{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,10]],"date-time":"2026-10-10T23:09:35Z","timestamp":1791673775782,"version":"4.3.4"},"reference-count":38,"publisher":"Oxford University Press (OUP)","issue":"3","license":[{"start":{"date-parts":[[2020,8,19]],"date-time":"2020-08-19T00:00:00Z","timestamp":1597795200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/journals\/pages\/open_access\/funder_policies\/chorus\/standard_publication_model"}],"funder":[{"name":"Agencia Nacional de Promocion Cientifica y Tecnologica (ANPCyT) PICT","award":["2018 3384"],"award-info":[{"award-number":["2018 3384"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,5,20]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Motivation<\/jats:title>\n                  <jats:p>The genome-wide discovery of microRNAs (miRNAs) involves identifying sequences having the highest chance of being a novel miRNA precursor (pre-miRNA), within all the possible sequences in a complete genome. The known pre-miRNAs are usually just a few in comparison to the millions of candidates that have to be analyzed. This is of particular interest in non-model species and recently sequenced genomes, where the challenge is to find potential pre-miRNAs only from the sequenced genome. The task is unfeasible without the help of computational methods, such as deep learning. However, it is still very difficult to find an accurate predictor, with a low false positive rate in this genome-wide context. Although there are many available tools, these have not been tested in realistic conditions, with sequences from whole genomes and the high class imbalance inherent to such data.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>In this work, we review six recent methods for tackling this problem with machine learning. We compare the models in five genome-wide datasets: Arabidopsis thaliana, Caenorhabditis elegans, Anopheles gambiae, Drosophila melanogaster, Homo sapiens. The models have been designed for the pre-miRNAs prediction task, where there is a class of interest that is significantly underrepresented (the known pre-miRNAs) with respect to a very large number of unlabeled samples. It was found that for the smaller genomes and smaller imbalances, all methods perform in a similar way. However, for larger datasets such as the H. sapiens genome, it was found that deep learning approaches using raw information from the sequences reached the best scores, achieving low numbers of false positives.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Availability<\/jats:title>\n                  <jats:p>The source code to reproduce these results is in: http:\/\/sourceforge.net\/projects\/sourcesinc\/files\/gwmirna Additionally, the datasets are freely available in: https:\/\/sourceforge.net\/projects\/sourcesinc\/files\/mirdata<\/jats:p>\n               <\/jats:sec>","DOI":"10.1093\/bib\/bbaa184","type":"journal-article","created":{"date-parts":[[2020,7,20]],"date-time":"2020-07-20T11:07:13Z","timestamp":1595243233000},"source":"Crossref","is-referenced-by-count":16,"title":["Genome-wide discovery of pre-miRNAs: comparison of recent approaches based on machine learning"],"prefix":"10.1093","volume":"22","author":[{"given":"Leandro A","family":"Bugnon","sequence":"first","affiliation":[{"name":"Research Institute for Signals, Systems and Computational Intelligence sinc(i), FICH\/UNL-CONICET, Ciudad Universitaria, Santa Fe, Argentina"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cristian","family":"Yones","sequence":"additional","affiliation":[{"name":"Research Institute for Signals, Systems and Computational Intelligence sinc(i), FICH\/UNL-CONICET, Ciudad Universitaria, Santa Fe, Argentina"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Diego H","family":"Milone","sequence":"additional","affiliation":[{"name":"Research Institute for Signals, Systems and Computational Intelligence sinc(i), FICH\/UNL-CONICET, Ciudad Universitaria, Santa Fe, Argentina"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Georgina","family":"Stegmayer","sequence":"additional","affiliation":[{"name":"Research Institute for Signals, Systems and Computational Intelligence sinc(i), FICH\/UNL-CONICET, Ciudad Universitaria, Santa Fe, Argentina"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2020,8,19]]},"reference":[{"issue":"15","key":"2021052110412420500_ref1","doi-asserted-by":"crossref","first-page":"321","DOI":"10.1038\/nrc3932","article-title":"MicroRNA biogenesis pathways in cancer","volume":"6","author":"Lin","year":"2015","journal-title":"Nat Rev Cancer"},{"issue":"1","key":"2021052110412420500_ref2","first-page":"1","article-title":"The role of MicroRNAs in human cancer","volume":"1","author":"Croce","year":"2016","journal-title":"Signal Transduct Target Ther"},{"issue":"10","key":"2021052110412420500_ref3","doi-asserted-by":"crossref","first-page":"1122","DOI":"10.7150\/thno.11543","article-title":"MicroRNAs: new biomarkers for diagnosis, prognosis, therapy prediction and therapeutic tools for breast cancer","volume":"5","author":"Bertoli","year":"2015","journal-title":"Theranostics"},{"issue":"1\u20132","key":"2021052110412420500_ref4","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s00335-009-9241-2","article-title":"Computational approaches for microRNA studies: a review","volume":"21","author":"Li","year":"2010","journal-title":"Mamm Genome"},{"key":"2021052110412420500_ref5","doi-asserted-by":"crossref","first-page":"1","DOI":"10.3389\/fgene.2012.00209","article-title":"Computational methods for ab initio detection of microRNAs","volume":"3","author":"Allmer","year":"2012","journal-title":"Front Genet"},{"issue":"4","key":"2021052110412420500_ref6","doi-asserted-by":"crossref","first-page":"407","DOI":"10.1038\/nbt1394","article-title":"Discovering microRNAs from deep sequencing data using miRDeep","volume":"26","author":"Friedl\u00e4nder","year":"2008","journal-title":"Nat Biotechnol"},{"issue":"1","key":"2021052110412420500_ref7","doi-asserted-by":"crossref","first-page":"68","DOI":"10.1093\/nar\/gkp347","article-title":"miRanalyzer: a microRNA detection and analysis tool for next-generation sequencing experiments","volume":"37","author":"Hackenberg","year":"2009","journal-title":"Nucleic Acids Res"},{"issue":"39","key":"2021052110412420500_ref8","article-title":"MiRTRAP, a computational method for the systematic identification of miRNAs from high throughput sequencing data","volume":"11","author":"Hendrix","year":"2010","journal-title":"Genome Biol"},{"issue":"1","key":"2021052110412420500_ref9","doi-asserted-by":"crossref","first-page":"132","DOI":"10.1093\/nar\/gkr247","article-title":"MiRanalyzer: An update on the detection and analysis of microRNAs in high-throughput sequencing experiments","volume":"39","author":"Hackenberg","year":"2011","journal-title":"Nucleic Acids Res"},{"issue":"18","key":"2021052110412420500_ref10","doi-asserted-by":"crossref","first-page":"2226","DOI":"10.1093\/bioinformatics\/btq329","article-title":"MIReNA: finding microRNAs with high accuracy and no learning at genome scale and from deep sequencing data","volume":"26","author":"Mathelier","year":"2010","journal-title":"Bioinformatics"},{"issue":"1","key":"2021052110412420500_ref11","doi-asserted-by":"crossref","first-page":"37","DOI":"10.1093\/nar\/gkr688","article-title":"MiRDeep2 accurately identifies known and hundreds of novel microRNA genes in seven animal clades","volume":"40","author":"Friedl\u00e4nder","year":"2012","journal-title":"Nucleic Acids Res"},{"issue":"1","key":"2021052110412420500_ref12","doi-asserted-by":"crossref","first-page":"275","DOI":"10.1186\/1471-2105-15-275","article-title":"MiRPlant: An integrated tool for identification of plant miRNA from RNA sequencing data","volume":"15","author":"An","year":"2014","journal-title":"BMC Bioinformatics"},{"issue":"21","key":"2021052110412420500_ref13","doi-asserted-by":"crossref","first-page":"177","DOI":"10.1093\/nar\/gkx836","article-title":"Mirnovo: genome-free prediction of microRNAs from small RNA sequencing data and single-cells using decision forests","volume":"45","author":"Vitsios","year":"2017","journal-title":"Nucleic Acids Res"},{"key":"2021052110412420500_ref14","article-title":"Delineating the impact of machine learning elements in pre-microRNA detection","volume":"5","author":"Demirci","year":"2017","journal-title":"PeerJ"},{"issue":"5","key":"2021052110412420500_ref15","doi-asserted-by":"crossref","first-page":"1607","DOI":"10.1093\/bib\/bby037","article-title":"Predicting novel microRNA: a comprehensive comparison of machine learning approaches","volume":"20","author":"Stegmayer","year":"2018","journal-title":"Brief Bioinform"},{"key":"2021052110412420500_ref16","doi-asserted-by":"crossref","first-page":"1181","DOI":"10.1093\/bib\/bbx136","article-title":"Computational tools for plant small RNA detection and categorization","volume":"20","author":"Morgado","year":"2019","journal-title":"Brief Bioinform"},{"issue":"1","key":"2021052110412420500_ref17","doi-asserted-by":"crossref","first-page":"192","DOI":"10.1109\/TCBB.2013.146","article-title":"Improved and promising identification of human MicroRNAs by incorporating a high-quality negative set","volume":"11","author":"Wei","year":"2014","journal-title":"IEEE\/ACM Trans Comput Biol Bioinform"},{"issue":"1","key":"2021052110412420500_ref18","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1093\/bib\/bbs075","article-title":"Identifying miRNAs, targets and functions","volume":"15","author":"Liu","year":"2014","journal-title":"Brief Bioinform"},{"key":"2021052110412420500_ref19","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.biosystems.2015.10.003","article-title":"miRNAfe: a comprehensive tool for feature extraction in microRNA prediction","volume":"138","author":"Yones","year":"2015","journal-title":"Biosystems"},{"issue":"5","key":"2021052110412420500_ref20","first-page":"1836","article-title":"Trends in the development of miRNA bioinformatics tools","volume":"20","author":"Liang","year":"2018","journal-title":"Brief Bioinform"},{"issue":"8","key":"2021052110412420500_ref21","doi-asserted-by":"crossref","DOI":"10.1109\/TNNLS.2019.2914471","article-title":"Deep Neural Architectures for Highly Imbalanced Data in Bioinformatics","volume":"31","author":"Bugnon","year":"2020","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"2021052110412420500_ref22","doi-asserted-by":"crossref","first-page":"310","DOI":"10.1186\/1471-2105-6-310","article-title":"Classification of real and pseudo microRNA precursors using local structure-sequence features and support vector machine","volume":"6","author":"Xue","year":"2005","journal-title":"BMC Bioinformatics"},{"key":"2021052110412420500_ref23","article-title":"Prediction of microRNA hairpins using one-class support vector machines","volume-title":"2nd International Conference on Bioinformatics and Biomedical Engineering, iCBBE 2008","author":"Dang","year":"2008"},{"issue":"03","key":"2021052110412420500_ref24","doi-asserted-by":"crossref","first-page":"247","DOI":"10.4236\/jbise.2010.33033","article-title":"A comparison study between one-class and two-class machine learning for MicroRNA target detection","volume":"03","author":"Yousef","year":"2010","journal-title":"J Biomed Sci Eng"},{"issue":"6","key":"2021052110412420500_ref25","doi-asserted-by":"crossref","first-page":"1316","DOI":"10.1109\/TCBB.2016.2576459","article-title":"High class-imbalance in pre-miRNA prediction: a novel approach based on deepSOM","volume":"14","author":"Stegmayer","year":"2016","journal-title":"IEEE\/ACM Trans Comput Biol Bioinform"},{"key":"2021052110412420500_ref26","volume-title":"Self-organizing Maps","author":"Kohonen","year":"2005"},{"issue":"4","key":"2021052110412420500_ref27","doi-asserted-by":"crossref","first-page":"541","DOI":"10.1093\/bioinformatics\/btx612","article-title":"Genome-wide pre-miRNA discovery from few labeled examples","volume":"34","author":"Yones","year":"2018","journal-title":"Bioinformatics"},{"issue":"7553","key":"2021052110412420500_ref28","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"Lecun","year":"2015","journal-title":"Nature"},{"issue":"5","key":"2021052110412420500_ref29","first-page":"851","article-title":"Deep learning in bioinformatics","volume":"18","author":"Min","year":"2017","journal-title":"Brief Bioinform"},{"key":"2021052110412420500_ref30","doi-asserted-by":"crossref","first-page":"14","DOI":"10.1007\/978-3-642-33275-3_2","article-title":"An introduction to restricted Boltzmann machines","author":"Fischer","year":"2012","journal-title":"Lecture Notes in Computer Science"},{"key":"2021052110412420500_ref31","doi-asserted-by":"crossref","DOI":"10.1109\/BIGCOMP.2017.7881722","article-title":"DP-miRNA: An improved prediction of precursor microRNA using deep learning model","volume-title":"2017 IEEE International Conference on Big Data and Smart Computing, BigComp 2017","author":"Thomas","year":"2017"},{"key":"2021052110412420500_ref32","article-title":"Deep neural network based precursor microRNA prediction on eleven species","author":"Thomas","year":"2017"},{"issue":"Suppl 23","key":"2021052110412420500_ref33","first-page":"1","article-title":"Fast and accurate microRNA search using CNN","volume":"20","author":"Tang","year":"2019","journal-title":"BMC Bioinformatics"},{"issue":"1","key":"2021052110412420500_ref34","first-page":"1","article-title":"Nucleotide-level convolutional neural networks for pre-miRNA classification","volume":"9","author":"Zheng","year":"2019","journal-title":"Sci Rep"},{"key":"2021052110412420500_ref35","article-title":"deepMiRGene: Deep Neural Network based Precursor microRNA Prediction","volume-title":"NIPS","author":"Park","year":"2017"},{"key":"2021052110412420500_ref36","doi-asserted-by":"crossref","first-page":"104209","DOI":"10.1016\/j.dib.2019.104209","article-title":"Genome-wide hairpins datasets of animals and plants for novel miRNA prediction","volume":"25","author":"Bugnon","year":"2019","journal-title":"Data Brief"},{"issue":"2","key":"2021052110412420500_ref37","doi-asserted-by":"crossref","first-page":"281","DOI":"10.1016\/S0092-8674(04)00045-5","article-title":"MicroRNAs: genomics, biogenesis, mechanism, and function","volume":"116","author":"Bartel","year":"2004","journal-title":"Cell"},{"issue":"3","key":"2021052110412420500_ref38","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0118432","article-title":"The precision-recall plot is more informative than the ROC plot when evaluating binary classifiers on imbalanced datasets","volume":"10","author":"Saito","year":"2015","journal-title":"PLoS One"}],"container-title":["Briefings in Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/academic.oup.com\/bib\/article-pdf\/22\/3\/bbaa184\/37966367\/bbaa184.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"http:\/\/academic.oup.com\/bib\/article-pdf\/22\/3\/bbaa184\/37966367\/bbaa184.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,5,21]],"date-time":"2021-05-21T10:43:51Z","timestamp":1621593831000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bib\/article\/doi\/10.1093\/bib\/bbaa184\/5894456"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,8,19]]},"references-count":38,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2021,5,20]]}},"URL":"https:\/\/doi.org\/10.1093\/bib\/bbaa184","relation":{},"ISSN":["1467-5463","1477-4054"],"issn-type":[{"value":"1467-5463","type":"print"},{"value":"1477-4054","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2021,5]]},"published":{"date-parts":[[2020,8,19]]},"article-number":"bbaa184"}}