"39","author":"Thomas-Chollier","year":"2011","journal-title":"Nucleic Acids Res"},{"key":"2021110815090432200_ref42","doi-asserted-by":"crossref","first-page":"2256","DOI":"10.1093\/bioinformatics\/btn408","article-title":"GIMSAN: a Gibbs motif finder with significance analysis","volume":"24","author":"Ng","year":"2008","journal-title":"Bioinformatics"},{"key":"2021110815090432200_ref43","doi-asserted-by":"crossref","first-page":"2303","DOI":"10.1093\/bioinformatics\/btn444","article-title":"Seeder: discriminative seeding DNA motif discovery","volume":"24","author":"Fauteux","year":"2008","journal-title":"Bioinformatics"},{"key":"2021110815090432200_ref44","doi-asserted-by":"crossref","first-page":"755","DOI":"10.1186\/s12864-018-5148-1","article-title":"MODSIDE: a motif discovery pipeline and similarity detector","volume":"19","author":"Tran","year":"2018","journal-title":"BMC Genomics"},{"key":"2021110815090432200_ref45","doi-asserted-by":"crossref","first-page":"W104","DOI":"10.1093\/nar\/gks602","article-title":"The XXmotif web server for eXhaustive, weight matriX-based motif discovery in nucleotide sequences","volume":"40","author":"Luehr","year":"2012","journal-title":"Nucleic Acids Res"},{"key":"2021110815090432200_ref46","doi-asserted-by":"crossref","first-page":"W12","DOI":"10.1093\/nar\/gku315","article-title":"DMINDA: an integrated web server for DNA motif identification and analyses","volume":"42","author":"Ma","year":"2014","journal-title":"Nucleic Acids Res"},{"key":"2021110815090432200_ref47","doi-asserted-by":"crossref","first-page":"e42","DOI":"10.1093\/nar\/gkq948","article-title":"A new framework for identifying cis-regulatory motifs in prokaryotes","volume":"39","author":"Li","year":"2011","journal-title":"Nucleic Acids Res"},{"key":"2021110815090432200_ref48","doi-asserted-by":"crossref","first-page":"576","DOI":"10.1016\/j.molcel.2010.05.004","article-title":"Simple combinations of lineage-determining transcription factors prime cis-regulatory elements required for macrophage and B cell identities","volume":"38","author":"Heinz","year":"2010","journal-title":"Mol Cell"},{"key":"2021110815090432200_ref49","doi-asserted-by":"crossref","first-page":"405","DOI":"10.1093\/bioinformatics\/btp681","article-title":"Tmod: toolbox of motif discovery","volume":"26","author":"Sun","year":"2010","journal-title":"Bioinformatics"},{"key":"2021110815090432200_ref50","doi-asserted-by":"crossref","first-page":"2240","DOI":"10.1093\/bioinformatics\/bti336","article-title":"A Gibbs sampler for identification of symmetrically structured, spaced DNA motifs with improved estimation of the signal length","volume":"21","author":"Favorov","year":"2005","journal-title":"Bioinformatics"},{"key":"2021110815090432200_ref51","doi-asserted-by":"crossref","first-page":"679","DOI":"10.1016\/0022-5193(80)90186-1","article-title":"Markov analysis of viral DNA\/RNA sequences","volume":"82","author":"Garden","year":"1980","journal-title":"J Theor Biol"},{"key":"2021110815090432200_ref52","doi-asserted-by":"crossref","DOI":"10.3390\/ijms22115521","article-title":"DeepD2V: a novel deep learning-based framework for predicting transcription factor binding sites from combined DNA sequence","volume":"22","author":"Deng","year":"2021","journal-title":"Int J Mol Sci"},{"key":"2021110815090432200_ref53","doi-asserted-by":"publisher","DOI":"10.1093\/bib\/bbaa435","article-title":"Locating transcription factor binding sites by fully convolutional neural network","author":"Zhang","year":"2021","journal-title":"Brief Bioinform"},{"key":"2021110815090432200_ref54","doi-asserted-by":"publisher","DOI":"10.1093\/bib\/bbab233","article-title":"Identifying complex motifs in massive omics data with a variable-convolutional layer in deep neural network","author":"Li","year":"2021","journal-title":"Brief Bioinform"}],"container-title":["Briefings in Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bib\/article-pdf\/22\/6\/bbab303\/41090206\/bbab303.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bib\/article-pdf\/22\/6\/bbab303\/41090206\/bbab303.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,11,8]],"date-time":"2021-11-08T15:27:17Z","timestamp":1636385237000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bib\/article\/doi\/10.1093\/bib\/bbab303\/6341664"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,8,5]]},"references-count":54,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2021,11,5]]}},"URL":"https:\/\/doi.org\/10.1093\/bib\/bbab303","relation":{},"ISSN":["1467-5463","1477-4054"],"issn-type":[{"value":"1467-5463","type":"print"},{"value":"1477-4054","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2021,11]]},"published":{"date-parts":[[2021,8,5]]},"article-number":"bbab303"}}