{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,23]],"date-time":"2026-09-23T23:30:57Z","timestamp":1790206257983,"version":"4.1.0"},"reference-count":33,"publisher":"Oxford University Press (OUP)","issue":"11","license":[{"start":{"date-parts":[[2018,10,23]],"date-time":"2018-10-23T00:00:00Z","timestamp":1540252800000},"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\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["11661141019"],"award-info":[{"award-number":["11661141019"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61621003"],"award-info":[{"award-number":["61621003"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61422309"],"award-info":[{"award-number":["61422309"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61379092"],"award-info":[{"award-number":["61379092"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Strategic Priority Research Program of the Chinese Academy of Sciences","award":["XDB13040600"],"award-info":[{"award-number":["XDB13040600"]}]},{"DOI":"10.13039\/501100002367","name":"Chinese Academy of Sciences","doi-asserted-by":"publisher","award":["KFZD-SW-219"],"award-info":[{"award-number":["KFZD-SW-219"]}],"id":[{"id":"10.13039\/501100002367","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Key Research and Development Program of China","award":["2017YFC0908405"],"award-info":[{"award-number":["2017YFC0908405"]}]},{"name":"CAS Frontier Science Research Key Project for Top Young Scientist","award":["QYZDB-SSW-SYS008"],"award-info":[{"award-number":["QYZDB-SSW-SYS008"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019,6,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Motivation<\/jats:title>\n                  <jats:p>With the accumulation of DNA sequencing data, convolution neural network (CNN) based methods such as DeepBind and DeepSEA have achieved great success for predicting the function of primary DNA sequences. Previous studies confirm the importance of utilizing the reverse complement and flanking DNA sequences, which has a natural connection with data augmentation. However, it is not fully understood how these DNA sequences work during model training and testing.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>In this study, we proposed several CNN tricks to improve the DNA sequence related prediction tasks and took the DNA\u2013protein binding prediction as an illustrative task for demonstration. Different from the DeepBind, we treated the reverse complement DNA sequence as another sample, which enables the CNN model to automatically learn the complex relationships between the double strand DNA sequences. This trick promotes the using of deeper CNN models, improving the prediction performance. Next, we augmented the training sets by extending the DNA sequences and cropping each one to three shorter sequences. This approach greatly improves the prediction due to more environmental information from extending step and strong regularization effect of the cropping step. Moreover, this practice fits well with wider CNN models, which also increases the prediction accuracy. On the basis of DNA sequence augmentation, we integrated the results of different effective CNN models to mine the prediction potential of primary DNA sequences. On 156 datasets of predicting DNA\u2013protein binding, our final prediction significantly outperformed the state-of-the-art results with an average AUC increase of 0.057 (P-value\u2009=\u20096\u2009\u00d7\u200910\u221262).<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Availability and implementation<\/jats:title>\n                  <jats:p>Source codes are available at https:\/\/github.com\/zhanglabtools\/DNADataAugmentation.<\/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\/bty893","type":"journal-article","created":{"date-parts":[[2018,10,22]],"date-time":"2018-10-22T11:27:22Z","timestamp":1540207642000},"page":"1837-1843","source":"Crossref","is-referenced-by-count":42,"title":["Simple tricks of convolutional neural network architectures improve DNA\u2013protein binding prediction"],"prefix":"10.1093","volume":"35","author":[{"given":"Zhen","family":"Cao","sequence":"first","affiliation":[{"name":"NCMIS, CEMS, RCSDS, Academy of Mathematics and Systems Science, Chinese Academy of Sciences, Beijing, China"},{"name":"School of Mathematical Sciences, University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shihua","family":"Zhang","sequence":"additional","affiliation":[{"name":"NCMIS, CEMS, RCSDS, Academy of Mathematics and Systems Science, Chinese Academy of Sciences, Beijing, China"},{"name":"School of Mathematical Sciences, University of Chinese Academy of Sciences, Beijing, China"},{"name":"Center for Excellence in Animal Evolution and Genetics, Chinese Academy of Sciences, Kunming, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2018,10,23]]},"reference":[{"key":"2023012713073641100_bty893-B1","article-title":"Tensorflow: large-scale machine learning on heterogeneous distributed systems","author":"Abadi","year":"2016"},{"key":"2023012713073641100_bty893-B2","doi-asserted-by":"crossref","first-page":"559","DOI":"10.1038\/nrg2814","article-title":"Annotating non-coding regions of the genome","volume":"11","author":"Alexander","year":"2010","journal-title":"Nat. Rev. Genet."},{"key":"2023012713073641100_bty893-B3","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":"2023012713073641100_bty893-B4","doi-asserted-by":"crossref","first-page":"1045","DOI":"10.1038\/nbt1010-1045","article-title":"The NIH Roadmap Epigenomics Mapping Consortium","volume":"28","author":"Bernstein","year":"2010","journal-title":"Nat. Biotechnol."},{"key":"2023012713073641100_bty893-B5","article-title":"Probe efficient feature representation of gapped k-mer frequency vectors from sequences using deep neural networks","author":"Cao","year":"2018","journal-title":"IEEE\/ACM Trans. Comput. Biol. Bioinform"},{"key":"2023012713073641100_bty893-B6","first-page":"3642","article-title":"Multi-column deep neural networks for image classification","volume-title":"IEEE Conference on Computer Vision and Pattern Recognition","author":"Ciregan","year":"2012"},{"key":"2023012713073641100_bty893-B7","first-page":"1337","article-title":"Deep learning with COTS HPS systems","volume-title":"Proceedings of the 30th International Conference on Machine Learning","author":"Coates","year":"2013"},{"key":"2023012713073641100_bty893-B8","doi-asserted-by":"crossref","first-page":"233","DOI":"10.1145\/1143844.1143874","article-title":"The relationship between Precision-Recall and ROC curves","volume-title":"Proceedings of the 23rd International Conference on Machine Learning","author":"Davis","year":"2006"},{"key":"2023012713073641100_bty893-B9","doi-asserted-by":"crossref","first-page":"57","DOI":"10.1038\/nature11247","article-title":"An integrated encyclopedia of DNA elements in the human genome","volume":"489","author":"Dunham","year":"2012","journal-title":"Nature"},{"key":"2023012713073641100_bty893-B10","first-page":"1","article-title":"ROC graphs: notes and practical considerations for researchers","volume":"31","author":"Fawcett","year":"2004","journal-title":"Mach. Learn."},{"key":"2023012713073641100_bty893-B11","doi-asserted-by":"crossref","first-page":"e1003711","DOI":"10.1371\/journal.pcbi.1003711","article-title":"Enhanced regulatory sequence prediction using gapped k-mer features","volume":"10","author":"Ghandi","year":"2014","journal-title":"PLoS Comput. Biol."},{"key":"2023012713073641100_bty893-B12","doi-asserted-by":"crossref","first-page":"2205","DOI":"10.1093\/bioinformatics\/btw203","article-title":"gkmSVM: an R package for gapped-kmer SVM","volume":"32","author":"Ghandi","year":"2016","journal-title":"Bioinformatics"},{"key":"2023012713073641100_bty893-B13","first-page":"770","article-title":"Deep residual learning for image recognition","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"He","year":"2016"},{"key":"2023012713073641100_bty893-B14","first-page":"448","article-title":"Batch normalization: accelerating deep network training by reducing internal covariate shift","author":"Ioffe","year":"2015","journal-title":"Proceedings of the 32nd International Conference on Machine Learning"},{"key":"2023012713073641100_bty893-B15","doi-asserted-by":"crossref","first-page":"232","DOI":"10.1126\/science.1183621","article-title":"Variation in transcription factor binding among humans","volume":"328","author":"Kasowski","year":"2010","journal-title":"Science"},{"key":"2023012713073641100_bty893-B16","doi-asserted-by":"crossref","first-page":"990","DOI":"10.1101\/gr.200535.115","article-title":"Basset: learning the regulatory code of the accessible genome with deep convolutional neural networks","volume":"26","author":"Kelley","year":"2016","journal-title":"Genome Res."},{"key":"2023012713073641100_bty893-B17","article-title":"Adam: a method for stochastic optimization","author":"Kingma","year":"2014"},{"key":"2023012713073641100_bty893-B18","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","volume-title":"Advances in Neural Information Processing Systems","author":"Krizhevsky","year":"2012"},{"key":"2023012713073641100_bty893-B19","doi-asserted-by":"crossref","first-page":"955","DOI":"10.1038\/ng.3331","article-title":"A method to predict the impact of regulatory variants from DNA sequence","volume":"47","author":"Lee","year":"2015","journal-title":"Nat. Genet."},{"key":"2023012713073641100_bty893-B20","doi-asserted-by":"crossref","first-page":"2196","DOI":"10.1093\/bioinformatics\/btw142","article-title":"LS-GKM: a new gkm-SVM for large-scale datasets","volume":"32","author":"Lee","year":"2016","journal-title":"Bioinformatics"},{"key":"2023012713073641100_bty893-B21","doi-asserted-by":"crossref","first-page":"e24756","DOI":"10.1371\/journal.pone.0024756","article-title":"iDNA-Prot: identification of DNA binding proteins using random forest with grey model","volume":"6","author":"Lin","year":"2011","journal-title":"PLoS One"},{"key":"2023012713073641100_bty893-B22","doi-asserted-by":"crossref","first-page":"35","DOI":"10.1093\/bioinformatics\/btw539","article-title":"iRSpot-EL: identify recombination spots with an ensemble learning approach","volume":"33","author":"Liu","year":"2017","journal-title":"Bioinformatics"},{"key":"2023012713073641100_bty893-B23","doi-asserted-by":"crossref","DOI":"10.1093\/bioinformatics\/bty458","article-title":"iEnhancer-EL: identifying enhancers and their strength with ensemble learning approach","volume":"34","author":"Liu","year":"2018","journal-title":"Bioinformatics"},{"key":"2023012713073641100_bty893-B24","doi-asserted-by":"crossref","first-page":"33","DOI":"10.1093\/bioinformatics\/btx579","article-title":"iPromoter-2\u2009L: a two-layer predictor for identifying promoters and their types by multi-window-based PseKNC","volume":"34","author":"Liu","year":"2018","journal-title":"Bioinformatics"},{"key":"2023012713073641100_bty893-B25","doi-asserted-by":"crossref","first-page":"155","DOI":"10.1038\/nrg2521","article-title":"Long non-coding RNAs: insights into functions","volume":"10","author":"Mercer","year":"2009","journal-title":"Nat. Rev. Genet."},{"key":"2023012713073641100_bty893-B26","doi-asserted-by":"crossref","first-page":"e1005403","DOI":"10.1371\/journal.pcbi.1005403","article-title":"Imputation for transcription factor binding predictions based on deep learning","volume":"13","author":"Qin","year":"2017","journal-title":"PLoS Comput. Biol."},{"key":"2023012713073641100_bty893-B27","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014"},{"key":"2023012713073641100_bty893-B28","doi-asserted-by":"crossref","first-page":"2767","DOI":"10.1056\/NEJMoa0807917","article-title":"Shared and distinct genetic variants in type 1 diabetes and celiac disease","volume":"359","author":"Smyth","year":"2008","journal-title":"New Engl. J. Med."},{"key":"2023012713073641100_bty893-B29","first-page":"1929","article-title":"Dropout: a simple way to prevent neural networks from overfitting","volume":"15","author":"Srivastava","year":"2014","journal-title":"J. Mach. Learn. Res."},{"key":"2023012713073641100_bty893-B30","first-page":"2818","article-title":"Rethinking the inception architecture for computer vision","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Szegedy","year":"2016"},{"key":"2023012713073641100_bty893-B31","doi-asserted-by":"crossref","first-page":"1720","DOI":"10.1080\/07391102.2014.968624","article-title":"Identification of DNA-binding proteins by incorporating evolutionary information into pseudo amino acid composition via the top-n-gram approach","volume":"33","author":"Xu","year":"2015","journal-title":"J. Biomol. Struct. Dyn."},{"key":"2023012713073641100_bty893-B32","doi-asserted-by":"crossref","first-page":"931","DOI":"10.1038\/nmeth.3547","article-title":"Predicting effects of noncoding variants with deep learning-based sequence model","volume":"12","author":"Zhou","year":"2015","journal-title":"Nat. Methods"},{"key":"2023012713073641100_bty893-B33","doi-asserted-by":"crossref","first-page":"i121","DOI":"10.1093\/bioinformatics\/btw255","article-title":"Convolutional neural network architectures for predicting DNA\u2013protein binding","volume":"32","author":"Zeng","year":"2016","journal-title":"Bioinformatics"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/35\/11\/1837\/48935078\/bioinformatics_35_11_1837.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/35\/11\/1837\/48935078\/bioinformatics_35_11_1837.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,27]],"date-time":"2023-01-27T14:12:57Z","timestamp":1674828777000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/35\/11\/1837\/5142724"}},"subtitle":[],"editor":[{"given":"John","family":"Hancock","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2018,10,23]]},"references-count":33,"journal-issue":{"issue":"11","published-print":{"date-parts":[[2019,6,1]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/bty893","relation":{},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"value":"1367-4803","type":"print"},{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2019,6,1]]},"published":{"date-parts":[[2018,10,23]]}}}